From 0056238bbd19b4c824883a84fda5493f229e6f53 Mon Sep 17 00:00:00 2001 From: Ziya <199893125+ZiyaZhang@users.noreply.github.com> Date: Tue, 7 Jul 2026 01:01:24 -0700 Subject: [PATCH 001/359] =?UTF-8?q?docs(rfc):=20propose=20recallable=20com?= =?UTF-8?q?paction=20=E2=80=94=20split=20checkpoints=20and=20in-session=20?= =?UTF-8?q?history=20recall?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- docs/rfc/INDEX.md | 1 + .../2026-07-06-recallable-compaction.md | 106 ++++++++++++++++++ 2 files changed, 107 insertions(+) create mode 100644 docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index bcd78d8b88..7bfda3401e 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -12,6 +12,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Multiplex concurrent ACP sessions over one connection](proposed/feature/2026-06-14-acp-multi-session.md) | 2026-06-14 | | [Optional Code Mode — model writes TypeScript against an SDK of all tools](proposed/feature/2026-06-15-optional-code-mode.md) | 2026-06-15 | | [Pre-tool input rewrite — a consistent design](proposed/feature/2026-06-30-pre-tool-input-rewrite.md) | 2026-06-30 | +| [Recallable compaction — index checkpoints, a state checkpoint, and in-session history recall](proposed/feature/2026-07-06-recallable-compaction.md) | 2026-07-06 | ### Simplification diff --git a/docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md b/docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md new file mode 100644 index 0000000000..302026e33f --- /dev/null +++ b/docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md @@ -0,0 +1,106 @@ +# RFC: Recallable compaction — index checkpoints, a state checkpoint, and in-session history recall + +Status: proposed + +## Problem + +Compaction is a one-way door. The summary the model sees carries no reference to what it shadows — the `shadowedRange` provenance lives only on the log-only `compact/summary` event — and no tool lets the model read a shadowed span back. Whatever the summarizer drops is gone from the model's reachable world, even though the append-only log holds every byte. Repeated compaction compounds this: the head checkpoint is rewritten every pass, so the request prefix takes a full prompt-cache miss each time, and earlier summaries are re-summarized generation after generation. + +The root cause is one artifact playing two conflicting roles. An **index** wants to be frozen, chronological, and cheap; the model's **working memory** wants a global view, re-prioritization, and mutability. A single summary can be neither well. + +No mainstream coding harness gives the model in-loop recall, and none of the surveyed implementations makes compaction prefix-cache-aware. An event-sourced session — originals durable, seq-addressable, replay-exact — is the natural substrate for both. + +## Proposal + +Split the checkpoint into two classes and make shadowed history reachable. + +### Frozen index checkpoints + +Newly stale history splits into chunks by deterministic policy: accumulate toward `chunkTokens`, snap edges to balanced tool-pairing cuts (`isToolPairingBalanced`), prefer turn boundaries, and place the final boundary as close to the retain boundary as balance allows, so the trailing slice shrinks to roughly one turn. Each chunk is compacted by one `compactRegion` call into an **index stub** (`stubTokens`, ~100–200 tokens): + +- two or three lines of what happened; +- a keyword line of low-frequency literal anchors — exact error strings, values, config keys — grouped by kind; +- a code-composed footer: `[checkpoint c: shadows conversation span #–#; originals retrievable via history_read]`. Pointers are assembled from provenance, never model-authored. + +A committed stub is never rewritten and never re-enters a later compaction region. A slice consisting of recalled content is stubbed by code alone — a pointer line, no LLM call. A failed stub call degrades the same way: its slice gets a code-only pointer stub and the pass continues, making the state rewrite the only hard LLM dependency in a pass. + +### The state checkpoint + +One mutable working-memory document (at most one; zero before the first pass), positioned after all stubs and before the retained tail. Each pass rewrites it from the previous state plus this pass's staled content — O(previous + new), under the merge-don't-restate rule already in the summarization prompt — covering decisions, current state, constraints, and next steps. It carries its own footer and a size cap at the scale of today's summary. Stub calls receive the pass-start state as background, context only. + +An inflation guard bounds the whole pass: if the post-compaction size is not strictly below the pre-compaction size, nothing commits and the turn proceeds; the attempt defers until more stale history accumulates. The guard compares one metric on both sides — provider-reported usage (the counters PR #197 introduces), falling back to the character estimator on both sides. + +### Pass execution + +- Chunk slices are surface position ranges. A pass runs two phases: all summarize calls execute concurrently, buffered off-surface; then regions commit strictly left to right — chunks first, trailing slice last — so the state checkpoint lands after every stub through contiguous single-node replaces. Wall-clock stays near one summarize call. +- The superseded state checkpoint folds into the next pass's first chunk as ordinary history: no tombstone, no new primitive. Its stub omits it, `history_read` renders it labeled `[prior state checkpoint]`, and its footer travels with the rendered text, keeping every trailing slice reachable through the two-hop chain. +- Range selection is frozen-aware: the compactable span begins after the last committed index checkpoint, at the surface head only when none exists. A legacy session's existing head checkpoint is adopted as state-class — its text the merge base, its node folded like any superseded state. +- A crash in the summarize phase commits nothing; a crash mid-commit leaves a left-to-right prefix committed, and the resumed pass reads its merge base from the log's latest state-class `compact/summary` event and commits the remaining regions unconditionally — restoring `[stubs…][state][tail]` outranks shrinking. + +### The recall tools + +A new package `@deepseek-ai/dsh-tool-recall` (consumer-only, over the `dsh-session` and `dsh-compact` vocabularies) registers two model-facing tools: + +- `history_read(checkpoint, offset?)` — renders the shadowed span of any checkpoint in the log, including superseded ones, as `User:`/`Assistant:`/`Tool result:` transcript, paginated by a configured budget with a continuation cursor. +- `history_search(query, checkpoint?, limit?)` — case-insensitive literal scan over every shadowed span; returns snippets with checkpoint ids and coverage metadata (`scanned`/`matched`/`truncated`). The zero-match hint notes the scan is literal and points at direct `history_read` of a plausible checkpoint. + +Both read `exec.agent.session.events` (the tool-todo access pattern; non-agent callers rejected), render only surface-type message events, and return ordinary `tool/result`s — recalled bytes land at the context tail, logged, so reconstructability holds with no special casing. There is no new storage and no sidecar index: the session log is the archive, `compact/summary` provenance is the index metadata, and the tools are a read path over both. The tool schemas and the package's one system-prompt section are static strings; checkpoint ids reach the model only through footers. The transcript renderer moves from `compact-basic` into `dsh-session`, shared by summarizer and tools. + +### Cache and cost + +The request prefix after a pass is `[system][stubs…][state][tail]`. Frozen stubs are byte-stable across passes, so the miss begins at the token replacing the previous state checkpoint and stays O(new chunks + state + tail) — against position zero today. Recall output lands at the tail, leaving the prefix untouched. Per-pass summarize input is roughly twice today's plus an m·S background term, bounded by a `chunkTokens` floor (a small multiple of the state cap) and a validated `stubTokens`/`chunkTokens` ratio ceiling; a shared-prefix input layout (preamble, then the byte-identical pass-start state, slice content in the tail) lets sibling calls earn cached-rate rereads. + +### Packaging + +The design ships as a new backend `dsh-compact-recallable` on the existing `ctx.compact` seam, enabled by default in the shipped example configs; `compact-basic` remains as the reference implementation and the seam's design twin, in the pattern of the paired LLM adapters. The seam JSDoc's "at most one auto-generated checkpoint, always at the head" clause is relaxed to name both backend behaviors. + +### Relation to in-flight work + +- **Tool-result pruning (PR #113)**: its replacement nodes carry `sourceEventSeqs`; the same registry fold lists pruned results as recallable. Follow-up scope; neither blocks the other. +- **Provider-usage token pressure (PR #197)**: supplies the guard's accounting; the implementation stacks after it. +- **"Query sessions" backlog item**: the cross-session generalization; this RFC scopes to the live session with tool names and rendering chosen so that work extends rather than collides. +- **Training**: when to recall is a learned behavior. The deterministic footers and keyword anchors give training a stable target, and recall usage is fully visible in the session log for trajectory export; benchmark and RL design proceed with the post-training side. + +### Follow-ups + +Specified during review, deferred until observation calls for them: + +- Guard degradation ladder (code-only rollup of the oldest stub prefix, footers preserved, rolled-up ids remain recall targets; then one summary after the frozen boundary) — on observed guard livelock or stub-region pressure. +- Echo detection on stub outputs (sentence-scale n-grams, short literals exempt, retry then strip) — on observed division-of-labor leakage. +- Periodic state refresh from chunk originals — on observed drift in the handoff probe. +- `stateFallbackThreshold` (full-detail state prompt below a stub count) — on short-session regression. +- Lazy registration of the recall tools — on measured context tax in never-compacting sessions. +- Split summarizer models; model-chosen chunk boundaries; cross-session recall; semantic search fallback — each behind its own evidence. + +## Alternatives considered + +- **Staged delivery** (ship recall tools alone over today's backend; gate the checkpoint split on observed recall usage) — rejected: untrained models under-use any new tool, so the gate would measure training absence rather than design value, while the training side needs the complete mechanism to build environments against; the pre-release window is when persisted-format changes are cheapest; and the cache economics are first-party knowledge, not a hypothesis awaiting telemetry. The implementation still lands as stacked PRs with the recall tools first — construction order, not a decision gate. +- **All-frozen full-size summaries, no state checkpoint** — rejected: unbounded permanent-prefix growth, self-accelerating toward thrashing, with nothing left to re-prioritize. +- **Pure stubs, no state checkpoint** — rejected: presumes the model knows what it is missing; fails on unknown unknowns. +- **LLM aging/consolidation of frozen chunks** — rejected as a routine mechanism: summary-of-summary loss and frozen-prefix churn; the code-only rollup is its surviving form, deferred. +- **Full prefix as chunk-summarizer input** — rejected: O(N²); the state document gives the same background at O(state). +- **One summarize call emitting all outputs** — rejected: the summarize path has no structured-output enforcement; parsing one free-text response apart is the fragile seam the fail-closed design avoids. +- **Model-chosen chunk boundaries** — deferred: parse-and-validate cost against unproven value; chunk policy sits behind config. +- **Model-authored pointers** — rejected: pointers must be exact; deterministic assembly is. +- **FTS/vector index sidecar** — rejected in-session: the live log is in memory and bounded, a literal scan under budget suffices; an index earns its keep at cross-session scope. +- **Semantic search fallback / secondary-model extraction in the recall path** — rejected: an LLM or embedding call there breaks keyless replay determinism; recall stays a pure function of the log. +- **Raw events instead of rendered transcript** — rejected: leaks log-only vocabulary and chunk noise; the model reads what a model once saw. +- **Doing nothing (resume/fork as recovery)** — rejected: it makes recovery a human act. + +## Acceptance criteria + +- Auto-compaction over a long session yields `[stubs…][state][tail]` after every completed pass; prior stubs stay byte-identical across passes; committed stubs never fall inside a later region; the superseded state checkpoint folds without a tombstone, renders labeled, and stays reachable and searchable through the two-hop chain. +- Every checkpoint's surface text ends with the deterministic footer; footers round-trip through replay byte-identically; the state checkpoint's provenance records its wider input range. +- Nothing commits before all summaries exist and the guard passes on like-for-like accounting; a guard failure commits nothing and does not fail the turn; a mid-commit kill resumed at the next pre-step completes the pass with the state region committed unconditionally, merge base read from the log; a legacy head checkpoint is adopted as state-class. +- `history_read` renders any logged checkpoint's span under budget with a working cursor; `history_search` covers every shadowed span with checkpoint-id snippets and coverage metadata, asserted in particular by finding content that exists only in a span shadowed by a superseded state checkpoint — the regression pin for trailing-slice reachability; both reject non-agent callers and never-existing ids or orphaned `compact/start` with typed errors; recalled content appears as ordinary `tool/result`s; request-reconstruction invariants pass over sessions with compaction plus recall; one keyless snapshot scenario covers compact-then-recall end to end; tool schemas and the prompt section are byte-identical across passes. +- On the long-horizon bench suite: task success does not regress against `compact-basic` at equal budgets; a handoff-fidelity probe (restate K known decisions and constraints after a pass) scores no worse; recall usage frequency and hit usefulness are reported per run via the dsh bench report pipeline, alongside the stub-directory attention measurement and cache-hit telemetry. +- Seam JSDoc, the compaction capability-seam RFC, `architecture.md`, and the generated tool, config, persistence, and module-graph catalogs update in the same change; all budgets live in config; new source directories hold per-file 100% coverage with HMR disposal tests. + +## Risks + +- **Recall is a learned behavior**: untrained models will under-use it, and the bench report exists to track the gap while training closes it. Until then the state checkpoint keeps the floor at today's summary quality. +- **Unknown unknowns remain**: a detail absent from summaries and keywords draws no recall. Recall converts "unreachable even when suspected" into "reachable when suspected". +- **The stub directory occupies attention**: dozens of stable index cards per request may dilute focus; the bench measurement in the acceptance criteria tracks it against `compact-basic`. +- **Cost**: per-pass summarize input is roughly twice today's; short sessions sit near today's cost and quality, and the design pays off with session length. +- **State drift and division-of-labor leakage** are observable through the handoff probe and stub review; their counters are specified follow-ups. +- **Two backends** are a maintenance surface; the seam contract and the shared recall consumer bound it, and the bench comparison decides the default over time. From ac64a0c7b123df217618a3581c04f36bcea8ab9e Mon Sep 17 00:00:00 2001 From: Ziya <199893125+ZiyaZhang@users.noreply.github.com> Date: Tue, 7 Jul 2026 02:58:56 -0700 Subject: [PATCH 002/359] docs(rfc): specify stub input layering; add amortized stub drafting follow-up --- .../rfc/proposed/feature/2026-07-06-recallable-compaction.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md b/docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md index 302026e33f..e657887fe1 100644 --- a/docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md +++ b/docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md @@ -22,11 +22,11 @@ Newly stale history splits into chunks by deterministic policy: accumulate towar - a keyword line of low-frequency literal anchors — exact error strings, values, config keys — grouped by kind; - a code-composed footer: `[checkpoint c: shadows conversation span #–#; originals retrievable via history_read]`. Pointers are assembled from provenance, never model-authored. -A committed stub is never rewritten and never re-enters a later compaction region. A slice consisting of recalled content is stubbed by code alone — a pointer line, no LLM call. A failed stub call degrades the same way: its slice gets a code-only pointer stub and the pass continues, making the state rewrite the only hard LLM dependency in a pass. +A committed stub is never rewritten and never re-enters a later compaction region. A stub call's input is layered: the fixed preamble and the byte-identical pass-start state checkpoint (the shared prefix across all calls in the phase), then the keyword lines of all previously committed stubs — so a new entry indexes what is distinctive to its chunk instead of repeating the directory — the one or two most recent committed stubs for chronological continuity, and the slice itself. Sibling stubs from the same pass are not inputs (the concurrent phase forbids it; turn-aligned boundaries carry local continuity instead), and the state checkpoint is background only, never material to summarize into the stub. A slice consisting of recalled content is stubbed by code alone — a pointer line, no LLM call. A failed stub call degrades the same way: its slice gets a code-only pointer stub and the pass continues, making the state rewrite the only hard LLM dependency in a pass. ### The state checkpoint -One mutable working-memory document (at most one; zero before the first pass), positioned after all stubs and before the retained tail. Each pass rewrites it from the previous state plus this pass's staled content — O(previous + new), under the merge-don't-restate rule already in the summarization prompt — covering decisions, current state, constraints, and next steps. It carries its own footer and a size cap at the scale of today's summary. Stub calls receive the pass-start state as background, context only. +One mutable working-memory document (at most one; zero before the first pass), positioned after all stubs and before the retained tail. Each pass rewrites it from the previous state plus this pass's staled content — O(previous + new), under the merge-don't-restate rule already in the summarization prompt — covering decisions, current state, constraints, and next steps. It carries its own footer and a size cap at the scale of today's summary. An inflation guard bounds the whole pass: if the post-compaction size is not strictly below the pre-compaction size, nothing commits and the turn proceeds; the attempt defers until more stale history accumulates. The guard compares one metric on both sides — provider-reported usage (the counters PR #197 introduces), falling back to the character estimator on both sides. @@ -70,6 +70,7 @@ Specified during review, deferred until observation calls for them: - Periodic state refresh from chunk originals — on observed drift in the handoff probe. - `stateFallbackThreshold` (full-detail state prompt below a stub count) — on short-session regression. - Lazy registration of the recall tools — on measured context tax in never-compacting sessions. +- Amortized stub drafting at pre-step: as soon as stale-but-uncompacted content accumulates past `chunkTokens`, draft that chunk's stub at the next pre-step (a log-only draft event, written while the chunk's surrounding context is still live) and let the compaction pass commit drafts instead of summarizing in bulk — the deterministic, replay-exact equivalent of background compaction (the Claude Code session-memory pattern; OpenClaw demonstrates the synchronous semantics are identical). Trigger: observed pass latency, or stub-quality gains from drafting near-live proving out. - Split summarizer models; model-chosen chunk boundaries; cross-session recall; semantic search fallback — each behind its own evidence. ## Alternatives considered From 7089c88e4a13e719ad4c071156d531a4fe0e763d Mon Sep 17 00:00:00 2001 From: Ziya <199893125+ZiyaZhang@users.noreply.github.com> Date: Tue, 7 Jul 2026 21:07:06 -0700 Subject: [PATCH 003/359] docs(rfc): self-contained work references; add richer search query forms follow-up --- .../proposed/feature/2026-07-06-recallable-compaction.md | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md b/docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md index e657887fe1..1de660ac31 100644 --- a/docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md +++ b/docs/rfc/proposed/feature/2026-07-06-recallable-compaction.md @@ -28,7 +28,7 @@ A committed stub is never rewritten and never re-enters a later compaction regio One mutable working-memory document (at most one; zero before the first pass), positioned after all stubs and before the retained tail. Each pass rewrites it from the previous state plus this pass's staled content — O(previous + new), under the merge-don't-restate rule already in the summarization prompt — covering decisions, current state, constraints, and next steps. It carries its own footer and a size cap at the scale of today's summary. -An inflation guard bounds the whole pass: if the post-compaction size is not strictly below the pre-compaction size, nothing commits and the turn proceeds; the attempt defers until more stale history accumulates. The guard compares one metric on both sides — provider-reported usage (the counters PR #197 introduces), falling back to the character estimator on both sides. +An inflation guard bounds the whole pass: if the post-compaction size is not strictly below the pre-compaction size, nothing commits and the turn proceeds; the attempt defers until more stale history accumulates. The guard compares one metric on both sides — provider-reported usage from the request path, falling back to the character estimator on both sides. ### Pass execution @@ -56,8 +56,8 @@ The design ships as a new backend `dsh-compact-recallable` on the existing `ctx. ### Relation to in-flight work -- **Tool-result pruning (PR #113)**: its replacement nodes carry `sourceEventSeqs`; the same registry fold lists pruned results as recallable. Follow-up scope; neither blocks the other. -- **Provider-usage token pressure (PR #197)**: supplies the guard's accounting; the implementation stacks after it. +- **Tool-result pruning** (the in-flight pruning service): its replacement nodes carry `sourceEventSeqs`; the same registry fold lists pruned results as recallable. Follow-up scope; neither blocks the other. +- **Provider-usage token accounting** (the in-flight move of compaction pressure onto provider-reported usage): supplies the guard's accounting; the implementation stacks after it. - **"Query sessions" backlog item**: the cross-session generalization; this RFC scopes to the live session with tool names and rendering chosen so that work extends rather than collides. - **Training**: when to recall is a learned behavior. The deterministic footers and keyword anchors give training a stable target, and recall usage is fully visible in the session log for trajectory export; benchmark and RL design proceed with the post-training side. @@ -72,6 +72,7 @@ Specified during review, deferred until observation calls for them: - Lazy registration of the recall tools — on measured context tax in never-compacting sessions. - Amortized stub drafting at pre-step: as soon as stale-but-uncompacted content accumulates past `chunkTokens`, draft that chunk's stub at the next pre-step (a log-only draft event, written while the chunk's surrounding context is still live) and let the compaction pass commit drafts instead of summarizing in bulk — the deterministic, replay-exact equivalent of background compaction (the Claude Code session-memory pattern; OpenClaw demonstrates the synchronous semantics are identical). Trigger: observed pass latency, or stub-quality gains from drafting near-live proving out. - Split summarizer models; model-chosen chunk boundaries; cross-session recall; semantic search fallback — each behind its own evidence. +- Richer `history_search` query forms — regex, and structured queries over logged JSON tool results (sql/jq-style, or agent-authored queries against an indexed store) — on demand from observed search misses; literal matching ships first because the recall path stays a pure function of the log. ## Alternatives considered From 87a1774fefd99bf458898154e7e40ca3715a48f2 Mon Sep 17 00:00:00 2001 From: lintianle Date: Thu, 9 Jul 2026 16:07:58 +0800 Subject: [PATCH 004/359] feat: add docs website --- website/.gitignore | 3 + website/.vitepress/config/index.ts | 17 + website/.vitepress/config/zh-CN.ts | 99 +++++ website/package.json | 15 + website/zh-CN/api/cordis/context.md | 85 +++++ website/zh-CN/api/cordis/events.md | 120 ++++++ website/zh-CN/api/cordis/fiber.md | 108 ++++++ website/zh-CN/api/cordis/registry.md | 87 +++++ website/zh-CN/api/cordis/service.md | 97 +++++ website/zh-CN/api/harness/agent.md | 85 +++++ website/zh-CN/api/harness/bash.md | 81 +++++ website/zh-CN/api/harness/fs.md | 78 ++++ website/zh-CN/api/harness/llm.md | 124 +++++++ website/zh-CN/api/harness/session.md | 56 +++ website/zh-CN/api/harness/subagent.md | 85 +++++ website/zh-CN/api/harness/tools.md | 122 +++++++ website/zh-CN/api/index.md | 25 ++ website/zh-CN/design/composability.md | 72 ++++ website/zh-CN/design/context-model.md | 129 +++++++ website/zh-CN/design/effects-coeffects.md | 69 ++++ website/zh-CN/design/index.md | 39 ++ website/zh-CN/design/reactive-coeffects.md | 90 +++++ website/zh-CN/design/revertible-effects.md | 128 +++++++ website/zh-CN/develop/basic/config.md | 108 ++++++ website/zh-CN/develop/basic/index.md | 148 ++++++++ website/zh-CN/develop/basic/tool.md | 199 ++++++++++ website/zh-CN/develop/framework/events.md | 152 ++++++++ website/zh-CN/develop/framework/index.md | 139 +++++++ website/zh-CN/develop/framework/service.md | 147 ++++++++ website/zh-CN/develop/practice/index.md | 156 ++++++++ website/zh-CN/develop/practice/llm-adapter.md | 169 +++++++++ website/zh-CN/guide/config.md | 342 ++++++++++++++++++ website/zh-CN/guide/index.md | 47 +++ website/zh-CN/guide/quickstart.md | 98 +++++ website/zh-CN/index.md | 21 ++ 35 files changed, 3540 insertions(+) create mode 100644 website/.gitignore create mode 100644 website/.vitepress/config/index.ts create mode 100644 website/.vitepress/config/zh-CN.ts create mode 100644 website/package.json create mode 100644 website/zh-CN/api/cordis/context.md create mode 100644 website/zh-CN/api/cordis/events.md create mode 100644 website/zh-CN/api/cordis/fiber.md create mode 100644 website/zh-CN/api/cordis/registry.md create mode 100644 website/zh-CN/api/cordis/service.md create mode 100644 website/zh-CN/api/harness/agent.md create mode 100644 website/zh-CN/api/harness/bash.md create mode 100644 website/zh-CN/api/harness/fs.md create mode 100644 website/zh-CN/api/harness/llm.md create mode 100644 website/zh-CN/api/harness/session.md create mode 100644 website/zh-CN/api/harness/subagent.md create mode 100644 website/zh-CN/api/harness/tools.md create mode 100644 website/zh-CN/api/index.md create mode 100644 website/zh-CN/design/composability.md create mode 100644 website/zh-CN/design/context-model.md create mode 100644 website/zh-CN/design/effects-coeffects.md create mode 100644 website/zh-CN/design/index.md create mode 100644 website/zh-CN/design/reactive-coeffects.md create mode 100644 website/zh-CN/design/revertible-effects.md create mode 100644 website/zh-CN/develop/basic/config.md create mode 100644 website/zh-CN/develop/basic/index.md create mode 100644 website/zh-CN/develop/basic/tool.md create mode 100644 website/zh-CN/develop/framework/events.md create mode 100644 website/zh-CN/develop/framework/index.md create mode 100644 website/zh-CN/develop/framework/service.md create mode 100644 website/zh-CN/develop/practice/index.md create mode 100644 website/zh-CN/develop/practice/llm-adapter.md create mode 100644 website/zh-CN/guide/config.md create mode 100644 website/zh-CN/guide/index.md create mode 100644 website/zh-CN/guide/quickstart.md create mode 100644 website/zh-CN/index.md diff --git a/website/.gitignore b/website/.gitignore new file mode 100644 index 0000000000..2c1fa99cb4 --- /dev/null +++ b/website/.gitignore @@ -0,0 +1,3 @@ +node_modules/ +.vitepress/dist/ +.vitepress/cache/ diff --git a/website/.vitepress/config/index.ts b/website/.vitepress/config/index.ts new file mode 100644 index 0000000000..b4978ca4aa --- /dev/null +++ b/website/.vitepress/config/index.ts @@ -0,0 +1,17 @@ +import { defineConfig } from 'vitepress' +import { zhCN } from './zh-CN' + +export default defineConfig({ + title: 'DeepSeek Harness', + description: '插件化 Agent 开发框架', + + locales: { + 'zh-CN': zhCN, + }, + + themeConfig: { + socialLinks: [ + { icon: 'github', link: 'https://github.com/deepseek-harness/deepseek-harness' }, + ], + }, +}) diff --git a/website/.vitepress/config/zh-CN.ts b/website/.vitepress/config/zh-CN.ts new file mode 100644 index 0000000000..83767b6cbc --- /dev/null +++ b/website/.vitepress/config/zh-CN.ts @@ -0,0 +1,99 @@ +import type { DefaultTheme, LocaleSpecificConfig } from 'vitepress' + +const guideSidebar: DefaultTheme.SidebarItem[] = [ + { + text: '入门', + items: [ + { text: '介绍', link: '/zh-CN/guide/' }, + { text: '快速开始', link: '/zh-CN/guide/quickstart' }, + { text: '配置文件', link: '/zh-CN/guide/config' }, + ], + }, +] + +const developSidebar: DefaultTheme.SidebarItem[] = [ + { + text: '基础', + items: [ + { text: '第一个插件', link: '/zh-CN/develop/basic/' }, + { text: '开发一个 Tool', link: '/zh-CN/develop/basic/tool' }, + { text: '插件配置', link: '/zh-CN/develop/basic/config' }, + ], + }, + { + text: '框架能力', + items: [ + { text: '插件与生命周期', link: '/zh-CN/develop/framework/' }, + { text: '服务与依赖', link: '/zh-CN/develop/framework/service' }, + { text: '事件系统', link: '/zh-CN/develop/framework/events' }, + ], + }, + { + text: '实战', + items: [ + { text: '能力的三层拆分', link: '/zh-CN/develop/practice/' }, + { text: 'LLM 适配器', link: '/zh-CN/develop/practice/llm-adapter' }, + ], + }, +] + +const apiSidebar: DefaultTheme.SidebarItem[] = [ + { + text: '框架 API', + items: [ + { text: '总览', link: '/zh-CN/api/' }, + { text: 'Context', link: '/zh-CN/api/cordis/context' }, + { text: 'Events', link: '/zh-CN/api/cordis/events' }, + { text: 'Fiber', link: '/zh-CN/api/cordis/fiber' }, + { text: 'Registry', link: '/zh-CN/api/cordis/registry' }, + { text: 'Service', link: '/zh-CN/api/cordis/service' }, + ], + }, + { + text: 'Harness API', + items: [ + { text: 'Tools (dsh-tools)', link: '/zh-CN/api/harness/tools' }, + { text: 'LLM (dsh-llm)', link: '/zh-CN/api/harness/llm' }, + { text: 'Session (dsh-session)', link: '/zh-CN/api/harness/session' }, + { text: 'Agent (dsh-agent)', link: '/zh-CN/api/harness/agent' }, + { text: 'Bash (dsh-bash)', link: '/zh-CN/api/harness/bash' }, + { text: 'Filesystem (dsh-fs)', link: '/zh-CN/api/harness/fs' }, + { text: 'Subagent (dsh-subagent)', link: '/zh-CN/api/harness/subagent' }, + ], + }, +] + +const designSidebar: DefaultTheme.SidebarItem[] = [ + { + text: '系统设计', + items: [ + { text: '概述', link: '/zh-CN/design/' }, + { text: '可组合性与插件系统', link: '/zh-CN/design/composability' }, + { text: '作用与余作用', link: '/zh-CN/design/effects-coeffects' }, + { text: '可逆作用', link: '/zh-CN/design/revertible-effects' }, + { text: '响应式余作用', link: '/zh-CN/design/reactive-coeffects' }, + { text: '上下文模型', link: '/zh-CN/design/context-model' }, + ], + }, +] + +export const zhCN: LocaleSpecificConfig = { + label: '简体中文', + lang: 'zh-CN', + themeConfig: { + nav: [ + { text: '入门', link: '/zh-CN/guide/', activeMatch: '/zh-CN/guide/' }, + { text: '开发', link: '/zh-CN/develop/basic/', activeMatch: '/zh-CN/develop/' }, + { text: 'API', link: '/zh-CN/api/', activeMatch: '/zh-CN/api/' }, + { text: '设计', link: '/zh-CN/design/', activeMatch: '/zh-CN/design/' }, + ], + sidebar: { + '/zh-CN/guide/': guideSidebar, + '/zh-CN/develop/': developSidebar, + '/zh-CN/api/': apiSidebar, + '/zh-CN/design/': designSidebar, + }, + outline: { label: '本页目录' }, + docFooter: { prev: '上一篇', next: '下一篇' }, + }, +} diff --git a/website/package.json b/website/package.json new file mode 100644 index 0000000000..33c32fae4c --- /dev/null +++ b/website/package.json @@ -0,0 +1,15 @@ +{ + "name": "@deepseek-ai/website", + "private": true, + "version": "0.0.1", + "type": "module", + "scripts": { + "dev": "vitepress dev . --port 5173 --open", + "build": "vitepress build .", + "preview": "vitepress preview ." + }, + "devDependencies": { + "vitepress": "^1.6.3", + "vue": "^3.5.13" + } +} diff --git a/website/zh-CN/api/cordis/context.md b/website/zh-CN/api/cordis/context.md new file mode 100644 index 0000000000..a18f275dad --- /dev/null +++ b/website/zh-CN/api/cordis/context.md @@ -0,0 +1,85 @@ +# Context + +上下文对象是 Cordis 的核心。所有服务、方法、属性都通过 `ctx` 访问。 + +## 服务与混入 + +Context 基于组合式 API 设计，大部分属性和方法挂载在服务上。以下是核心 API： + +- [`ctx.on`](./events#ctx-on) — 注册事件监听器 +- [`ctx.emit`](./events#ctx-emit) — 触发事件 +- [`ctx.bail`](./events#ctx-bail) — 短路事件 +- [`ctx.serial`](./events#ctx-serial) — 顺序异步事件 +- [`ctx.waterfall`](./events#ctx-waterfall) — 管道事件 +- [`ctx.effect`](./fiber#fiber-effect) — 注册可逆效果 +- [`ctx.plugin`](./registry#ctx-plugin) — 加载子插件 +- [`ctx.inject`](./registry#ctx-inject) — 获取依赖的插件 +- [`ctx.get`](#ctx-get) — 获取服务 +- [`ctx.set`](#ctx-set) — 设置服务 +- [`ctx.provide`](#ctx-provide) — 声明服务 + +## 实例属性 + +### ctx.fiber + +- **类型:** [`Fiber`](./fiber) + +当前上下文的作用域对象。 + +## 实例方法 + +### ctx.extend(meta) + +- **meta:** `object` +- **返回值:** `Context` + +构造一个以当前上下文为原型的新上下文实例。 + +### ctx.intercept(name, config) + +- **name:** `string` 服务名称 +- **config:** `object` 配置拦截 +- **返回值:** `Context` + +为指定服务添加一层配置拦截，返回新的上下文实例。 + +### ctx.isolate(name, label?) + +- **name:** `string` 服务名称 +- **label:** `symbol` 隔离域符号（可选） +- **返回值:** `Context` + +创建一个针对指定服务的隔离域，返回新的上下文实例。隔离域中的同名服务互不影响。 + +### ctx.get(name) + +- **name:** `string` 服务名称 +- **返回值:** `Service | undefined` + +获取指定名称的服务实例。 + +### ctx.set(name, value) + +- **name:** `string` 服务名称 +- **value:** `any` 服务值 + +设置指定名称的服务。 + +### ctx.provide(name, value?, options?) + +- **name:** `string` 服务名称 +- **value:** `any` 初始值（可选） +- **options:** `object` +- **返回值:** `void` + +声明一个服务。声明后其他插件可以通过 `inject` 依赖它。 + +## 静态属性 + +### Context.events + +内置事件服务的 symbol key。 + +### Context.current + +当前活跃的 Context 实例（在异步链中通过 AsyncLocalStorage 追踪）。 diff --git a/website/zh-CN/api/cordis/events.md b/website/zh-CN/api/cordis/events.md new file mode 100644 index 0000000000..dbc03a87bc --- /dev/null +++ b/website/zh-CN/api/cordis/events.md @@ -0,0 +1,120 @@ +# Events + +`ctx.events` 是内置服务，提供事件系统相关的全部 API。 + +## 实例方法 + +### ctx.on(event, listener, options?) {#ctx-on} + +- **event:** `string` 事件名称 +- **listener:** `Function` 事件监听器 +- **options:** `object` + - **prepend:** `boolean` 是否注册为前置（默认 `false`） + - **global:** `boolean` 是否注册为全局（默认 `false`） +- **返回值:** `() => void` 取消注册函数 + +注册一个事件监听器。返回的函数可用于手动取消注册，但通常不需要——插件卸载时会自动清理。 + +```typescript +ctx.on('agent/turn-end', (data) => { + console.log('turn ended:', data) +}) +``` + +### ctx.emit(thisArg?, event, ...args) {#ctx-emit} + +- **thisArg:** `any` 监听器的 `this` 参数（可选） +- **event:** `string` 事件名称 +- **args:** `any[]` 事件参数 +- **返回值:** `void` + +同步触发所有匹配的监听器（并行，不等待异步完成）。 + +### ctx.parallel(thisArg?, event, ...args) + +- 签名同 `emit` +- **返回值:** `Promise` + +异步触发所有匹配的监听器（并行等待）。 + +### ctx.bail(thisArg?, event, ...args) {#ctx-bail} + +- **返回值:** `any` + +同步依次触发监听器。第一个返回非 `undefined`/`null`/`false` 值的监听器停止链并返回该值。 + +### ctx.serial(thisArg?, event, ...args) {#ctx-serial} + +- **返回值:** `Promise` + +异步依次触发监听器。语义同 `bail` 的异步版本。 + +### ctx.waterfall(thisArg?, event, ...args) {#ctx-waterfall} + +- **返回值:** `Promise` + +管道模式：每个监听器接收前一个的输出。监听器内部必须调用 `next()` 才会传递给下一个。 + +```typescript +// 注册 +ctx.on('llm/pre-request', async (messages, next) => { + messages.push(extraMsg) + return next(messages) // 必须调用 +}) + +// 触发 +const result = await ctx.waterfall('llm/pre-request', initialMessages) +``` + +::: warning +不调用 `next()` 即为否决 (veto)——管道终止。这是设计行为，用于拦截/网关。 +::: + +## Harness 内置事件 + +### agent/pre-step + +- **触发模式:** serial +- **参数:** `{ agentId, turnIndex }` + +Agent 执行一步之前触发。 + +### agent/post-step + +- **触发模式:** emit +- **参数:** `{ agentId, turnIndex, blocks }` + +Agent 执行一步之后触发。 + +### tool/call + +- **触发模式:** emit +- **参数:** `{ name, args, callId }` + +Tool 被模型调用时触发。 + +### tool/result + +- **触发模式:** emit +- **参数:** `{ name, result, callId }` + +Tool 返回结果时触发。 + +### session/event + +- **触发模式:** emit +- **参数:** `SessionEvent` + +会话事件被记录时触发。 + +### compact/start + +- **触发模式:** emit + +上下文压缩开始。 + +### compact/end + +- **触发模式:** emit + +上下文压缩结束。 diff --git a/website/zh-CN/api/cordis/fiber.md b/website/zh-CN/api/cordis/fiber.md new file mode 100644 index 0000000000..ffb8f23bb5 --- /dev/null +++ b/website/zh-CN/api/cordis/fiber.md @@ -0,0 +1,108 @@ +# Fiber + +Fiber（作用域）是插件实例的运行时容器，管理其生命周期和效果。 + +## 状态机 + +``` +PENDING → LOADING → ACTIVE → UNLOADING → DISPOSED + ↘ FAILED +``` + +| 状态 | 数值 | 含义 | +|------|------|------| +| PENDING | 0 | 依赖未就绪，等待中 | +| LOADING | 1 | 正在执行 `apply` | +| ACTIVE | 2 | 运行中 | +| FAILED | 3 | `apply` 抛出异常 | +| UNLOADING | 4 | 正在撤销效果 | +| DISPOSED | 5 | 已完全卸载 | + +## 实例属性 + +### fiber.uid + +- **类型:** `number` + +Fiber 的唯一标识符。 + +### fiber.status + +- **类型:** `number` + +当前状态（见状态机）。 + +### fiber.config + +- **类型:** `object` + +传递给插件的配置对象。 + +### fiber.error + +- **类型:** `Error | undefined` + +如果状态是 FAILED，包含导致失败的异常。 + +## 实例方法 + +### fiber.effect(callback) {#fiber-effect} + +- **callback:** `() => (() => void) | void` +- **返回值:** `() => void` + +注册一个效果。`callback` 在 Fiber 激活时执行；如果返回函数，该函数在 Fiber dispose 时执行。 + +```typescript +ctx.effect(() => { + const timer = setInterval(tick, 1000) + return () => clearInterval(timer) +}) +``` + +等价地可以通过 `ctx.effect()` 调用（ctx 代理到当前 fiber）。 + +### fiber.dispose() + +- **返回值:** `Promise` + +手动 dispose 该 Fiber。按注册逆序撤销所有效果，递归 dispose 所有子 Fiber。 + +```typescript +const child = ctx.plugin(somePlugin) +// 之后: +await child.dispose() +``` + +### fiber.update(config) + +- **config:** `object` 新配置 +- **返回值:** `void` + +热更新配置。如果新旧配置不同，触发 dispose + 重新 apply。 + +### fiber.restart() + +- **返回值:** `void` + +强制重启：dispose 后重新加载。 + +### fiber.then(resolve, reject?) + +- **返回值:** `Promise` + +使 Fiber 可以被 `await`：等到状态进入 ACTIVE 或 FAILED。 + +```typescript +const fiber = ctx.plugin(myPlugin) +await fiber // 等待插件加载完成 +``` + +## 访问当前 Fiber + +```typescript +export function apply(ctx: Context) { + const fiber = ctx.fiber // 当前插件的 Fiber + console.log(fiber.status) // 1 (LOADING, 因为正在 apply 中) +} +``` diff --git a/website/zh-CN/api/cordis/registry.md b/website/zh-CN/api/cordis/registry.md new file mode 100644 index 0000000000..e0f66d8ed7 --- /dev/null +++ b/website/zh-CN/api/cordis/registry.md @@ -0,0 +1,87 @@ +# Registry + +插件注册表，管理插件的加载和依赖解析。 + +## 实例方法 + +### ctx.plugin(plugin, config?) {#ctx-plugin} + +- **plugin:** `Plugin` 插件（函数、对象或类） +- **config:** `object` 传递给插件的配置（可选） +- **返回值:** `Fiber` + +加载一个子插件，返回其 Fiber。子 Fiber 的生命周期绑定到父上下文。 + +```typescript +// 函数插件 +ctx.plugin(myPlugin, { key: 'value' }) + +// 类插件 +ctx.plugin(MyService) + +// 返回的 Fiber 可以 await 或 dispose +const fiber = ctx.plugin(myPlugin) +await fiber +``` + +### ctx.inject(names, callback) {#ctx-inject} + +- **names:** `string[]` 服务名列表 +- **callback:** `(ctx: Context) => void` +- **返回值:** `() => void` + +等待指定服务全部就绪后执行 callback。如果服务消失，callback 的效果会自动撤销；服务恢复后重新执行。 + +```typescript +ctx.inject(['tools', 'llm'], (ctx) => { + // tools 和 llm 都就绪了 + ctx.tools.register(/* ... */) +}) +``` + +这是 `export const inject = [...]` 声明的底层 API。大多数情况下直接使用声明式写法即可。 + +## 插件形态 + +`ctx.plugin()` 接受三种插件形态： + +### 函数插件 + +```typescript +function myPlugin(ctx: Context, config?: Config) { + // ... +} +myPlugin.name = 'my-plugin' +myPlugin.inject = ['tools'] +``` + +### 对象插件 + +```typescript +const myPlugin = { + name: 'my-plugin', + inject: ['tools'], + apply(ctx: Context, config?: Config) { + // ... + }, +} +``` + +### 类插件（Service） + +```typescript +class MyService extends Service { + static inject = ['tools'] + constructor(ctx: Context) { + super(ctx, 'myService') + } +} +``` + +## 插件元信息 + +| 属性 | 类型 | 说明 | +|------|------|------| +| `name` | `string` | 插件名称（日志用） | +| `inject` | `string[] \| { required?: string[], optional?: string[] }` | 依赖声明 | +| `Config` | `Schema \| object` | 配置 schema 或默认值 | diff --git a/website/zh-CN/api/cordis/service.md b/website/zh-CN/api/cordis/service.md new file mode 100644 index 0000000000..a57a00c461 --- /dev/null +++ b/website/zh-CN/api/cordis/service.md @@ -0,0 +1,97 @@ +# Service + +Service 基类，用于创建对外暴露能力的插件。 + +## 基本用法 + +```typescript +import { Service, type Context } from 'cordis' + +declare module 'cordis' { + interface Context { + myService: MyService + } +} + +export default class MyService extends Service { + constructor(ctx: Context) { + super(ctx, 'myService') + } + + // 公开方法 + doSomething() { + // ... + } +} +``` + +加载后，其他插件可通过 `ctx.myService` 访问。 + +## 构造函数 + +### new Service(ctx, name) + +- **ctx:** `Context` 上下文 +- **name:** `string` 服务名（注册到 `ctx[name]`） + +## 实例属性 + +### service.ctx + +- **类型:** `Context` + +该服务绑定的上下文。 + +### service\[Service.tracker\] + +- **类型:** `object` + +服务追踪信息（名称、绑定状态等）。 + +## 生命周期 + +Service 子类可以覆写以下方法： + +### start() + +服务激活时调用。在这里初始化资源。 + +### stop() + +服务停用时调用。在这里释放资源。 + +## 静态属性 + +### Service.inject + +- **类型:** `string[] | { required?: string[], optional?: string[] }` + +声明本服务依赖的其他服务。 + +## 与 inject 的关系 + +当一个 Service 被加载： +1. 框架为该服务名创建声明 (`ctx.provide`) +2. 实例赋值到 `ctx[name]` +3. 依赖该服务的所有 Fiber 从 PENDING 转为 LOADING + +当 Service 被卸载： +1. `ctx[name]` 被置为 `undefined` +2. 依赖它的 Fiber 被 dispose +3. 当新的 provider 出现时，dependant Fiber 重新加载 + +## 示例：Harness 中的 Service + +```typescript +// dsh-tools 的 ToolRegistry 就是一个 Service +export class ToolRegistry extends Service { + constructor(ctx: Context) { + super(ctx, 'tools') + } + + register(tool: ToolDefinition): () => void { + // ...注册逻辑 + return dispose + } +} +``` diff --git a/website/zh-CN/api/harness/agent.md b/website/zh-CN/api/harness/agent.md new file mode 100644 index 0000000000..bf46c7e4e1 --- /dev/null +++ b/website/zh-CN/api/harness/agent.md @@ -0,0 +1,85 @@ +# Agent (dsh-agent) + +Agent 实例管理和生命周期。 + +**包名:** `@deepseek-ai/dsh-agent` +**服务名:** `ctx.agents` + +## Agent Service + +### ctx.agents.create(options) + +- **options:** `AgentOptions` +- **返回值:** `Agent` + +创建一个新的 Agent 实例。 + +### ctx.agents.get(id) + +- **id:** `AgentId` +- **返回值:** `Agent | undefined` + +获取指定 ID 的 Agent 实例。 + +## AgentOptions + +```typescript +interface AgentOptions { + /** Agent ID（branded） */ + id?: AgentId + /** 使用的模型名 */ + model: string + /** 系统提示词（支持 {{model}} 变量） */ + persona?: string + /** 关联的 session */ + session?: Session +} +``` + +## Agent 实例 + +### agent.id + +- **类型:** `AgentId` + +Agent 的唯一标识符（branded string）。 + +### agent.model + +- **类型:** `string` + +Agent 使用的模型名。 + +### agent.step(input) + +- **input:** `ContentBlock[]` +- **返回值:** `Promise` + +执行一步：将输入发送给模型，获取响应，执行 tool calls。这是 agent-loop 内部使用的核心方法。 + +## Agent Loop + +Agent 的执行循环由 `dsh-agent-loop` 管理。它： + +1. 组装 system prompt + 历史消息 + 当前输入 +2. 调用 LLM（通过 `ctx.llm`） +3. 解析响应中的 tool calls +4. 执行 tools +5. 将 tool results 追加到 session +6. 如果 finish reason 是 `tool-calls`，回到步骤 2 + +### 扩展点 + +- `agent/pre-step` 事件 — 在每一步 LLM 调用前触发 +- `agent/post-step` 事件 — 在每一步完成后触发 +- `llm/pre-request` waterfall — 可修改发送给模型的消息 + +## AgentId + +Opaque branded string： + +```typescript +import { AgentId } from '@deepseek-ai/dsh-agent' + +const id = AgentId('main') +``` diff --git a/website/zh-CN/api/harness/bash.md b/website/zh-CN/api/harness/bash.md new file mode 100644 index 0000000000..8e8d8d3068 --- /dev/null +++ b/website/zh-CN/api/harness/bash.md @@ -0,0 +1,81 @@ +# Bash (dsh-bash) + +Bash 命令执行接口。 + +**接口包:** `@deepseek-ai/dsh-bash` +**实现:** `@deepseek-ai/dsh-bash-local` +**消费者:** `@deepseek-ai/dsh-tool-bash`（内置于 agent-core） + +## Bash Service + +### ctx.bash.execute(request) + +- **request:** `BashRequest` +- **返回值:** `Promise` + +执行一个 bash 命令。 + +## BashRequest + +```typescript +interface BashRequest { + /** 要执行的命令 */ + command: string + /** 工作目录 */ + workdir?: string + /** 超时时间 (ms) */ + timeoutMs?: number +} +``` + +## BashResult + +```typescript +interface BashResult { + /** 退出码 */ + exitCode: number + /** stdout 输出 */ + stdout: string + /** stderr 输出 */ + stderr: string + /** 是否超时 */ + timedOut: boolean +} +``` + +## 配置 (dsh-bash-local) + +```typescript +interface Config { + /** 命令超时时间，默认 120000 (2 分钟) */ + timeoutMs: number +} +``` + +在 `cordis.yml` 中： + +```yaml +- name: '@deepseek-ai/dsh-bash-local' + config: + timeoutMs: 60000 +``` + +## 模型可用的 Tools + +`dsh-tool-bash` 向模型暴露以下 tools（由 `agent-core` 捆绑）： + +| Tool | 说明 | +|------|------| +| `bash` | 执行命令（同步，等待完成） | +| `bash_output` | 获取后台命令的输出 | +| `bash_kill` | 终止后台命令 | + +## 设计模式 + +Bash 是 Harness 的"能力三件套"典型案例： + +- `dsh-bash`（接口）：定义 `ctx.bash` 和 `BashRequest`/`BashResult` 类型 +- `dsh-bash-local`（实现）：通过 `child_process.spawn` 在本地执行 +- `dsh-tool-bash`（消费者）：将能力包装为模型可调用的 tool + +换一个沙箱执行器只需替换 `dsh-bash-local`，接口和 tool 不变。 diff --git a/website/zh-CN/api/harness/fs.md b/website/zh-CN/api/harness/fs.md new file mode 100644 index 0000000000..4e336ff962 --- /dev/null +++ b/website/zh-CN/api/harness/fs.md @@ -0,0 +1,78 @@ +# Filesystem (dsh-fs) + +文件系统操作接口。 + +**接口包:** `@deepseek-ai/dsh-fs` +**实现:** `@deepseek-ai/dsh-fs-local` + `@deepseek-ai/dsh-fs-policy` +**消费者:** `@deepseek-ai/dsh-tool-fs` + +## FS Service + +### ctx.fs.read(path, options?) + +- **path:** `string` +- **options:** `{ offset?: number; limit?: number }` +- **返回值:** `Promise` + +读取文件内容。 + +### ctx.fs.write(path, content) + +- **path:** `string` +- **content:** `string` +- **返回值:** `Promise` + +写入文件（覆盖）。 + +### ctx.fs.edit(path, edits) + +- **path:** `string` +- **edits:** `Edit[]` +- **返回值:** `Promise` + +对文件执行精确的字符串替换编辑。 + +### ctx.fs.stat(path) + +- **path:** `string` +- **返回值:** `Promise` + +获取文件/目录信息。 + +## 配置 (dsh-fs-local) + +```typescript +interface Config { + /** 工作目录（相对路径的基准） */ + cwd: string +} +``` + +## 策略门 (dsh-fs-policy) + +`dsh-fs-policy` 是一个可选的中间层插件，实现 read-before-write/edit 策略——模型必须先读取文件才能写入或编辑。这防止模型盲目覆盖文件。 + +在 `cordis.yml` 中，它位于 `fs-local` 和 `tool-fs` 之间： + +```yaml +- name: '@deepseek-ai/dsh-fs-local' + config: + cwd: !!js process.cwd() +- name: '@deepseek-ai/dsh-fs-policy' +- name: '@deepseek-ai/dsh-tool-fs' +``` + +## 模型可用的 Tools + +| Tool | 说明 | +|------|------| +| `read` | 读取文件内容（支持 offset/limit） | +| `write` | 写入文件（需要先 read） | +| `edit` | 精确字符串替换（需要先 read） | + +## 三件套结构 + +- `dsh-fs`：接口定义 +- `dsh-fs-local`：本地文件系统实现 +- `dsh-fs-policy`：策略门（read-before-write 检查） +- `dsh-tool-fs`：模型 tool 层 diff --git a/website/zh-CN/api/harness/llm.md b/website/zh-CN/api/harness/llm.md new file mode 100644 index 0000000000..82a4d8e225 --- /dev/null +++ b/website/zh-CN/api/harness/llm.md @@ -0,0 +1,124 @@ +# LLM (dsh-llm) + +LLM 服务接口和适配器注册。 + +**包名:** `@deepseek-ai/dsh-llm` +**服务名:** `ctx.llm` + +## LLM Service + +### ctx.llm.registerAdapter(models, adapter) + +- **models:** `string[]` 该适配器支持的模型名列表 +- **adapter:** `LlmAdapter` 适配器实例 +- **返回值:** `() => void` disposer + +注册一个 LLM 适配器。当请求中指定的模型名在 `models` 列表中时，路由到该适配器。 + +```typescript +ctx.llm.registerAdapter(['deepseek-v4-flash', 'deepseek-v4-pro'], adapter) +``` + +## LlmAdapter + +适配器基类。子类必须实现 `stream()` 方法。 + +### stream(options) + +- **options:** `GenerateOptions` +- **返回值:** `AsyncIterable` + +将统一请求格式转换为具体 API 的流式调用。 + +## GenerateOptions + +```typescript +interface GenerateOptions { + model: string + messages: Message[] + tools?: ToolSpec[] + system?: string + maxTokens?: number + temperature?: number +} +``` + +| 字段 | 说明 | +|------|------| +| `model` | 请求的模型名 | +| `messages` | 对话历史 | +| `tools` | 当前可用的 tool 列表（JSON Schema 格式） | +| `system` | 系统提示词 | +| `maxTokens` | 最大输出 token | +| `temperature` | 采样温度 | + +## StreamChunk + +流式响应的增量 chunk 类型： + +```typescript +type StreamChunk = + | { type: 'block-start'; index: number; blockType: 'text' | 'tool-call' } + | { type: 'text-delta'; index: number; text: string } + | { type: 'tool-call-delta'; index: number; id: CallId; name: string; argumentsDelta: string } + | { type: 'block-end'; index: number; block: ContentBlock } + | { type: 'usage'; usage: TokenUsage } + | { type: 'finish'; reason: FinishReason } +``` + +### 协议规则 + +1. 每个内容块以 `block-start` 开始，以 `block-end` 结束 +2. `index` 从 0 递增 +3. `text-delta` 只在 `blockType: 'text'` 的块中 +4. `tool-call-delta` 只在 `blockType: 'tool-call'` 的块中 +5. `usage` 在 `finish` 之前 +6. `finish` 必须是最后一个 chunk + +## CallId + +Tool call 的 opaque branded ID： + +```typescript +import { CallId } from '@deepseek-ai/dsh-llm' + +const id = CallId('call-abc123') +``` + +## TokenUsage + +```typescript +interface TokenUsage { + inputTokens: number + outputTokens: number +} +``` + +## FinishReason + +```typescript +type FinishReason = + | { kind: 'stop' } + | { kind: 'tool-calls' } + | { kind: 'max-tokens' } +``` + +## Message + +对话消息类型： + +```typescript +interface Message { + role: 'user' | 'assistant' + content: ContentBlock[] +} +``` + +## ContentBlock + +```typescript +type ContentBlock = + | { type: 'text'; text: string } + | { type: 'tool-call'; id: CallId; name: string; arguments: string } + | { type: 'tool-result'; callId: CallId; content: ContentBlock[]; isError?: boolean } +``` diff --git a/website/zh-CN/api/harness/session.md b/website/zh-CN/api/harness/session.md new file mode 100644 index 0000000000..5ff5b0d97b --- /dev/null +++ b/website/zh-CN/api/harness/session.md @@ -0,0 +1,56 @@ +# Session (dsh-session) + +会话事件流管理。 + +**包名:** `@deepseek-ai/dsh-session` +**服务名:** `ctx.session` + +## 概述 + +Session 是 Agent 的对话状态容器。所有模型可见的内容都必须经过 session 事件流记录——这是"model-visible = logged"原则的实现。 + +## SessionSurface + +会话的外部接口，用于查询当前状态。 + +### surface.messages + +- **类型:** `Message[]` + +当前会话的完整消息列表（经过 compaction 处理后的视图）。 + +### surface.events + +- **类型:** `SessionEvent[]` + +原始事件流。 + +## SessionEvent + +会话中所有变更以事件形式记录： + +```typescript +type SessionEvent = + | { type: 'user/message'; content: ContentBlock[] } + | { type: 'assistant/message'; content: ContentBlock[] } + | { type: 'tool/call'; name: string; args: unknown; callId: CallId } + | { type: 'tool/result'; callId: CallId; content: ContentBlock[]; isError?: boolean } + | { type: 'compact/start'; range: [number, number] } + | { type: 'compact/end'; summary: string } + | { type: 'todo/write'; items: TodoItem[] } + // ... 更多事件类型 +``` + +## 设计原则 + +### Model-visible = Logged + +任何到达模型请求的内容都必须能从 session log 重建。如果你要引入新的模型可见输入，必须先定义对应的 session event。 + +### 事件是 append-only + +Session 事件流是只追加的。修改历史（如 compaction）通过新事件（compact/start + compact/end）表达，而不是修改旧事件。 + +### 持久化 + +Session 事件流可以通过 `dsh-session-persistence` 持久化到磁盘（JSONL 或 SQLite），实现跨进程恢复。 diff --git a/website/zh-CN/api/harness/subagent.md b/website/zh-CN/api/harness/subagent.md new file mode 100644 index 0000000000..97ad7b5c87 --- /dev/null +++ b/website/zh-CN/api/harness/subagent.md @@ -0,0 +1,85 @@ +# Subagent (dsh-subagent) + +子代理委派接口。 + +**接口包:** `@deepseek-ai/dsh-subagent` +**实现:** `@deepseek-ai/dsh-subagent-spawn` / `@deepseek-ai/dsh-subagent-fork` +**消费者:** `@deepseek-ai/dsh-tool-subagent` + +## Subagent Service + +### ctx.subagent.run(request) + +- **request:** `SubagentRequest` +- **返回值:** `Promise` + +委派一个任务给子代理执行。 + +## SubagentRequest + +```typescript +interface SubagentRequest { + /** 使用的 provider 名称 */ + provider: string + /** 委派给子代理的提示 */ + prompt: string + /** 子代理使用的模型（可选，默认继承父） */ + model?: string +} +``` + +## SubagentResult + +```typescript +interface SubagentResult { + /** 子代理的最终回复 */ + response: string +} +``` + +## Provider 模式 + +Subagent 支持多种"后端"（provider），通过配置选择： + +### spawn + +创建一个全新的子代理实例，没有父级的对话历史： + +```yaml +- name: '@deepseek-ai/dsh-subagent-spawn' + config: + providerName: spawn +``` + +### fork + +创建一个携带父级已完成 turn 前缀的子代理，子代理"知道"父级的对话上下文： + +```yaml +- name: '@deepseek-ai/dsh-subagent-fork' + config: + providerName: fork +``` + +## 模型可用的 Tools + +通过 `dsh-tool-subagent` 暴露。可以加载多次，每次绑定不同 provider： + +```yaml +# 暴露为 "subagent" tool，使用 spawn 后端 +- name: '@deepseek-ai/dsh-tool-subagent' + config: + provider: spawn + toolName: subagent + +# 暴露为 "subagent_fork" tool，使用 fork 后端 +- name: '@deepseek-ai/dsh-tool-subagent' + config: + provider: fork + toolName: subagent_fork +``` + +## 使用场景 + +- **spawn** — 独立子任务（如"搜索这个问题"），子代理不需要知道父级上下文 +- **fork** — 需要上下文的子任务（如"基于我们刚才讨论的，去实现这个"），子代理继承父级的对话前缀 diff --git a/website/zh-CN/api/harness/tools.md b/website/zh-CN/api/harness/tools.md new file mode 100644 index 0000000000..d2011ad85e --- /dev/null +++ b/website/zh-CN/api/harness/tools.md @@ -0,0 +1,122 @@ +# Tools (dsh-tools) + +Tool 注册表和 `defineTool` DSL。 + +**包名:** `@deepseek-ai/dsh-tools` +**服务名:** `ctx.tools` + +## ToolRegistry + +### ctx.tools.register(tool) + +- **tool:** `ToolDefinition` +- **返回值:** `() => void` disposer + +注册一个 tool。返回的 disposer 可手动撤销注册（通常不需要，插件卸载时自动撤销）。 + +## defineTool\(options) + +类型安全的 tool 定义辅助函数。 + +```typescript +import { defineTool } from '@deepseek-ai/dsh-tools' + +const tool = defineTool({ + name: 'read_file', + description: 'Read a file from disk.', + parameters: { + path: { type: 'string', required: true, description: 'Absolute file path' }, + offset: { type: 'number' }, + limit: { type: 'number', description: 'Max lines to read' }, + }, + async execute(args) { + // args: { path: string; offset?: number; limit?: number } + }, +}) +``` + +### DefineToolOptions\ + +| 字段 | 类型 | 说明 | +|------|------|------| +| `name` | `string` | Tool 名称（全局唯一） | +| `description` | `string` | 发送给模型的描述 | +| `parameters` | `SchemaSpec` | 参数 schema（见下文） | +| `execute` | `(args: InferArgs, exec: ToolExecution) => Promise` | 执行函数 | +| `presentCall?` | `(args: InferArgs) => ToolCallView \| undefined` | UI 展示（纯函数） | +| `presentResult?` | `(args: InferArgs, result: ToolResult) => ToolResultView \| undefined` | 结果 UI 展示（纯函数） | + +## SchemaSpec + +参数 schema DSL。每个属性是一个 `SchemaProp`： + +```typescript +interface SchemaProp { + type: 'string' | 'number' | 'boolean' | 'object' | 'array' + required?: true + description?: string + enum?: string[] + properties?: SchemaSpec // type: 'object' 时 + items?: SchemaProp // type: 'array' 时 +} +``` + +### 类型推导 (InferArgs) + +`InferArgs` 自动从 `SchemaSpec` 推导 TypeScript 类型： + +- `required: true` → 必填字段 +- 无 `required` → 可选字段（`?`） +- `type: 'object'` + `properties` → 递归推导嵌套对象 +- `type: 'array'` + `items` → 推导为数组 + +## ToolDefinition + +运行时 tool 定义（`defineTool` 的返回值）： + +```typescript +interface ToolDefinition { + name: string + description: string + parameters: Record // JSON Schema + execute(args: unknown, exec: ToolExecution): Promise + presentCall?(args: unknown): ToolCallView | undefined + presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined +} +``` + +## ToolExecuteReturn + +```typescript +type ToolExecuteReturn = + | ContentBlock[] // 仅内容 + | { content: ContentBlock[]; meta?: unknown } // 内容 + 元信息 +``` + +## ToolArgsError + +当模型生成的参数不匹配 schema 时抛出： + +```typescript +class ToolArgsError extends HarnessError { + code: 'INVALID_ARGS' + violations: string[] +} +``` + +框架自动捕获并转换为 `isError` 结果返回给模型。 + +## validateArgs(spec, args) + +- **spec:** `SchemaSpec` +- **args:** `unknown` +- **返回值:** `string[]` 违规信息列表（空 = 合法） + +手动校验参数。`defineTool` 内部使用，通常不需要直接调用。 + +## schemaSpecToJsonSchema(spec) + +- **spec:** `SchemaSpec` +- **返回值:** `JsonSchemaObject` + +将 SchemaSpec 转换为标准 JSON Schema。用于发送给模型的 wire format。 diff --git a/website/zh-CN/api/index.md b/website/zh-CN/api/index.md new file mode 100644 index 0000000000..371cd1e622 --- /dev/null +++ b/website/zh-CN/api/index.md @@ -0,0 +1,25 @@ +# API 参考 + +本节提供 DeepSeek Harness 的完整 API 参考文档，分为两部分： + +## 框架 API + +Cordis 微内核提供的基础能力，所有插件开发都建立在这些 API 之上： + +- [Context](./cordis/context) — 上下文对象，所有服务和方法的入口 +- [Events](./cordis/events) — 事件系统 API（emit / on / bail / serial / waterfall） +- [Fiber](./cordis/fiber) — 作用域生命周期（状态机、effect、dispose） +- [Registry](./cordis/registry) — 插件注册（plugin / inject） +- [Service](./cordis/service) — 服务基类 + +## Harness API + +DeepSeek Harness SDK 提供的扩展 API，用于构建 Agent 能力： + +- [Tools (dsh-tools)](./harness/tools) — Tool 注册、defineTool DSL、Schema 类型系统 +- [LLM (dsh-llm)](./harness/llm) — LLM 服务、适配器注册、StreamChunk 协议 +- [Session (dsh-session)](./harness/session) — 会话事件流、消息类型 +- [Agent (dsh-agent)](./harness/agent) — Agent 实例管理、生命周期 +- [Bash (dsh-bash)](./harness/bash) — Bash 执行接口 +- [Filesystem (dsh-fs)](./harness/fs) — 文件系统接口 +- [Subagent (dsh-subagent)](./harness/subagent) — 子代理委派接口 diff --git a/website/zh-CN/design/composability.md b/website/zh-CN/design/composability.md new file mode 100644 index 0000000000..8370d8e136 --- /dev/null +++ b/website/zh-CN/design/composability.md @@ -0,0 +1,72 @@ +# 可组合性与插件系统 + +## 组合 + +编程的本质就是组合。将小的构建块拼装为更大的系统，再将大系统作为块继续拼装——这是从函数到模块到微服务一脉相承的思想。 + +组合可以分为两种： + +- **静态组合**：编译期确定的组合，例如函数调用、模块导入。 +- **动态组合**：运行时确定的组合，例如热更新、插件加载/卸载。 + +静态组合是逻辑的组合；动态组合为可组合性引入了时间和空间两个新维度。 + +## 三种可组合性 + +| 维度 | 定义 | 对应问题 | +|------|------|----------| +| **逻辑可组合性** (Logical) | 功能能否被任意拆分和组装 | 接口设计是否正交 | +| **时间可组合性** (Temporal) | 能否灵活、安全地控制组合的运行时序 | 能否热加载/卸载而不泄漏 | +| **空间可组合性** (Spatial) | 能否灵活、安全地管理组合的依赖关系 | 依赖缺失时行为是否确定 | + +一门编程语言或应用框架越多地使用组合范式，就称它的可组合性越好。 + +## 传统插件系统的问题 + +插件系统是动态组合的典型形式。浏览器扩展、IDE 插件、操作系统驱动，都是其实例。然而大多数插件系统并不可靠。 + +### 不可逆的插件化 + +以 VSCode 为例： + +- 卸载或更新插件时需要重启整个系统。 +- 无法在运行时追踪和回收副作用，导致内存泄漏和非预期的资源占用。 +- 即便提供了 `deactivate` 钩子，也无法强制开发者正确实现清理逻辑。 + +**根本原因**：未做到时间可组合——系统不知道某个插件产生了哪些副作用、占用了哪些资源。 + +### 不完全的插件化 + +- 无法表达插件间的依赖关系，扩展能力受限。 +- 只有外围功能被下放给插件，核心功能依然通过修改主体代码来实现。 + +**根本原因**：未做到空间可组合——系统缺乏对依赖关系的建模和管理。 + +## Cordis 的解法 + +Cordis 同时解决了上述两个问题： + +1. **可逆作用** (Revertible Effects) 实现时间可组合性——所有注册自动追踪、自动回收。 +2. **响应式余作用** (Reactive Coeffects) 实现空间可组合性——依赖声明驱动加载顺序。 + +两者通过**上下文模型** (Context Model) 统一为单一的编程范式：开发者只需通过 `ctx` 调用框架 API，可逆性和依赖管理由框架保证。 + +## 在 Harness 中的体现 + +DeepSeek Harness 将 Cordis 的可组合性应用到 Agent 开发领域： + +```typescript +// 一个 Harness 插件天然是可逆的 +export const inject = ['tools', 'llm'] // 空间可组合：声明依赖 + +export function apply(ctx: Context) { + // 时间可组合：注册会被自动追踪和回收 + ctx.tools.register(defineTool('my-tool', { + description: '...', + parameters: { /* ... */ }, + async execute(args) { /* ... */ }, + })) +} +``` + +插件卸载时，tool 自动注销、事件监听自动移除——无需手动清理。依赖的服务（如 `llm`）消失时，插件自动挂起；恢复时自动重新加载。 diff --git a/website/zh-CN/design/context-model.md b/website/zh-CN/design/context-model.md new file mode 100644 index 0000000000..cc25df88e5 --- /dev/null +++ b/website/zh-CN/design/context-model.md @@ -0,0 +1,129 @@ +# 上下文模型 + +上下文 (Context) 是 Cordis 将作用与余作用统一的运行时模型。它提供了一种编程范式，允许开发者无心智负担地编写时间、空间可组合的程序。 + +## 作用上下文 (Effect Context) + +当副作用被记录到全局环境时，$\mathcal{C}\times\left(\mathcal{C}\to\mathcal{C}\right)$ 也就变成了一个更大的 $\mathcal{C}$。 + +递归地定义： + +$$ +\begin{matrix} +\mathcal{C}_1=\mathcal{C}_0\times\left(\mathcal{C}_0\to\mathcal{C}_0\right)\\ +\mathcal{C}_2=\mathcal{C}_1\times\left(\mathcal{C}_1\to\mathcal{C}_1\right)\\ +\cdots\\ +\mathcal{C}_{n+1}=\mathcal{C}_n\times\left(\mathcal{C}_n\to\mathcal{C}_n\right)\\ +\end{matrix} +$$ + +每一层 $\mathcal{C}$ 包含上一层的状态，同时记录了上一层的副作用。 + +利用递归类型得到真正的作用上下文： + +$$ +\mathcal{C}=\mathcal{C}\times\left(\mathcal{C}\to\mathcal{C}\right) +$$ + +这就是 Cordis Context 的理论根基：**上下文既是状态容器，又是副作用追踪器。** + +## 上下文的派生 + +当一个插件被加载时，从当前上下文派生出新的上下文实例： + +``` +Root Context +├── Plugin A Context ← 管理 A 的副作用 +│ └── Sub-plugin Context +└── Plugin B Context ← 管理 B 的副作用 +``` + +- 子级上下文管理插件内部的全部副作用 +- 插件整体作为一个副作用被父级上下文收集 +- 父级 dispose 时，子级先被 dispose（保证依赖逆序） + +## 余作用上下文 (Coeffect Context) + +余作用由作用产生： + +- **提供服务**本身是一种作用——它占用了服务命名空间资源 +- 因此服务的提供被记录在作用上下文中 +- 上下文将作用与余作用关联起来，提供了统一的时间、空间可组合性 + +```typescript +// 提供服务 = 一个 effect（占用 ctx.llm 这个 "资源"） +class LlmService extends Service { + // 当此插件卸载时，ctx.llm 被回收（effect 的逆操作） + // 所有依赖 llm 的插件因 coeffect 不满足而挂起 +} +``` + +## 基于上下文的开发范式 + +上下文模型提供了两个关键优势： + +### 无感性 (Transparent) + +框架将领域中的所有方法都封装为 effect 版本。开发者只需调用 `ctx` 上的方法，就能自动获得时间/空间可组合性： + +```typescript +export function apply(ctx: Context) { + // 以下每一行都是 effect——卸载时自动逆序回收 + ctx.on('agent/step-result', validateResult) + ctx.tools.register(myTool) + ctx.llm.registerAdapter(['my-model'], adapter) + + // 开发者无需知道"可逆作用"的存在 + // 只需通过 ctx 调用，框架保证一切安全 +} +``` + +### 渐进性 (Incremental) + +可以逐步将现有框架中的 API 替换为可组合版本，无需一次性重写： + +```typescript +// 第一步：用 ctx.effect 包装遗留 API +ctx.effect(() => { + const legacy = legacySystem.register(handler) + return () => legacySystem.unregister(legacy) +}) + +// 第二步：在未来将遗留 API 原生改造为 effect +// 两种方式可以并存 +``` + +## 在 Harness 中的完整图景 + +DeepSeek Harness 的运行时是一个 Context 树： + +``` +Root Context (Cordis 应用) +├── dsh-session (提供 ctx.sessions) +├── dsh-tools (提供 ctx.tools) +├── dsh-llm (提供 ctx.llm) +│ └── deepseek-adapter (注册模型适配器) +├── dsh-agent-loop (提供 ctx.agentLoop) +├── dsh-bash (提供 ctx.bash) +│ └── bash-local (本地执行器实现) +├── dsh-fs (提供 ctx.fs) +│ └── fs-local (本地 FS 实现) +├── dsh-system-prompt (提供 ctx.systemPrompt) +└── Agent Context (由 agents.create() 派生) + ├── Agent 自己注册的 tools + ├── Agent 的 session + └── Subagent Context (进一步派生) +``` + +每个节点都是一个 Context 实例。插件加载/卸载、服务出现/消失、Agent 创建/销毁——这一切都在 Context 树上以统一的语义发生。 + +## 总结 + +| 概念 | 解决的问题 | Cordis 机制 | +|------|-----------|-------------| +| 作用上下文 | 副作用追踪与回收 | `ctx.effect()` / `fiber.dispose()` | +| 上下文派生 | 副作用的层级隔离 | `ctx.plugin()` 创建子 Context | +| 余作用上下文 | 依赖的动态管理 | `inject` 声明 + 服务生命周期 | +| 统一范式 | 开发者无需关心底层机制 | 只需通过 `ctx` 调用 API | + +这就是为什么 Harness 能在保持「一切皆插件」的同时，不给插件开发者增加心智负担——**上下文模型把复杂性封装在了框架内部**。 diff --git a/website/zh-CN/design/effects-coeffects.md b/website/zh-CN/design/effects-coeffects.md new file mode 100644 index 0000000000..01c181315f --- /dev/null +++ b/website/zh-CN/design/effects-coeffects.md @@ -0,0 +1,69 @@ +# 作用与余作用 + +## 作用 (Effects) + +Effects 是程序中对系统状态或外部环境产生影响的操作：I/O、状态修改、资源占用等。 + +学术界对作用有两种主要建模方式： + +### 单子作用 (Monadic Effects) + +- 通过单子 (monad) 将副作用封装为类型安全的计算链。 +- 提供 `return`（纯值注入）和 `bind`（链式组合）两个基本操作。 +- 以纯函数式的方式处理带有副作用的计算。(Moggi 1991, Wadler 1992) +- 代表语言：Haskell (IO Monad)、Rust (Result/Option) + +### 代数作用 (Algebraic Effects) + +- 允许在函数中"抛出"一个 effect，在调用栈的更高层次"捕获"并处理。 +- 类似异常处理，但更通用——处理后可以恢复执行。 +- 代表语言：Koka、Eff、OCaml 5+ (Kiselyov 2018, Kawahara 2020) + +## 余作用 (Coeffects) + +Coeffects 是程序执行时依赖的上下文信息：环境变量、系统资源、外部服务等。 + +- Coeffects 是 effects 的对偶 (dual) 概念，通常通过余单子 (comonad) 建模。(Petricek 2013, 2014; Brünnler 2014) +- 更前沿的理论将带有资源的上下文建模为 **graded algebra**（有序半环加最大元）： + - 加法 = 并行组合；0 元 = 无资源 + - 乘法 = 串行组合；1 元 = 单位资源 + - 序 = 资源约束；最大元 = 无限资源 + - (Breuvart 2015, Gaboardi 2016, Dal Lago 2022) + +## 现有理论的不足 + +这些理论主要面向**静态分析**和**短时程序**： + +1. **缺乏运行时追踪**：类型系统能标记副作用的存在，但无法在运行时追踪和回收。对长时运行程序（服务端、Agent），这意味着资源泄漏不可避免。 + +2. **缺乏动态性**：面向编译期分析，无法处理运行时的加载/卸载需求。 + +3. **崩溃而非降级**：类型不满足时直接拒绝编译或运行时崩溃，而长时运行程序更希望安全降级——挂起不满足依赖的部分，而非停止整个系统。 + +## Cordis 的突破 + +Cordis 选择了不同的路径——在运行时层面解决可组合性问题： + +| 现有理论 | Cordis 方案 | +|----------|-------------| +| 类型标记副作用 | 运行时追踪并自动回收副作用 | +| 编译期拒绝 | 运行时挂起/恢复 | +| 面向短时程序 | 面向长时运行程序设计 | + +这由两个互补机制实现： + +- **[可逆作用](./revertible-effects)** — 将副作用形式化为可逆的群操作 +- **[响应式余作用](./reactive-coeffects)** — 将依赖建模为具有生命周期的服务 + +## 在 Agent 开发中的意义 + +对 DeepSeek Harness 而言，作用/余作用模型直接支撑了以下能力： + +| 作用 (Effect) | 余作用 (Coeffect) | +|---------------|-------------------| +| 注册一个 tool | 依赖 tool registry 服务 | +| 注册一个 LLM adapter | 依赖 LLM 服务接口 | +| 监听 session 事件 | 依赖 session 服务存在 | +| 启动子进程 | 依赖 bash executor 实现 | + +每一个 effect 都可逆（tool 可注销、adapter 可移除）；每一个 coeffect 都有生命周期（服务消失则依赖者挂起）。这就是 Agent 能被安全热替换的根本原因。 diff --git a/website/zh-CN/design/index.md b/website/zh-CN/design/index.md new file mode 100644 index 0000000000..de6ebcf7aa --- /dev/null +++ b/website/zh-CN/design/index.md @@ -0,0 +1,39 @@ +# 系统设计 + +DeepSeek Harness 建立在 Cordis 微内核之上，采用「一切皆插件」的架构。本节阐述这套设计背后的理论基础和设计哲学。 + +## 核心思想 + +Harness 追求三种可组合性的统一： + +| 维度 | 含义 | Cordis 对应机制 | +|------|------|----------------| +| 逻辑可组合性 | 功能能否自由拆分和拼装 | 插件系统、事件系统 | +| 时间可组合性 | 运行时能否安全地加载/卸载功能 | 可逆作用、自动清理 | +| 空间可组合性 | 依赖关系能否被安全地声明和管理 | 服务生命周期、依赖注入 | + +这三种可组合性在上下文模型中统一为单一的编程范式。 + +## 目录 + +- [可组合性与插件系统](./composability) — 组合的本质，以及传统插件系统为什么不可靠 +- [作用与余作用](./effects-coeffects) — Cordis 效果系统的理论模型 +- [可逆作用](./revertible-effects) — 时间可组合性的形式化定义与证明 +- [响应式余作用](./reactive-coeffects) — 空间可组合性的服务语义 +- [上下文模型](./context-model) — Context 如何将作用与余作用统一 + +## 设计如何映射到 Harness + +| 理论概念 | Harness 中的体现 | +|----------|-----------------| +| 可逆作用 | `ctx.tools.register()` 返回 disposer；插件卸载时工具自动注销 | +| 响应式余作用 | `inject: ['llm']` 声明依赖；LLM 适配器不可用时插件自动挂起 | +| 上下文派生 | 子 Agent 拥有独立 Context，继承父级服务但有独立生命周期 | +| Waterfall 事件 | `agent/request` 链式拦截，任一监听器可决定最终请求参数 | +| Capability seam | bash/fs/web 三层拆分：接口 → 实现 → 模型工具 | + +## 进一步阅读 + +- [插件与生命周期](/zh-CN/develop/framework/) — 实践中的 Fiber 状态机 +- [服务与依赖](/zh-CN/develop/framework/service) — 服务声明与注入 +- [能力的三层拆分](/zh-CN/develop/practice/) — Capability seam 模式 diff --git a/website/zh-CN/design/reactive-coeffects.md b/website/zh-CN/design/reactive-coeffects.md new file mode 100644 index 0000000000..45345f934a --- /dev/null +++ b/website/zh-CN/design/reactive-coeffects.md @@ -0,0 +1,90 @@ +# 响应式余作用 + +响应式余作用 (Reactive Coeffects) 是 Cordis 实现**空间可组合性**的核心机制。 + +- 将代码中的资源依赖抽象为服务 (service) 的概念 +- 通过运行时生命周期语义，实现自动、安全、高效的资源管理 + +## 依赖的本质是生命周期 + +传统的依赖注入（如 Angular DI、Spring IoC）解决的是"怎么拿到依赖"的问题，但忽略了一个关键问题：**依赖是有生命周期的**。 + +一个数据库连接池可能重启，一个 API 服务可能下线，一个 LLM adapter 可能被热替换。当依赖消失时，依赖者应当如何表现？ + +- 崩溃？——对长时运行程序不可接受。 +- 继续运行？——可能产生不一致状态。 +- **自动挂起，等待恢复？**——Cordis 的选择。 + +## 服务与生命周期 + +Cordis 将程序中的资源依赖抽象为**服务** (service)： + +- 任何插件都可以声明自己依赖的服务列表 +- 服务存在明确的生命周期（提供、撤销） +- 运行时对依赖不满足的插件**等待**，而非拒绝 +- 服务生命周期结束前，依赖该服务的插件**先一步被回收** + +```typescript +// LLM 适配器插件：提供 llm 服务 +export class LlmService extends Service { + static inject = ['http'] // 自身依赖 http + // 当 http 不可用时，LlmService 自动挂起 + // 挂起导致 ctx.llm 不可用 + // 所有 inject: ['llm'] 的插件级联挂起 +} +``` + +## 与现有理论的对比 + +### 与 Comonad 余作用比较 + +基于 Comonad 的余作用（Petricek 2013）将上下文建模为静态结构，侧重于编译期分析。Cordis 的响应式余作用额外引入了**时序语义**： + +- 服务可在运行时出现/消失 +- 依赖关系随之动态建立/解除 +- 效果的生命周期由依赖关系决定 + +### 与 Grade Algebra 余作用比较 + +基于 Grade Algebra 的余作用（Gaboardi 2016）用有序半环描述资源的组合规则。Cordis 的服务依赖可以建模为**交换半群**： + +- 服务名构成依赖集合 +- 集合并（∪）对应并行依赖 +- 交换律：依赖 A + B ≡ 依赖 B + A（声明顺序无关） +- 结合律：依赖分组方式不影响语义 + +但 Cordis 还增加了代数不具备的运行时行为：当集合中的某个服务不可用时，整个依赖集不满足，触发挂起。 + +## 在 Cordis 中的实现 + +```typescript +// 声明依赖 +export const inject = ['tools', 'llm'] + +export function apply(ctx: Context) { + // 到这里时，ctx.tools 和 ctx.llm 一定可用 + // 如果任一服务消失，此插件自动卸载 + // 服务恢复后，自动重新执行 apply +} +``` + +服务生命周期变化时的行为： + +``` +llm service 可用 → 依赖 llm 的插件 PENDING → ACTIVE +llm service 消失 → 依赖 llm 的插件 ACTIVE → DISPOSED +llm service 恢复 → 依赖 llm 的插件重新 PENDING → ACTIVE +``` + +## 为什么 Agent 需要响应式余作用 + +在 Harness 场景下，响应式余作用直接支撑： + +| 场景 | 行为 | +|------|------| +| LLM adapter 热替换 | 依赖 `llm` 的插件自动挂起/恢复，中间不丢状态 | +| 按需加载 bash 执行器 | bash tool 只在 `bash` 服务就绪后注册 | +| 子 Agent 独立服务空间 | 通过 `ctx.isolate()` 隔离服务实例，互不干扰 | +| 可选能力降级 | `inject: { web: { required: false } }` 允许 web 不可用时继续运行 | + +这意味着 Harness 插件开发者无需编写防御性的 "if service exists" 检查——框架保证：当你的 `apply` 被调用时，声明的依赖一定已就绪。 diff --git a/website/zh-CN/design/revertible-effects.md b/website/zh-CN/design/revertible-effects.md new file mode 100644 index 0000000000..5133400e75 --- /dev/null +++ b/website/zh-CN/design/revertible-effects.md @@ -0,0 +1,128 @@ +# 可逆作用 + +可逆作用 (Revertible Effects) 是 Cordis 实现**时间可组合性**的核心机制。 + +- 在单子作用的基础上增加可逆性约束 +- 提供面向长时运行程序的作用系统 +- 确保程序可以在插件粒度上回到任意状态 + +## 副作用的封装 + +现实中的程序需要与各种副作用打交道。假设一个不纯函数： + +$$ +f_\text{impure}: \text{X}\to\text{Y} +$$ + +我们将所有可能的副作用用类型 $\mathcal{C}$ 封装，函数变为： + +$$ +f: \mathcal{C}\times\text{X}\to\mathcal{C}\times\text{Y} +$$ + +对于长时运行程序，忽略函数本身的入参和出参，$f$ 属于函数空间 $\mathfrak{F}=\mathcal{C}\to\mathcal{C}$。 + +## 从幺半群到群 + +任何函数 $f: \mathcal{C}\to\mathcal{C}$ 都是状态空间到自身的变换。在组合 $\circ$ 下构成**幺半群**： + +1. 封闭性：$f\circ g$ 也是 $\mathcal{C}\to\mathcal{C}$ +2. 结合律：$(f\circ g)\circ h=f\circ (g\circ h)$ +3. 单位元：$\text{id}$，使得 $f\circ\text{id}=\text{id}\circ f=f$ + +如果额外要求每个 $f$ 存在逆元 $f^{-1}$（即副作用可回收），$\mathfrak{F}$ 升级为**群**。 + +## 副作用都可逆吗？ + +观察计算机中的副作用模式： + +| 操作 | 占用资源 | 逆操作 | +|------|----------|--------| +| 打开文件 | 文件描述符 | 关闭文件 | +| 创建子进程 | 进程号 | 杀死进程 | +| 监听端口 | 端口 | 取消监听 | +| 添加回调函数 | 事件槽位 | 删除回调 | +| 分配内存 | 内存区块 | 回收内存 | + +**副作用就是对资源的占用。** 计算机的资源天然设计为可重复使用，因此这些副作用一定是可逆的。 + +## 追踪和回收副作用 + +Cordis 通过 $\text{effect}$ 和 $\text{restore}$ 函子追踪和回收逆函数。 + +### effect 函子 + +$$ +\begin{array}{} +\text{effect}&:& +\left(\mathcal{C}\to\mathcal{C}\right)&\to& +\mathcal{C}\times\left(\mathcal{C}\to\mathcal{C}\right)&\to& +\mathcal{C}\times\left(\mathcal{C}\to\mathcal{C}\right)\\ +\text{effect}&=&f&\mapsto&\left(c, h\right)&\mapsto&\left(f(c), h\circ f^{-1}\right) +\end{array} +$$ + +直觉：执行 $f$ 产生的副作用记入状态 $c$，同时将逆操作 $f^{-1}$ 追加到回收链 $h$ 中。 + +### 同态性证明 + +$\text{effect}$ 是从 $\mathcal{C}\to\mathcal{C}$ 到 $\mathcal{C}\times(\mathcal{C}\to\mathcal{C})\to\mathcal{C}\times(\mathcal{C}\to\mathcal{C})$ 的同态： + +$$ +\begin{aligned} +\text{effect}\ (f\circ g) \left(c, h\right) +&=\left((f\circ g)(c), h\circ (f\circ g)^{-1}\right)\\ +&=\left(f(g(c)), h\circ g^{-1}\circ f^{-1}\right)\\ +&=\left(\text{effect}\ f\right)\left(g(c), h\circ g^{-1}\right)\\ +&=\left(\text{effect}\ f\right)\circ\left(\text{effect}\ g\right) \left(c, h\right) +\end{aligned} +$$ + +这意味着：组合两个操作后再追踪 = 分别追踪后再组合。副作用追踪与执行顺序无关。 + +### restore 函子 + +$$ +\begin{array}{} +\text{restore}&:& +\mathcal{C}\times\left(\mathcal{C}\to\mathcal{C}\right)&\to& +\mathcal{C}\times\left(\mathcal{C}\to\mathcal{C}\right)\\ +\text{restore}&=&\left(c, h\right)&\mapsto&\left(h(c),\text{id}\right) +\end{array} +$$ + +直觉：将回收链 $h$ 应用到当前状态，一次性回收所有已追踪的副作用。 + +## 在 Cordis 中的实现 + +理论映射到 API： + +| 数学概念 | Cordis API | 说明 | +|----------|-----------|------| +| $\text{effect}(f)$ | `ctx.effect(() => { ...; return dispose })` | 注册副作用并返回清理函数 | +| $\text{restore}$ | `fiber.dispose()` | 执行 Fiber 的整个回收链 | +| $f^{-1}$ | dispose 返回值 / cleanup 函数 | 逆操作 | + +```typescript +export function apply(ctx: Context) { + // effect: 创建资源，返回其逆操作 + ctx.effect(() => { + const server = startServer(8080) // f: 占用端口 + return () => server.close() // f⁻¹: 释放端口 + }) + + // 框架 API 内部已封装 effect + ctx.on('event', handler) // 内部: effect(addListener, removeListener) + ctx.tools.register(myTool) // 内部: effect(addTool, removeTool) +} +// 当此插件被卸载时，restore 自动按逆序执行所有 f⁻¹ +``` + +## 为什么 Agent 需要可逆作用 + +在 Harness 场景下，可逆作用直接支撑： + +- **热替换 LLM 适配器**：卸载旧适配器（回收注册）、加载新适配器，无需重启 +- **动态 tool 管理**：根据对话上下文动态添加/移除 tool，不泄漏 +- **子 Agent 生命周期**：子 Agent 完成后，其注册的所有临时 tool 和监听器自动清理 +- **优雅关闭**：进程退出时所有插件按依赖逆序 dispose，确保资源完全释放 diff --git a/website/zh-CN/develop/basic/config.md b/website/zh-CN/develop/basic/config.md new file mode 100644 index 0000000000..49bcc4ca77 --- /dev/null +++ b/website/zh-CN/develop/basic/config.md @@ -0,0 +1,108 @@ +# 插件配置 + +让你的插件接受用户在 `cordis.yml` 中传入的配置。 + +## 定义 Config 类型 + +在插件中导出一个 `Config` 类型和可选的默认值： + +```typescript +import type { Context } from 'cordis' + +export const name = 'my-plugin' + +export interface Config { + greeting: string + maxRetries: number + verbose?: boolean +} + +export const Config = { + greeting: 'Hello', + maxRetries: 3, + verbose: false, +} + +export function apply(ctx: Context, config: Config) { + console.log(config.greeting) // 用户配置或默认值 +} +``` + +用户在 `cordis.yml` 中这样使用： + +```yaml +- name: './src/my-plugin.ts' + config: + greeting: 'Hi there' + maxRetries: 5 +``` + +未提供的字段使用导出的 `Config` 对象中的默认值。 + +## Schema 校验 + +对于需要严格校验的场景，使用 Schemastery 定义 schema： + +```typescript +import type { Context } from 'cordis' +import Schema from 'schemastery' + +export const name = 'validated-plugin' + +export interface Config { + apiKey: string + timeout: number + mode: 'fast' | 'accurate' +} + +export const Config = Schema.object({ + apiKey: Schema.string().required(), + timeout: Schema.number().default(30000), + mode: Schema.union(['fast', 'accurate']).default('fast'), +}) + +export function apply(ctx: Context, config: Config) { + // config 已经过校验，类型安全 +} +``` + +Schema 在插件加载时执行校验。如果配置不合法，插件会加载失败并给出明确错误信息。 + +## 设计原则 + +### 无硬编码可调参数 + +Harness 的约定：**任何两个部署可能想要不同值的东西，都应该是配置字段**。 + +```typescript +// 错误 — 硬编码超时时间 +const TIMEOUT = 30000 + +// 正确 — 可配置 +export interface Config { + timeoutMs: number // 默认 30000 +} +``` + +检验标准：能否在 `cordis.yml` 中改变这个值，而不需要修改代码？ + +### 配置错误要响亮 + +如果配置引用了不存在的东西（比如一个不存在的模型名），应该尽早报错，而不是静默跳过： + +```typescript +export function apply(ctx: Context, config: Config) { + if (!ctx.llm.hasAdapter(config.model)) { + throw new Error(`Model "${config.model}" is not registered by any LLM adapter`) + } +} +``` + +## 配合 HMR + +配置变更会触发插件热替换：修改 `cordis.yml` 中某个插件的 `config`，框架会卸载旧实例、加载新实例。由于注册都是效果（自动清理），这个过程是安全的。 + +## 下一步 + +- [插件与生命周期](../framework/) — 深入了解插件的完整生命周期 +- [服务与依赖](../framework/service) — 让你的插件对外提供服务 diff --git a/website/zh-CN/develop/basic/index.md b/website/zh-CN/develop/basic/index.md new file mode 100644 index 0000000000..71d6962edd --- /dev/null +++ b/website/zh-CN/develop/basic/index.md @@ -0,0 +1,148 @@ +# 第一个插件 + +本文带你编写一个最小的 Harness 插件并加载到 Agent 中。 + +## 插件是什么 + +在 Harness 中，插件是一个导出 `apply` 函数的 TypeScript 模块。框架在加载时调用 `apply`，传入一个 `ctx`（上下文对象），你通过 `ctx` 注册能力： + +```typescript +import type { Context } from 'cordis' + +export const name = 'my-plugin' + +export function apply(ctx: Context) { + // 在这里注册能力 +} +``` + +就这么简单。 + +## 创建插件文件 + +在你的项目目录下创建 `src/my-plugin.ts`： + +```typescript +import type { Context } from 'cordis' + +export const name = 'hello-plugin' + +export function apply(ctx: Context) { + // 监听 agent-loop 的 ready 事件 + ctx.on('ready', () => { + console.log('[hello-plugin] 插件已加载!') + }) +} +``` + +## 注册到 cordis.yml + +在你的 `cordis.yml` 中添加一条： + +```yaml +- id: hello + name: './src/my-plugin.ts' +``` + +启动后你会在控制台看到 `[hello-plugin] 插件已加载!`。 + +## 自动清理 + +通过 `ctx` 注册的任何东西——事件监听、tool、定时器——在插件卸载时都会被自动清理。你不需要手动 removeListener 或 clearInterval。 + +如果你有需要手动清理的资源（比如一个网络连接），用 `ctx.effect()` 告诉框架怎么清理： + +```typescript +export function apply(ctx: Context) { + ctx.effect(() => { + const timer = setInterval(() => { + console.log('heartbeat') + }, 5000) + + // 返回的函数会在插件卸载时被调用 + return () => clearInterval(timer) + }) +} +``` + +## 声明依赖 + +如果你的插件需要使用其他服务（如 `tools`、`llm`），需要声明 `inject`： + +```typescript +export const name = 'my-tool-plugin' +export const inject = ['tools'] + +export function apply(ctx: Context) { + // ctx.tools 现在可用 + ctx.tools.register(/* ... */) +} +``` + +框架会确保依赖的服务就绪后才加载你的插件。 + +## 插件的三种形态 + +除了函数形式，插件还支持对象形式和类形式： + +### 对象形式 + +```typescript +export default { + name: 'my-plugin', + inject: ['tools'], + apply(ctx: Context) { + // ... + }, +} +``` + +### 类形式 + +```typescript +import { Service } from 'cordis' + +export default class MyService extends Service { + static inject = ['tools'] + + constructor(ctx: Context) { + super(ctx, 'myService') + } + + start() { + // 服务启动逻辑 + } +} +``` + +大多数情况下，函数形式足够了。类形式用于需要对外提供服务的插件（见 [服务与依赖](../framework/service)）。 + +## 完整示例 + +参考仓库中的 `examples/echo-agent/src/echo-tool.ts`，这是一个注册 tool 的插件： + +```typescript +import type { Context } from 'cordis' +import { defineTool } from '@deepseek-ai/dsh-tools' + +export const name = 'echo-tool' +export const inject = ['tools'] + +export function apply(ctx: Context) { + ctx.tools.register(defineTool({ + name: 'echo', + description: 'Echo the given text back, uppercased.', + parameters: { + text: { type: 'string', required: true }, + }, + async execute(args) { + return [{ type: 'text', text: `ECHO: ${args.text.toUpperCase()}` }] + }, + })) +} +``` + +## 下一步 + +- [开发一个 Tool](./tool) — 详细了解 tool 定义 DSL +- [插件配置](./config) — 让插件接受用户配置 diff --git a/website/zh-CN/develop/basic/tool.md b/website/zh-CN/develop/basic/tool.md new file mode 100644 index 0000000000..96d58da78d --- /dev/null +++ b/website/zh-CN/develop/basic/tool.md @@ -0,0 +1,199 @@ +# 开发一个 Tool + +Tool 是模型可以调用的能力。本文介绍如何用 `defineTool` 编写一个 tool。 + +## 最小示例 + +```typescript +import type { Context } from 'cordis' +import { defineTool } from '@deepseek-ai/dsh-tools' + +export const name = 'my-tool' +export const inject = ['tools'] + +export function apply(ctx: Context) { + ctx.tools.register(defineTool({ + name: 'greet', + description: 'Greet someone by name.', + parameters: { + name: { type: 'string', required: true, description: 'The name to greet' }, + }, + async execute(args) { + // args 自动推导为 { name: string } + return [{ type: 'text', text: `Hello, ${args.name}!` }] + }, + })) +} +``` + +## 参数定义 + +`parameters` 用一种简洁的格式描述参数，框架会自动转换为模型需要的 JSON Schema。 + +### 基本类型 + +```typescript +parameters: { + path: { type: 'string', required: true }, + limit: { type: 'number' }, + recursive: { type: 'boolean' }, +} +// 推导类型: { path: string; limit?: number; recursive?: boolean } +``` + +### 枚举 + +```typescript +parameters: { + mode: { type: 'string', required: true, enum: ['read', 'write', 'append'] }, +} +// 推导类型: { mode: string } (运行时校验 enum 值) +``` + +### 嵌套对象 + +```typescript +parameters: { + options: { + type: 'object', + properties: { + timeout: { type: 'number' }, + retries: { type: 'number' }, + }, + }, +} +// 推导类型: { options?: { timeout?: number; retries?: number } } +``` + +### 数组 + +```typescript +parameters: { + tags: { + type: 'array', + items: { type: 'string' }, + }, +} +// 推导类型: { tags?: string[] } +``` + +### 每个属性的字段 + +| 字段 | 类型 | 说明 | +|------|------|------| +| `type` | `'string' \| 'number' \| 'boolean' \| 'object' \| 'array'` | 值类型 | +| `required` | `true` | 标记为必填（影响类型推导） | +| `description` | `string` | 发送给模型的描述 | +| `enum` | `string[]` | 允许的枚举值 | +| `properties` | `SchemaSpec` | 嵌套属性（type 为 object 时） | +| `items` | `SchemaProp` | 数组元素 schema（type 为 array 时） | + +## execute 函数 + +`execute` 接收经过校验的 `args`（类型自动推导）和一个 `exec` 上下文对象： + +```typescript +async execute(args, exec) { + // args: 根据 parameters 自动推导的类型 + // exec: ToolExecution 对象，提供执行上下文 + + // 返回 ContentBlock 数组 + return [{ type: 'text', text: 'result here' }] +} +``` + +### 返回值 + +`execute` 必须返回一个 `ContentBlock[]`，告诉模型 tool 的执行结果： + +```typescript +// 文本结果 +return [{ type: 'text', text: 'file content here...' }] + +// 多个 block +return [ + { type: 'text', text: 'Found 3 matches:' }, + { type: 'text', text: matchResults.join('\n') }, +] +``` + +### 参数校验 + +`defineTool` 在调用 `execute` 之前会自动校验模型生成的参数。如果参数不合法，会抛出 `ToolArgsError`，框架将其转换为 `isError` 结果返回给模型，让模型自行修正。 + +你不需要在 `execute` 里手动校验参数类型。 + +## 展示层 (Presentation) + +Tool 可以定义 UI 渲染方法，用于在终端或 ACP 客户端中展示 tool call 和 result： + +```typescript +defineTool({ + name: 'bash', + // ... + presentCall(args) { + return { + intent: 'terminal', + title: `bash(${JSON.stringify(args.command).slice(0, 60)})`, + } + }, + presentResult(args, result) { + return { + intent: 'terminal', + body: result.content.map(b => b.type === 'text' ? b.text : '').join(''), + } + }, +}) +``` + +`presentCall` 和 `presentResult` 是**纯函数**，不能有副作用——UI 可能在流式传输中和会话回放中多次调用它们。 + +## 注册与卸载 + +`ctx.tools.register()` 返回值就是 disposer。但由于你在 `ctx` 上调用，框架已经自动追踪了这个注册——插件卸载时会自动移除 tool。你不需要手动调用 disposer。 + +```typescript +// 这样就够了: +ctx.tools.register(defineTool({ /* ... */ })) + +// 不需要: +// const dispose = ctx.tools.register(...) +// ctx.on('dispose', dispose) +``` + +## 完整实战示例 + +一个文件计数 tool： + +```typescript +import type { Context } from 'cordis' +import { defineTool } from '@deepseek-ai/dsh-tools' +import { readdir } from 'node:fs/promises' + +export const name = 'file-counter' +export const inject = ['tools'] + +export function apply(ctx: Context) { + ctx.tools.register(defineTool({ + name: 'count_files', + description: 'Count files in a directory.', + parameters: { + path: { type: 'string', required: true, description: 'Directory path' }, + extension: { type: 'string', description: 'Filter by extension (e.g. ".ts")' }, + }, + async execute(args) { + const entries = await readdir(args.path, { withFileTypes: true }) + let files = entries.filter(e => e.isFile()) + if (args.extension) { + files = files.filter(f => f.name.endsWith(args.extension!)) + } + return [{ type: 'text', text: `Found ${files.length} files.` }] + }, + })) +} +``` + +## 下一步 + +- [插件配置](./config) — 让你的 tool 可配置 +- [能力三件套](../practice/) — 了解 seam/impl/consumer 模式 diff --git a/website/zh-CN/develop/framework/events.md b/website/zh-CN/develop/framework/events.md new file mode 100644 index 0000000000..0546fd68e7 --- /dev/null +++ b/website/zh-CN/develop/framework/events.md @@ -0,0 +1,152 @@ +# 事件系统 + +事件是 Cordis 插件间通信的核心机制。Harness 大量使用事件来实现松耦合的扩展点。 + +## 基本用法 + +### 监听事件 + +```typescript +ctx.on('event-name', (payload) => { + // 处理事件 +}) +``` + +### 触发事件 + +```typescript +ctx.emit('event-name', payload) +``` + +## 事件模式 + +Cordis 提供多种事件触发模式，适用于不同场景： + +### emit — 广播 + +所有监听器并行执行，不关心返回值： + +```typescript +// 触发 +ctx.emit('agent/turn-end', { agentId, turnIndex }) + +// 监听 +ctx.on('agent/turn-end', ({ agentId, turnIndex }) => { + console.log(`Turn ${turnIndex} ended`) +}) +``` + +### bail — 短路 + +依次调用监听器，第一个返回非 `undefined` 值的结果作为最终值： + +```typescript +// 触发 +const result = ctx.bail('some-check', input) + +// 监听（返回值阻止后续监听器） +ctx.on('some-check', (input) => { + if (shouldBlock(input)) return 'blocked' + // 返回 undefined 继续传递给下一个监听器 +}) +``` + +### serial — 顺序执行 + +所有监听器按注册顺序依次执行（异步安全）： + +```typescript +await ctx.serial('setup-phase', context) +``` + +### waterfall — 管道 + +每个监听器接收前一个的输出，形成数据管道。**必须调用 `next()` 传递给下游**，不调用即为否决： + +```typescript +// 触发 +const finalMessages = await ctx.waterfall('llm/pre-request', messages) + +// 监听（必须调用 next） +ctx.on('llm/pre-request', async (messages, next) => { + // 可以修改 messages + messages.push(extraMessage) + // 必须调用 next() 传递给下一个监听器 + return next(messages) +}) +``` + +::: warning +Waterfall 监听器**必须调用 `next()`**。不调用 `next` 等于否决整个管道，这是故意为之的设计——用于实现拦截/网关逻辑。 +::: + +## Typed Events + +Harness 使用 TypeScript 声明合并来为事件提供类型安全： + +```typescript +declare module 'cordis' { + interface Events { + 'my-plugin/ready': (payload: { id: string }) => void + 'my-plugin/check': (input: string) => boolean | undefined + } +} + +// 现在 ctx.on('my-plugin/ready', ...) 和 ctx.emit('my-plugin/ready', ...) +// 都有正确的类型推导 +``` + +## 命名约定 + +Harness 事件遵循 `namespace/action` 命名： + +``` +agent/pre-step — agent 执行一步之前 +agent/post-step — agent 执行一步之后 +tool/call — tool 被调用 +tool/result — tool 返回结果 +llm/pre-request — LLM 请求发送前 +session/event — 会话事件被记录 +compact/start — 压缩开始 +compact/end — 压缩结束 +``` + +## 事件也是效果 + +通过 `ctx.on()` 注册的监听器会在插件卸载时自动移除： + +```typescript +export function apply(ctx: Context) { + // 这个监听器在插件 dispose 时自动清理 + ctx.on('agent/turn-end', handler) +} +``` + +## 实战示例：日志插件 + +一个记录所有 tool 调用的简单插件： + +```typescript +import type { Context } from 'cordis' + +export const name = 'tool-logger' + +export function apply(ctx: Context) { + ctx.on('tool/call', ({ name, args }) => { + console.log(`[tool] ${name}(${JSON.stringify(args)})`) + }) + + ctx.on('tool/result', ({ name, result }) => { + const text = result.content + .filter(b => b.type === 'text') + .map(b => b.text) + .join('') + console.log(`[tool result] ${text.slice(0, 100)}`) + }) +} +``` + +## 下一步 + +- [能力三件套](../practice/) — 事件在 capability seam 中的角色 +- [LLM 适配器](../practice/llm-adapter) — 实现一个完整的 LLM 后端 diff --git a/website/zh-CN/develop/framework/index.md b/website/zh-CN/develop/framework/index.md new file mode 100644 index 0000000000..8d2f7c2b8a --- /dev/null +++ b/website/zh-CN/develop/framework/index.md @@ -0,0 +1,139 @@ +# 插件与生命周期 + +深入了解 Cordis 插件模型和生命周期状态机。 + +## Fiber 状态机 + +每个被加载的插件对应一个 **Fiber**（作用域）。Fiber 有以下状态： + +``` +PENDING → LOADING → ACTIVE + ↘ FAILED +ACTIVE → UNLOADING → DISPOSED +``` + +| 状态 | 含义 | +|------|------| +| PENDING | 已声明但依赖未就绪 | +| LOADING | 依赖就绪，正在执行 `apply` | +| ACTIVE | 插件运行中 | +| FAILED | `apply` 抛出异常 | +| UNLOADING | 正在卸载，清理中 | +| DISPOSED | 已完全卸载 | + +## 依赖驱动的加载 + +声明了 `inject` 的插件不会立即加载，而是等待依赖的服务就绪： + +```typescript +export const inject = ['tools', 'llm'] + +export function apply(ctx: Context) { + // 到这里时，ctx.tools 和 ctx.llm 一定存在 +} +``` + +如果依赖的服务消失（比如提供者被热替换），插件会被自动卸载（ACTIVE → DISPOSED），待服务恢复后重新加载。 + +## 自动清理机制 + +通过 `ctx` 做的任何注册，在插件卸载时都会自动撤销： + +```typescript +export function apply(ctx: Context) { + // 事件监听——卸载时自动移除 + ctx.on('some-event', handler) + + // 自定义资源——卸载时调用返回的函数 + ctx.effect(() => { + const connection = createConnection() + return () => connection.close() + }) +} +``` + +以下操作都会被自动追踪和清理： +- `ctx.on(event, handler)` — 事件监听 +- `ctx.tools.register(tool)` — tool 注册 +- `ctx.llm.registerAdapter(names, adapter)` — LLM 适配器注册 +- `ctx.effect(() => cleanup)` — 自定义资源 + +插件卸载时，这些注册按倒序逐个撤销。 + +## 嵌套上下文 + +`ctx.plugin()` 创建子 Fiber，它继承父上下文但有独立的生命周期： + +```typescript +export function apply(ctx: Context) { + // 注册一个子插件 + ctx.plugin(childPlugin) + + // 子插件有自己的 Fiber，父卸载时子也卸载 +} +``` + +## dispose 语义 + +当你需要提前终止一个插件实例： + +```typescript +const fiber = ctx.plugin(myPlugin) + +// 之后可以手动 dispose +fiber.dispose() +``` + +`dispose` 保证： +1. 该插件注册的所有东西被撤销 +2. 它的子插件也被递归卸载 +3. 所有异步清理完成后 Promise resolve + +## 热替换 (HMR) + +在开发环境中（`cordis.yml` 加载了 `@cordisjs/plugin-hmr`），修改插件源文件会自动触发： + +1. 卸载旧插件（清理所有注册） +2. 重新加载新代码 +3. 执行新的 `apply` + +因为所有注册都会被自动清理，所以热替换天然安全——不会留下旧状态。 + +## 实战：理解生命周期 + +```typescript +export function apply(ctx: Context) { + console.log('plugin loading') + + ctx.on('ready', () => { + console.log('context ready') + }) + + ctx.on('dispose', () => { + console.log('plugin disposing') + }) + + ctx.effect(() => { + console.log('effect registered') + return () => console.log('effect cleaned up') + }) +} +``` + +加载时输出： +``` +plugin loading +effect registered +context ready +``` + +卸载时输出（逆序）： +``` +plugin disposing +effect cleaned up +``` + +## 下一步 + +- [服务与依赖](./service) — 让你的插件对外提供能力 +- [事件系统](./events) — 插件间通信的核心机制 diff --git a/website/zh-CN/develop/framework/service.md b/website/zh-CN/develop/framework/service.md new file mode 100644 index 0000000000..08d9a1b2c8 --- /dev/null +++ b/website/zh-CN/develop/framework/service.md @@ -0,0 +1,147 @@ +# 服务与依赖 + +服务 (Service) 是插件对外暴露能力的方式。依赖 (inject) 是插件声明自己需要哪些服务。 + +## 什么是服务 + +在 Harness 中，`tools`、`llm`、`agents` 都是服务。服务是挂载在 `ctx` 上的命名能力： + +```typescript +ctx.tools // ToolRegistry 服务 +ctx.llm // LLM 服务 +ctx.agents // Agent 服务 +``` + +任何插件都可以提供一个新服务，供其他插件使用。 + +## 使用服务 + +声明 `inject` 来使用已有服务： + +```typescript +export const inject = ['tools'] + +export function apply(ctx: Context) { + // ctx.tools 在这里一定存在且就绪 + ctx.tools.register(/* ... */) +} +``` + +框架保证：在 `apply` 执行时，`inject` 声明的服务已经全部就绪。如果服务还没准备好，你的插件会等着，不会执行。 + +## 提供服务 + +### 使用 Service 基类 + +```typescript +import { Service, type Context } from 'cordis' + +export default class MetricsService extends Service { + static inject = ['llm'] // 本服务也可以依赖其他服务 + + constructor(ctx: Context) { + super(ctx, 'metrics') // 'metrics' 是服务名 + } + + // 服务的公开方法 + record(event: string, value: number) { + // ... + } +} +``` + +加载这个插件后，其他插件就可以通过 `ctx.metrics` 访问它： + +```typescript +export const inject = ['metrics'] + +export function apply(ctx: Context) { + ctx.metrics.record('tool_call', 1) +} +``` + +### 类型声明 + +使用 TypeScript 声明合并让 `ctx.metrics` 有正确类型： + +```typescript +import { Service, type Context } from 'cordis' + +declare module 'cordis' { + interface Context { + metrics: MetricsService + } +} + +export default class MetricsService extends Service { + constructor(ctx: Context) { + super(ctx, 'metrics') + } + + record(event: string, value: number) { /* ... */ } +} +``` + +## 依赖的行为 + +### 必选依赖 vs 可选依赖 + +```typescript +// 必选：服务不存在时，插件不会加载 +export const inject = ['tools'] + +// 可选：服务不存在时，插件仍然加载，但 ctx.xxx 可能是 undefined +export const inject = { optional: ['metrics'] } +``` + +### 服务消失时的行为 + +如果一个必选依赖的服务在运行时消失（比如提供者被卸载）： + +1. 依赖它的插件自动 dispose +2. 当服务重新出现时，插件自动重新加载 + +这保证了不会出现"调用一个已不存在的服务"的情况。 + +## 服务隔离 + +`cordis.yml` 支持服务隔离——同一个服务可以有多个实例，不同插件组看到不同实例： + +```yaml +- id: group-a + name: 'group:' + config: + - name: '@deepseek-ai/dsh-bash-local' + config: + timeoutMs: 5000 + - name: './src/plugin-a.ts' + +- id: group-b + name: 'group:' + config: + - name: '@deepseek-ai/dsh-bash-local' + config: + timeoutMs: 60000 + - name: './src/plugin-b.ts' +``` + +`plugin-a` 和 `plugin-b` 各自看到自己组内的 bash 实例，互不影响。 + +## Harness 内置服务一览 + +| 服务名 | 提供者 | 用途 | +|--------|--------|------| +| `tools` | dsh-tools | Tool 注册表 | +| `llm` | dsh-llm | LLM 调用 + 适配器注册 | +| `agents` | dsh-agent | Agent 实例管理 | +| `session` | dsh-session | 会话事件流 | +| `systemPrompt` | dsh-system-prompt | 系统提示词组装 | +| `bash` | dsh-bash-local | Bash 命令执行 | +| `fs` | dsh-fs-local | 文件系统操作 | +| `subagent` | dsh-subagent | 子代理委派 | +| `persistence` | dsh-session-persistence | 会话持久化 | + +## 下一步 + +- [事件系统](./events) — 插件间松耦合通信 +- [能力三件套](../practice/) — 服务在 seam 模式中的应用 diff --git a/website/zh-CN/develop/practice/index.md b/website/zh-CN/develop/practice/index.md new file mode 100644 index 0000000000..dd0ec1cb60 --- /dev/null +++ b/website/zh-CN/develop/practice/index.md @@ -0,0 +1,156 @@ +# 能力的三层拆分 + +当一个能力（插件）足够通用（比如"执行 bash 命令"），Harness 会把它拆成三个包：**接口**、**实现**、**消费者**。这样可以独立替换其中任何一层。 + +## 以 Bash 为例 + +考虑 "Bash 执行" 这个能力： + +- **接口** (`dsh-bash`) — 定义"bash 执行"长什么样：输入是什么、输出是什么 +- **实现** (`dsh-bash-local`) — 真正在本地跑命令的代码 +- **消费者** (`dsh-tool-bash`) — 把这个能力包装成模型能调用的 tool + +``` +┌─────────────┐ ┌──────────────────┐ ┌──────────────┐ +│ dsh-bash │────▶│ dsh-bash-local │ │ dsh-tool-bash│ +│ (接口) │ │ (实现) │ │ (消费者/tool)│ +└─────────────┘ └──────────────────┘ └──────────────┘ + ▲ │ + └────────────────────────────────────────────┘ + inject: ['bash'] +``` + +## 拆分的好处 + +### 具体实现可替换 + +同一个接口可以有多种实现。用户通过 `cordis.yml` 选择： + +```yaml +# 本地执行 +- name: '@deepseek-ai/dsh-bash-local' + +# 或：远程沙箱执行（未来） +# - name: '@deepseek-ai/dsh-bash-remote' +# config: +# endpoint: 'https://sandbox.example.com' +``` + +接口不变、tool 不变，只换实现。 + +### 独立演进 + +- 接口定义稳定后很少改动 +- 实现可以独立优化（性能、安全） +- 消费者（tool）可以调整对模型的呈现方式 + +### 依赖解耦 + +- 实现 depend on 接口 +- 消费者 depend on 接口 +- 实现和消费者**互不依赖** + +## Harness 中内置的三件套 + +| 能力 | 接口 (seam) | 实现 | 消费者 (tool) | +|------|-------------|------|---------------| +| Bash | `dsh-bash` | `dsh-bash-local` | `dsh-tool-bash` | +| 文件系统 | `dsh-fs` | `dsh-fs-local` + `dsh-fs-policy` | `dsh-tool-fs` | +| Web | `dsh-web` | `dsh-web-fetch-local` / `dsh-web-search-*` | `dsh-tool-web` | +| 子代理 | `dsh-subagent` | `dsh-subagent-spawn` / `dsh-subagent-fork` | `dsh-tool-subagent` | +| 压缩 | `dsh-compact` | `dsh-compact-basic` | (内置于 agent-loop) | + +## 开发你自己的三件套 + +### 第一步：定义接口 + +```typescript +// packages/my-cap/my-cap/src/index.ts +import { Service, type Context } from 'cordis' + +declare module 'cordis' { + interface Context { + myCap: MyCapService + } +} + +export abstract class MyCapService extends Service { + constructor(ctx: Context) { + super(ctx, 'myCap') + } + + /** 执行能力的核心方法 */ + abstract execute(request: MyCapRequest): Promise +} + +export interface MyCapRequest { + input: string +} + +export interface MyCapResult { + output: string +} +``` + +### 第二步：编写实现 + +```typescript +// packages/my-cap/my-cap-local/src/index.ts +import type { Context } from 'cordis' +import { MyCapService, type MyCapRequest, type MyCapResult } from '@deepseek-ai/dsh-my-cap' + +class MyCapLocal extends MyCapService { + async execute(request: MyCapRequest): Promise { + // 具体实现 + return { output: request.input.toUpperCase() } + } +} + +export const name = 'my-cap-local' + +export function apply(ctx: Context) { + ctx.plugin(MyCapLocal) +} +``` + +### 第三步：编写消费者 (tool) + +```typescript +// packages/my-cap/tool-my-cap/src/index.ts +import type { Context } from 'cordis' +import { defineTool } from '@deepseek-ai/dsh-tools' + +export const name = 'tool-my-cap' +export const inject = ['tools', 'myCap'] + +export function apply(ctx: Context) { + ctx.tools.register(defineTool({ + name: 'my_cap', + description: 'Execute my capability.', + parameters: { + input: { type: 'string', required: true }, + }, + async execute(args) { + const result = await ctx.myCap.execute({ input: args.input }) + return [{ type: 'text', text: result.output }] + }, + })) +} +``` + +### 在 cordis.yml 中组合 + +```yaml +- name: '@deepseek-ai/dsh-my-cap-local' +- name: '@deepseek-ai/dsh-tool-my-cap' +``` + +## 设计要点 + +- **不要预防性拆分** — 只有当你确实需要可替换实现时才拆三件套。一个简单的 tool 插件不需要拆分。 +- **接口定义 Request/Result 类型** — 实现和消费者只依赖接口包。 +- **Explicit > Implicit** — 实现中的默认值处理应该是显式的 `resolve(request): Spec` 步骤，不是隐藏在 `run()` 中的 `?? default`。 + +## 下一步 + +- [LLM 适配器](./llm-adapter) — 实现一个 LLM 后端（最常见的 seam 扩展） diff --git a/website/zh-CN/develop/practice/llm-adapter.md b/website/zh-CN/develop/practice/llm-adapter.md new file mode 100644 index 0000000000..20b1fa2c88 --- /dev/null +++ b/website/zh-CN/develop/practice/llm-adapter.md @@ -0,0 +1,169 @@ +# LLM 适配器 + +本文介绍如何为 Harness 接入一个新的 LLM 提供方。 + +## 概述 + +LLM 适配器是一个继承 `LlmAdapter` 的类，实现 `stream()` 方法，将 Harness 的统一请求格式转换为具体 API 的调用。 + +## 最小实现 + +```typescript +import type { Context } from 'cordis' +import { LlmAdapter, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm' + +class MyAdapter extends LlmAdapter { + private apiKey: string + + constructor(apiKey: string) { + super() + this.apiKey = apiKey + } + + async *stream(options: GenerateOptions): AsyncIterable { + // 1. 将 options.messages 转换为你的 API 格式 + // 2. 调用 API（流式） + // 3. 将 API 响应转换为 StreamChunk 序列 + } +} + +export interface Config { + apiKey: string + models: string[] +} + +export const name = 'my-llm-adapter' +export const inject = ['llm'] + +export function apply(ctx: Context, config: Config) { + const adapter = new MyAdapter(config.apiKey) + ctx.llm.registerAdapter(config.models, adapter) +} +``` + +## StreamChunk 协议 + +`stream()` 必须按以下协议 yield chunk： + +```typescript +// 1. 每个内容块以 block-start 开始 +yield { type: 'block-start', index: 0, blockType: 'text' } + +// 2. 文本块使用 text-delta +yield { type: 'text-delta', index: 0, text: 'Hello' } +yield { type: 'text-delta', index: 0, text: ' world' } + +// 3. 每个内容块以 block-end 结束（携带完整 block） +yield { + type: 'block-end', + index: 0, + block: { type: 'text', text: 'Hello world' }, +} + +// 4. Tool call 块 +yield { type: 'block-start', index: 1, blockType: 'tool-call' } +yield { + type: 'tool-call-delta', + index: 1, + id: CallId('call-123'), + name: 'bash', + argumentsDelta: '{"command":"ls"}', +} +yield { + type: 'block-end', + index: 1, + block: { + type: 'tool-call', + id: CallId('call-123'), + name: 'bash', + arguments: '{"command":"ls"}', + }, +} + +// 5. Token 用量 +yield { type: 'usage', usage: { inputTokens: 100, outputTokens: 50 } } + +// 6. 结束原因 +yield { type: 'finish', reason: { kind: 'stop' } } +// 或: { kind: 'tool-calls' } 表示模型想调用 tool +``` + +### 关键规则 + +- 每个 `block-start` 必须有对应的 `block-end` +- `index` 从 0 递增，标识内容块顺序 +- `tool-call-delta` 的 `argumentsDelta` 是 JSON 字符串的增量（可以一次 yield 全部，也可以分多次） +- `finish` 必须是最后一个 chunk +- `usage` 在 `finish` 之前 yield + +## GenerateOptions + +`stream()` 接收的请求包含： + +```typescript +interface GenerateOptions { + /** 模型名 */ + model: string + /** 对话历史 */ + messages: Message[] + /** 可用的 tool 列表 */ + tools?: ToolSpec[] + /** 系统提示词 */ + system?: string + /** 最大输出 token */ + maxTokens?: number + /** 温度 */ + temperature?: number +} +``` + +你的适配器需要将这些映射到具体 API 的参数。 + +## 注册适配器 + +```typescript +ctx.llm.registerAdapter(['model-name-1', 'model-name-2'], adapter) +``` + +第一个参数是该适配器支持的模型名列表。当用户在 `cordis.yml` 中配置 `model: model-name-1` 时，框架会路由到这个适配器。 + +## 在 cordis.yml 中使用 + +```yaml +- id: my-llm + name: './src/my-llm-adapter.ts' + config: + apiKey: !!js process.env.MY_API_KEY + models: + - my-model-v1 + - my-model-v2 + +- id: stdio-agent + name: '@deepseek-ai/dsh-stdio-agent' + config: + model: my-model-v1 # 引用上面注册的模型名 +``` + +## 实战参考 + +仓库中有两个完整实现可供参考： + +- `packages/llm/llm-deepseek/` — DeepSeek API 适配器（OpenAI 兼容格式） +- `packages/llm/llm-pi-ai/` — Pi AI 适配器（不同的 API 格式） +- `examples/echo-agent/src/mock-llm.ts` — 最简 mock 适配器（教学用） + +mock 适配器是学习 StreamChunk 协议的最佳起点——它用纯本地逻辑演示了完整的 chunk 序列。 + +## 错误处理 + +适配器中的异常会被 agent-loop 捕获并转化为 `LlmError`，告知上层。不需要在 `stream()` 内部做错误恢复——让异常冒泡即可。 + +```typescript +async *stream(options: GenerateOptions): AsyncIterable { + const response = await fetch(this.endpoint, { /* ... */ }) + if (!response.ok) { + throw new Error(`API error: ${response.status}`) + } + // ... 正常流式处理 +} +``` diff --git a/website/zh-CN/guide/config.md b/website/zh-CN/guide/config.md new file mode 100644 index 0000000000..d555a0a478 --- /dev/null +++ b/website/zh-CN/guide/config.md @@ -0,0 +1,342 @@ +# 配置文件 + +Harness 使用 `cordis.yml` 描述一个 Agent 加载哪些插件、以什么参数运行。 + +## 从例子开始 + +### echo-agent 的配置 + +这是一开始的第一个 Agent 的完整配置： + +```yaml +# 热替换：修改代码后自动重载，不用手动重启 +- id: hmr + name: '@cordisjs/plugin-hmr' + config: + root: ['.'] + +# Mock 模型：从本地 `.ts` 文件加载，注册一个名为 `mock-llm` 的工具 +# 本地模拟 LLM 响应，不联网 +- id: mock-llm + name: './src/mock-llm.ts' + +# Echo 工具：收到文本后转大写返回 +- id: echo-tool + name: './src/echo-tool.ts' + +# Bash 执行器：从 npm 包 `@deepseek-ai/dsh-bash-local`加载，提供 bash 命令执行能力 +- id: bash + name: '@deepseek-ai/dsh-bash-local' + +# 应用主体：把 session 管理、tool 调度、agent loop 等组装成一个可交互的终端 Agent +# 只需告诉它用哪个模型 (`model`)、什么人设 (`persona`) +- id: stdio-agent + name: '@deepseek-ai/dsh-stdio-agent' + config: + model: mock-echo + persona: 'You are echo-agent, a demo agent.' + welcome: 'echo-agent ready. Type a message ("echo " triggers the tool).' + persistenceRoot: './.sessions' +``` + +### coding-agent 的配置 + +真实场景——接入 DeepSeek API，带完整工具链： + +```yaml +# 热替换：同上，开发时自动重载 +- id: hmr + name: '@cordisjs/plugin-hmr' + config: + root: ['.'] + +# LLM 后端：从 npm 包加载，具备接入 DeepSeek API 能力 +# `!!js` 从环境变量读取密钥，不会写进配置文件 +# `models` 声明该适配器能处理哪些模型名 +- id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + config: + apiKey: !!js process.env.DEEPSEEK_API_KEY + baseURL: !!js process.env.DEEPSEEK_BASE_URL + models: + - deepseek-v4-pro + - deepseek-v4-flash + +# Bash 执行器：让 Agent 能跑 shell 命令 +# timeoutMs 设置单条命令的超时时间 +- id: bash + name: '@deepseek-ai/dsh-bash-local' + config: + timeoutMs: 60000 + +# 应用主体：和 echo-agent 一样的框架，只是配置不同 +# `model` 指定默认使用哪个模型（要和上面 models 列表里的名字对应） +# `persona` 是系统提示词，{{model}} 会被替换为实际模型名 +# `resumeSessionId` 设了就恢复旧对话，没设就每次新建 +- id: stdio-agent + name: '@deepseek-ai/dsh-stdio-agent' + config: + model: deepseek-v4-flash + resumeSessionId: !!js process.env.RESUME_SESSION_ID + persistenceRoot: './.sessions' + welcome: 'agent REPL ready. Give it a coding task.' + persona: | + You are coding-agent, a coding assistant powered by the {{model}} model. + Verify your work by running the code or tests. Keep answers brief and factual. + +# 自动压缩：对话太长时自动总结旧内容，腾出上下文空间 +# contextWindow 是模型能看到的 token 上限 +# thresholdRatio 超过这个比例就触发压缩 +- id: compact-basic + name: '@deepseek-ai/dsh-compact-basic' + config: + contextWindow: 128000 + thresholdRatio: 0.8 + retainTokens: 20480 + maxTokens: 8192 + +# 子代理：把子任务分配给独立的 Agent 去做 +# subagent 是服务注册，spawn/fork 是两种委派方式： +# spawn — 全新子代理，不知道父级在聊什么 +# fork — 继承父级对话上下文的子代理 +# tool-subagent 把委派能力暴露给模型，toolName 是模型看到的工具名 +- id: subagent + name: '@deepseek-ai/dsh-subagent' + +- id: subagent-spawn + name: '@deepseek-ai/dsh-subagent-spawn' + config: + providerName: spawn + +- id: subagent-fork + name: '@deepseek-ai/dsh-subagent-fork' + config: + providerName: fork + +- id: tool-subagent + name: '@deepseek-ai/dsh-tool-subagent' + config: + provider: spawn + toolName: subagent + +- id: tool-subagent-fork + name: '@deepseek-ai/dsh-tool-subagent' + config: + provider: fork + toolName: subagent_fork + +# 任务追踪：模型可以用 todo_write 记录和更新任务清单 +- id: tool-todo + name: '@deepseek-ai/dsh-tool-todo' + +# 文件系统：让 Agent 能读写编辑文件 +# fs-local 提供本地文件操作能力，cwd 是工作目录 +# fs-policy 是安全策略——必须先读才能写，防止模型盲写 +# tool-fs 把能力暴露给模型（read / write / edit 三个工具） +- id: fs-local + name: '@deepseek-ai/dsh-fs-local' + config: + cwd: !!js process.cwd() + +- id: fs-policy + name: '@deepseek-ai/dsh-fs-policy' + +- id: tool-fs + name: '@deepseek-ai/dsh-tool-fs' +``` + +和 echo-agent 对比：同一个 `dsh-stdio-agent` 应用主体，只是把 mock 换成了真实 API，加上了更多工具插件。 + +## 语法详解 + +### 插件声明字段 + +每个插件条目支持以下字段： + +| 字段 | 类型 | 必填 | 说明 | +|------|------|------|------| +| `name` | string | 是 | 插件来源（npm 包名或相对路径） | +| `id` | string | 否 | 实例标识符，用于日志和调试 | +| `config` | object | 否 | 传递给插件的配置 | +| `disabled` | boolean | 否 | 设为 `true` 临时禁用该插件 | + +### 插件来源 (`name`) + +**npm 包** — 已安装的 `@deepseek-ai/dsh-*` 包或第三方包： + +```yaml +- name: '@deepseek-ai/dsh-llm-deepseek' +``` + +**相对路径** — 本地 TypeScript 文件（相对于 `cordis.yml` 所在目录）： + +```yaml +- name: './src/my-tool.ts' +``` + +### 环境变量 (`!!js`) + +用 `!!js` 标签在配置中引用运行时表达式： + +```yaml +config: + apiKey: !!js process.env.DEEPSEEK_API_KEY + cwd: !!js process.cwd() +``` + +::: warning +是 `!!js`（两个感叹号），不是 `!js`。写错了会静默失败。 +::: + +环境变量从仓库根目录的 `.env` 文件自动加载（已被 gitignore）。 + +### 禁用插件 + +不想删配置但暂时不加载？加一行 `disabled`： + +```yaml +- id: compact-basic + name: '@deepseek-ai/dsh-compact-basic' + disabled: true + config: + contextWindow: 128000 +``` + +## 各插件配置参考 + +### stdio-agent（标准应用主体） + +**包名:** `@deepseek-ai/dsh-stdio-agent` + +| 字段 | 类型 | 默认值 | 说明 | +|------|------|--------|------| +| `model` | string | **必填** | 使用的模型名，需与 LLM 适配器注册的名字一致 | +| `persona` | string | `''` | 系统提示词。支持 `{{model}}` 等模板变量 | +| `toolOrder` | string[] | — | 模型看到的工具顺序。省略则按字母排序 | +| `persistenceRoot` | string | `'./.sessions'` | 会话日志存储目录 | +| `welcome` | string | `'ready.'` | 启动时显示的欢迎信息 | +| `resumeSessionId` | string | — | 恢复指定会话 ID。留空则每次新建 | + +### llm-deepseek（DeepSeek 适配器） + +**包名:** `@deepseek-ai/dsh-llm-deepseek` + +| 字段 | 类型 | 默认值 | 说明 | +|------|------|--------|------| +| `apiKey` | string | `$DEEPSEEK_API_KEY` | API 密钥。省略则从环境变量读取 | +| `baseURL` | string | `$DEEPSEEK_BASE_URL` 或官方地址 | API 端点 | +| `models` | string[] | `['deepseek-v4-flash', 'deepseek-v4-pro']` | 注册的模型名列表 | +| `thinking` | `'enabled'` \| `'disabled'` | `'enabled'` | 是否开启思维链 | +| `reasoningEffort` | `'high'` \| `'max'` | — | 思维链深度（仅 thinking 开启时有效） | + +### bash-local（Bash 执行器） + +**包名:** `@deepseek-ai/dsh-bash-local` + +| 字段 | 类型 | 默认值 | 说明 | +|------|------|--------|------| +| `cwd` | string | `process.cwd()` | 命令执行的工作目录 | +| `timeoutMs` | number | `120000` | 单条命令的超时时间（毫秒） | +| `maxTimeoutMs` | number | `600000` | 单条命令超时的上限（模型不能请求更久） | +| `maxOutputBytes` | number | `64000` | 单次输出的内存上限（超出后溢出到临时文件） | +| `graceMs` | number | `3000` | kill 时从 SIGTERM 到 SIGKILL 的等待时间 | + +### compact-basic（自动压缩） + +**包名:** `@deepseek-ai/dsh-compact-basic` + +| 字段 | 类型 | 默认值 | 说明 | +|------|------|--------|------| +| `contextWindow` | number | **必填** | 模型的上下文窗口大小（token） | +| `thresholdRatio` | number | **必填** | token 占用超过此比例时触发压缩（0-1） | +| `retainTokens` | number | **必填** | 压缩后至少保留多少 token 的近期内容 | +| `maxTokens` | number | **必填** | 总结时的最大输出 token | +| `summarizationModel` | string | `''`（用当前模型） | 专门用于总结的模型名 | +| `compactionRetries` | number | **必填** | 首次压缩后仍超标时的额外重试次数 | +| `auto` | boolean | `true` | 是否自动在每步前检查并触发压缩 | +| `charsPerToken` | number | `4` | 每 token 估算字符数。中文应设 1-2 | + +### fs-local（文件系统） + +**包名:** `@deepseek-ai/dsh-fs-local` + +| 字段 | 类型 | 默认值 | 说明 | +|------|------|--------|------| +| `cwd` | string | `process.cwd()` | 工作目录，相对路径以此为基准 | + +### fs-policy（文件系统策略） + +**包名:** `@deepseek-ai/dsh-fs-policy` + +无配置项。加载即启用"必须先读才能写"的安全策略。 + +### tool-fs（文件系统工具） + +**包名:** `@deepseek-ai/dsh-tool-fs` + +无配置项。加载后向模型暴露 `read`、`write`、`edit` 三个工具。 + +### tool-web（Web 工具） + +**包名:** `@deepseek-ai/dsh-tool-web` + +| 字段 | 类型 | 默认值 | 说明 | +|------|------|--------|------| +| `search` | boolean | `true` | 是否注册 `web_search` 工具 | +| `fetch` | boolean | `true` | 是否注册 `web_fetch` 工具 | +| `searchMaxResults` | number | `8` | 单次搜索返回的最大结果数 | + +### subagent-spawn / subagent-fork（子代理后端） + +**包名:** `@deepseek-ai/dsh-subagent-spawn` / `@deepseek-ai/dsh-subagent-fork` + +| 字段 | 类型 | 默认值 | 说明 | +|------|------|--------|------| +| `providerName` | string | `'spawn'` / `'fork'` | 注册到子代理服务的 provider 名称 | + +### tool-subagent（子代理工具） + +**包名:** `@deepseek-ai/dsh-tool-subagent` + +| 字段 | 类型 | 默认值 | 说明 | +|------|------|--------|------| +| `provider` | string | **必填** | 使用哪个 provider（如 `spawn`、`fork`） | +| `toolName` | string | `'subagent'` | 暴露给模型的工具名。多次加载时必须不同 | +| `agentOptions.model` | string | — | 子代理使用的模型名（省略则继承父代理） | + +### tool-todo（任务清单） + +**包名:** `@deepseek-ai/dsh-tool-todo` + +无配置项。加载后向模型暴露 `todo_write` 工具。 + +### hmr（热替换） + +**包名:** `@cordisjs/plugin-hmr` + +| 字段 | 类型 | 默认值 | 说明 | +|------|------|--------|------| +| `root` | string[] | **必填** | 监听文件变更的目录列表 | + +::: tip +hmr 仅用于开发环境。它需要 `node --expose-internals` 启动参数，`demo:*` 脚本已自动添加。 +::: + +--- + +## 加载顺序 + +`cordis.yml` 的顺序就是加载顺序。推荐： + +1. **hmr** — 热替换（仅开发时需要） +2. **LLM 适配器** — 模型后端 +3. **执行器** — bash、fs 等能力提供者 +4. **应用主体** — `dsh-stdio-agent` 或 `dsh-acp-agent` +5. **附加插件** — compact、subagent、todo 等 + +应用主体内部已经捆绑了核心能力（session、tools、agent-loop），不需要手动加载。 + +## 下一步 + +- [开发插件](../develop/basic/) — 编写自己的插件 +- [API 参考](../api/) — 查看各插件完整接口 diff --git a/website/zh-CN/guide/index.md b/website/zh-CN/guide/index.md new file mode 100644 index 0000000000..8b7211b308 --- /dev/null +++ b/website/zh-CN/guide/index.md @@ -0,0 +1,47 @@ +# 介绍 + +DeepSeek Harness 是一个**插件化的 Agent 开发框架**，基于 [Cordis](https://github.com/cordiverse/cordis) 微内核构建。它的核心理念是：**一切皆插件**。 + +## 它是什么 + +Harness 将一个 AI Agent（智能体） 所需要的所有能力——LLM 调用、工具执行、会话管理、子任务分配——全部构建为可组合的插件。你通过一个 `cordis.yml` 配置文件来声明加载哪些插件、使用什么参数，就能组装出一个完整的 Agent。 + +```yaml +# 选择 LLM 后端 +- name: '@deepseek-ai/dsh-llm-deepseek' + config: + apiKey: !!js process.env.DEEPSEEK_API_KEY + +# 选择应用模板 +- name: '@deepseek-ai/dsh-stdio-agent' + config: + model: deepseek-v4-flash +``` + +## 适合谁 + +### 应用使用者 + +如果你只是想用一个现成的 Agent 应用（如编程助手、对话代理），你需要的全部操作就是： + +1. 复制一个 example 模板 +2. 填写 API key +3. 运行 + +不需要写任何代码。详见 [快速开始](./quickstart)。 + +### 插件开发者 + +如果你想为 Agent 添加新能力——一个自定义 tool、一个新的 LLM 适配器、一个新的执行后端——你需要编写一个插件。Harness 提供了清晰的扩展接口和类型安全的开发体验。详见 [开发](../develop/basic/)。 + +## 核心特性 + +- **只需要配置** — `cordis.yml` 决定能力集合，换模型、加工具只需改一行 +- **随时替换 (HMR)** — 开发时修改插件代码，无需重启进程 + +## 技术栈 + +- **运行时**: Node.js >= 24 +- **语言**: TypeScript (ESM) +- **框架**: Cordis +- **包管理**: pnpm workspaces diff --git a/website/zh-CN/guide/quickstart.md b/website/zh-CN/guide/quickstart.md new file mode 100644 index 0000000000..f15ac182cf --- /dev/null +++ b/website/zh-CN/guide/quickstart.md @@ -0,0 +1,98 @@ +# 快速开始 + +本指南带你在 5 分钟内跑起一个 Agent。 + +## 环境准备 + +- [Node.js](https://nodejs.org/) >= 24 +- [pnpm](https://pnpm.io/) >= 9 + +```sh +# 确认版本 +node -v # v24.x 或更高 +pnpm -v # 9.x 或更高 +``` + +## 第一步：运行 echo-agent + +echo-agent 不需要 API key，装好依赖就能跑。 + +```sh +# 克隆仓库 +git clone https://github.com/deepseek-harness/deepseek-harness.git +cd deepseek-harness + +# 安装依赖 +pnpm install +# 如果看到 ERR_PNPM_IGNORED_BUILDS，可以忽略——安装已经成功了。 +# 想消除这个提示可以跑一次: pnpm approve-builds + +# 启动 echo-agent +pnpm run demo:echo +``` + +启动后你会看到： + +``` +echo-agent ready. Type a message ("echo " triggers the tool). +> +``` + +试着输入： + +``` +> echo hello world +``` + +你会看到模型发起了一次 tool call（工具调用），echo 工具将文本转为大写并返回： + +``` +[tool call] echo({"text":"hello world"}) +[tool result] ECHO: HELLO WORLD +``` + +恭喜！环境没问题。 + +## 第二步：使用真实模型调用 + +接下来接入真实的 DeepSeek 模型，跑一个完整的命令行 Agent。 + +### 获取 API Key + +前往 [DeepSeek Platform](https://platform.deepseek.com/) 获取你的 API key。 + +### 配置环境变量 + +在仓库根目录创建 `.env` 文件（已被 gitignore）： + +```sh +DEEPSEEK_API_KEY=sk-your-key-here +``` + +### 启动 coding-agent + +```sh +pnpm run demo:repl +``` + +``` +agent REPL ready. Give it a coding task. +> +``` + +这就是一个完整的编程助手，它能读写文件、跑命令、拆分子任务。 + +试着给它一个任务： + +``` +> 在当前目录创建一个 hello.js，内容是打印 "Hello from Harness!"，然后运行它 +``` + +## 回头看 + +echo-agent 和 coding-agent 用的是同一个应用框架(`@deepseek-ai/dsh-stdio-agent`)，区别只在 `cordis.yml`——换了哪些插件、填了什么配置。你以后定制自己的 Agent 也是同样的方式。 + +## 下一步 + +- [配置文件](./config) — 了解 `cordis.yml` 的完整语法 +- [开发插件](../develop/basic/) — 编写你自己的 tool 或后端 diff --git a/website/zh-CN/index.md b/website/zh-CN/index.md new file mode 100644 index 0000000000..90b23e483a --- /dev/null +++ b/website/zh-CN/index.md @@ -0,0 +1,21 @@ +--- +layout: home +hero: + name: DeepSeek Harness + text: 插件化 Agent 开发框架 + tagline: 基于 Cordis 微内核，一切皆插件 + actions: + - theme: brand + text: 快速开始 + link: /zh-CN/guide/quickstart + - theme: alt + text: 开发插件 + link: /zh-CN/develop/basic/ +features: + - title: 插件化架构 + details: 基于 Cordis 效果系统，所有能力通过插件注册，加载即生效、卸载即还原。 + - title: 配置即组合 + details: 一个 cordis.yml 决定整个 Agent 的能力组合——换模型、加工具，只需改一行配置。 + - title: 开箱即用 + details: 内置 LLM 调用、文件读写、Bash 执行、子代理委派等完整工具链，复制模板即可运行。 +--- From eea0a99985741a9e8a89466c4955fd2a4c07dc97 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Fri, 10 Jul 2026 20:52:27 +0800 Subject: [PATCH 005/359] feat: expose agent session log location --- docs/config-catalog.md | 8 +- docs/cordis-catalog/services.md | 3 +- docs/core-data-structures/persistence.md | 17 +++- docs/module-graph.md | 9 +- docs/rfc/INDEX.md | 1 + ...0-bash-stdin-env-trusted-plugin-surface.md | 2 +- .../feature/2026-06-30-hook-bridges.md | 4 +- ...agent-session-identity-and-log-location.md | 86 ++++++++++++++++ docs/tool-catalog.md | 2 +- .../snapshots/both-mode-turn/session.jsonl | 2 +- .../snapshots/code-mode-turn/session.jsonl | 2 +- .../tests/snapshots/text-turn/session.jsonl | 2 +- packages/bash/tool-bash/README.md | 8 +- packages/bash/tool-bash/package.json | 3 + packages/bash/tool-bash/src/index.ts | 21 ++++ .../bash/tool-bash/tests/integration.spec.ts | 45 ++++++++- packages/bash/tool-bash/tests/tools.spec.ts | 99 ++++++++++++++++++- packages/bash/tool-bash/tsconfig.json | 3 + .../cordis/tool-cordis/src/api-catalog.ts | 5 + packages/hooks/hooks-claude/README.md | 2 + packages/hooks/hooks-claude/package.json | 3 + packages/hooks/hooks-claude/src/index.ts | 44 +++++---- .../hooks/hooks-claude/tests/coverage.spec.ts | 28 +++++- packages/hooks/hooks-claude/tsconfig.json | 3 + packages/hooks/hooks-codex/README.md | 2 + packages/hooks/hooks-codex/package.json | 3 + packages/hooks/hooks-codex/src/index.ts | 29 +++--- .../hooks/hooks-codex/tests/coverage.spec.ts | 30 +++++- packages/hooks/hooks-codex/tsconfig.json | 3 + .../session-persistence-jsonl/README.md | 2 + .../session-persistence-jsonl/src/index.ts | 12 ++- .../tests/jsonl.spec.ts | 42 +++++++- .../session-persistence-sqlite/README.md | 2 + .../session-persistence-sqlite/src/index.ts | 12 ++- .../tests/sqlite.spec.ts | 6 ++ .../session-persistence/README.md | 7 +- .../session-persistence/src/index.ts | 21 ++++ .../tests/persistence.spec.ts | 4 + pnpm-lock.yaml | 18 ++++ scripts/type-equiv.manifest.json | 1 + 40 files changed, 526 insertions(+), 70 deletions(-) create mode 100644 docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 772924df9c..ce1518066b 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -273,7 +273,7 @@ export interface Config { } ``` -Source: [`packages/hooks/hooks-claude/src/index.ts:56`](../packages/hooks/hooks-claude/src/index.ts) +Source: [`packages/hooks/hooks-claude/src/index.ts:57`](../packages/hooks/hooks-claude/src/index.ts) ## `@deepseek-ai/dsh-hooks-codex` @@ -298,7 +298,7 @@ export interface Config { } ``` -Source: [`packages/hooks/hooks-codex/src/index.ts:43`](../packages/hooks/hooks-codex/src/index.ts) +Source: [`packages/hooks/hooks-codex/src/index.ts:44`](../packages/hooks/hooks-codex/src/index.ts) ## `@deepseek-ai/dsh-invariants` @@ -446,7 +446,7 @@ export interface Config { } ``` -Source: [`packages/session-persistence/session-persistence-jsonl/src/index.ts:35`](../packages/session-persistence/session-persistence-jsonl/src/index.ts) +Source: [`packages/session-persistence/session-persistence-jsonl/src/index.ts:36`](../packages/session-persistence/session-persistence-jsonl/src/index.ts) ## `@deepseek-ai/dsh-session-persistence-sqlite` @@ -481,7 +481,7 @@ export interface Config { export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist' ``` -Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:50`](../packages/session-persistence/session-persistence-sqlite/src/index.ts) +Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:51`](../packages/session-persistence/session-persistence-sqlite/src/index.ts) ## `@deepseek-ai/dsh-stdio-agent` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 79902ba2fc..a21a80fb77 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -159,6 +159,7 @@ Contracts every implementation MUST honor (a DB backend asserts them inside a tr - **Durability.** append returns only once the batch is durable (the file backend fsyncs; a DB commits). create MAY defer the physical write until the first append (lazy materialization). ```ts cordis-catalog +abstract locate(meta: SessionHeader): SessionLocation | undefined abstract create(meta: SessionHeader): Promise abstract append(id: SessionId, events: readonly SessionEvent[]): Promise abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }> @@ -167,7 +168,7 @@ abstract list(): Promise Types: [SessionEvent](../core-data-structures/core.md) -Source: [`packages/session-persistence/session-persistence/src/index.ts:102`](../../packages/session-persistence/session-persistence/src/index.ts) +Source: [`packages/session-persistence/session-persistence/src/index.ts:114`](../../packages/session-persistence/session-persistence/src/index.ts) ## `ctx.sessions` — `SessionStore` diff --git a/docs/core-data-structures/persistence.md b/docs/core-data-structures/persistence.md index 4dbb8fb2af..b5aa887e30 100644 --- a/docs/core-data-structures/persistence.md +++ b/docs/core-data-structures/persistence.md @@ -2,7 +2,7 @@ The **durability seam** for the event log. [session.md](session.md) describes the in-memory `Session` — the append-only `SessionEvent` log that is the source of truth. This page describes how that log is made durable: the abstract `SessionPersistence` service, its backends, the flush checkpoint, crash recovery, and the metadata header that travels alongside the log. The event vocabulary the log carries is enumerated, member by member, in the generated [persistence log event catalog](../persistence-catalog.md). -The seam is a textbook [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md): one abstract service ([dsh-session-persistence](../../packages/session-persistence/session-persistence), `ctx.sessionPersistence`) defining create/append/load/list over the existing `SessionEvent` — **no parallel persisted type** — and two interchangeable backends that pass the same `runPersistenceContract` suite. See the [session-persistence RFC](../rfc/implemented/architecture/2026-06-14-session-persistence.md). +The seam is a textbook [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md): one abstract service ([dsh-session-persistence](../../packages/session-persistence/session-persistence), `ctx.sessionPersistence`) defining locate/create/append/load/list over the existing `SessionEvent` — **no parallel persisted type** — and two interchangeable backends that pass the same `runPersistenceContract` suite. See the [session-persistence RFC](../rfc/implemented/architecture/2026-06-14-session-persistence.md). ## The flush checkpoint @@ -12,6 +12,19 @@ The seam is a textbook [capability seam](../rfc/implemented/architecture/2026-06 A backend that reloads a log crashed mid-turn finds an open `turn/start` with no `turn/end`. It does **not** truncate — a single turn can be huge in a long-horizon task (many steps, large tool output), and those events were durably appended before the crash. Instead it closes the orphaned turn with a synthetic `turn/end { reason: { kind: 'interrupted' } }`, keeping the log balanced and the turn-enclosure invariant intact. `interrupted` is the one `TurnEndReason` no loop emits (see [session.md](session.md#why-a-turn-ended-turnendreasonmap)). +## `SessionLocation` — optional per-session artifact target + +`SessionPersistence.locate(meta)` synchronously resolves a backend-owned independent artifact without reading, creating, or flushing it. JSONL returns its absolute target path; SQLite returns `undefined` because sessions share one database. A returned path can therefore name a file that does not yet exist or lacks the current unflushed turn; it is a location hint, not authorization or a freshness guarantee. + +```ts type-equiv +interface SessionLocation { + /** Backend-specific artifact kind, for example `jsonl`. */ + readonly kind: string + /** Absolute path to this session's backend-owned artifact. */ + readonly path: string +} +``` + ## `SessionHeader` — metadata beside the log Per-session metadata travels **separately** from the event log: format version, cwd, lineage, and the seed boundary are storage concerns, not conversation events, so they stay out of `SessionEventMap` and never reach `deriveMessages()`. The header is attached to a `Session` via `session.header`. @@ -75,7 +88,7 @@ Replay/fork is therefore `ctx.sessions.create(id, { seed: seedEvents })`; resumi ## The backends -Both implement the same abstract `SessionPersistence` (create/append/load/list over `SessionEvent`) and pass `runPersistenceContract`, proving the seam is genuinely backend-agnostic: +Both implement the same abstract `SessionPersistence` (locate/create/append/load/list over `SessionEvent`) and pass `runPersistenceContract`, proving the seam is genuinely backend-agnostic: - **[dsh-session-persistence-jsonl](../../packages/session-persistence/session-persistence-jsonl)** — an append-only JSONL log per session with crash-safe atomic writes, the interrupted-turn crash recovery above, and a read/replay path. - **[dsh-session-persistence-sqlite](../../packages/session-persistence/session-persistence-sqlite)** — `node:sqlite`, one row per `SessionEvent`. The row shape `(session_id, seq, type, time, data, source_event_seqs, surface_op)` maps 1:1 onto the event, including optional surface metadata, so there is no parallel persisted schema to keep in sync. diff --git a/docs/module-graph.md b/docs/module-graph.md index 68c680c914..bab33bdddd 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -162,6 +162,7 @@ flowchart TD pkg_tool_bash --> pkg_agent pkg_tool_bash --> pkg_bash pkg_tool_bash --> pkg_llm + pkg_tool_bash --> pkg_session_persistence pkg_tool_bash --> pkg_system_prompt pkg_tool_bash --> pkg_tools pkg_tool_fs --> pkg_fs @@ -187,6 +188,7 @@ flowchart TD pkg_hooks_codex --> pkg_hook_protocol pkg_hooks_codex --> pkg_llm pkg_hooks_codex --> pkg_session + pkg_hooks_codex --> pkg_session_persistence pkg_hooks_codex --> pkg_tools pkg_acp --> pkg_agent pkg_acp --> pkg_llm @@ -230,6 +232,7 @@ flowchart TD pkg_hooks_claude --> pkg_hook_protocol pkg_hooks_claude --> pkg_llm pkg_hooks_claude --> pkg_session + pkg_hooks_claude --> pkg_session_persistence pkg_hooks_claude --> pkg_subagent pkg_hooks_claude --> pkg_tools pkg_subagent_mock --> pkg_agent @@ -301,14 +304,14 @@ flowchart TD | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) | | [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) | | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | -| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | +| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`tools`](../packages/core/tools) | | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) | | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-cordis`](../packages/cordis/tool-cordis) | `cordis` | [`tools`](../packages/core/tools) | -| [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | +| [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools) | | [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | | [`tool-ask-user`](../packages/ui/tool-ask-user) | `ui` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) | @@ -317,7 +320,7 @@ flowchart TD | [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | -| [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | +| [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index ba2b9d88dc..603ccdbf26 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -67,6 +67,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [The session prefix — request-only messages in front of the derived history](implemented/feature/2026-07-07-session-prefix.md) | 2026-07-07 | | [Repeat-tool-call guard plugin](implemented/feature/2026-07-08-repeat-tool-guard.md) | 2026-07-08 | | [The self-referential cordis toolset](implemented/feature/2026-07-08-self-referential-cordis-toolset.md) | 2026-07-08 | +| [Expose agent session identity and JSONL location to tools and hooks](implemented/feature/2026-07-10-agent-session-identity-and-log-location.md) | 2026-07-10 | ### Simplification diff --git a/docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md b/docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md index e6ecc974d7..756436d07d 100644 --- a/docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md +++ b/docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md @@ -14,7 +14,7 @@ Add `stdin?: string` and `env?: Record` to **both** `BashExecReq Three deliberate choices: -1. **The model-facing `bash` tool simply does NOT expose `stdin`/`env` as parameters** — not as a security wall, but because bash syntax already covers the model's needs, so duplicating them as tool params would be redundant surface. [dsh-tool-bash](../../../../packages/bash/tool-bash)'s `bash` tool builds its `BashExecRequest` from `command`/`workdir`/`timeoutMs`/`signal`/`owner` only; a model that includes `env`/`stdin` keys in its tool-call arguments simply has them ignored. A regression guard (`tool-bash` "does not forward env/stdin" tests) drives the real tool with those extra args and asserts the recorded request carries neither field — its purpose is to catch a future refactor that blindly spreads `...args` into the request and silently starts forwarding model input into the post-scrub `env` merge, NOT to defend a trust boundary. In-process plugins (the hooks bridges, native plugins) that construct a `BashExecRequest` directly set the fields; the seam imposes no access policy (consistent with how `owner` works — the executor stores but never interprets it). +1. **The model-facing `bash` tool does NOT expose `stdin`/`env` as parameters** — not as a security wall, but because bash syntax already covers the model's needs, so duplicating them as tool params would be redundant surface. [dsh-tool-bash](../../../../packages/bash/tool-bash)'s `bash` tool builds its `BashExecRequest` from named schema fields and may add harness-owned environment such as the current [session identity and JSONL location](../feature/2026-07-10-agent-session-identity-and-log-location.md); a model that includes `env`/`stdin` keys in its tool-call arguments has them ignored and cannot replace that overlay. Regression guards drive the real tool with extra args and assert no model-provided field enters the request. In-process plugins (the hooks bridges, native plugins) that construct a `BashExecRequest` directly set the fields; the seam imposes no access policy (consistent with how `owner` works — the executor stores but never interprets it). 2. **`env` merges AFTER the credential scrub, so an explicit caller entry always wins** — even a credential-shaped name. This is correct because the scrub's job is narrow: stop the harness's *ambient* `process.env` credentials from leaking into a spawned command. A caller that explicitly sets a var has named a value it already holds (not the ambient secret), so the scrub is not a constraint on it. `childEnv(extra?)` layers `scrub(process.env)` → `ENV_OVERRIDES` (the model-friendly `TERM=dumb` etc.) → `extra`, last-wins. diff --git a/docs/rfc/implemented/feature/2026-06-30-hook-bridges.md b/docs/rfc/implemented/feature/2026-06-30-hook-bridges.md index 630d4dd3ed..431166e932 100644 --- a/docs/rfc/implemented/feature/2026-06-30-hook-bridges.md +++ b/docs/rfc/implemented/feature/2026-06-30-hook-bridges.md @@ -12,8 +12,8 @@ The framing that shapes the whole design: **a bridge is a faithfulness adapter, Two independent plugins in the `packages/hooks/` group, each a function/namespace plugin (`name`/`inject`/`Config`/`apply`, NO default export — see [postmortem 0001](../../../postmortem/0001-acp-default-export-drops-inject.md)) injecting only `bash`: -- **`dsh-hooks-claude`** — the CC dialect. Seven hook points: `SessionStart`, `UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `Stop`, `SubagentStart`, `SubagentStop`. Owns CC's per-event stdin payloads (a base of `session_id`/`cwd`/`hook_event_name` plus per-event fields), CC's env + `${CLAUDE_PLUGIN_ROOT}`/`${CLAUDE_PROJECT_DIR}` substitution, and the literal-or-regex matcher mode. A CC hook's stdin carries a **trailing newline**. -- **`dsh-hooks-codex`** — the Codex dialect: a deliberate SUBSET. Five hook points (`PreToolUse`, `PostToolUse`, `SessionStart`, `UserPromptSubmit`, `Stop` — no subagent/notification/compaction), an always-regex matcher, snake_case payloads with `turn_id`/`model`/`permission_mode` extras written WITHOUT a trailing newline, no env and no `${…}` substitution, and a block-only decision model (a Codex hook can never pre-approve, so `allow`/`ask` are not honored). A tool call's payload carries the real `tool_name` (the value the matcher tests, so a config's tool matcher fires) in Codex's `tool_input: { command }` shape. +- **`dsh-hooks-claude`** — the CC dialect. Seven hook points: `SessionStart`, `UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `Stop`, `SubagentStart`, `SubagentStop`. Owns CC's per-event stdin payloads (a base of `session_id`/`transcript_path`/`cwd`/`hook_event_name` plus per-event fields), CC's env + `${CLAUDE_PLUGIN_ROOT}`/`${CLAUDE_PROJECT_DIR}` substitution, and the literal-or-regex matcher mode. `transcript_path` comes from the persistence locator or is `''`; a CC hook's stdin carries a **trailing newline**. +- **`dsh-hooks-codex`** — the Codex dialect: a deliberate SUBSET. Five hook points (`PreToolUse`, `PostToolUse`, `SessionStart`, `UserPromptSubmit`, `Stop` — no subagent/notification/compaction), an always-regex matcher, snake_case payloads with `turn_id`/`model`/`permission_mode` extras written WITHOUT a trailing newline, no env and no `${…}` substitution, and a block-only decision model (a Codex hook can never pre-approve, so `allow`/`ask` are not honored). Its `transcript_path` comes from the same locator or is `null`; a tool call's payload carries the real `tool_name` (the value the matcher tests, so a config's tool matcher fires) in Codex's `tool_input: { command }` shape. ### Outcome → Decision mapping diff --git a/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md b/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md new file mode 100644 index 0000000000..8bc5f33820 --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md @@ -0,0 +1,86 @@ +# RFC: Expose agent session identity and JSONL location to tools and hooks + +Status: implemented + +## Problem + +An agent can identify its workspace through `session.header.cwd`, but a model using the bash tool cannot identify the session that owns the call or the durable JSONL file that records it. The default apps happen to use `./.sessions`, yet that is deployment config rather than a contract: `persistenceRoot` can point elsewhere, the JSONL backend hashes `cwd` into a bucket, and arbitrary session ids are path-encoded. Asking the agent to run `find` therefore makes the model guess backend layout and can select the wrong log under concurrent, resumed, forked, or subagent sessions. + +The same missing ownership boundary appears in the hook bridges. The Codex bridge emits `session_id` but fixes `transcript_path` to `null`; the Claude Code bridge emits `session_id` and `cwd` but no transcript path. Teaching each consumer to reconstruct the JSONL layout would duplicate backend policy and couple model tools and protocol adapters to one persistence implementation. + +The feature needs two distinct facts: a stable session identity that exists even without persistence, and an optional physical location owned by the active persistence backend. They must be resolved per agent invocation rather than written to global `process.env`, because one harness process can run multiple agents and in-process subagents concurrently. + +## Decision + +Extend the [`SessionPersistence`](../../implemented/architecture/2026-06-14-session-persistence.md) seam with a synchronous, side-effect-free location query: + +```ts +import type { SessionHeader } from '@deepseek-ai/dsh-session' + +export interface SessionLocation { + readonly kind: string + readonly path: string +} + +export abstract class SessionPersistence { + abstract locate(meta: SessionHeader): SessionLocation | undefined +} +``` + +`path` is an absolute local path to the backend's dedicated log for `meta`; `kind` identifies the representation. The JSONL backend returns `{ kind: 'jsonl', path }` using its already-resolved absolute root and existing cwd-bucket/id-encoding helpers. The SQLite backend returns `undefined` because a session is rows inside a shared database, not a dedicated transcript file. A backend with no honest local per-session path also returns `undefined`. + +`locate` performs no filesystem I/O, creates nothing, flushes nothing, and never searches by convention. It reports where this backend would materialize the session, so callers can receive a path before the file exists. Making the query synchronous and local-path-only keeps it usable while constructing tool and hook invocation context; a future remote/object-store locator is a separate capability rather than a blocking network call hidden inside prompt or tool assembly. + +The model-facing bash consumer derives a trusted environment overlay for each `ToolExecution` with an agent: + +- `DSH_SESSION_ID` is always the current `agent.session.header.id`, including when persistence is absent or non-file-backed. +- `DSH_SESSION_JSONL` is present only when the active `ctx.sessionPersistence.locate(header)` returns `kind: 'jsonl'`; its value is that location's absolute path. +- A call without an agent receives neither variable. + +The overlay is passed through the existing `BashExecRequest.env` surface from the [trusted stdin/env decision](../../implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). It applies to foreground and background starts, and `dsh-bash-local` merges it after its ambient credential scrub and terminal overrides. The model-facing tool continues to build the request from named schema fields: model-supplied `env`/`stdin` keys are ignored and cannot replace the overlay. A shell command can still overwrite its own variables (`DSH_SESSION_ID=x command`); these values are correlation metadata, never authority. + +The bash tool description tells the model that the current session id is available as `$DSH_SESSION_ID` and that JSONL deployments additionally expose `$DSH_SESSION_JSONL`. This guidance belongs with the tool that provides the variables, not in a permanent system-prompt section. The schema is already recorded in the request header under the [reconstructable-request contract](../../implemented/architecture/2026-07-05-reconstructable-requests.md), and every resulting tool output is a durable `tool/result`, so no new session event is needed. + +The [Claude Code and Codex hook bridges](../../implemented/feature/2026-06-30-hook-bridges.md) resolve transcript location from the same seam at payload construction time. Codex payloads use `transcript_path: string | null`; Claude Code payloads keep their string-shaped dialect field and use `transcript_path: string`, falling back to `''` when no local per-session file exists. Hook lookup is the same side-effect-free snapshot as bash lookup: it does not force materialization or make a pre-turn hook create an otherwise abandoned session artifact. + +## Peer product findings + +Peer products separate stable identity from physical storage rather than treating an absolute path as the only session key. Codex injects `CODEX_THREAD_ID` into each spawned shell environment after its environment policy has run, while its rollout recorder owns the exact path and exposes it separately to client events and hooks. Claude Code supplies `session_id` and `transcript_path` as structured hook/status-line input rather than a general Bash transcript environment contract. OpenCode carries session identity in structured tool execution context; Kimi Code expands a session-id placeholder in skill content; Reasonix keeps the active session path on its controller and rebinds it on branch/resume. + +The reusable principles are narrower than any one product's API: inject identity at the invocation boundary, let persistence resolve storage, do not mutate process-global environment for concurrent agents, and do not promise that a precomputed path is already materialized. DeepSeek Harness adds the optional JSONL path to bash because its requested user behavior is explicitly “ask the agent for this session's log,” while retaining the stable id as the primary identity. + +## Lifecycle and persistence semantics + +A fresh session receives its id before any turn. Its bash environment can therefore carry both values during the first turn, but JSONL lazy materialization remains unchanged: before the first successful turn-end `session/flush`, `$DSH_SESSION_JSONL` can name a file that does not yet exist. During an open later turn, the file contains only the last durably flushed prefix, not the current buffered events. Consumers that need a readable up-to-date transcript require a separate explicit checkpoint/materialization API; this decision deliberately does not add one. + +Resume reuses the loaded session header, so it exposes the same id and backend location. Fork and in-process spawn create a new session id; the JSONL backend derives a new file while preserving the existing `parentSession` lineage and inherited cwd rules. Concurrent parent/child agents compute overlays from their own `ToolExecution.agent`, so neither can inherit or overwrite the other's identity. + +Consumers resolve the active service through the Cordis context at invocation time and do not cache a concrete JSONL backend instance. This keeps HMR/reload behavior aligned with the service store: a replacement backend controls subsequent locations, and an absent/inactive backend removes only `DSH_SESSION_JSONL`, never the session id. + +## Testing + +Unit coverage pins each boundary. The persistence seam contract asserts JSONL returns an absolute encoded path under a custom root while SQLite returns `undefined`; JSONL tests cover cwd/no-cwd buckets and ids requiring escaping. Tool-bash request-recording tests cover foreground/background overlays, no-agent calls, absent/SQLite persistence, ignored model `env` keys, and separate parent/child identities. Both hook bridge suites assert their exact available/unavailable `transcript_path` dialect shapes. + +A keyless full-loop integration uses the real agent loop, JSONL persistence, `dsh-tool-bash`, and `dsh-bash-local` with only the model scripted. On the first turn the model runs a command that prints both variables and reports whether the path exists; the test verifies the values against the live session header and locator, verifies the file can be absent inside the tool call, then waits for idle and confirms the materialized file's header carries the same session id. Request-recording tests prove parent/child calls receive different overlays, while locator tests prove resume keeps the path and fork changes it. + +Snapshot coverage updates the existing request-header pin for the bash description and the hook payload scenarios affected by `transcript_path`. No with-key e2e is required: model choice is not the contract, and the deterministic behavior is exercised through the real local executor, persistence backend, loader composition, and snapshot replay without depending on a provider credential. + +## Alternatives considered + +**Expose only `DSH_SESSION_ID` and make the agent search.** This copies Codex's shell surface but not its separate persistence resolver. A recursive `find` knows neither a custom root nor a non-JSONL backend, duplicates layout rules, and can race or mis-select under multiple sessions. Stable id remains necessary, but it is insufficient for the requested direct-path behavior. + +**Expose only the absolute path.** A path can be unavailable for non-file persistence and can name a not-yet-created lazy artifact; it is not the stable identity other APIs use for resume, lineage, or ownership. Keeping id and optional location separate makes those semantics explicit. + +**Write the current session into global `process.env`.** One process can drive multiple ACP sessions and in-process subagents concurrently, so a global assignment is last-writer-wins shared mutable state. Per-`ToolExecution` request env gives every child process an immutable snapshot of the correct agent instead. + +**Add a model-facing `session_info` tool.** A dedicated tool would add schema and another call when bash already supplies the requested query surface. It would also need the same persistence resolver, so it does not remove the seam work; the environment variables are smaller and compose with ordinary shell scripts. + +**Make tool-bash depend directly on the JSONL backend.** Reading backend config or importing `logPath` from the implementation would violate the interface/implementation/consumer split and leave hooks to invent another route. The persistence service is the only layer that can state whether a physical per-session path exists. + +## Consequences + +Foreground and background bash calls now expose the current agent's stable session id, while only JSONL-backed sessions expose a file path. No-agent calls receive neither variable; absent and SQLite persistence still leave `DSH_SESSION_ID` available. Resume retains identity and location, while forks, spawns, and concurrent child agents derive new values from their own immutable headers. Model-supplied `env`/`stdin` fields remain ignored, and both hook bridges consume the same locator with their dialect-specific unavailable value. + +The path reveals the configured persistence root to the model and hooks. The bash tool already runs with the executor's filesystem authority, so this adds discoverability rather than permission; deployments needing isolation use a sandboxing executor or omit local-file persistence. A valid location can be absent or stale relative to an open turn because durability checkpoints happen at turn end. + +Commands can overwrite either variable inside their own shell syntax. The values are debugging/correlation facts rather than credentials, so external consumers still verify the file header before attributing a transcript. `DSH_SESSION_JSONL` remains representation-specific, and backends without a dedicated per-session file return `undefined` instead of squeezing database coordinates into a path contract. The pre-release seam extension intentionally requires every persistence backend to make that supported/unsupported choice without a compatibility shim. diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 6d97017f1d..dc7dcd3d71 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -124,7 +124,7 @@ Registered by the tool registry itself under `mode: code` / `mode: both` (see th ### `bash` -Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. +Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. ```json { diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index df7187bbbb..b8cf737a02 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is /var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-52lrTl.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's text output as a string. Tool arguments must be JSON-serializable.\n- A FAILED tool call rejects with an `Error` carrying the tool's error text — `try/catch` it to handle and continue.\n- Calls execute sequentially, even under `Promise.all`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ndeclare const tools: {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */\n bash(args: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately. No timeout applies. */\n run_in_background?: boolean;\n }): Promise;\n /** Ask the executor to kill a running background bash task by task id. */\n bash_kill(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output. */\n bash_output(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit(args: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n }): Promise;\n /** Read a UTF-8 text file and return line-numbered content. */\n read(args: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n }): Promise;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */\n subagent(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n }): Promise;\n /** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */\n subagent_fork(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n }): Promise;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write(args: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n }): Promise;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow(args: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: {\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n }[];\n };\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n }): Promise;\n /** Create or fully replace a UTF-8 text file. */\n write(args: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n }): Promise;\n}\n```","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is /var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-52lrTl.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's text output as a string. Tool arguments must be JSON-serializable.\n- A FAILED tool call rejects with an `Error` carrying the tool's error text — `try/catch` it to handle and continue.\n- Calls execute sequentially, even under `Promise.all`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ndeclare const tools: {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */\n bash(args: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately. No timeout applies. */\n run_in_background?: boolean;\n }): Promise;\n /** Ask the executor to kill a running background bash task by task id. */\n bash_kill(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output. */\n bash_output(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit(args: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n }): Promise;\n /** Read a UTF-8 text file and return line-numbered content. */\n read(args: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n }): Promise;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */\n subagent(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n }): Promise;\n /** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */\n subagent_fork(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n }): Promise;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write(args: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n }): Promise;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow(args: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: {\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n }[];\n };\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n }): Promise;\n /** Create or fully replace a UTF-8 text file. */\n write(args: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n }): Promise;\n}\n```","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl index 72533bcdeb..3d6e65d390 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611771394,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611771394,"data":{"content":[{"type":"text","text":"Using ONE run_code program: call the bash tool twice — exactly `echo CODE_ONE` then exactly `echo CODE_TWO` — and return the two outputs joined with a plus sign. Then reply with that joined string only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611771396,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611771396,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is /var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-BteTVR.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's text output as a string. Tool arguments must be JSON-serializable.\n- A FAILED tool call rejects with an `Error` carrying the tool's error text — `try/catch` it to handle and continue.\n- Calls execute sequentially, even under `Promise.all`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ndeclare const tools: {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */\n bash(args: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately. No timeout applies. */\n run_in_background?: boolean;\n }): Promise;\n /** Ask the executor to kill a running background bash task by task id. */\n bash_kill(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output. */\n bash_output(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit(args: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n }): Promise;\n /** Read a UTF-8 text file and return line-numbered content. */\n read(args: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n }): Promise;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */\n subagent(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n }): Promise;\n /** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */\n subagent_fork(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n }): Promise;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write(args: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n }): Promise;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow(args: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: {\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n }[];\n };\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n }): Promise;\n /** Create or fully replace a UTF-8 text file. */\n write(args: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n }): Promise;\n}\n```","tools":[{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611771396,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is /var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-BteTVR.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's text output as a string. Tool arguments must be JSON-serializable.\n- A FAILED tool call rejects with an `Error` carrying the tool's error text — `try/catch` it to handle and continue.\n- Calls execute sequentially, even under `Promise.all`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ndeclare const tools: {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */\n bash(args: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately. No timeout applies. */\n run_in_background?: boolean;\n }): Promise;\n /** Ask the executor to kill a running background bash task by task id. */\n bash_kill(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output. */\n bash_output(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit(args: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n }): Promise;\n /** Read a UTF-8 text file and return line-numbered content. */\n read(args: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n }): Promise;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */\n subagent(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n }): Promise;\n /** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */\n subagent_fork(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n }): Promise;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write(args: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n }): Promise;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow(args: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: {\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n }[];\n };\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n }): Promise;\n /** Create or fully replace a UTF-8 text file. */\n write(args: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n }): Promise;\n}\n```","tools":[{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611771869,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611771869,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611771978,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index 8475c97896..5f49c4295d 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is /var/folders/bn/vj1dvck95yd5jh3x4wskflxm0000gn/T/acp-snap-cwd-ka5r8w.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is /var/folders/bn/vj1dvck95yd5jh3x4wskflxm0000gn/T/acp-snap-cwd-ka5r8w.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/packages/bash/tool-bash/README.md b/packages/bash/tool-bash/README.md index eabb9298aa..40918ccefb 100644 --- a/packages/bash/tool-bash/README.md +++ b/packages/bash/tool-bash/README.md @@ -20,6 +20,12 @@ The plugin also contributes the `tool:bash` prompt section (order 105) — the c `command`, `workdir`, and `timeoutMs` are resolved against the executor's config defaults via `ctx.bash.resolve()` before execution, so the executor seam (`BashExecSpec`) receives explicit `workdir`/`timeoutMs` values. The workdir default is applied in the tool layer (from the calling agent's `session.header.cwd`) BEFORE `resolve()` — the per-session cwd must come from `exec.agent`, since N sessions share one executor; only when no session cwd is available does the executor fall back to its own config / `process.cwd()`. +### Session identity environment + +Every foreground and background call made for an agent receives `DSH_SESSION_ID=agent.session.header.id`. When the active persistence backend locates a JSONL artifact, the call also receives `DSH_SESSION_JSONL=`; absent persistence and non-file backends still provide the id but omit the JSONL variable. The path is a location hint: lazy materialization means it may not exist on the first turn, and during an open turn it can omit buffered events that have not reached `session/flush`. Neither value is an authorization credential. + +The overlay is computed from `ToolExecution.agent` for each call and passed through `BashExecRequest.env`; `process.env` is never modified, so concurrent parent/child agents keep separate values. The tool description names both variables so the model can inspect them without a permanent system-prompt section. + Result text: stdout, then a `[stderr]` section, then status markers — `[timed out after Nms]` whenever the executor's timer fired (reported independently of how the process ended, so a command that traps SIGTERM and exits 0 still shows it), `[killed by signal: …]` for a signal death, `[exit code: N]` for a non-zero exit (reported, **not** `isError`: the model decides how to react), and `[output truncated; full output: ]` when the tail was kept and a safe spill file is available. If the executor knows output was dropped but cannot safely advertise a complete spill file, the path is reported as `(unavailable)`. Only infrastructure failures (spawn errors, aborts) surface as `isError` results. ### `bash_output` @@ -44,7 +50,7 @@ When a background task finishes, a short notice is injected into the owning agen ## The tool builds its request from named args only -The `BashExecRequest` seam carries optional `stdin` and `env`, used by the hooks bridges to feed a hook command its JSON payload and `CLAUDE_*` env. This tool does **not** expose them as parameters: its request is built from `command`/`workdir`/`timeoutMs`/`signal`/`owner` only, so a model that includes `env` or `stdin` keys in its tool arguments has them ignored. This is not a trust boundary — a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), and the real defense against leaking the harness's ambient secrets is `dsh-bash-local`'s credential scrub, which works regardless. A regression guard drives the real tool with those extra args and asserts the resulting request carries neither field — its job is to catch a future refactor that blindly spreads `...args` into the request (which would silently forward model input into the post-scrub `env` merge), not to defend a wall. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). +The `BashExecRequest` seam carries optional `stdin` and `env`, used by trusted consumers. This tool does **not** expose them as model parameters: it builds the request from named schema fields and adds only the session overlay above, so model-supplied `env`/`stdin` keys are ignored and cannot replace the trusted values. This is not a trust boundary — a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), and the real defense against leaking ambient secrets is `dsh-bash-local`'s credential scrub. Regression guards assert extra model fields never enter the request while the trusted overlay still does. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). ## Permissions diff --git a/packages/bash/tool-bash/package.json b/packages/bash/tool-bash/package.json index d8836d6a21..fabbdea076 100644 --- a/packages/bash/tool-bash/package.json +++ b/packages/bash/tool-bash/package.json @@ -25,6 +25,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-bash": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session-persistence": "^0.0.1", "@deepseek-ai/dsh-system-prompt": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -36,6 +37,8 @@ "@deepseek-ai/dsh-bash-local": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", + "@deepseek-ai/dsh-session-persistence": "workspace:^", + "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.6" diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index d4a3105165..777332b7c3 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -43,6 +43,7 @@ import { isAbsolute, resolve as resolvePath } from 'node:path' import { defineTool } from '@deepseek-ai/dsh-tools' import type { GenericCallView, TerminalCallView, ToolResult, ToolResultView } from '@deepseek-ai/dsh-tools' import type { Agent } from '@deepseek-ai/dsh-agent' +import type {} from '@deepseek-ai/dsh-session-persistence' import type {} from '@deepseek-ai/dsh-system-prompt' import { BashTaskId, OwnerToken } from '@deepseek-ai/dsh-bash' import type { BashRunResult, BashTask, CollectedOutput } from '@deepseek-ai/dsh-bash' @@ -278,6 +279,22 @@ function resolveWorkdir(modelWorkdir: string | undefined, exec: { agent?: Agent return modelWorkdir } +/** + * Build the trusted per-execution session environment. Identity always comes + * from the calling agent's immutable session header; an optional JSONL path + * comes from the active persistence backend's side-effect-free locator. A + * non-agent caller has no current session, so it receives neither variable. + */ +function sessionEnvironment(ctx: Context, exec: { agent?: Agent }): Record | undefined { + const agent = exec.agent + if (agent === undefined) return undefined + + const env: Record = { DSH_SESSION_ID: agent.session.header.id } + const location = ctx.get('sessionPersistence')?.locate(agent.session.header) + if (location?.kind === 'jsonl') env.DSH_SESSION_JSONL = location.path + return env +} + /** Status line for background task reads. */ function statusLine(task: BashTask): string { switch (task.status) { @@ -360,6 +377,8 @@ export function apply(ctx: Context): void { description: 'Execute a bash command (`bash -c`) and return its stdout/stderr. ' + 'Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — ' + 'pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. ' + + 'The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, ' + + '`$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. ' + 'Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. ' + 'Set `run_in_background: true` for long-running commands: the call returns a task id immediately; ' + 'poll it with `bash_output` and stop it with `bash_kill`.', @@ -385,11 +404,13 @@ export function apply(ctx: Context): void { // session runs in its own workspace (see resolveWorkdir); an explicit // model workdir still wins. const workdir = resolveWorkdir(args.workdir, exec) + const env = sessionEnvironment(ctx, exec) const request = { command: args.command, ...workdir !== undefined ? { workdir } : {}, ...args.timeoutMs !== undefined ? { timeoutMs: args.timeoutMs } : {}, ...exec.signal ? { signal: exec.signal } : {}, + ...env !== undefined ? { env } : {}, } if (args.run_in_background === true) { // Stamp the owner token (the agent's session id) onto the spec so the diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index b3d6bb3f77..430b0c3f11 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -1,8 +1,12 @@ -import { describe, expect, it } from 'vitest' +import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' +import { existsSync, mkdtempSync, readFileSync, rmSync } from 'node:fs' +import { tmpdir } from 'node:os' +import { join } from 'node:path' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' +import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' @@ -17,10 +21,11 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent * through the agent loop, exercising the same seams a live model would * (tool/call + tool/result session events, agent.inject notifications). */ -async function harness(adapter: MockAdapter) { +async function harness(adapter: MockAdapter, sessionRoot?: string) { const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(SessionStore) + if (sessionRoot !== undefined) await ctx.plugin(SessionPersistenceJsonl, { root: sessionRoot }) await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) @@ -31,6 +36,9 @@ async function harness(adapter: MockAdapter) { return ctx } +const dirs: string[] = [] +afterEach(() => { for (const dir of dirs.splice(0)) rmSync(dir, { recursive: true, force: true }) }) + function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { @@ -68,6 +76,37 @@ function resultText(event: SessionEvent): string { } describe('bash tool through the agent loop', () => { + it('first-turn bash receives session identity before the lazy JSONL file materializes', async () => { + const root = mkdtempSync(join(tmpdir(), 'dsh-bash-session-env-')) + dirs.push(root) + const adapter = new MockAdapter([ + toolCallResponse('call-1', 'bash', { + command: 'printf \'%s\\n%s\\n\' "$DSH_SESSION_ID" "$DSH_SESSION_JSONL"; if [ -e "$DSH_SESSION_JSONL" ]; then printf \'present\\n\'; else printf \'absent\\n\'; fi', + description: 'inspect session environment', + }), + textResponse('Session environment inspected.'), + ]) + const ctx = await harness(adapter, root) + const handle = ctx.agents.create({ + agentId: AgentId('session-env'), + sessionId: SessionId('session-env-id'), + agentOptions: { model: 'mock' }, + }) + const agent = handle.agent as ReactLoopAgent + const location = ctx.sessionPersistence.locate(agent.session.header) + expect(location?.kind).toBe('jsonl') + + agent.send([{ type: 'text', text: 'inspect the current session' }]) + await waitForIdle(ctx, agent) + + const result = findEvent(events(agent), 'tool/result') + expect(resultText(result)).toBe(`session-env-id\n${location?.path}\nabsent\n`) + expect(existsSync(location!.path)).toBe(true) + const header = JSON.parse(readFileSync(location!.path, 'utf8').split('\n')[0]!) as { type: string; id: string } + expect(header).toMatchObject({ type: 'session', id: 'session-env-id' }) + await handle.dispose() + }) + it('foreground: model calls bash, sees the result, replies', async () => { const adapter = new MockAdapter([ toolCallResponse('call-1', 'bash', { command: 'echo integration-ok', description: 'test command' }, 'Running it.'), diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index 7d4b34f74f..5539787399 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -10,6 +10,8 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' +import SessionStore from '@deepseek-ai/dsh-session' +import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' import { renderResult } from '@deepseek-ai/dsh-tool-bash' @@ -910,16 +912,111 @@ describe('the model-facing bash tool builds its request from named args only (no kill(): boolean { return false } } - async function setupRecording() { + async function setupRecording(withJsonl = false) { const ctx = new Context() await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + if (withJsonl) { + await ctx.plugin(SessionStore) + await ctx.plugin(SessionPersistenceJsonl, { root: join(spillDir, 'jsonl') }) + } await ctx.plugin(RecordingBashExecutor) await ctx.plugin(ToolBash) return { ctx, bash: ctx.bash as RecordingBashExecutor } } + it('describes the trusted session variables to the model', async () => { + const { ctx } = await setupRecording() + const description = ctx.tools.get('bash')?.description ?? '' + expect(description).toContain('DSH_SESSION_ID') + expect(description).toContain('DSH_SESSION_JSONL') + }) + + it('injects the session id and JSONL target path into a foreground request', async () => { + const { ctx, bash } = await setupRecording(true) + const agent = registerFakeAgent(ctx, 'request-fg', () => undefined) + const path = ctx.sessionPersistence.locate(agent.session.header)?.path + + await ctx.tools.execute({ + callId: CallId('session-env-fg'), + name: 'bash', + arguments: { command: 'true', description: 'run command' }, + agent, + }) + + expect(bash.requests[0]?.env).toEqual({ + DSH_SESSION_ID: 'request-fg', + DSH_SESSION_JSONL: path, + }) + }) + + it('injects the same trusted variables into a background request without forwarding model env', async () => { + const { ctx, bash } = await setupRecording(true) + const agent = registerFakeAgent(ctx, 'request-bg', () => undefined) + const path = ctx.sessionPersistence.locate(agent.session.header)?.path + + await ctx.tools.execute({ + callId: CallId('session-env-bg'), + name: 'bash', + arguments: { + command: 'sleep 1', + description: 'run command', + run_in_background: true, + env: { DSH_SESSION_ID: 'spoofed', DSH_SESSION_JSONL: '/tmp/spoofed' }, + }, + agent, + }) + + expect(bash.requests[0]?.env).toEqual({ + DSH_SESSION_ID: 'request-bg', + DSH_SESSION_JSONL: path, + }) + }) + + it('injects only the stable session id when no JSONL locator is available', async () => { + const { ctx, bash } = await setupRecording() + const agent = registerFakeAgent(ctx, 'request-id-only', () => undefined) + const ambient = process.env.DSH_SESSION_ID + + await ctx.tools.execute({ + callId: CallId('session-env-id-only'), + name: 'bash', + arguments: { command: 'true', description: 'run command' }, + agent, + }) + + expect(bash.requests[0]?.env).toEqual({ DSH_SESSION_ID: 'request-id-only' }) + expect(process.env.DSH_SESSION_ID).toBe(ambient) + }) + + it('keeps parent and child agent session environments isolated', async () => { + const { ctx, bash } = await setupRecording(true) + const parent = registerFakeAgent(ctx, 'request-parent', () => undefined) + const child = registerFakeAgent(ctx, 'request-child', () => undefined) + + for (const [callId, agent] of [['parent', parent], ['child', child]] as const) { + await ctx.tools.execute({ + callId: CallId(`session-env-${callId}`), + name: 'bash', + arguments: { command: 'true', description: 'run command' }, + agent, + }) + } + + expect(bash.requests.map(request => request.env)).toEqual([ + { + DSH_SESSION_ID: 'request-parent', + DSH_SESSION_JSONL: ctx.sessionPersistence.locate(parent.session.header)?.path, + }, + { + DSH_SESSION_ID: 'request-child', + DSH_SESSION_JSONL: ctx.sessionPersistence.locate(child.session.header)?.path, + }, + ]) + expect(bash.requests[0]?.env?.DSH_SESSION_JSONL).not.toBe(bash.requests[1]?.env?.DSH_SESSION_JSONL) + }) + it('does not forward env/stdin even when the model includes them as extra arguments', async () => { const { ctx, bash } = await setupRecording() // Extra args: the model includes `env` and `stdin` keys hoping they reach the diff --git a/packages/bash/tool-bash/tsconfig.json b/packages/bash/tool-bash/tsconfig.json index 89b10bfea8..6828cd1738 100644 --- a/packages/bash/tool-bash/tsconfig.json +++ b/packages/bash/tool-bash/tsconfig.json @@ -23,6 +23,9 @@ { "path": "../../core/agent" }, + { + "path": "../../session-persistence/session-persistence" + }, { "path": "../../bash/bash" } diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 68fd63ae25..667bf69fae 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -129,6 +129,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ key: 'sessionPersistence', summary: 'Abstract durable session-persistence service.', methods: [ + 'abstract locate(meta: SessionHeader): SessionLocation | undefined', 'abstract create(meta: SessionHeader): Promise', 'abstract append(id: SessionId, events: readonly SessionEvent[]): Promise', 'abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }>', @@ -701,6 +702,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'SessionId', declaration: 'export type SessionId = Branded<\'SessionId\'>;', }, + { + name: 'SessionLocation', + declaration: 'export interface SessionLocation {\n readonly kind: string;\n readonly path: string;\n}', + }, { name: 'StreamChunk', declaration: 'export type StreamChunk = {\n type: \'block-start\';\n index: number;\n blockType: ContentBlockType;\n} | {\n type: \'text-delta\';\n index: number;\n text: string;\n} | {\n type: \'reasoning-delta\';\n index: number;\n text: string;\n} | {\n type: \'tool-call-delta\';\n index: number;\n id: CallId;\n name?: string;\n argumentsDelta: string;\n} | {\n type: \'block-end\';\n index: number;\n block: ContentBlock;\n} | {\n type: \'usage\';\n usage: TokenUsage;\n} | {\n type: \'finish\';\n reason: FinishReason;\n};', diff --git a/packages/hooks/hooks-claude/README.md b/packages/hooks/hooks-claude/README.md index 306bfdbfeb..b2e593cd4a 100644 --- a/packages/hooks/hooks-claude/README.md +++ b/packages/hooks/hooks-claude/README.md @@ -46,6 +46,8 @@ The three emit points run detached — no seam awaits a `SessionStart`/`Subagent The matcher subject is the tool name (`PreToolUse`/`PostToolUse`), the session source (`SessionStart`), or a constant `agent_type` of `general-purpose` (`SubagentStart`/`SubagentStop` — the harness subagent seam carries no per-kind label, so the bridge reports Claude Code's own Task-tool default; a default/`*`/empty `agent_type` matcher fires, a specific-kind matcher does not); `UserPromptSubmit`/`Stop` ignore matchers. Multiple file-configured hooks on one point run **serially, in config order**, and fold most-restrictively (`deny > ask > allow`, see `dsh-hook-protocol`); serial keeps each hook's `hook/invoked`/`hook/result` pair adjacent in the log, and the fold is order-independent for the decision (see the RFC's "run serially, not concurrently" note). +Every agent-scoped stdin payload carries `session_id` and string-shaped `transcript_path`. The bridge resolves the latter through `ctx.sessionPersistence.locate(session.header)` when available and otherwise sends `''`. Lookup does not create or flush the artifact, so a path can be absent before the first turn-end checkpoint or omit the current open turn. + ## Context source Injected context carries an explicit `{ kind: 'plugin', plugin: 'hooks-claude' }` source. `agent.inject()` defaults a missing source to `{ kind: 'user' }`, which would mislabel plugin context as a user prompt — so the bridge always names itself. diff --git a/packages/hooks/hooks-claude/package.json b/packages/hooks/hooks-claude/package.json index 5cc39f9999..571f533723 100644 --- a/packages/hooks/hooks-claude/package.json +++ b/packages/hooks/hooks-claude/package.json @@ -29,6 +29,7 @@ "@deepseek-ai/dsh-hook-protocol": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", + "@deepseek-ai/dsh-session-persistence": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -41,6 +42,8 @@ "@deepseek-ai/dsh-hook-protocol": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", + "@deepseek-ai/dsh-session-persistence": "workspace:^", + "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", diff --git a/packages/hooks/hooks-claude/src/index.ts b/packages/hooks/hooks-claude/src/index.ts index d16e26e4a6..2e86329d56 100644 --- a/packages/hooks/hooks-claude/src/index.ts +++ b/packages/hooks/hooks-claude/src/index.ts @@ -27,6 +27,7 @@ import type { Context } from 'cordis' import z from 'schemastery' import type { Agent, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm' +import type {} from '@deepseek-ai/dsh-session-persistence' import type { PostToolDecision, PreToolDecision, ToolExecution, ToolExecutionResult } from '@deepseek-ai/dsh-tools' import { appendHookInvoked, @@ -246,7 +247,7 @@ export function apply(ctx: Context, config: Config): void { // to the interception seams; today the contract is "injected as soon as the // hook resolves", not "before the first request". --- ctx.on('agent/session-start', (agent, source) => { - detached.track(runPoint('SessionStart', source, sessionStartPayload(agent, source), { agent, signal: detached.signal }) + detached.track(runPoint('SessionStart', source, sessionStartPayload(ctx, agent, source), { agent, signal: detached.signal }) .then((merged) => { const context = contextFrom(merged) if (context) agent.inject(context.content, { source: context.source }) @@ -260,7 +261,7 @@ export function apply(ctx: Context, config: Config): void { // matcher subject (CC ignores matchers for this event). --- ctx.on('agent/prompt-submit', async (agent, content, _source, next): Promise => { const turn = lastTurn(agent) - const merged = await runPoint('UserPromptSubmit', '', promptPayload(agent, content), { agent, turn }) + const merged = await runPoint('UserPromptSubmit', '', promptPayload(ctx, agent, content), { agent, turn }) if (merged.decision === 'deny') { return { kind: 'block', reason: merged.reason ?? 'blocked by UserPromptSubmit hook' } } @@ -281,7 +282,7 @@ export function apply(ctx: Context, config: Config): void { // --- PreToolUse → PreToolDecision. Matcher subject is the tool name. --- ctx.on('tools/pre-execute', async (exec, next): Promise => { const turn = lastTurn(exec.agent) - const merged = await runPoint('PreToolUse', exec.name, preToolPayload(exec), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) + const merged = await runPoint('PreToolUse', exec.name, preToolPayload(ctx, exec), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) if (merged.decision === 'deny') return { kind: 'deny', reason: merged.reason ?? 'blocked by PreToolUse hook' } if (merged.decision === 'ask') return { kind: 'ask', ...merged.reason !== undefined ? { reason: merged.reason } : {} } return next() @@ -290,7 +291,7 @@ export function apply(ctx: Context, config: Config): void { // --- PostToolUse → PostToolDecision. Matcher subject is the tool name. --- ctx.on('tools/post-execute', async (exec, result, next): Promise => { const turn = lastTurn(exec.agent) - const merged = await runPoint('PostToolUse', exec.name, postToolPayload(exec, result), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) + const merged = await runPoint('PostToolUse', exec.name, postToolPayload(ctx, exec, result), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) const context = contextFrom(merged) if (merged.decision === 'deny') { return { kind: 'block', feedback: [{ type: 'text', text: merged.reason ?? 'blocked by PostToolUse hook' }], ...context ? { additionalContext: context } : {} } @@ -317,7 +318,7 @@ export function apply(ctx: Context, config: Config): void { // false, so a Stop hook that unconditionally blocks would force-continue every // step — a hook author must self-limit until the guard lands. --- ctx.on('agent/turn-continuation', async (agent, turn, _default, next): Promise => { - const merged = await runPoint('Stop', '', stopPayload(agent), { agent, turn }) + const merged = await runPoint('Stop', '', stopPayload(ctx, agent), { agent, turn }) if (merged.decision === 'deny') { // A blocking Stop hook forces continuation. It carries its reason as // next-step steering; a blocking hook that emitted no reason (exit 2, empty @@ -339,7 +340,7 @@ export function apply(ctx: Context, config: Config): void { // a specific-kind matcher does not (documented in the RFC). --- ctx.on('subagent/start', (info) => { const child = ctx.get('agents')?.get(info.id) - detached.track(runPoint('SubagentStart', SUBAGENT_TYPE, subagentPayload('SubagentStart', info, child), { ...child ? { agent: child } : {}, signal: detached.signal }) + detached.track(runPoint('SubagentStart', SUBAGENT_TYPE, subagentPayload(ctx, 'SubagentStart', info, child), { ...child ? { agent: child } : {}, signal: detached.signal }) .then((merged) => { const context = contextFrom(merged) if (context && child) child.inject(context.content, { source: context.source }) @@ -355,7 +356,7 @@ export function apply(ctx: Context, config: Config): void { // reject — no `.catch` is needed (the tracker's settlement bookkeeping // would absorb one anyway). const child = ctx.get('agents')?.get(info.id) - detached.track(runPoint('SubagentStop', SUBAGENT_TYPE, subagentPayload('SubagentStop', info, child), { ...child ? { agent: child } : {}, signal: detached.signal })) + detached.track(runPoint('SubagentStop', SUBAGENT_TYPE, subagentPayload(ctx, 'SubagentStop', info, child), { ...child ? { agent: child } : {}, signal: detached.signal })) }) } @@ -385,28 +386,31 @@ function blocksToText(content: ContentBlock[]): string { return content.filter((b): b is Extract => b.type === 'text').map(b => b.text).join('') } -function base(agent: Agent | undefined, event: string): Record { +function base(ctx: Context, agent: Agent | undefined, event: string): Record { return { session_id: agent?.session.header.id ?? '', + transcript_path: agent === undefined + ? '' + : ctx.get('sessionPersistence')?.locate(agent.session.header)?.path ?? '', cwd: agent?.session.header.cwd ?? process.cwd(), hook_event_name: event, } } -function sessionStartPayload(agent: Agent, source: string): Record { - return { ...base(agent, 'SessionStart'), source } +function sessionStartPayload(ctx: Context, agent: Agent, source: string): Record { + return { ...base(ctx, agent, 'SessionStart'), source } } -function promptPayload(agent: Agent, content: ContentBlock[]): Record { - return { ...base(agent, 'UserPromptSubmit'), prompt: blocksToText(content) } +function promptPayload(ctx: Context, agent: Agent, content: ContentBlock[]): Record { + return { ...base(ctx, agent, 'UserPromptSubmit'), prompt: blocksToText(content) } } -function preToolPayload(exec: ToolExecution): Record { - return { ...base(exec.agent, 'PreToolUse'), tool_name: exec.name, tool_input: exec.arguments, tool_use_id: exec.callId } +function preToolPayload(ctx: Context, exec: ToolExecution): Record { + return { ...base(ctx, exec.agent, 'PreToolUse'), tool_name: exec.name, tool_input: exec.arguments, tool_use_id: exec.callId } } -function postToolPayload(exec: ToolExecution, result: ToolExecutionResult): Record { - return { ...base(exec.agent, 'PostToolUse'), tool_name: exec.name, tool_input: exec.arguments, tool_use_id: exec.callId, tool_response: blocksToText(result.content) } +function postToolPayload(ctx: Context, exec: ToolExecution, result: ToolExecutionResult): Record { + return { ...base(ctx, exec.agent, 'PostToolUse'), tool_name: exec.name, tool_input: exec.arguments, tool_use_id: exec.callId, tool_response: blocksToText(result.content) } } -function stopPayload(agent: Agent): Record { - return { ...base(agent, 'Stop'), stop_hook_active: false } +function stopPayload(ctx: Context, agent: Agent): Record { + return { ...base(ctx, agent, 'Stop'), stop_hook_active: false } } /** * Build a SubagentStart/SubagentStop payload from the CC base (the child's @@ -414,9 +418,9 @@ function stopPayload(agent: Agent): Record { * fields. `agent_type` is the CC-default {@link SUBAGENT_TYPE}; `stop_hook_active` * is present on SubagentStop only (the loop-guard flag, always false this cut). */ -function subagentPayload(event: 'SubagentStart' | 'SubagentStop', info: { id: string }, child: Agent | undefined): Record { +function subagentPayload(ctx: Context, event: 'SubagentStart' | 'SubagentStop', info: { id: string }, child: Agent | undefined): Record { return { - ...base(child, event), + ...base(ctx, child, event), agent_id: info.id, agent_type: SUBAGENT_TYPE, ...event === 'SubagentStop' ? { stop_hook_active: false } : {}, diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index f06cdcf6b4..fb7705a149 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -1,10 +1,11 @@ import { afterEach, describe, expect, it, vi } from 'vitest' -import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync } from 'node:fs' +import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync, readFileSync } from 'node:fs' import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' @@ -27,11 +28,12 @@ function hooks(d: string, h: unknown): string { writeFileSync(join(d, 'hooks.json'), JSON.stringify({ hooks: h })); return join(d, 'hooks.json') } -type HarnessOpts = { pluginRoot?: string; projectDir?: string; stderrSummaryMaxChars?: number } +type HarnessOpts = { pluginRoot?: string; projectDir?: string; stderrSummaryMaxChars?: number; sessionRoot?: string } async function harness(configPath: string, adapter: MockAdapter, opts: HarnessOpts = {}): Promise { const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(SessionStore) + if (opts.sessionRoot !== undefined) await ctx.plugin(SessionPersistenceJsonl, { root: opts.sessionRoot }) await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) @@ -56,6 +58,28 @@ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): } describe('hooks-claude coverage — config option arms + substitution + skip warning', () => { + it('uses the persistence locator for transcript_path and an empty string without one', async () => { + async function capture(sessionRoot?: string): Promise<{ payload: { transcript_path: string }; expected: string | undefined }> { + const d = dir() + const cap = join(d, 'payload') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'capture.sh', `#!/usr/bin/env bash\ncat > "${cap}"\n`) }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('transcript'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + return { + payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string }, + expected: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path, + } + } + + const located = await capture(dir()) + expect(located.payload.transcript_path).toBe(located.expected) + expect((await capture()).payload.transcript_path).toBe('') + }) + it('honors pluginRoot + projectDir substitution and warns on a skipped non-command hook', async () => { const d = dir() // ${CLAUDE_PLUGIN_ROOT} resolves to d; the script writes its own cwd-independent marker. diff --git a/packages/hooks/hooks-claude/tsconfig.json b/packages/hooks/hooks-claude/tsconfig.json index 909db9b5c3..07c88610f9 100644 --- a/packages/hooks/hooks-claude/tsconfig.json +++ b/packages/hooks/hooks-claude/tsconfig.json @@ -29,6 +29,9 @@ { "path": "../../core/session" }, + { + "path": "../../session-persistence/session-persistence" + }, { "path": "../../subagent/subagent" }, diff --git a/packages/hooks/hooks-codex/README.md b/packages/hooks/hooks-codex/README.md index b3fbc39928..255108de50 100644 --- a/packages/hooks/hooks-codex/README.md +++ b/packages/hooks/hooks-codex/README.md @@ -48,6 +48,8 @@ The hooks themselves run in the agent's session workspace: for the agent-scoped A tool call's payload carries the real `tool_name` (the same value the matcher tests) and Codex's `tool_input: { command }` shape (the `command` arg when present, else `''`). The matcher subject is the tool name (`PreToolUse`/`PostToolUse`) or the session source (`SessionStart`); `UserPromptSubmit`/`Stop` ignore matchers. +Every agent-scoped stdin payload carries `session_id` and `transcript_path`. The bridge resolves the latter through `ctx.sessionPersistence.locate(session.header)` when available and otherwise sends `null`, preserving the Codex `string | null` shape. Lookup does not create or flush the artifact, so a path can be absent before the first turn-end checkpoint or omit the current open turn. + `SessionStart` — the one emit point — runs detached; each run chain is tracked, and disposing the bridge aborts a still-running hook process, then drains the continuation before the dispose resolves (`createDetachedRuns` in `dsh-hook-protocol`). ## Context source diff --git a/packages/hooks/hooks-codex/package.json b/packages/hooks/hooks-codex/package.json index f26b57fe11..2dc358e461 100644 --- a/packages/hooks/hooks-codex/package.json +++ b/packages/hooks/hooks-codex/package.json @@ -29,6 +29,7 @@ "@deepseek-ai/dsh-hook-protocol": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", + "@deepseek-ai/dsh-session-persistence": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", "cordis": "^4.0.0-rc.6" }, @@ -40,6 +41,8 @@ "@deepseek-ai/dsh-hook-protocol": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", + "@deepseek-ai/dsh-session-persistence": "workspace:^", + "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.6" diff --git a/packages/hooks/hooks-codex/src/index.ts b/packages/hooks/hooks-codex/src/index.ts index e164d98a70..798743b38b 100644 --- a/packages/hooks/hooks-codex/src/index.ts +++ b/packages/hooks/hooks-codex/src/index.ts @@ -20,6 +20,7 @@ import type { Context } from 'cordis' import z from 'schemastery' import type { Agent, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm' +import type {} from '@deepseek-ai/dsh-session-persistence' import type { PostToolDecision, PreToolDecision, ToolExecution, ToolExecutionResult } from '@deepseek-ai/dsh-tools' import { appendHookInvoked, @@ -196,7 +197,7 @@ export function apply(ctx: Context, config: Config): void { // the model (a slow hook can miss the first request). Gating is a deferred // loop-level change; the contract is "injected as soon as the hook resolves". ctx.on('agent/session-start', (agent, source) => { - detached.track(runPoint('SessionStart', source, { ...base(agent, 'SessionStart', model), source }, { agent, plainStdoutAsContext: true, signal: detached.signal }) + detached.track(runPoint('SessionStart', source, { ...base(ctx, agent, 'SessionStart', model), source }, { agent, plainStdoutAsContext: true, signal: detached.signal }) .then((merged) => { const context = contextFrom(merged) if (context) agent.inject(context.content, { source: context.source }) @@ -207,7 +208,7 @@ export function apply(ctx: Context, config: Config): void { // UserPromptSubmit → PromptDecision. Codex can only BLOCK (no allow/ask). ctx.on('agent/prompt-submit', async (agent, content, _source, next): Promise => { const turn = lastTurn(agent) - const merged = await runPoint('UserPromptSubmit', '', { ...turnBase(agent, 'UserPromptSubmit', model), prompt: blocksToText(content) }, { agent, turn, plainStdoutAsContext: true }) + const merged = await runPoint('UserPromptSubmit', '', { ...turnBase(ctx, agent, 'UserPromptSubmit', model), prompt: blocksToText(content) }, { agent, turn, plainStdoutAsContext: true }) if (merged.decision === 'deny') return { kind: 'block', reason: merged.reason ?? 'blocked by UserPromptSubmit hook' } // Context alone is not a veto: DELEGATE so a later prompt-submit listener can // still block/rewrite, then fold our context onto its decision. @@ -224,7 +225,7 @@ export function apply(ctx: Context, config: Config): void { // PreToolUse → PreToolDecision. Codex blocks only (no allow/ask honored). ctx.on('tools/pre-execute', async (exec, next): Promise => { const turn = lastTurn(exec.agent) - const merged = await runPoint('PreToolUse', exec.name, preToolPayload(exec, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) + const merged = await runPoint('PreToolUse', exec.name, preToolPayload(ctx, exec, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) if (merged.decision === 'deny') return { kind: 'deny', reason: merged.reason ?? 'blocked by PreToolUse hook' } return next() }) @@ -232,7 +233,7 @@ export function apply(ctx: Context, config: Config): void { // PostToolUse → PostToolDecision (block with feedback, or attach context). ctx.on('tools/post-execute', async (exec, result, next): Promise => { const turn = lastTurn(exec.agent) - const merged = await runPoint('PostToolUse', exec.name, postToolPayload(exec, result, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) + const merged = await runPoint('PostToolUse', exec.name, postToolPayload(ctx, exec, result, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) const context = contextFrom(merged) if (merged.decision === 'deny') { return { kind: 'block', feedback: [{ type: 'text', text: merged.reason ?? 'blocked by PostToolUse hook' }], ...context ? { additionalContext: context } : {} } @@ -256,7 +257,7 @@ export function apply(ctx: Context, config: Config): void { // force-continue every step (`stop_hook_active` is always false here); the // loop-guard (stop_hook_active + a max-consecutive cap) is deferred. ctx.on('agent/turn-continuation', async (agent, turn, _default, next): Promise => { - const merged = await runPoint('Stop', '', { ...turnBase(agent, 'Stop', model), stop_hook_active: false, last_assistant_message: null }, { agent, turn }) + const merged = await runPoint('Stop', '', { ...turnBase(ctx, agent, 'Stop', model), stop_hook_active: false, last_assistant_message: null }, { agent, turn }) if (merged.decision === 'deny') { // A blocking Stop hook forces continuation; a block with no reason (exit 2, // empty stderr) still forces it — fall back to a generic steering line @@ -285,10 +286,12 @@ function blocksToText(content: ContentBlock[]): string { } /** Base fields on every Codex payload (no turn_id). */ -function base(agent: Agent | undefined, event: string, model: string): Record { +function base(ctx: Context, agent: Agent | undefined, event: string, model: string): Record { return { session_id: agent?.session.header.id ?? '', - transcript_path: null, + transcript_path: agent === undefined + ? null + : ctx.get('sessionPersistence')?.locate(agent.session.header)?.path ?? null, cwd: agent?.session.header.cwd ?? process.cwd(), hook_event_name: event, model, @@ -297,8 +300,8 @@ function base(agent: Agent | undefined, event: string, model: string): Record { - return { ...base(agent, event, model), turn_id: String(lastTurn(agent)) } +function turnBase(ctx: Context, agent: Agent | undefined, event: string, model: string): Record { + return { ...base(ctx, agent, event, model), turn_id: String(lastTurn(agent)) } } /** Extract a `command` string from a tool call's parsed arguments, else ''. */ @@ -310,14 +313,14 @@ function commandOf(args: unknown): string { return '' } -function preToolPayload(exec: ToolExecution, model: string): Record { +function preToolPayload(ctx: Context, exec: ToolExecution, model: string): Record { // `tool_name` is the REAL tool name (matching the `exec.name` matcher subject); // a hardcoded constant would disagree with what the matcher tests and make a // config's tool matcher never fire. `tool_input` keeps Codex's `{ command }` // shape (its shell payload), derived from the call's `command` arg when present. - return { ...turnBase(exec.agent, 'PreToolUse', model), tool_name: exec.name, tool_input: { command: commandOf(exec.arguments) }, tool_use_id: exec.callId } + return { ...turnBase(ctx, exec.agent, 'PreToolUse', model), tool_name: exec.name, tool_input: { command: commandOf(exec.arguments) }, tool_use_id: exec.callId } } -function postToolPayload(exec: ToolExecution, result: ToolExecutionResult, model: string): Record { - return { ...turnBase(exec.agent, 'PostToolUse', model), tool_name: exec.name, tool_input: { command: commandOf(exec.arguments) }, tool_use_id: exec.callId, tool_response: blocksToText(result.content) } +function postToolPayload(ctx: Context, exec: ToolExecution, result: ToolExecutionResult, model: string): Record { + return { ...turnBase(ctx, exec.agent, 'PostToolUse', model), tool_name: exec.name, tool_input: { command: commandOf(exec.arguments) }, tool_use_id: exec.callId, tool_response: blocksToText(result.content) } } diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index c83137df53..0dfac498d2 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -5,6 +5,7 @@ import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' @@ -23,9 +24,12 @@ function hooks(d: string, h: unknown): string { writeFileSync(join(d, 'hooks.json'), JSON.stringify({ hooks: h })); return join(d, 'hooks.json') } -async function harness(configPath: string, adapter: MockAdapter, opts: { stderrSummaryMaxChars?: number } = {}): Promise { +type HarnessOpts = { stderrSummaryMaxChars?: number; sessionRoot?: string } +async function harness(configPath: string, adapter: MockAdapter, opts: HarnessOpts = {}): Promise { const ctx = new Context() - await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt) + await ctx.plugin(LlmService); await ctx.plugin(SessionStore) + if (opts.sessionRoot !== undefined) await ctx.plugin(SessionPersistenceJsonl, { root: opts.sessionRoot }) + await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksCodex, { configPath, model: 'm', ...opts }) @@ -47,6 +51,28 @@ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): } describe('hooks-codex coverage — decision mapping paths', () => { + it('uses the persistence locator for transcript_path and null without one', async () => { + async function capture(sessionRoot?: string): Promise<{ payload: { transcript_path: string | null }; expected: string | undefined }> { + const d = dir() + const cap = join(d, 'payload') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'capture.sh', `#!/usr/bin/env bash\ncat > "${cap}"\n`) }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('transcript'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + return { + payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string | null }, + expected: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path, + } + } + + const located = await capture(dir()) + expect(located.payload.transcript_path).toBe(located.expected) + expect((await capture()).payload.transcript_path).toBeNull() + }) + it('UserPromptSubmit block (exit 2) → rejected turn; default reason on empty stderr', async () => { const d = dir() hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) diff --git a/packages/hooks/hooks-codex/tsconfig.json b/packages/hooks/hooks-codex/tsconfig.json index f936b500aa..ae3c91e9dd 100644 --- a/packages/hooks/hooks-codex/tsconfig.json +++ b/packages/hooks/hooks-codex/tsconfig.json @@ -29,6 +29,9 @@ { "path": "../../core/session" }, + { + "path": "../../session-persistence/session-persistence" + }, { "path": "../../llm/llm" }, diff --git a/packages/session-persistence/session-persistence-jsonl/README.md b/packages/session-persistence/session-persistence-jsonl/README.md index 9a76381614..7d04f90629 100644 --- a/packages/session-persistence/session-persistence-jsonl/README.md +++ b/packages/session-persistence/session-persistence-jsonl/README.md @@ -19,6 +19,8 @@ The JSONL durable session-persistence backend — a concrete `SessionPersistence |---|---|---| | `root` | `string` (required) | Root directory for all session files. **No default** — a `process.cwd()` default would scatter files as the process's cwd changes (bash calls, subprocesses). | +`locate(meta)` returns `{ kind: 'jsonl', path }` using the resolved absolute root and the same cwd-bucket/id encoding as materialization. It performs no filesystem I/O: the target can be returned before the file exists, and an existing file contains only the last flushed prefix. + ## Durability and crash semantics - **Lazy materialization.** `create(meta)` writes nothing; the `.jsonl` (header + first batch) is written atomically (temp-write + `fsync` + rename) on the first `append`. A created-but-never-appended session leaves nothing on disk and is absent from `list`. diff --git a/packages/session-persistence/session-persistence-jsonl/src/index.ts b/packages/session-persistence/session-persistence-jsonl/src/index.ts index a69c979756..658deb156e 100644 --- a/packages/session-persistence/session-persistence-jsonl/src/index.ts +++ b/packages/session-persistence/session-persistence-jsonl/src/index.ts @@ -11,8 +11,9 @@ * (the `session/event` → buffer → `session/flush` drain, per-session * serialization, write cursors, fork-seed persistence, HMR live-adoption, * crash-repair sequencing, dispose quiescence) lives in the backend-agnostic - * {@link PersistenceCoordinator} this class composes. The four public - * {@link SessionPersistence} methods delegate to the coordinator. + * {@link PersistenceCoordinator} this class composes. The four stateful public + * {@link SessionPersistence} methods delegate to the coordinator; the pure + * locator remains backend-owned. * * @module @deepseek-ai/dsh-session-persistence-jsonl */ @@ -24,7 +25,7 @@ import { dirname, resolve } from 'node:path' import { randomBytes } from 'node:crypto' import { SessionPersistence, PersistenceCoordinator, - type PersistenceBackend, type StoredPrefix, + type PersistenceBackend, type SessionLocation, type StoredPrefix, } from '@deepseek-ai/dsh-session-persistence' import type { Session, SessionEvent, SessionId, SessionHeader } from '@deepseek-ai/dsh-session' import { @@ -90,6 +91,11 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi // --- SessionPersistence service surface (delegated to the coordinator) --- + /** Resolve the absolute target path without touching the filesystem. */ + locate(meta: SessionHeader): SessionLocation { + return { kind: 'jsonl', path: logPath(this.root, meta.cwd, meta.id) } + } + create(meta: SessionHeader): Promise { return this.coordinator.create(meta) } diff --git a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts index 6eed63a2f4..3b052cdfde 100644 --- a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts +++ b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts @@ -2,7 +2,7 @@ import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import { appendFile, mkdtemp, mkdir, rm, readFile, writeFile, readdir, stat } from 'node:fs/promises' import { tmpdir } from 'node:os' -import { join } from 'node:path' +import { isAbsolute, join, relative, resolve } from 'node:path' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' @@ -96,6 +96,19 @@ describe('SessionPersistenceJsonl: format helpers', () => { it('encodeSegment rejects an empty id', () => { expect(() => encodeSegment('')).toThrow(/empty/) }) + + it('resolves a relative custom root before locating a session', async () => { + const absoluteRoot = await freshRoot() + const ctx = new Context() + await ctx.plugin(SessionStore) + const fiber = await ctx.plugin(SessionPersistenceJsonl, { root: relative(process.cwd(), absoluteRoot) }) + const m = meta('relative-location', '/work') + expect(ctx.sessionPersistence.locate(m)).toEqual({ + kind: 'jsonl', + path: logPath(resolve(absoluteRoot), '/work', m.id), + }) + await fiber.dispose() + }) }) describe('SessionPersistenceJsonl: durability and crash semantics', () => { @@ -110,8 +123,13 @@ describe('SessionPersistenceJsonl: durability and crash semantics', () => { it('lazy materialization: create() writes no file until the first append', async () => { const m = meta('lazy', '/work') + const location = ctx.sessionPersistence.locate(m) + expect(location).toEqual({ kind: 'jsonl', path: logPath(root, '/work', m.id) }) + expect(isAbsolute(location!.path)).toBe(true) + await ctx.sessionPersistence.create(m) - // nothing on disk yet + // locate() is a pure target-path calculation: neither it nor create() + // materializes a file before the first append. const dir = sessionDir(root, '/work') await expect(stat(logPath(root, '/work', m.id))).rejects.toThrow() expect((await ctx.sessionPersistence.list()).map(h => h.id)).not.toContain(m.id) @@ -123,6 +141,26 @@ describe('SessionPersistenceJsonl: durability and crash semantics', () => { void dir }) + it('keeps the same location on resume and gives a fork its own location', async () => { + const parent = meta('location-parent', '/work') + const parentLocation = ctx.sessionPersistence.locate(parent) + await ctx.sessionPersistence.create(parent) + await ctx.sessionPersistence.append(parent.id, oneTurnLog()) + + const loaded = await ctx.sessionPersistence.load(parent.id) + expect(ctx.sessionPersistence.locate(loaded.meta)).toEqual(parentLocation) + + const child = { + ...loaded.meta, + id: SessionId('location-child'), + parentSession: parent.id, + seedLength: loaded.events.length, + } + const childLocation = ctx.sessionPersistence.locate(child) + expect(childLocation?.path).not.toBe(parentLocation?.path) + expect(childLocation).toEqual({ kind: 'jsonl', path: logPath(root, '/work', child.id) }) + }) + it('round-trip is byte-identical (incl. assistant/chunk verbatim)', async () => { const m = meta('chunks') const log: SessionEvent[] = [ diff --git a/packages/session-persistence/session-persistence-sqlite/README.md b/packages/session-persistence/session-persistence-sqlite/README.md index c14d3a70ea..4ac84c9173 100644 --- a/packages/session-persistence/session-persistence-sqlite/README.md +++ b/packages/session-persistence/session-persistence-sqlite/README.md @@ -2,6 +2,8 @@ A SQLite durable session-persistence backend — a second `SessionPersistence` implementation ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), built to validate that the abstract seam and the shared `runPersistenceContract` suite are genuinely backend-agnostic. It satisfies the SAME contract as `dsh-session-persistence-jsonl` (append-only, contiguous-seq, lazy materialization, interrupted-turn close on load), expressed over `node:sqlite` rows instead of file bytes. +`locate(meta)` returns `undefined`: all sessions share one database, so there is no honest independent per-session transcript path. + > **TODO:** this backend talks to `node:sqlite` directly. If a cordis database service (`cordis/db` / a `@cordisjs` SQL driver plugin) is adopted, route through that instead of holding a raw `DatabaseSync` here — the contract surface (`SessionPersistence`) would not change, only the storage driver. ## Storage model diff --git a/packages/session-persistence/session-persistence-sqlite/src/index.ts b/packages/session-persistence/session-persistence-sqlite/src/index.ts index 30387b4837..29b8042cd3 100644 --- a/packages/session-persistence/session-persistence-sqlite/src/index.ts +++ b/packages/session-persistence/session-persistence-sqlite/src/index.ts @@ -11,8 +11,9 @@ * Like the JSONL backend it supplies ONLY the storage primitives (the * {@link PersistenceBackend} hooks below — INSERT/DELETE/SELECT inside * transactions); all the write-path orchestration lives in the backend-agnostic - * {@link PersistenceCoordinator} this class composes. The four public - * {@link SessionPersistence} methods delegate to the coordinator. + * {@link PersistenceCoordinator} this class composes. The four stateful public + * {@link SessionPersistence} methods delegate to the coordinator; the pure + * locator remains backend-owned. * * @module @deepseek-ai/dsh-session-persistence-sqlite */ @@ -24,7 +25,7 @@ import { mkdir } from 'node:fs/promises' import { dirname, resolve } from 'node:path' import { SessionPersistence, PersistenceCoordinator, - type PersistenceBackend, type StoredPrefix, + type PersistenceBackend, type SessionLocation, type StoredPrefix, } from '@deepseek-ai/dsh-session-persistence' import type { Session, SessionEvent, SurfaceEventType, SessionId, SessionHeader } from '@deepseek-ai/dsh-session' import { @@ -109,6 +110,11 @@ export class SessionPersistenceSqlite extends SessionPersistence implements Pers // --- SessionPersistence service surface (delegated to the coordinator) --- + /** SQLite has one database, not an independent local artifact per session. */ + locate(_meta: SessionHeader): SessionLocation | undefined { + return undefined + } + create(meta: SessionHeader): Promise { return this.coordinator.create(meta) } diff --git a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts index a6eda72685..e055ea436e 100644 --- a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts +++ b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts @@ -144,6 +144,12 @@ describe('scanRows', () => { }) describe('SessionPersistenceSqlite: durability and crash semantics', () => { + it('has no independent per-session log location', async () => { + const { ctx, dispose } = await backend() + expect(ctx.sessionPersistence.locate(meta('sqlite-location'))).toBeUndefined() + await dispose() + }) + it('an interrupted turn (rows after the last turn/end) is PRESERVED and closed during load', async () => { const path = await freshDbPath() const m = meta('crash') diff --git a/packages/session-persistence/session-persistence/README.md b/packages/session-persistence/session-persistence/README.md index 8bd3fed568..ca86ee0e71 100644 --- a/packages/session-persistence/session-persistence/README.md +++ b/packages/session-persistence/session-persistence/README.md @@ -8,6 +8,7 @@ The persisted unit IS the existing `SessionEvent` (event-sourced model — the l | Method | Contract | |---|---| +| `locate(meta): SessionLocation \| undefined` | Resolve an absolute per-session artifact target without I/O or materialization. Backends without an independent local artifact return `undefined`. | | `create(meta): Promise` | Register a new session's metadata. MAY defer the physical write until the first `append` (lazy materialization). | | `append(id, events): Promise` | Durably persist a batch (from the `session/flush` drain). Append-only; first event `seq` == stored next-seq after any repair; rejects non-JSON-serializable data naming the offending type. | | `load(id): Promise<{ meta; events }>` | Reload meta + log. Preserves an interrupted (unclosed) final turn and closes it with synthetic closers — an error `tool/result` per unanswered `tool-call`, then `step/end?`+`turn/end {interrupted}` (a turn can be huge — never truncated); only a torn tail fragment is dropped. Events contiguous (`events[i].seq === i`); rejects a committed-region gap/parse error or unknown `version`. | @@ -24,7 +25,7 @@ The persisted unit IS the existing `SessionEvent` (event-sourced model — the l The two first-party backends were byte-identical (or same-algorithm) for ALL of their write-path orchestration — the in-memory bookkeeping (per-id state, write-behind buffers, per-id serialization chains, per-session init promises), the `session/event` → buffer → `session/flush` drain, lazy materialization, crash-tail repair on load, the four `session/created` adoption cases (new / HMR-adopt / collision / ownerless-claim), and dispose-time quiescence. Only the STORAGE primitives differed (write bytes vs. INSERT rows). -`PersistenceCoordinator` owns that orchestration once. A first-party backend composes one (`new PersistenceCoordinator(ctx, this)`), implements the small `PersistenceBackend` hook interface, and delegates its four public service methods to the coordinator. This keeps the duplicated, correctness-heavy orchestration in a single place (it used to receive the same fixes twice). +`PersistenceCoordinator` owns that orchestration once. A first-party backend composes one (`new PersistenceCoordinator(ctx, this)`), implements the small `PersistenceBackend` hook interface, and delegates its four stateful service methods to the coordinator; the pure `locate` query stays backend-owned. This keeps the duplicated, correctness-heavy orchestration in a single place (it used to receive the same fixes twice). The `PersistenceBackend` hooks (the only seam between the coordinator and storage): @@ -46,6 +47,6 @@ Import `runPersistenceContract` from `tests/contract.ts` (the public-API contrac Three backends run these suites: an in-memory reference (in `tests/`), `dsh-session-persistence-jsonl` (append-only file log) and `dsh-session-persistence-sqlite` (`node:sqlite`, each `SessionEvent` one row `(session_id, seq, type, time, data, source_event_seqs, surface_op)`). All passing the same contract + coordinator suite is the proof that the seam is genuinely backend-agnostic — lazy materialization, crash-tail-on-load, and contiguous-seq hold identically over file bytes and over a transactional store. -## Metadata types +## Metadata and location types -Re-exported from `dsh-session`: `SessionHeader` (immutable session metadata: `version`, `id`, `createdAt`, `cwd?`, `parentSession?`, `seedLength?`). +Re-exported from `dsh-session`: `SessionHeader` (immutable session metadata: `version`, `id`, `createdAt`, `cwd?`, `parentSession?`, `seedLength?`). `SessionLocation` is `{ readonly kind: string; readonly path: string }`; its path is an absolute backend target, not proof that the artifact exists or contains an unflushed turn. diff --git a/packages/session-persistence/session-persistence/src/index.ts b/packages/session-persistence/session-persistence/src/index.ts index 1588ed2526..7e3a532f65 100644 --- a/packages/session-persistence/session-persistence/src/index.ts +++ b/packages/session-persistence/session-persistence/src/index.ts @@ -38,6 +38,18 @@ declare module 'cordis' { } } +/** + * A backend-resolved, per-session local artifact location. The path is an + * absolute target path and can name an artifact that has not materialized yet. + * Consumers must treat it as a location hint, never as an authorization token. + */ +export interface SessionLocation { + /** Backend-specific artifact kind, for example `jsonl`. */ + readonly kind: string + /** Absolute path to this session's backend-owned artifact. */ + readonly path: string +} + /** * Whether a live session's seed reproduces a persisted prefix exactly. Backends * use this collision check to distinguish a legitimate resume/HMR rebind from a @@ -104,6 +116,15 @@ export abstract class SessionPersistence extends Service { super(ctx, 'sessionPersistence') } + /** + * Resolve this backend's independent local artifact for a session without + * reading, creating, flushing, or otherwise materializing it. Backends such + * as SQLite that do not own one artifact per session return `undefined`. + * @param meta - the immutable session header whose artifact is requested. + * @returns the backend-specific absolute location, when one exists. + */ + abstract locate(meta: SessionHeader): SessionLocation | undefined + /** * Register a new session's metadata. A backend MAY defer the physical write * until the first {@link append} (lazy materialization), in which case a diff --git a/packages/session-persistence/session-persistence/tests/persistence.spec.ts b/packages/session-persistence/session-persistence/tests/persistence.spec.ts index 4e4cf67822..2e28931a98 100644 --- a/packages/session-persistence/session-persistence/tests/persistence.spec.ts +++ b/packages/session-persistence/session-persistence/tests/persistence.spec.ts @@ -49,6 +49,10 @@ class MemoryPersistence extends SessionPersistence implements PersistenceBackend // --- service surface (delegated to the coordinator) --- + locate(_meta: SessionHeader): undefined { + return undefined + } + create(m: SessionHeader): Promise { return this.coordinator.create(m) } diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 4425c6bd41..b42cd5dae0 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -120,6 +120,12 @@ importers: '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session + '@deepseek-ai/dsh-session-persistence': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence + '@deepseek-ai/dsh-session-persistence-jsonl': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence-jsonl '@deepseek-ai/dsh-system-prompt': specifier: workspace:^ version: link:../../core/system-prompt @@ -514,6 +520,12 @@ importers: '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session + '@deepseek-ai/dsh-session-persistence': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence + '@deepseek-ai/dsh-session-persistence-jsonl': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence-jsonl '@deepseek-ai/dsh-subagent': specifier: workspace:^ version: link:../../subagent/subagent @@ -554,6 +566,12 @@ importers: '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session + '@deepseek-ai/dsh-session-persistence': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence + '@deepseek-ai/dsh-session-persistence-jsonl': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence-jsonl '@deepseek-ai/dsh-system-prompt': specifier: workspace:^ version: link:../../core/system-prompt diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index 881ce06578..937ca72a0d 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -34,6 +34,7 @@ { "doc": "docs/core-data-structures/persistence.md", "symbol": "SessionHeader", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/persistence.md", "symbol": "CreateSessionOptions", "source": "packages/core/session/src/types.ts" }, + { "doc": "docs/core-data-structures/persistence.md", "symbol": "SessionLocation", "source": "packages/session-persistence/session-persistence/src/index.ts" }, { "doc": "docs/core-data-structures/tools.md", "symbol": "ToolDefinition", "source": "packages/core/tools/src/index.ts" }, { "doc": "docs/core-data-structures/tools.md", "symbol": "SchemaProp", "source": "packages/core/tools/src/schema.ts" }, From c20445199529f6f85b8fe56dd678e77aa8a07234 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Fri, 10 Jul 2026 20:55:41 +0800 Subject: [PATCH 006/359] test: split hook transcript locator cases --- .../hooks/hooks-claude/tests/coverage.spec.ts | 37 ++++++++++--------- .../hooks/hooks-codex/tests/coverage.spec.ts | 37 ++++++++++--------- 2 files changed, 40 insertions(+), 34 deletions(-) diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index fb7705a149..4a235775bc 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -58,26 +58,29 @@ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): } describe('hooks-claude coverage — config option arms + substitution + skip warning', () => { - it('uses the persistence locator for transcript_path and an empty string without one', async () => { - async function capture(sessionRoot?: string): Promise<{ payload: { transcript_path: string }; expected: string | undefined }> { - const d = dir() - const cap = join(d, 'payload') - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'capture.sh', `#!/usr/bin/env bash\ncat > "${cap}"\n`) }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('transcript'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - return { - payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string }, - expected: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path, - } + async function captureTranscriptPath(sessionRoot?: string): Promise<{ payload: { transcript_path: string }; expected: string | undefined }> { + const d = dir() + const cap = join(d, 'payload') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'capture.sh', `#!/usr/bin/env bash\ncat > "${cap}"\n`) }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('transcript'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + return { + payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string }, + expected: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path, } + } - const located = await capture(dir()) + it('uses the persistence locator for transcript_path', async () => { + const located = await captureTranscriptPath(dir()) expect(located.payload.transcript_path).toBe(located.expected) - expect((await capture()).payload.transcript_path).toBe('') + }) + + it('uses an empty transcript_path without a persistence locator', async () => { + expect((await captureTranscriptPath()).payload.transcript_path).toBe('') }) it('honors pluginRoot + projectDir substitution and warns on a skipped non-command hook', async () => { diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index 0dfac498d2..ff9508c9bc 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -51,26 +51,29 @@ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): } describe('hooks-codex coverage — decision mapping paths', () => { - it('uses the persistence locator for transcript_path and null without one', async () => { - async function capture(sessionRoot?: string): Promise<{ payload: { transcript_path: string | null }; expected: string | undefined }> { - const d = dir() - const cap = join(d, 'payload') - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'capture.sh', `#!/usr/bin/env bash\ncat > "${cap}"\n`) }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('transcript'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - return { - payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string | null }, - expected: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path, - } + async function captureTranscriptPath(sessionRoot?: string): Promise<{ payload: { transcript_path: string | null }; expected: string | undefined }> { + const d = dir() + const cap = join(d, 'payload') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'capture.sh', `#!/usr/bin/env bash\ncat > "${cap}"\n`) }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('transcript'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + return { + payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string | null }, + expected: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path, } + } - const located = await capture(dir()) + it('uses the persistence locator for transcript_path', async () => { + const located = await captureTranscriptPath(dir()) expect(located.payload.transcript_path).toBe(located.expected) - expect((await capture()).payload.transcript_path).toBeNull() + }) + + it('uses null transcript_path without a persistence locator', async () => { + expect((await captureTranscriptPath()).payload.transcript_path).toBeNull() }) it('UserPromptSubmit block (exit 2) → rejected turn; default reason on empty stderr', async () => { From 869f94d9d85e9a1db03afbb7c670fe608c93f5a3 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Fri, 10 Jul 2026 20:56:24 +0800 Subject: [PATCH 007/359] revert: split hook transcript locator cases --- .../hooks/hooks-claude/tests/coverage.spec.ts | 37 +++++++++---------- .../hooks/hooks-codex/tests/coverage.spec.ts | 37 +++++++++---------- 2 files changed, 34 insertions(+), 40 deletions(-) diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index 4a235775bc..fb7705a149 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -58,29 +58,26 @@ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): } describe('hooks-claude coverage — config option arms + substitution + skip warning', () => { - async function captureTranscriptPath(sessionRoot?: string): Promise<{ payload: { transcript_path: string }; expected: string | undefined }> { - const d = dir() - const cap = join(d, 'payload') - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'capture.sh', `#!/usr/bin/env bash\ncat > "${cap}"\n`) }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('transcript'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - return { - payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string }, - expected: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path, + it('uses the persistence locator for transcript_path and an empty string without one', async () => { + async function capture(sessionRoot?: string): Promise<{ payload: { transcript_path: string }; expected: string | undefined }> { + const d = dir() + const cap = join(d, 'payload') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'capture.sh', `#!/usr/bin/env bash\ncat > "${cap}"\n`) }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('transcript'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + return { + payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string }, + expected: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path, + } } - } - it('uses the persistence locator for transcript_path', async () => { - const located = await captureTranscriptPath(dir()) + const located = await capture(dir()) expect(located.payload.transcript_path).toBe(located.expected) - }) - - it('uses an empty transcript_path without a persistence locator', async () => { - expect((await captureTranscriptPath()).payload.transcript_path).toBe('') + expect((await capture()).payload.transcript_path).toBe('') }) it('honors pluginRoot + projectDir substitution and warns on a skipped non-command hook', async () => { diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index ff9508c9bc..0dfac498d2 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -51,29 +51,26 @@ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): } describe('hooks-codex coverage — decision mapping paths', () => { - async function captureTranscriptPath(sessionRoot?: string): Promise<{ payload: { transcript_path: string | null }; expected: string | undefined }> { - const d = dir() - const cap = join(d, 'payload') - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'capture.sh', `#!/usr/bin/env bash\ncat > "${cap}"\n`) }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('transcript'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - return { - payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string | null }, - expected: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path, + it('uses the persistence locator for transcript_path and null without one', async () => { + async function capture(sessionRoot?: string): Promise<{ payload: { transcript_path: string | null }; expected: string | undefined }> { + const d = dir() + const cap = join(d, 'payload') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'capture.sh', `#!/usr/bin/env bash\ncat > "${cap}"\n`) }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('transcript'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + return { + payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string | null }, + expected: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path, + } } - } - it('uses the persistence locator for transcript_path', async () => { - const located = await captureTranscriptPath(dir()) + const located = await capture(dir()) expect(located.payload.transcript_path).toBe(located.expected) - }) - - it('uses null transcript_path without a persistence locator', async () => { - expect((await captureTranscriptPath()).payload.transcript_path).toBeNull() + expect((await capture()).payload.transcript_path).toBeNull() }) it('UserPromptSubmit block (exit 2) → rejected turn; default reason on empty stderr', async () => { From dfcc93da766e6d31cc16d061492fe4403420e85f Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sat, 11 Jul 2026 22:59:30 +0800 Subject: [PATCH 008/359] test: give hook locator checks loaded-runner headroom --- packages/hooks/hooks-claude/tests/coverage.spec.ts | 2 +- packages/hooks/hooks-codex/tests/coverage.spec.ts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index fb7705a149..67bd0a809b 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -78,7 +78,7 @@ describe('hooks-claude coverage — config option arms + substitution + skip war const located = await capture(dir()) expect(located.payload.transcript_path).toBe(located.expected) expect((await capture()).payload.transcript_path).toBe('') - }) + }, 15_000) // Two real agent/hook subprocess loops need loaded pre-push runner headroom. it('honors pluginRoot + projectDir substitution and warns on a skipped non-command hook', async () => { const d = dir() diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index 0dfac498d2..ecf0eb3782 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -71,7 +71,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const located = await capture(dir()) expect(located.payload.transcript_path).toBe(located.expected) expect((await capture()).payload.transcript_path).toBeNull() - }) + }, 15_000) // Two real agent/hook subprocess loops need loaded pre-push runner headroom. it('UserPromptSubmit block (exit 2) → rejected turn; default reason on empty stderr', async () => { const d = dir() From df9617aaff2e45bea858fc75c037e77486945faa Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sun, 12 Jul 2026 15:41:42 +0800 Subject: [PATCH 009/359] feat(bash): generalize managed shell environment --- docs/architecture.md | 2 + docs/capability-seams.md | 3 + docs/config-catalog.md | 26 ++- docs/cordis-catalog/services.md | 16 +- docs/core-data-structures/bash.md | 10 +- ...0-bash-stdin-env-trusted-plugin-surface.md | 4 +- ...agent-session-identity-and-log-location.md | 69 +++--- docs/tool-catalog.md | 2 +- .../snapshots/both-mode-turn/session.jsonl | 2 +- .../both-mode-turn/system-prompt.golden.md | 2 +- .../code-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/skill-load/session.jsonl | 2 +- .../tests/snapshots/text-turn/session.jsonl | 2 +- .../snapshots/mode-switching/session.jsonl | 2 +- packages/bash/bash-local/README.md | 2 +- packages/bash/bash-local/src/index.ts | 7 +- packages/bash/bash-local/src/run.ts | 48 ++-- .../bash/bash-local/tests/executor.spec.ts | 28 ++- packages/bash/bash-local/tests/run.spec.ts | 33 ++- packages/bash/bash/README.md | 4 +- packages/bash/bash/src/index.ts | 1 + packages/bash/bash/src/types.ts | 32 ++- packages/bash/tool-bash/README.md | 23 +- packages/bash/tool-bash/package.json | 3 + packages/bash/tool-bash/src/index.ts | 216 ++++++++++++++++-- .../bash/tool-bash/tests/bash-env.spec.ts | 189 +++++++++++++++ .../bash/tool-bash/tests/integration.spec.ts | 19 +- packages/bash/tool-bash/tests/tools.spec.ts | 38 ++- .../cordis/tool-cordis/src/api-catalog.ts | 29 ++- packages/core/agent-core/README.md | 4 +- packages/core/agent-core/src/index.ts | 23 +- .../core/agent-core/tests/agent-core.spec.ts | 49 +++- packages/ui/acp-agent/README.md | 1 + packages/ui/acp-agent/src/index.ts | 4 + packages/ui/acp-agent/tests/acp-agent.spec.ts | 3 +- packages/ui/stdio-agent/README.md | 1 + packages/ui/stdio-agent/src/index.ts | 4 + .../ui/stdio-agent/tests/stdio-agent.spec.ts | 3 +- pnpm-lock.yaml | 72 +++--- scripts/gen-doc-graphs.ts | 7 + 40 files changed, 790 insertions(+), 197 deletions(-) create mode 100644 packages/bash/tool-bash/tests/bash-env.spec.ts diff --git a/docs/architecture.md b/docs/architecture.md index c1755dc815..a75f064834 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -26,6 +26,7 @@ Composition is preferred over inheritance. `packages/core/` is a repository grou |---|---|---| | `ctx.llm` | [`llm/`](../packages/llm/README.md) | adapter registry and streaming model calls | | `ctx.bash` | [`bash/`](../packages/bash/README.md) | foreground/background command execution | +| `ctx.bashEnv` | [`dsh-tool-bash`](../packages/bash/tool-bash/README.md) | declared, per-execution `DSH_*` environment facts for model bash | | `ctx.sandbox` | [`sandbox/`](../packages/sandbox/README.md) | same-world process confinement (argv wrapping, per-call policy) | | `ctx.codeRuntime` | [`code-runtime/`](../packages/code-runtime/README.md) | model-written program execution | | `ctx.fs` | [`fs/`](../packages/fs/README.md) | filesystem provider primitives and policy events | @@ -144,6 +145,7 @@ New behavior should attach to a documented extension point; changing the shipped | Add a model provider | register an adapter on `ctx.llm` | | Add a model-facing capability | register a tool on `ctx.tools`; schemas flow into prompt assembly | | Add command execution | implement and register a `ctx.bash` backend | +| Expose a Harness fact to model bash | register a declared `DSH_*` contributor on `ctx.bashEnv` | | Add filesystem access or policy | implement a `ctx.fs` provider or listen on `fs/*` policy events | | Confine spawned processes | a `ctx.sandbox` backend; consumers wrap their argv before spawning | | Intercept prompts, requests, tool use, or continuation | listen on the relevant `agent/*` or `tools/*` waterfall | diff --git a/docs/capability-seams.md b/docs/capability-seams.md index 7b84133cbc..d0d6bdb08f 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -51,6 +51,7 @@ flowchart LR pkg_bash_sandbox["bash-sandbox"] pkg_hooks_claude["hooks-claude"] pkg_hooks_codex["hooks-codex"] + svc_bashEnv["ctx.bashEnv
Managed bash environment registry"] pkg_sandbox["sandbox"] svc_sandbox["ctx.sandbox
Process-sandbox seam"] pkg_sandbox_local["sandbox-local"] @@ -114,6 +115,7 @@ flowchart LR pkg_subagent_mock --> svc_subagents pkg_subagent_spawn --> svc_subagents pkg_system_prompt --> svc_systemPrompt + pkg_tool_bash --> svc_bashEnv pkg_tools --> svc_tools pkg_user_interaction --> svc_userInteraction pkg_web --> svc_web @@ -183,6 +185,7 @@ flowchart LR | `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`stdio-agent`](../packages/ui/stdio-agent), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles and the create/resume factory seam. | | `ctx.agentLoop` | `bundle` | [`agent-loop`](../packages/core/agent-loop) | - | [`agent-core`](../packages/core/agent-core) | - | The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package. | | `ctx.bash` | `seam` | [`bash`](../packages/bash/bash) | [`bash-local`](../packages/bash/bash-local), [`bash-sandbox`](../packages/bash/bash-sandbox) | [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors replace bash-local without touching them. | +| `ctx.bashEnv` | `core` | [`tool-bash`](../packages/bash/tool-bash) | - | - | - | Plugins declare effect-scoped DSH_* facts; tool-bash collects one trusted snapshot per execution and the executor rebuilds the namespace. | | `ctx.sandbox` | `seam` | [`sandbox`](../packages/sandbox/sandbox) | [`sandbox-local`](../packages/sandbox/sandbox-local) | [`bash-sandbox`](../packages/bash/bash-sandbox) | - | Consumers hand over the exact argv they are about to spawn; same-world backends wrap it under a per-call policy and report enforcement. | | `ctx.approval` | `seam` | `approval` | [`acp`](../packages/ui/acp) | [`tools`](../packages/core/tools), [`tool-bash`](../packages/bash/tool-bash) | - | One-shot permission decisions dispatched over the `approval/request` waterfall; answerers are listeners (the ACP bridge for its own agents), absence fails closed to `unavailable`. | | `ctx.codeRuntime` | `seam` | [`code-runtime`](../packages/code-runtime/code-runtime) | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | [`tools`](../packages/core/tools) | - | Runs one model-written program against host-provided async bindings; backends differ by substrate and language (the tool registry consumes it for Code Mode). | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 8bafb4aef1..b297595592 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -54,6 +54,8 @@ export interface Config { toolOrder?: string[] /** Tool-registry config — its presentation `mode` (forwarded through agent-core; see dsh-tools). */ tools?: ToolsConfig + /** DeepSeek Harness home directory exposed to bash and used for local skill discovery. */ + dshHome?: string /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */ persistenceRoot?: string /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-core. */ @@ -74,7 +76,8 @@ Source: [`packages/ui/acp-agent/src/index.ts:52`](../packages/ui/acp-agent/src/i * bridge, simply omits it), `persona` and `toolOrder` to the system-prompt * plugin (the deployment's persona section and the explicit model-facing tool * order), the `tools` object to the tool registry (its presentation `mode`), - * and `skills` to the skill registry/local provider/tool consumer. Every field + * `dshHome` to the bash environment registry and local skill provider, and + * `skills` to the skill registry/local provider/tool consumer. Every field * is optional INPUT here because each owner's schema supplies the default; * the schema is the INTERSECTION of the owners' own schemas (with registry * schemas nested under their bundle keys), so validation and defaulting can @@ -89,6 +92,8 @@ export interface Config { toolOrder?: SystemPromptConfig['toolOrder'] /** The tool registry's config — its presentation `mode` (see dsh-tools' `Config`). */ tools?: ToolsConfig + /** DeepSeek Harness home directory shared by shell context and local skill discovery. */ + dshHome?: string /** Skill registry, local provider, and model-facing consumer config. */ skills?: SkillConfig } @@ -106,7 +111,7 @@ export interface SkillConfig { Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts) -Source: [`packages/core/agent-core/src/index.ts:87`](../packages/core/agent-core/src/index.ts) +Source: [`packages/core/agent-core/src/index.ts:89`](../packages/core/agent-core/src/index.ts) ## `@deepseek-ai/dsh-agent-loop` @@ -625,6 +630,8 @@ export interface Config { toolOrder?: string[] /** Tool-registry config — its presentation `mode` (forwarded through agent-core; see dsh-tools). */ tools?: ToolsConfig + /** DeepSeek Harness home directory exposed to bash and used for local skill discovery. */ + dshHome?: string /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */ persistenceRoot?: string /** stdin-chat banner printed once on start. Defaults to `'ready.'`. */ @@ -807,6 +814,20 @@ export interface Config { Source: [`packages/core/system-prompt/src/index.ts:179`](../packages/core/system-prompt/src/index.ts) +## `@deepseek-ai/dsh-tool-bash` + +Requires: `tools` · `bash` · `systemPrompt` + +```ts config-catalog +/** Configuration for the bash tool and its managed child environment. */ +export interface Config { + /** DeepSeek Harness home directory exposed as `DSH_HOME`; defaults to `$DSH_HOME` or `~/.dsh`. */ + dshHome?: string +} +``` + +Source: [`packages/bash/tool-bash/src/index.ts:86`](../packages/bash/tool-bash/src/index.ts) + ## `@deepseek-ai/dsh-tool-cordis` Requires: `tools` @@ -1141,7 +1162,6 @@ These load from a `cordis.yml` entry with no `config:` block; they declare no co - `@deepseek-ai/dsh-subagent` ([`packages/subagent/subagent/src/index.ts`](../packages/subagent/subagent/src/index.ts)) - `@deepseek-ai/dsh-timeout-policy` — requires `tools` ([`packages/timeout/timeout-policy/src/index.ts`](../packages/timeout/timeout-policy/src/index.ts)) - `@deepseek-ai/dsh-tool-ask-user` — requires `tools` · `userInteraction` ([`packages/ui/tool-ask-user/src/index.ts`](../packages/ui/tool-ask-user/src/index.ts)) -- `@deepseek-ai/dsh-tool-bash` — requires `tools` · `bash` · `systemPrompt` ([`packages/bash/tool-bash/src/index.ts`](../packages/bash/tool-bash/src/index.ts)) - `@deepseek-ai/dsh-tool-todo` — requires `tools` ([`packages/todo/tool-todo/src/index.ts`](../packages/todo/tool-todo/src/index.ts)) - `@deepseek-ai/dsh-user-interaction` ([`packages/ui/user-interaction/src/index.ts`](../packages/ui/user-interaction/src/index.ts)) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index d60dc13128..87ecaa328a 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -79,7 +79,21 @@ onTaskDone(listener: BashTaskListener): () => void Types: [BashExecRequest](../core-data-structures/bash.md) · [BashExecSpec](../core-data-structures/bash.md) · [BashRunResult](../core-data-structures/bash.md) · [BashTask](../core-data-structures/bash.md) · [BashTaskRead](../core-data-structures/bash.md) -Source: [`packages/bash/bash/src/index.ts:62`](../../packages/bash/bash/src/index.ts) +Source: [`packages/bash/bash/src/index.ts:63`](../../packages/bash/bash/src/index.ts) + +## `ctx.bashEnv` — `BashEnvRegistry` + +Registry (`ctx.bashEnv`) for trusted, per-execution `DSH_*` variables. The namespace is rebuilt for every model bash call: ambient `DSH_*` values are discarded by the executor, then the registry's current snapshot is injected. Built-in shell facts remain owned by the registry itself while plugins can register additional, enumerable facts with effect-scoped disposal. + +```ts cordis-catalog +register(contributor: BashEnvContributor): () => void +collect(execution: ToolExecution): DshEnvironment +list(): BashEnvVariableInfo[] +``` + +Types: [ToolExecution](../core-data-structures/tools.md) + +Source: [`packages/bash/tool-bash/src/index.ts:143`](../../packages/bash/tool-bash/src/index.ts) ## `ctx.codeRuntime` — `CodeRuntime` (abstract seam) diff --git a/docs/core-data-structures/bash.md b/docs/core-data-structures/bash.md index 51f7cb0696..02f8d85bc3 100644 --- a/docs/core-data-structures/bash.md +++ b/docs/core-data-structures/bash.md @@ -35,6 +35,12 @@ interface BashExecRequest { * uses shell syntax like `FOO=bar cmd`). */ env?: Record | undefined + /** + * Trusted DeepSeek Harness variables for this execution. Keys are restricted + * to `DSH_*`; implementations remove inherited `DSH_*` before merging this + * overlay so unavailable current facts never fall back to stale ambient ones. + */ + dshEnv?: DshEnvironment | undefined /** * Opaque OWNER token for a background task — the consumer's isolation key * (the tool layer passes the owning agent's `session.header.id`). The @@ -84,6 +90,8 @@ interface BashExecSpec { * config default, absent means "no extra env". */ env?: Record | undefined + /** Trusted managed variables carried through from the request. */ + dshEnv?: DshEnvironment | undefined /** * Opaque owner token, REQUIRED-but-nullable (mirrors `workdir`/`timeoutMs` * being required on the resolved spec): {@link BashExecutor.resolve} carries @@ -108,7 +116,7 @@ interface BashExecSpec { The `owner` token is the isolation key: the executor stores it but never interprets it (access policy is the consumer's job), so a background task started by one agent isn't readable cross-session. A required-but-nullable field makes a forgotten owner a visible `undefined` rather than a silently-unowned task. -`stdin` and `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its JSON payload on stdin and its `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` env. The model-facing `dsh-tool-bash` tool does not expose them as parameters — its request is built from `command`/`workdir`/`timeoutMs`/`signal`/`owner` only — because a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), so duplicating them as tool params would be redundant. This is NOT a security boundary: the credential scrub in `dsh-bash-local` is what stops the harness's ambient secrets reaching a spawned command, and it works regardless of these fields (a model cannot read a value the scrub removed, and tool-call args are static JSON, never shell-evaluated). A guard test asserts the tool doesn't forward model `env`/`stdin` — to catch a future `...args` spread, not to defend a trust wall. `env` is merged AFTER the scrub so an explicit caller entry (a value it already holds) wins even on a credential-shaped name. See [the bash-stdin-env RFC](../rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). +`stdin` and ordinary `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its payload and non-Harness environment. `dshEnv` is the distinct trusted channel for a current `DSH_*` snapshot collected by model-facing tool-bash. The tool does not expose any of them as parameters; model-provided extras are ignored. `dsh-bash-local` removes ambient credentials and all ambient `DSH_*`, merges terminal defaults and ordinary `env`, then applies `dshEnv`; ordinary `env` containing `DSH_*` is rejected. This makes secret scrubbing and Harness namespace ownership separate explicit contracts. See [the bash-stdin-env RFC](../rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [the session environment RFC](../rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md). Both ids the seam handles are [branded](core.md) (zero-cost `string` brands, the same machinery as `SessionId`/`AgentId`): `BashTaskId` (a tracked background task, generated `bash-N` by the local executor) and `OwnerToken` (the opaque isolation key). `OwnerToken` is deliberately a DISTINCT brand from `SessionId`, not an alias: the bash seam is a capability seam that must not know what an owner token *means*, so it never imports `dsh-session`'s vocabulary — the `dsh-tool-bash` consumer is the single boundary that casts the owning agent's `SessionId` into an `OwnerToken`. Branding both stops a raw `string` (or a `BashTaskId` where an `OwnerToken` is expected, or vice versa) from slipping through the type checker on the model-facing `task_id` path. diff --git a/docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md b/docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md index 756436d07d..dafeb6cedf 100644 --- a/docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md +++ b/docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md @@ -14,9 +14,9 @@ Add `stdin?: string` and `env?: Record` to **both** `BashExecReq Three deliberate choices: -1. **The model-facing `bash` tool does NOT expose `stdin`/`env` as parameters** — not as a security wall, but because bash syntax already covers the model's needs, so duplicating them as tool params would be redundant surface. [dsh-tool-bash](../../../../packages/bash/tool-bash)'s `bash` tool builds its `BashExecRequest` from named schema fields and may add harness-owned environment such as the current [session identity and JSONL location](../feature/2026-07-10-agent-session-identity-and-log-location.md); a model that includes `env`/`stdin` keys in its tool-call arguments has them ignored and cannot replace that overlay. Regression guards drive the real tool with extra args and assert no model-provided field enters the request. In-process plugins (the hooks bridges, native plugins) that construct a `BashExecRequest` directly set the fields; the seam imposes no access policy (consistent with how `owner` works — the executor stores but never interprets it). +1. **The model-facing `bash` tool does NOT expose `stdin`/`env` as parameters** — not as a security wall, but because bash syntax already covers the model's needs, so duplicating them as tool params would be redundant surface. [dsh-tool-bash](../../../../packages/bash/tool-bash)'s `bash` tool builds its `BashExecRequest` from named schema fields; a model that includes `env`/`stdin` keys has them ignored. Harness-owned variables use the distinct `dshEnv` channel added by the [session environment decision](../feature/2026-07-10-agent-session-identity-and-log-location.md), so ordinary `env` cannot replace them. In-process plugins such as hook bridges construct requests directly and set ordinary `stdin`/`env`; the seam otherwise imposes no access policy. -2. **`env` merges AFTER the credential scrub, so an explicit caller entry always wins** — even a credential-shaped name. This is correct because the scrub's job is narrow: stop the harness's *ambient* `process.env` credentials from leaking into a spawned command. A caller that explicitly sets a var has named a value it already holds (not the ambient secret), so the scrub is not a constraint on it. `childEnv(extra?)` layers `scrub(process.env)` → `ENV_OVERRIDES` (the model-friendly `TERM=dumb` etc.) → `extra`, last-wins. +2. **`env` merges AFTER the credential scrub, so an explicit caller entry wins even on a credential-shaped name.** The later managed-namespace decision reserves `DSH_*`: ambient entries are removed, ordinary `env` cannot set them, and trusted `dshEnv` merges last. The complete order is `scrub(process.env, including DSH_*)` → `ENV_OVERRIDES` → ordinary `env` → `dshEnv`. 3. **`stdin`/`env` are required-absent-OK (plain optional) on the resolved spec, NOT required-but-nullable like `owner`.** `owner` is required-but-nullable because a *silently* missing owner yields an unowned, cross-session-readable task — a security footgun that a visible `undefined` guards against. `stdin`/`env` have no such hazard: a missing one means "no stdin / no extra env", which is the safe, ordinary case (every model-driven call). So they stay plain optionals, matching `signal`. diff --git a/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md b/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md index 8bc5f33820..35968a3896 100644 --- a/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md +++ b/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md @@ -4,11 +4,9 @@ Status: implemented ## Problem -An agent can identify its workspace through `session.header.cwd`, but a model using the bash tool cannot identify the session that owns the call or the durable JSONL file that records it. The default apps happen to use `./.sessions`, yet that is deployment config rather than a contract: `persistenceRoot` can point elsewhere, the JSONL backend hashes `cwd` into a bucket, and arbitrary session ids are path-encoded. Asking the agent to run `find` therefore makes the model guess backend layout and can select the wrong log under concurrent, resumed, forked, or subagent sessions. +An agent can identify its workspace through `session.header.cwd`, but a model using bash cannot reliably identify the session that owns the call or the durable transcript that records it. Searching `./.sessions` guesses deployment config and JSONL layout; custom roots, alternate persistence backends, resume, forks, and concurrent parent/child agents make that guess unreliable. Hooks have the same need for transcript location, while future plugins may need to expose other harness-owned environment facts to shell commands. -The same missing ownership boundary appears in the hook bridges. The Codex bridge emits `session_id` but fixes `transcript_path` to `null`; the Claude Code bridge emits `session_id` and `cwd` but no transcript path. Teaching each consumer to reconstruct the JSONL layout would duplicate backend policy and couple model tools and protocol adapters to one persistence implementation. - -The feature needs two distinct facts: a stable session identity that exists even without persistence, and an optional physical location owned by the active persistence backend. They must be resolved per agent invocation rather than written to global `process.env`, because one harness process can run multiple agents and in-process subagents concurrently. +The boundary must preserve two properties: the owner of a fact decides how to resolve it, and every child receives a per-execution snapshot rather than process-global mutable state. In particular, a nested harness must not leak its ambient `DSH_*` values into a child whose current agent, persistence backend, or configuration differs. ## Decision @@ -17,70 +15,71 @@ Extend the [`SessionPersistence`](../../implemented/architecture/2026-06-14-sess ```ts import type { SessionHeader } from '@deepseek-ai/dsh-session' -export interface SessionLocation { +interface SessionLocation { readonly kind: string readonly path: string } -export abstract class SessionPersistence { - abstract locate(meta: SessionHeader): SessionLocation | undefined +interface SessionPersistence { + locate(meta: SessionHeader): SessionLocation | undefined } ``` -`path` is an absolute local path to the backend's dedicated log for `meta`; `kind` identifies the representation. The JSONL backend returns `{ kind: 'jsonl', path }` using its already-resolved absolute root and existing cwd-bucket/id-encoding helpers. The SQLite backend returns `undefined` because a session is rows inside a shared database, not a dedicated transcript file. A backend with no honest local per-session path also returns `undefined`. +`path` is an absolute local path to the backend's dedicated log for `meta`; `kind` identifies the representation. JSONL returns `{ kind: 'jsonl', path }` using its resolved root and path helpers. SQLite and any backend without an honest local per-session artifact return `undefined`. The query creates and flushes nothing, so it can report a lazy target path before that file exists. -`locate` performs no filesystem I/O, creates nothing, flushes nothing, and never searches by convention. It reports where this backend would materialize the session, so callers can receive a path before the file exists. Making the query synchronous and local-path-only keeps it usable while constructing tool and hook invocation context; a future remote/object-store locator is a separate capability rather than a blocking network call hidden inside prompt or tool assembly. +The model-facing bash package owns a `ctx.bashEnv` registry. A contributor declares its stable name, every `DSH_*` key it may return, a description for each key, and `resolve(execution: ToolExecution)`. Duplicate contributor names, duplicate key ownership, reserved keys, malformed declarations, undeclared runtime output, and non-string output fail loudly. Registration is a Cordis effect and is removed with the contributing plugin fiber. `list()` exposes declarations without running resolvers, keeping the environment surface enumerable for diagnostics and future prompt/UI consumers. -The model-facing bash consumer derives a trusted environment overlay for each `ToolExecution` with an agent: +The registry rebuilds a trusted overlay for every foreground and background bash `ToolExecution`: -- `DSH_SESSION_ID` is always the current `agent.session.header.id`, including when persistence is absent or non-file-backed. -- `DSH_SESSION_JSONL` is present only when the active `ctx.sessionPersistence.locate(header)` returns `kind: 'jsonl'`; its value is that location's absolute path. -- A call without an agent receives neither variable. +- `DSH_HOME` is always the absolute configured Harness home, resolved from tool-bash/agent-core `dshHome`, then ambient `$DSH_HOME`, then `~/.dsh`. +- `DSH_SHELL=1` is always present and identifies a model bash child managed by DeepSeek Harness. +- `DSH_SESSION_ID` is present when the execution has an agent and equals `agent.session.header.id`. +- The built-in persistence translator contributes `DSH_SESSION_JSONL` only when `ctx.sessionPersistence.locate(header)` returns `kind: 'jsonl'`. -The overlay is passed through the existing `BashExecRequest.env` surface from the [trusted stdin/env decision](../../implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). It applies to foreground and background starts, and `dsh-bash-local` merges it after its ambient credential scrub and terminal overrides. The model-facing tool continues to build the request from named schema fields: model-supplied `env`/`stdin` keys are ignored and cannot replace the overlay. A shell command can still overwrite its own variables (`DSH_SESSION_ID=x command`); these values are correlation metadata, never authority. +Session persistence remains the fact owner: JSONL does not depend on tool-bash or register shell variables itself, and hooks continue to consume `locate()` directly. Tool-bash is the translation layer from the persistence fact into a shell convention. Other plugins that need shell-visible facts depend on the registry and register their own keys; they do not modify `process.env`. -The bash tool description tells the model that the current session id is available as `$DSH_SESSION_ID` and that JSONL deployments additionally expose `$DSH_SESSION_JSONL`. This guidance belongs with the tool that provides the variables, not in a permanent system-prompt section. The schema is already recorded in the request header under the [reconstructable-request contract](../../implemented/architecture/2026-07-05-reconstructable-requests.md), and every resulting tool output is a durable `tool/result`, so no new session event is needed. +The bash seam carries the managed overlay separately as `BashExecRequest.dshEnv` / `BashExecSpec.dshEnv`. Ordinary `env` remains the general in-process plugin surface used by hooks, but cannot contain `DSH_*`; the local executor rejects that wrong channel, removes every inherited ambient `DSH_*`, applies its ordinary scrub/terminal environment/explicit `env`, and finally merges the trusted `dshEnv` snapshot. This guarantees that a missing value means absent now rather than inherited from an outer or previous harness. The model-facing tool still ignores model-supplied `env`/`stdin` arguments. -The [Claude Code and Codex hook bridges](../../implemented/feature/2026-06-30-hook-bridges.md) resolve transcript location from the same seam at payload construction time. Codex payloads use `transcript_path: string | null`; Claude Code payloads keep their string-shaped dialect field and use `transcript_path: string`, falling back to `''` when no local per-session file exists. Hook lookup is the same side-effect-free snapshot as bash lookup: it does not force materialization or make a pre-turn hook create an otherwise abandoned session artifact. +The bash tool description teaches only the durable convention: current harness environment facts are available through managed `$DSH_*` variables and may be inspected when needed. It does not enumerate persistence-specific keys or add a permanent system-prompt section. Tool schemas are already logged in request headers and tool output is logged as `tool/result`, so no new session event is required. + +The [Claude Code and Codex hook bridges](../../implemented/feature/2026-06-30-hook-bridges.md) resolve transcript location from the same persistence seam when constructing payloads. Codex uses `transcript_path: string | null`; Claude Code preserves its string field and falls back to `''`. Hook lookup neither materializes nor flushes a session. ## Peer product findings -Peer products separate stable identity from physical storage rather than treating an absolute path as the only session key. Codex injects `CODEX_THREAD_ID` into each spawned shell environment after its environment policy has run, while its rollout recorder owns the exact path and exposes it separately to client events and hooks. Claude Code supplies `session_id` and `transcript_path` as structured hook/status-line input rather than a general Bash transcript environment contract. OpenCode carries session identity in structured tool execution context; Kimi Code expands a session-id placeholder in skill content; Reasonix keeps the active session path on its controller and rebinds it on branch/resume. - -The reusable principles are narrower than any one product's API: inject identity at the invocation boundary, let persistence resolve storage, do not mutate process-global environment for concurrent agents, and do not promise that a precomputed path is already materialized. DeepSeek Harness adds the optional JSONL path to bash because its requested user behavior is explicitly “ask the agent for this session's log,” while retaining the stable id as the primary identity. +Peer products separate stable identity from physical storage. Codex injects stable `CODEX_THREAD_ID` into spawned shells while recorder and hook surfaces own transcript paths. Claude Code supplies `session_id` and `transcript_path` as structured hook/status input. OpenCode carries identity in structured tool context; Kimi Code expands a session placeholder; Reasonix keeps the active session path on its controller. The portable rule is to inject identity at the invocation boundary, let storage resolve location, and never use a process-global current-session variable in a concurrent harness. ## Lifecycle and persistence semantics -A fresh session receives its id before any turn. Its bash environment can therefore carry both values during the first turn, but JSONL lazy materialization remains unchanged: before the first successful turn-end `session/flush`, `$DSH_SESSION_JSONL` can name a file that does not yet exist. During an open later turn, the file contains only the last durably flushed prefix, not the current buffered events. Consumers that need a readable up-to-date transcript require a separate explicit checkpoint/materialization API; this decision deliberately does not add one. +A fresh session receives its id before the first turn, so its first bash call can read `DSH_SESSION_ID` and a JSONL target. The JSONL file may still be absent until the first successful turn-end checkpoint, and during an open turn it contains only the last flushed prefix. `DSH_SESSION_JSONL` is a location hint, not an authorization credential or freshness guarantee. -Resume reuses the loaded session header, so it exposes the same id and backend location. Fork and in-process spawn create a new session id; the JSONL backend derives a new file while preserving the existing `parentSession` lineage and inherited cwd rules. Concurrent parent/child agents compute overlays from their own `ToolExecution.agent`, so neither can inherit or overwrite the other's identity. +Resume reuses the loaded header and therefore the same id and location. Fork and spawn create new session ids and locations. Parent and child calls resolve from their own `ToolExecution.agent`; each command receives an immutable snapshot even when calls overlap. A persistence service replacement affects later collections because the translator queries `ctx.get('sessionPersistence')` at execution time; the registry itself is effect-scoped and HMR-safe. -Consumers resolve the active service through the Cordis context at invocation time and do not cache a concrete JSONL backend instance. This keeps HMR/reload behavior aligned with the service store: a replacement backend controls subsequent locations, and an absent/inactive backend removes only `DSH_SESSION_JSONL`, never the session id. +`dshHome` is session-independent deployment context. Agent-core routes one value to both tool-bash and local skill discovery; if top-level `dshHome` and `skills.local.dshHome` are both supplied and resolve differently, composition fails instead of exposing contradictory homes. Persistence may change independently without freezing its facts into the session prefix. ## Testing -Unit coverage pins each boundary. The persistence seam contract asserts JSONL returns an absolute encoded path under a custom root while SQLite returns `undefined`; JSONL tests cover cwd/no-cwd buckets and ids requiring escaping. Tool-bash request-recording tests cover foreground/background overlays, no-agent calls, absent/SQLite persistence, ignored model `env` keys, and separate parent/child identities. Both hook bridge suites assert their exact available/unavailable `transcript_path` dialect shapes. +Unit coverage pins registry declaration validation, effect disposal, per-execution collection, the `dshHome` precedence, and the local executor's `DSH_*` scrub/rebuild order. Request-recording tests cover foreground/background snapshots, no-agent calls, absent/JSONL persistence, ignored model `env`, and parent/child isolation. JSONL/SQLite locator contract tests and both hook bridge suites pin available and unavailable transcript dialects. -A keyless full-loop integration uses the real agent loop, JSONL persistence, `dsh-tool-bash`, and `dsh-bash-local` with only the model scripted. On the first turn the model runs a command that prints both variables and reports whether the path exists; the test verifies the values against the live session header and locator, verifies the file can be absent inside the tool call, then waits for idle and confirms the materialized file's header carries the same session id. Request-recording tests prove parent/child calls receive different overlays, while locator tests prove resume keeps the path and fork changes it. - -Snapshot coverage updates the existing request-header pin for the bash description and the hook payload scenarios affected by `transcript_path`. No with-key e2e is required: model choice is not the contract, and the deterministic behavior is exercised through the real local executor, persistence backend, loader composition, and snapshot replay without depending on a provider credential. +A keyless full-loop integration drives the real agent loop, JSONL persistence, tool-bash, and bash-local on the first turn. The child prints `DSH_HOME`, `DSH_SHELL`, session id, JSONL target, and an inherited stale sentinel; the test verifies current values, absence of the stale variable, pre-flush file absence, and the eventual persisted header. Snapshot coverage pins the generic bash description in the recorded request header. No with-key test is required because the contract is deterministic local execution rather than model choice. ## Alternatives considered -**Expose only `DSH_SESSION_ID` and make the agent search.** This copies Codex's shell surface but not its separate persistence resolver. A recursive `find` knows neither a custom root nor a non-JSONL backend, duplicates layout rules, and can race or mis-select under multiple sessions. Stable id remains necessary, but it is insufficient for the requested direct-path behavior. +**Only an id plus `find`.** Search cannot know a custom root or backend layout and races under multiple sessions. -**Expose only the absolute path.** A path can be unavailable for non-file persistence and can name a not-yet-created lazy artifact; it is not the stable identity other APIs use for resume, lineage, or ownership. Keeping id and optional location separate makes those semantics explicit. +**Only an absolute path.** A path can be unavailable, lazy, or representation-specific and is not stable session identity. -**Write the current session into global `process.env`.** One process can drive multiple ACP sessions and in-process subagents concurrently, so a global assignment is last-writer-wins shared mutable state. Per-`ToolExecution` request env gives every child process an immutable snapshot of the correct agent instead. +**Global `process.env`.** Concurrent agents would overwrite one another and nested harnesses would inherit stale current-session values. -**Add a model-facing `session_info` tool.** A dedicated tool would add schema and another call when bash already supplies the requested query surface. It would also need the same persistence resolver, so it does not remove the seam work; the environment variables are smaller and compose with ordinary shell scripts. +**Put persistence instructions in the session prefix.** A session prefix is frozen while the active service can change across HMR or future backend switching; persistence-specific guidance would become stale. -**Make tool-bash depend directly on the JSONL backend.** Reading backend config or importing `logPath` from the implementation would violate the interface/implementation/consumer split and leave hooks to invent another route. The persistence service is the only layer that can state whether a physical per-session path exists. +**A typed waterfall event.** Listeners cannot declare ownership without running, and later listeners can silently overwrite keys. A registry detects key conflicts at registration and remains enumerable. + +**Have each persistence backend register bash env directly.** That reverses the dependency from storage into one consumer and forces bash into deployments that do not use it. `locate()` is also still required by hooks. + +**A model-facing `session_info` tool.** It adds schema and another call while bash already supplies the query surface; the registry generalizes to future environment facts without one tool per fact. ## Consequences -Foreground and background bash calls now expose the current agent's stable session id, while only JSONL-backed sessions expose a file path. No-agent calls receive neither variable; absent and SQLite persistence still leave `DSH_SESSION_ID` available. Resume retains identity and location, while forks, spawns, and concurrent child agents derive new values from their own immutable headers. Model-supplied `env`/`stdin` fields remain ignored, and both hook bridges consume the same locator with their dialect-specific unavailable value. +Every model bash child receives current Harness home and shell identity, and agent calls additionally receive stable session identity. JSONL-backed calls get an optional target path; non-file persistence omits it honestly. The complete `DSH_*` namespace inside these children is managed by the harness: ambient values are removed, current trusted values are re-added, and ordinary callers cannot use `env` to bypass ownership checks. -The path reveals the configured persistence root to the model and hooks. The bash tool already runs with the executor's filesystem authority, so this adds discoverability rather than permission; deployments needing isolation use a sandboxing executor or omit local-file persistence. A valid location can be absent or stale relative to an open turn because durability checkpoints happen at turn end. - -Commands can overwrite either variable inside their own shell syntax. The values are debugging/correlation facts rather than credentials, so external consumers still verify the file header before attributing a transcript. `DSH_SESSION_JSONL` remains representation-specific, and backends without a dedicated per-session file return `undefined` instead of squeezing database coordinates into a path contract. The pre-release seam extension intentionally requires every persistence backend to make that supported/unsupported choice without a compatibility shim. +The namespace is discoverable but not secret. Paths can reveal configured roots, lazy targets can be absent or stale, and a command can override variables inside its own shell syntax. Consumers treat them as correlation and environment facts, verify transcript metadata when attribution matters, and rely on sandbox/filesystem policy rather than variable secrecy for authorization. diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index dab5c38c6d..2e1d508a89 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -125,7 +125,7 @@ Registered by the tool registry itself under `mode: code` / `mode: both` (see th ### `bash` -Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. +Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. ```json { diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index 00cae7e166..0dce51f14d 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index 59b0c90fd1..e5ce264494 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -28,7 +28,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index 59b0c90fd1..e5ce264494 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -28,7 +28,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 4e85370582..faf8c9ca9f 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index 10423c2d44..33a27965ca 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl b/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl index 793106afc5..64b1e5dde8 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl +++ b/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783613224997,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783613224997,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: cat notes.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783613224997,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783613224997,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783613224997,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783613225437,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783613225438,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783613225658,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/packages/bash/bash-local/README.md b/packages/bash/bash-local/README.md index 1ac8a7d06b..9a00dc4a9b 100644 --- a/packages/bash/bash-local/README.md +++ b/packages/bash/bash-local/README.md @@ -22,7 +22,7 @@ Design surveyed against the bash tools of Claude Code, OpenCode, Codex, and pi; - **Spawn per call, no shell state** — every call is a fresh non-login `bash -c` (deterministic; no rc files). All four surveyed tools spawn per call. `XXX(stateful-shell)` in `src/run.ts` records the two proven stateful designs (Claude Code's cwd-only persistence; Codex's PTY exec sessions) for when real workflows demand them. - **Process-group kills with escalation** — children are spawned `detached` (own process group); kills send SIGTERM to the group, then SIGKILL after the `graceMs` grace (default 3s — OpenCode's escalation; pipelines and subshells die with the parent). ESRCH is tolerated; daemons that re-parent away from the group can still survive — same caveat as the surveyed tools. - **Tail-keep truncation + spill files** — output beyond `maxOutputBytes` keeps the in-memory TAIL (errors/results cluster at the end — pi/OpenCode rationale) while the FULL stream is appended to a temp file whose path is reported when available. If the final spill close reports a delayed writeback failure, the executor still returns the tail but withholds the path rather than advertising a possibly incomplete file. -- **Model-friendly env + credential scrub** — `process.env` minus credential-shaped vars (`*KEY*`/`*SECRET*`/`*TOKEN*`), then `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat` (Codex's hardcoded set) so pagers and ANSI color don't garble results. This scrub is the security control that keeps the harness's *ambient* credentials out of a spawned command. A spec's `env` is merged LAST (after the scrub), so a caller's explicit entry — a value it already holds — wins even on a credential-shaped name. The spec's `stdin`, when supplied, is written to the child and closed; with none supplied, fd 0 is `/dev/null` — the exact pre-seam default, so a command that probes stdin's file type is unaffected. Both `env`/`stdin` are set by in-process plugins (the hooks bridges); the model-facing tool doesn't expose them. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). +- **Model-friendly env + credential/namespace scrub** — start with `process.env` minus credential-shaped vars (`*KEY*`/`*SECRET*`/`*TOKEN*`) and every `DSH_*`, then apply `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat`. Ordinary spec `env` is merged next and may restore caller-held credential-shaped values, but is rejected if it tries to set reserved `DSH_*`; the trusted spec `dshEnv` snapshot is merged last. This keeps ambient secrets out and prevents a nested/previous harness identity from surviving when the current registry omits it. The spec's `stdin`, when supplied, is written to the child and closed; with none supplied, fd 0 is `/dev/null`. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [the session environment RFC](../../../docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md). - **Background tasks** — `start()` returns immediately, no timeout applies (Claude Code detaches timeouts when backgrounding), `readOutput()` is incremental with whole-stream byte offsets, and disposal kills everything. The spec's opaque `owner` token is stored on the tracked task and returned by `ownerOf(id)` — the executor never interprets it (the consumer's access policy does), and because it lives with the task here it survives a `tool-bash` HMR reload. ## Sandboxing diff --git a/packages/bash/bash-local/src/index.ts b/packages/bash/bash-local/src/index.ts index 6903c06e32..3d7a0113bd 100644 --- a/packages/bash/bash-local/src/index.ts +++ b/packages/bash/bash-local/src/index.ts @@ -126,10 +126,11 @@ export class LocalBashExecutor extends BashExecutor { workdir: request.workdir ?? this.config.cwd ?? process.cwd(), timeoutMs, ...request.signal ? { signal: request.signal } : {}, - // Carry stdin/env through verbatim — optional, no config default (absent - // means none). env merges AFTER the scrub in run.ts. + // Carry stdin/ordinary env/trusted dshEnv through verbatim — optional, + // no config default. run.ts owns the scrub and merge order. ...request.stdin !== undefined ? { stdin: request.stdin } : {}, ...request.env !== undefined ? { env: request.env } : {}, + ...request.dshEnv !== undefined ? { dshEnv: request.dshEnv } : {}, // Carry the owner through verbatim (required-but-nullable on the spec): // the executor never interprets it — the consumer's access policy does. owner: request.owner, @@ -153,6 +154,7 @@ export class LocalBashExecutor extends BashExecutor { signal: d.signal, stdin: spec.stdin, env: spec.env, + dshEnv: spec.dshEnv, }, this.internals).done // Classify the FIRST abort reason: a BASH_TIMEOUT TimeoutReason means our // timeout cut the command short; any other abort — an upstream cancel, or a @@ -179,6 +181,7 @@ export class LocalBashExecutor extends BashExecutor { signal: spec.signal, stdin: spec.stdin, env: spec.env, + dshEnv: spec.dshEnv, }, this.internals) const id = BashTaskId(`bash-${this.nextTaskId++}`) diff --git a/packages/bash/bash-local/src/run.ts b/packages/bash/bash-local/src/run.ts index bc4a017dea..47361b4e5e 100644 --- a/packages/bash/bash-local/src/run.ts +++ b/packages/bash/bash-local/src/run.ts @@ -27,7 +27,7 @@ import { randomBytes } from 'node:crypto' import { closeSync, mkdtempSync, openSync, writeSync } from 'node:fs' import { tmpdir } from 'node:os' import { join } from 'node:path' -import type { CollectedOutput } from '@deepseek-ai/dsh-bash' +import type { CollectedOutput, DshEnvironment } from '@deepseek-ai/dsh-bash' /** * Model-friendly environment overrides: disable colors, pagers, and @@ -50,27 +50,33 @@ export const ENV_OVERRIDES = { export const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i /** - * `process.env` minus credential-shaped vars, plus the model-friendly - * overrides, plus any caller-supplied `extra` entries. + * Build a child environment from scrubbed ambient values, terminal overrides, + * ordinary caller entries, and a trusted managed `DSH_*` snapshot. * - * Layering matters: the scrub drops `process.env` credentials, then - * `ENV_OVERRIDES` forces the model-friendly terminal vars, then `extra` is - * merged LAST so an explicit caller entry wins even when its name matches the - * scrub pattern (the scrub is the control that stops the HARNESS's ambient - * credentials leaking into a spawned command; a caller that explicitly sets a - * var named a value it already holds, not that ambient secret). `extra` is set - * by in-process plugins (the hooks bridges), not the model — `dsh-tool-bash` - * builds its request from named fields only and does not forward model input - * here (see its README, § "The tool builds its request from named args only"). - * @param extra - caller-supplied entries merged last; an explicit entry wins even against the scrub and the overrides. + * Ambient credentials and all ambient `DSH_*` are removed first; + * `ENV_OVERRIDES` then forces model-friendly terminal values, ordinary `extra` + * follows, and `dshEnv` merges last. Ordinary `extra` may restore a + * credential-shaped name whose value the caller already holds, but cannot set + * the managed namespace. `dsh-tool-bash` builds both channels from trusted + * named fields and never forwards model-provided environment objects. + * @param extra - ordinary caller-supplied entries; `DSH_*` names are rejected. + * @param dshEnv - trusted managed `DSH_*` entries for the current execution. * @returns the environment to hand to `spawn` for the child process. */ -export function childEnv(extra?: Record): NodeJS.ProcessEnv { +export function childEnv( + extra?: Readonly>, + dshEnv?: DshEnvironment, +): NodeJS.ProcessEnv { const env: NodeJS.ProcessEnv = {} for (const [key, value] of Object.entries(process.env)) { - if (!SENSITIVE_ENV_PATTERN.test(key)) env[key] = value + if (!SENSITIVE_ENV_PATTERN.test(key) && !key.startsWith('DSH_')) env[key] = value } - return { ...env, ...ENV_OVERRIDES, ...extra } + for (const key of Object.keys(extra ?? {})) { + if (key.startsWith('DSH_')) { + throw new Error(`ordinary bash env cannot set reserved variable "${key}"; use dshEnv`) + } + } + return { ...env, ...ENV_OVERRIDES, ...extra, ...dshEnv } } /** What to run and under which limits (resolved — no defaults in here). */ @@ -96,12 +102,12 @@ export interface SpawnSpec { */ stdin?: string | undefined /** - * Extra environment entries, merged onto the scrubbed env AFTER the - * credential scrub and the model-friendly overrides (so an explicit entry - * wins). Set by in-process plugins; the model-facing tool does not forward - * model input here. + * Ordinary environment entries merged after the credential scrub and + * terminal overrides. `DSH_*` names are rejected and belong in `dshEnv`. */ env?: Record | undefined + /** Harness-owned `DSH_*` entries merged after ambient `DSH_*` removal. */ + dshEnv?: DshEnvironment | undefined } /** @@ -346,7 +352,7 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB // typed `spawn` overload infer non-null stdout/stderr, which the // `ChildProcessByStdio` annotation captures (stdin `Writable | null`; stdout/ // stderr the non-null `Readable` the collectors attach to without a cast). - const env = childEnv(spec.env) + const env = childEnv(spec.env, spec.dshEnv) const child: ChildProcessByStdio = spec.stdin !== undefined ? spawn('bash', ['-c', spec.command], { cwd: spec.cwd, env, stdio: ['pipe', 'pipe', 'pipe'], detached: true }) : spawn('bash', ['-c', spec.command], { cwd: spec.cwd, env, stdio: ['ignore', 'pipe', 'pipe'], detached: true }) diff --git a/packages/bash/bash-local/tests/executor.spec.ts b/packages/bash/bash-local/tests/executor.spec.ts index 450ad7a81f..e6bc8cda84 100644 --- a/packages/bash/bash-local/tests/executor.spec.ts +++ b/packages/bash/bash-local/tests/executor.spec.ts @@ -136,21 +136,28 @@ describe('LocalBashExecutor.run', () => { await expect(bash.run(bash.resolve({ command: 'true', workdir: '/nonexistent-dsh' }))).rejects.toThrow(/ENOENT/) }) - it('resolve() carries stdin/env onto the spec, and run() threads them to the command', async () => { + it('resolve() carries stdin/env/dshEnv onto the spec, and run() threads them to the command', async () => { const { bash } = await setup() - const spec = bash.resolve({ command: 'cat; echo "[$DSH_SEAM_VAR]"', stdin: 'piped\n', env: { DSH_SEAM_VAR: 'env-ok' } }) - // resolve() keeps the stdin/env fields verbatim (optional, no default). + const spec = bash.resolve({ + command: 'cat; echo "[$SEAM_VAR][$DSH_SEAM_VAR]"', + stdin: 'piped\n', + env: { SEAM_VAR: 'env-ok' }, + dshEnv: { DSH_SEAM_VAR: 'dsh-ok' }, + }) + // resolve() keeps the optional input/environment fields verbatim. expect(spec.stdin).toBe('piped\n') - expect(spec.env).toEqual({ DSH_SEAM_VAR: 'env-ok' }) + expect(spec.env).toEqual({ SEAM_VAR: 'env-ok' }) + expect(spec.dshEnv).toEqual({ DSH_SEAM_VAR: 'dsh-ok' }) const result = await bash.run(spec) - expect(result.stdout.text).toBe('piped\n[env-ok]\n') + expect(result.stdout.text).toBe('piped\n[env-ok][dsh-ok]\n') }) - it('resolve() omits stdin/env when the request supplies neither', async () => { + it('resolve() omits stdin/env/dshEnv when the request supplies none', async () => { const { bash } = await setup() const spec = bash.resolve({ command: 'true' }) expect('stdin' in spec).toBe(false) expect('env' in spec).toBe(false) + expect('dshEnv' in spec).toBe(false) }) }) @@ -177,14 +184,15 @@ describe('LocalBashExecutor background tasks', () => { await Promise.all([first.done, second.done]) }) - it('threads stdin and extra env into a background task', async () => { + it('threads stdin, ordinary env, and managed env into a background task', async () => { const { bash } = await setup() const task = bash.start(bash.resolve({ - command: 'cat; echo "[$DSH_BG_VAR]"', + command: 'cat; echo "[$BG_VAR][$DSH_BG_VAR]"', stdin: 'bg-stdin\n', - env: { DSH_BG_VAR: 'bg-env' }, + env: { BG_VAR: 'bg-env' }, + dshEnv: { DSH_BG_VAR: 'bg-dsh-env' }, })) - const read = await readUntil(bash, task.id, '[bg-env]') + const read = await readUntil(bash, task.id, '[bg-env][bg-dsh-env]') expect(read.delta).toContain('bg-stdin') await task.done expect(task.exitCode).toBe(0) diff --git a/packages/bash/bash-local/tests/run.spec.ts b/packages/bash/bash-local/tests/run.spec.ts index 1d6e93afe3..48f00a861b 100644 --- a/packages/bash/bash-local/tests/run.spec.ts +++ b/packages/bash/bash-local/tests/run.spec.ts @@ -201,19 +201,19 @@ describe('stdin and extra env (set by in-process plugins)', () => { expect(piped.stdout.text).toBe('socket\n') }) - it('merges extra env entries onto the scrubbed environment', async () => { - const result = await runBash(spec('echo "$DSH_EXTRA_ONE/$DSH_EXTRA_TWO"', { - env: { DSH_EXTRA_ONE: 'alpha', DSH_EXTRA_TWO: 'beta' }, + it('merges ordinary extra env entries onto the scrubbed environment', async () => { + const result = await runBash(spec('echo "$EXTRA_ONE/$EXTRA_TWO"', { + env: { EXTRA_ONE: 'alpha', EXTRA_TWO: 'beta' }, })).done expect(result.stdout.text).toBe('alpha/beta\n') }) it('an explicit extra env entry overrides the model-friendly override and the scrub', async () => { // TERM is a model-friendly OVERRIDE (dumb); an explicit extra entry wins. - // DSH_OVERRIDE_KEY matches the credential scrub pattern, yet an explicit + // EXPLICIT_OVERRIDE_KEY matches the credential scrub pattern, yet an explicit // entry is still honored — the scrub only drops AMBIENT process.env creds. - const result = await runBash(spec('echo "$TERM/$DSH_OVERRIDE_KEY"', { - env: { TERM: 'xterm-256color', DSH_OVERRIDE_KEY: 'explicit-wins' }, + const result = await runBash(spec('echo "$TERM/$EXPLICIT_OVERRIDE_KEY"', { + env: { TERM: 'xterm-256color', EXPLICIT_OVERRIDE_KEY: 'explicit-wins' }, })).done expect(result.stdout.text).toBe('xterm-256color/explicit-wins\n') }) @@ -361,13 +361,13 @@ describe('abort edge cases', () => { }) describe('review fixes: env scrubbing and spill hardening', () => { - it('scrubs credential-shaped env vars from child processes', async () => { + it('scrubs credential-shaped and ambient DSH env vars from child processes', async () => { process.env.DSH_TEST_API_KEY = 'super-secret' process.env.DSH_TEST_TOKEN = 'also-secret' process.env.DSH_TEST_PLAIN = 'visible' try { const result = await runBash(spec('echo "[${DSH_TEST_API_KEY:-absent}|${DSH_TEST_TOKEN:-absent}|${DSH_TEST_PLAIN:-absent}]"')).done - expect(result.stdout.text.trim()).toBe('[absent|absent|visible]') + expect(result.stdout.text.trim()).toBe('[absent|absent|absent]') } finally { delete process.env.DSH_TEST_API_KEY delete process.env.DSH_TEST_TOKEN @@ -375,6 +375,23 @@ describe('review fixes: env scrubbing and spill hardening', () => { } }) + it('injects only the current trusted DSH environment after scrubbing ambient values', async () => { + process.env.DSH_STALE = 'old-value' + try { + const result = await runBash(spec('echo "[${DSH_STALE:-absent}|$DSH_SHELL|$DSH_SESSION_ID]"', { + dshEnv: { DSH_SHELL: '1', DSH_SESSION_ID: 'current-session' }, + })).done + expect(result.stdout.text.trim()).toBe('[absent|1|current-session]') + } finally { + delete process.env.DSH_STALE + } + }) + + it('rejects DSH variables on the ordinary env channel', () => { + expect(() => runBash(spec('true', { env: { DSH_WRONG_CHANNEL: 'bad' } }))) + .toThrow(/DSH_WRONG_CHANNEL.*dshEnv/) + }) + it('creates spill files with owner-only permissions and random names', async () => { const result = await runBash( spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { maxOutputBytes: 500 }), diff --git a/packages/bash/bash/README.md b/packages/bash/bash/README.md index ac7e00c3a3..11a50c954a 100644 --- a/packages/bash/bash/README.md +++ b/packages/bash/bash/README.md @@ -30,8 +30,8 @@ Implementations subclass `BashExecutor`, implement the abstract methods, and cal ## Vocabulary -`BashExecRequest` (command, workdir?, timeoutMs?, signal?, stdin?, env?, owner?, sandboxMode?) resolves to `BashExecSpec` (command, workdir, timeoutMs, signal?, stdin?, env?, owner, sandboxMode) before execution; `owner` and `sandboxMode` are optional on the request and **required-but-nullable** on the resolved spec, so a forgotten one is a visible `undefined` rather than a silently-absent property. `sandboxMode` is the explicit per-call sandbox-policy input: an escalation grant a human just issued ([the sandbox RFC § Escalation](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md), which outranks) or the session's standing override ([the sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)); a sandboxing executor's `resolve()` stamps its configured default when the request carries none, and a non-sandboxing executor carries the field verbatim and confines nothing. +`BashExecRequest` (command, workdir?, timeoutMs?, signal?, stdin?, env?, dshEnv?, owner?, sandboxMode?) resolves to `BashExecSpec` (command, workdir, timeoutMs, signal?, stdin?, env?, dshEnv?, owner, sandboxMode) before execution; `owner` and `sandboxMode` are optional on the request and **required-but-nullable** on the resolved spec, so a forgotten one is a visible `undefined` rather than a silently-absent property. `sandboxMode` is the explicit per-call sandbox-policy input: an escalation grant a human just issued ([the sandbox RFC § Escalation](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md), which outranks) or the session's standing override ([the sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)); a sandboxing executor's `resolve()` stamps its configured default when the request carries none, and a non-sandboxing executor carries the field verbatim and confines nothing. The seam also owns the per-session mode override vocabulary (the sandbox RFC § Per-session mode switching): the log-only `'bash/sandbox-mode'` session event, the pure fold `effectiveSandboxMode(events)` (last event wins; `undefined` means "apply the executor default"), and THE write path `setSandboxMode(session, mode)` — the session log is the store, so an override survives restart by replay and two sessions can never see each other's mode. Writers must respect turn-enclosure: the ACP bridge anchors an idle switch at the next turn rather than appending between turns. The task id (`BashTaskId`) and the `owner` token (`OwnerToken`) are [branded](../../util/brand) — `OwnerToken` is a DISTINCT brand from `SessionId` (the seam never imports `dsh-session`; the `dsh-tool-bash` consumer is the single boundary that casts its `SessionId` into one). `run()` returns `BashRunResult` (exitCode, signal, timedOut, aborted, timeoutMs, stdout/stderr as `CollectedOutput`) and `start()`/`readOutput()` use `BashTask`/`BashTaskRead` for the background side. A sandboxing executor additionally stamps `sandbox` result facts on results and settled tasks (`BashSandboxInfo`: the mode it executed under, the conservative `denied` classification, and — for confined modes — the backend's `enforcement` completeness); the mode/enforcement vocabulary is owned by the [`dsh-sandbox`](../../sandbox/sandbox/) seam, and the facts are documented in [core-data-structures/bash.md](../../../docs/core-data-structures/bash.md). See `src/types.ts` for the full contracts. -`stdin` and `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its JSON payload on stdin and its `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` env. The model-facing `dsh-tool-bash` tool does not expose them as parameters — a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), so they would be redundant tool params. This is not a security boundary: the implementation's credential scrub (not these fields) is what keeps the harness's ambient secrets out of a spawned command. They are plain optionals on the resolved spec (unlike `owner`'s required-but-nullable): a missing one means "none", the safe default. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). +`stdin` and ordinary `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its JSON payload and `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` values. `dshEnv` is a separate trusted overlay restricted by type to `DSH_*` keys; model bash uses it for the current snapshot collected by `ctx.bashEnv`. Implementations remove inherited `DSH_*`, reject those names in ordinary `env`, then merge `dshEnv`, so an omitted current fact cannot fall back to stale ambient state. The model-facing tool exposes none of these as parameters. All three remain optional on the resolved spec; absent means no input/overlay. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [the session environment RFC](../../../docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md). diff --git a/packages/bash/bash/src/index.ts b/packages/bash/bash/src/index.ts index 63c5757175..6c9acedf20 100644 --- a/packages/bash/bash/src/index.ts +++ b/packages/bash/bash/src/index.ts @@ -30,6 +30,7 @@ export type { BashTaskRead, BashTaskStatus, CollectedOutput, + DshEnvironment, } from './types.ts' declare module 'cordis' { diff --git a/packages/bash/bash/src/types.ts b/packages/bash/bash/src/types.ts index 39dbc162c6..ebc0d36898 100644 --- a/packages/bash/bash/src/types.ts +++ b/packages/bash/bash/src/types.ts @@ -12,6 +12,9 @@ import type { SandboxEnforcement, SandboxMode } from '@deepseek-ai/dsh-sandbox' /** Identifies one background task within an executor (generated `bash-N`). */ export type BashTaskId = Branded<'BashTaskId'> +/** Trusted DeepSeek Harness variables for one bash execution. */ +export type DshEnvironment = Readonly> + /** * Brand a string as a {@link BashTaskId}. * @param id - the raw task-id string (the executor generates `bash-N`). @@ -106,15 +109,19 @@ export interface BashExecRequest { */ stdin?: string | undefined /** - * Extra environment entries for the command, merged AFTER the - * implementation's credential scrub (so an explicit entry here is honored even - * when its name matches the scrub pattern — the caller named a value it holds, - * not the harness's ambient secret). Set by in-process plugins (the hooks - * bridges set `CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, …); the model-facing - * bash tool does not expose it as a parameter (a model that needs an env var - * uses shell syntax like `FOO=bar cmd`). + * Ordinary environment entries for the command, merged after the credential + * scrub. `DSH_*` is reserved for {@link dshEnv} and implementations reject it + * here. Set by in-process plugins (the hooks bridges set + * `CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, …); the model-facing bash tool + * does not expose it as a parameter. */ env?: Record | undefined + /** + * Harness-owned `DSH_*` variables for this execution. Executors discard + * ambient `DSH_*` entries before merging this snapshot, so an unavailable + * current fact cannot inherit a stale value from the harness process. + */ + dshEnv?: DshEnvironment | undefined /** * Opaque OWNER token for a background task — the consumer's isolation key * (the tool layer passes the owning agent's `session.header.id`). The @@ -163,13 +170,14 @@ export interface BashExecSpec { */ stdin?: string | undefined /** - * Extra environment entries, carried through verbatim from - * {@link BashExecRequest.env} and merged by the implementation AFTER its - * credential scrub (an explicit entry wins even when its name matches the - * scrub pattern). OPTIONAL on the spec for the same reason as `stdin` — no - * config default, absent means "no extra env". + * Ordinary environment entries carried through from + * {@link BashExecRequest.env}. `DSH_*` remains reserved for {@link dshEnv}. + * OPTIONAL on the spec for the same reason as `stdin`: absent means no + * ordinary extra environment. */ env?: Record | undefined + /** Trusted `DSH_*` snapshot carried through from {@link BashExecRequest.dshEnv}. */ + dshEnv?: DshEnvironment | undefined /** * Opaque owner token, REQUIRED-but-nullable (mirrors `workdir`/`timeoutMs` * being required on the resolved spec): {@link BashExecutor.resolve} carries diff --git a/packages/bash/tool-bash/README.md b/packages/bash/tool-bash/README.md index 4bbfff2f6a..ccbb1c0033 100644 --- a/packages/bash/tool-bash/README.md +++ b/packages/bash/tool-bash/README.md @@ -22,11 +22,26 @@ The plugin also contributes the `tool:bash` prompt section (order 105) — the c `command`, `workdir`, and `timeoutMs` are resolved against the executor's config defaults via `ctx.bash.resolve()` before execution, so the executor seam (`BashExecSpec`) receives explicit `workdir`/`timeoutMs` values. The workdir default is applied in the tool layer (from the calling agent's `session.header.cwd`) BEFORE `resolve()` — the per-session cwd must come from `exec.agent`, since N sessions share one executor; only when no session cwd is available does the executor fall back to its own config / `process.cwd()`. -### Session identity environment +### Managed shell environment -Every foreground and background call made for an agent receives `DSH_SESSION_ID=agent.session.header.id`. When the active persistence backend locates a JSONL artifact, the call also receives `DSH_SESSION_JSONL=`; absent persistence and non-file backends still provide the id but omit the JSONL variable. The path is a location hint: lazy materialization means it may not exist on the first turn, and during an open turn it can omit buffered events that have not reached `session/flush`. Neither value is an authorization credential. +Every foreground and background model bash call receives a newly collected trusted `DSH_*` environment. `DSH_HOME` is the absolute Harness home (`dshHome` config, then ambient `$DSH_HOME`, then `~/.dsh`) and `DSH_SHELL=1` identifies the managed child. Agent calls additionally receive `DSH_SESSION_ID=agent.session.header.id`; when the active persistence seam locates a JSONL artifact they also receive `DSH_SESSION_JSONL=`. The JSONL path is a location hint: it may not exist before the first flush or contain the current buffered turn, and it is not an authorization credential. -The overlay is computed from `ToolExecution.agent` for each call and passed through `BashExecRequest.env`; `process.env` is never modified, so concurrent parent/child agents keep separate values. The tool description names both variables so the model can inspect them without a permanent system-prompt section. +`ctx.bashEnv` owns collection. Other plugins can register an effect-scoped contributor with a stable name, declared keys/descriptions, and `resolve(execution: ToolExecution)`; duplicate ownership and undeclared runtime keys fail loudly, while `list()` enumerates declarations without executing providers. Harness built-ins reserve `DSH_HOME`, `DSH_SHELL`, and `DSH_SESSION_ID`; tool-bash's persistence translator owns `DSH_SESSION_JSONL` by reading the backend-neutral `sessionPersistence.locate()` seam. + +```ts +import type { Context } from 'cordis' +import type {} from '@deepseek-ai/dsh-tool-bash' + +export function apply(ctx: Context): void { + ctx.bashEnv.register({ + name: 'deployment-region', + variables: { DSH_DEPLOYMENT_REGION: { description: 'Current deployment region.' } }, + resolve: execution => execution.agent === undefined ? {} : { DSH_DEPLOYMENT_REGION: 'cn-north' }, + }) +} +``` + +The overlay is computed from the current `ToolExecution` and passed through the dedicated `BashExecRequest.dshEnv` channel. The local executor removes all inherited `DSH_*` before merging that snapshot, so nested harnesses and concurrent parent/child agents cannot leak stale identities. `process.env` is never modified. The tool description teaches the generic `$DSH_*` convention rather than naming persistence-specific variables or adding a permanent system-prompt section. Result text: stdout, then a `[stderr]` section, then status markers — `[sandbox: file access denied under mode]` when a sandboxing executor classified the failure as a policy denial (reported first so `[exit code: N]` stays the last line; the static description tells the model a denial is policy, not a command bug, and forbids retrying around it), `[timed out after Nms]` whenever the executor's timer fired (reported independently of how the process ended, so a command that traps SIGTERM and exits 0 still shows it), `[killed by signal: …]` for a signal death, `[exit code: N]` for a non-zero exit (reported, **not** `isError`: the model decides how to react), and `[output truncated; full output: ]` when the tail was kept and a safe spill file is available. If the executor knows output was dropped but cannot safely advertise a complete spill file, the path is reported as `(unavailable)`. Only infrastructure failures (spawn errors, aborts) surface as `isError` results. @@ -52,7 +67,7 @@ When a background task finishes, a short notice is injected into the owning agen ## The tool builds its request from named args only -The `BashExecRequest` seam carries optional `stdin` and `env`, used by trusted consumers. This tool does **not** expose them as model parameters: it builds the request from named schema fields and adds only the session overlay above, so model-supplied `env`/`stdin` keys are ignored and cannot replace the trusted values. This is not a trust boundary — a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), and the real defense against leaking ambient secrets is `dsh-bash-local`'s credential scrub. Regression guards assert extra model fields never enter the request while the trusted overlay still does. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). +The `BashExecRequest` seam carries optional `stdin` and ordinary `env` for in-process consumers plus the harness-owned `dshEnv` channel above. This tool does **not** expose any of them as model parameters: it builds the request from named schema fields, so model-supplied `env`/`stdin` keys are ignored and cannot replace the managed values. A model already has equivalent command-local power through shell syntax (`FOO=bar cmd`, a heredoc); ambient-secret protection comes from `dsh-bash-local`'s credential scrub, while `dshEnv` ownership prevents stale or spoofed Harness context. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). ## Permissions and escalation diff --git a/packages/bash/tool-bash/package.json b/packages/bash/tool-bash/package.json index d4d24aa098..003aadad74 100644 --- a/packages/bash/tool-bash/package.json +++ b/packages/bash/tool-bash/package.json @@ -32,6 +32,9 @@ "@deepseek-ai/dsh-tools": "^0.0.1", "cordis": "^4.0.0-rc.6" }, + "dependencies": { + "schemastery": "^3.18.0" + }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index b76e2478c8..7ebf1621f3 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -55,8 +55,10 @@ * @module @deepseek-ai/dsh-tool-bash */ -import type { Context } from 'cordis' -import { isAbsolute, resolve as resolvePath } from 'node:path' +import { Service, type Context } from 'cordis' +import z from 'schemastery' +import { homedir } from 'node:os' +import { isAbsolute, join, resolve as resolvePath } from 'node:path' import { defineTool } from '@deepseek-ai/dsh-tools' import type { GenericCallView, TerminalCallView, ToolExecution, ToolResult, ToolResultView } from '@deepseek-ai/dsh-tools' import type { Agent } from '@deepseek-ai/dsh-agent' @@ -69,11 +71,178 @@ import type {} from '@deepseek-ai/dsh-system-prompt' import type {} from '@deepseek-ai/dsh-user-approval' import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' import { BashTaskId, OwnerToken, effectiveSandboxMode } from '@deepseek-ai/dsh-bash' -import type { BashRunResult, BashTask, CollectedOutput } from '@deepseek-ai/dsh-bash' +import type { BashRunResult, BashTask, CollectedOutput, DshEnvironment } from '@deepseek-ai/dsh-bash' + +declare module 'cordis' { + interface Context { + bashEnv: BashEnvRegistry + } +} export const name = 'tool-bash' export const inject = ['tools', 'bash', 'systemPrompt'] +/** Configuration for the bash tool and its managed child environment. */ +export interface Config { + /** DeepSeek Harness home directory exposed as `DSH_HOME`; defaults to `$DSH_HOME` or `~/.dsh`. */ + dshHome?: string +} + +/** Runtime configuration schema for the bash tool plugin. */ +export const Config: z = z.object({ + dshHome: z.string(), +}) + +/** Model-visible metadata for one managed `DSH_*` environment variable. */ +export interface BashEnvVariable { + /** Concise description of the environment fact represented by the variable. */ + description: string +} + +/** + * A plugin contribution to the managed environment of each model bash call. + * Declared keys make ownership conflicts detectable before the first command; + * `resolve` computes only the values available for the current execution. + */ +export interface BashEnvContributor { + /** Stable contributor name used in diagnostics and duplicate detection. */ + name: string + /** Complete set of `DSH_*` keys this contributor may return. */ + variables: Readonly> + /** + * Resolve this contributor's available values for one tool execution. + * @param execution - the bash tool execution and its optional calling agent. + * @returns a partial map containing only keys declared in {@link variables}. + */ + resolve(execution: ToolExecution): Readonly>> +} + +/** An enumerable declaration returned by {@link BashEnvRegistry.list}. */ +export interface BashEnvVariableInfo extends BashEnvVariable { + /** Contributor that owns the variable. */ + contributor: string + /** Declared `DSH_*` environment variable name. */ + key: `DSH_${string}` +} + +const RESERVED_BASH_ENV_KEYS = new Set<`DSH_${string}`>([ + 'DSH_HOME', + 'DSH_SHELL', + 'DSH_SESSION_ID', +]) +const BASH_ENV_KEY = /^DSH_[A-Z][A-Z0-9_]*$/ + +/** + * Registry (`ctx.bashEnv`) for trusted, per-execution `DSH_*` variables. + * The namespace is rebuilt for every model bash call: ambient `DSH_*` values + * are discarded by the executor, then the registry's current snapshot is + * injected. Built-in shell facts remain owned by the registry itself while + * plugins can register additional, enumerable facts with effect-scoped + * disposal. + */ +export class BashEnvRegistry extends Service { + private readonly contributors = new Map() + private readonly keyOwners = new Map<`DSH_${string}`, string>() + private readonly dshHome: string + + /** + * Create and install the `ctx.bashEnv` service. + * @param ctx - Cordis context that owns the service and registrations. + * @param config - home-directory configuration for the built-in variables. + */ + constructor(ctx: Context, config: Config = {}) { + super(ctx, 'bashEnv') + this.dshHome = resolvePath(config.dshHome ?? process.env.DSH_HOME ?? join(homedir(), '.dsh')) + } + + /** + * Register one environment contributor. Names and keys are unique; built-in + * keys are reserved. Registration is disposed with the calling plugin fiber. + * @param contributor - declared key ownership and per-execution resolver. + * @returns the disposer that unregisters the contribution. + */ + register(contributor: BashEnvContributor): () => void { + const dispose = this.ctx.effect(function* (this: BashEnvRegistry) { + if (contributor.name.trim().length === 0) { + throw new Error('bash env contributor name must be non-empty') + } + if (this.contributors.has(contributor.name)) { + throw new Error(`bash env contributor "${contributor.name}" is already registered`) + } + + const variables = Object.entries(contributor.variables) as [`DSH_${string}`, BashEnvVariable][] + for (const [key, variable] of variables) { + if (!BASH_ENV_KEY.test(key)) { + throw new Error(`bash env contributor "${contributor.name}" declared invalid key "${key}"`) + } + if (RESERVED_BASH_ENV_KEYS.has(key)) { + throw new Error(`bash env contributor "${contributor.name}" cannot own reserved key "${key}"`) + } + if (variable.description.trim().length === 0) { + throw new Error(`bash env contributor "${contributor.name}" must describe "${key}"`) + } + const owner = this.keyOwners.get(key) + if (owner !== undefined) { + throw new Error(`bash env key "${key}" is already owned by contributor "${owner}"; contributor "${contributor.name}" cannot also own it`) + } + } + + this.contributors.set(contributor.name, contributor) + for (const [key] of variables) this.keyOwners.set(key, contributor.name) + yield () => { + this.contributors.delete(contributor.name) + for (const [key] of variables) this.keyOwners.delete(key) + } + }.bind(this), 'bashEnv.register()') + return () => void dispose() + } + + /** + * Build the trusted `DSH_*` snapshot for one bash tool execution. + * @param execution - the current tool execution. + * @returns an immutable environment overlay containing built-ins and current contributions. + */ + collect(execution: ToolExecution): DshEnvironment { + const values: Record<`DSH_${string}`, string> = { + DSH_HOME: this.dshHome, + DSH_SHELL: '1', + } + if (execution.agent !== undefined) { + values.DSH_SESSION_ID = execution.agent.session.header.id + } + + for (const contributor of [...this.contributors.values()].sort((left, right) => left.name.localeCompare(right.name))) { + const resolved = contributor.resolve(execution) + for (const [rawKey, value] of Object.entries(resolved)) { + const key = rawKey as `DSH_${string}` + if (!Object.hasOwn(contributor.variables, key)) { + throw new Error(`bash env contributor "${contributor.name}" returned undeclared key "${key}"`) + } + if (typeof value !== 'string') { + throw new Error(`bash env contributor "${contributor.name}" returned a non-string value for "${key}"`) + } + values[key] = value + } + } + + return Object.freeze(Object.fromEntries(Object.entries(values).sort(([left], [right]) => left.localeCompare(right)))) + } + + /** + * Enumerate plugin-contributed variables without executing their resolvers. + * @returns declarations sorted by environment variable name. + */ + list(): BashEnvVariableInfo[] { + return [...this.contributors.values()] + .flatMap(contributor => Object.entries(contributor.variables).map(([key, variable]) => ({ + contributor: contributor.name, + description: variable.description, + key: key as `DSH_${string}`, + }))) + .sort((left, right) => left.key.localeCompare(right.key)) + } +} + /** * Validate the constraints the SchemaSpec can't express. `defineTool` now * validates parsed args against the SchemaSpec before `execute` runs (the @@ -168,8 +337,7 @@ function bashDescription(escalationModes: readonly SandboxMode[]): string { const base = 'Execute a bash command (`bash -c`) and return its stdout/stderr. ' + 'Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — ' + 'pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. ' - + 'The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, ' - + '`$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. ' + + 'Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. ' + 'Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). ' + 'Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. ' + 'Set `run_in_background: true` for long-running commands: the call returns a task id immediately; ' @@ -397,22 +565,6 @@ function resolveWorkdir(modelWorkdir: string | undefined, exec: { agent?: Agent return modelWorkdir } -/** - * Build the trusted per-execution session environment. Identity always comes - * from the calling agent's immutable session header; an optional JSONL path - * comes from the active persistence backend's side-effect-free locator. A - * non-agent caller has no current session, so it receives neither variable. - */ -function sessionEnvironment(ctx: Context, exec: { agent?: Agent }): Record | undefined { - const agent = exec.agent - if (agent === undefined) return undefined - - const env: Record = { DSH_SESSION_ID: agent.session.header.id } - const location = ctx.get('sessionPersistence')?.locate(agent.session.header) - if (location?.kind === 'jsonl') env.DSH_SESSION_JSONL = location.path - return env -} - /** Status line for background task reads. */ function statusLine(task: BashTask): string { switch (task.status) { @@ -422,7 +574,23 @@ function statusLine(task: BashTask): string { } } -export function apply(ctx: Context): void { +export function apply(ctx: Context, config: Config = {}): void { + const bashEnv = new BashEnvRegistry(ctx, config) + bashEnv.register({ + name: 'session-persistence', + variables: { + DSH_SESSION_JSONL: { + description: 'Absolute target path of the current session JSONL when the active persistence backend provides one.', + }, + }, + resolve(execution) { + const agent = execution.agent + if (agent === undefined) return {} + const location = ctx.get('sessionPersistence')?.locate(agent.session.header) + return location?.kind === 'jsonl' ? { DSH_SESSION_JSONL: location.path } : {} + }, + }) + // The bash tools' cross-call HABIT, which the per-tool descriptions cannot // carry (they describe one call each): the exit-code marker is only useful // if the model actually checks it every time. @@ -614,13 +782,13 @@ export function apply(ctx: Context): void { // session runs in its own workspace (see resolveWorkdir); an explicit // model workdir still wins. const workdir = resolveWorkdir(args.workdir, exec) - const env = sessionEnvironment(ctx, exec) + const dshEnv = bashEnv.collect(exec) const request = { command: args.command, ...workdir !== undefined ? { workdir } : {}, ...args.timeoutMs !== undefined ? { timeoutMs: args.timeoutMs } : {}, ...exec.signal ? { signal: exec.signal } : {}, - ...env !== undefined ? { env } : {}, + dshEnv, ...sandboxMode !== undefined ? { sandboxMode } : {}, } if (args.run_in_background === true) { diff --git a/packages/bash/tool-bash/tests/bash-env.spec.ts b/packages/bash/tool-bash/tests/bash-env.spec.ts new file mode 100644 index 0000000000..f412568232 --- /dev/null +++ b/packages/bash/tool-bash/tests/bash-env.spec.ts @@ -0,0 +1,189 @@ +import { homedir } from 'node:os' +import { join, resolve } from 'node:path' +import { afterEach, describe, expect, it, vi } from 'vitest' +import { Context } from 'cordis' +import { CallId } from '@deepseek-ai/dsh-llm' +import type { Agent } from '@deepseek-ai/dsh-agent' +import type { ToolExecution } from '@deepseek-ai/dsh-tools' +import { BashEnvRegistry } from '@deepseek-ai/dsh-tool-bash' + +afterEach(() => vi.unstubAllEnvs()) + +function execution(sessionId?: string): ToolExecution { + return { + callId: CallId('bash-env-call'), + name: 'bash', + arguments: { command: 'true' }, + ...(sessionId === undefined + ? {} + : { agent: { session: { header: { version: 0, id: sessionId, createdAt: 0 } } } as Agent }), + } +} + +describe('BashEnvRegistry', () => { + it('collects unconditional shell facts and the current agent session id', () => { + const ctx = new Context() + const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' }) + + expect(registry.collect(execution())).toEqual({ + DSH_HOME: resolve('./test-dsh-home'), + DSH_SHELL: '1', + }) + expect(registry.collect(execution('session-a'))).toEqual({ + DSH_HOME: resolve('./test-dsh-home'), + DSH_SESSION_ID: 'session-a', + DSH_SHELL: '1', + }) + }) + + it('resolves DSH_HOME from the ambient override or the user-home default', () => { + vi.stubEnv('DSH_HOME', './ambient-dsh-home') + const fromEnvironment = new BashEnvRegistry(new Context()) + expect(fromEnvironment.collect(execution()).DSH_HOME).toBe(resolve('./ambient-dsh-home')) + + vi.stubEnv('DSH_HOME', undefined) + const fromDefault = new BashEnvRegistry(new Context()) + expect(fromDefault.collect(execution()).DSH_HOME).toBe(join(homedir(), '.dsh')) + }) + + it('collects declared contributor variables and omits unavailable values', () => { + const ctx = new Context() + const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' }) + registry.register({ + name: 'optional-session-fact', + variables: { + DSH_SESSION_OPTIONAL: { description: 'Optional session-scoped test fact.' }, + }, + resolve: exec => exec.agent === undefined ? {} : { DSH_SESSION_OPTIONAL: exec.agent.session.header.id }, + }) + registry.register({ + name: 'always-available-fact', + variables: { + DSH_ALWAYS_AVAILABLE: { description: 'Always-available test fact.' }, + }, + resolve: () => ({ DSH_ALWAYS_AVAILABLE: 'yes' }), + }) + + expect(registry.collect(execution())).not.toHaveProperty('DSH_SESSION_OPTIONAL') + expect(registry.collect(execution()).DSH_ALWAYS_AVAILABLE).toBe('yes') + expect(registry.collect(execution('session-b')).DSH_SESSION_OPTIONAL).toBe('session-b') + expect(registry.list()).toEqual([ + { + contributor: 'always-available-fact', + description: 'Always-available test fact.', + key: 'DSH_ALWAYS_AVAILABLE', + }, + { + contributor: 'optional-session-fact', + description: 'Optional session-scoped test fact.', + key: 'DSH_SESSION_OPTIONAL', + }, + ]) + }) + + it('rejects duplicate variable ownership at registration time', () => { + const ctx = new Context() + const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' }) + registry.register({ + name: 'first', + variables: { DSH_SHARED: { description: 'First owner.' } }, + resolve: () => ({ DSH_SHARED: 'first' }), + }) + + expect(() => registry.register({ + name: 'second', + variables: { DSH_SHARED: { description: 'Second owner.' } }, + resolve: () => ({ DSH_SHARED: 'second' }), + })).toThrow(/DSH_SHARED.*first.*second|DSH_SHARED.*second.*first/) + }) + + it('rejects duplicate contributor names and malformed declarations', () => { + const registry = new BashEnvRegistry(new Context(), { dshHome: './test-dsh-home' }) + registry.register({ + name: 'declared', + variables: { DSH_DECLARED: { description: 'Declared fact.' } }, + resolve: () => ({}), + }) + + expect(() => registry.register({ + name: 'declared', + variables: { DSH_ANOTHER: { description: 'Another fact.' } }, + resolve: () => ({}), + })).toThrow(/already registered/) + expect(() => registry.register({ + name: ' ', + variables: { DSH_BLANK_NAME: { description: 'Blank owner.' } }, + resolve: () => ({}), + })).toThrow(/name must be non-empty/) + expect(() => registry.register({ + name: 'invalid-key', + variables: { dsh_invalid: { description: 'Invalid key.' } } as unknown as Record<'DSH_INVALID', { description: string }>, + resolve: () => ({}), + })).toThrow(/invalid key/) + expect(() => registry.register({ + name: 'reserved-key', + variables: { DSH_HOME: { description: 'Reserved key.' } }, + resolve: () => ({}), + })).toThrow(/reserved key/) + expect(() => registry.register({ + name: 'blank-description', + variables: { DSH_BLANK_DESCRIPTION: { description: ' ' } }, + resolve: () => ({}), + })).toThrow(/must describe/) + }) + + it('rejects undeclared variables returned by a contributor', () => { + const ctx = new Context() + const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' }) + registry.register({ + name: 'drifted-provider', + variables: { DSH_DECLARED: { description: 'Declared fact.' } }, + resolve: () => ({ DSH_UNDECLARED: 'bad' }), + }) + + expect(() => registry.collect(execution())).toThrow(/drifted-provider.*DSH_UNDECLARED/) + }) + + it('rejects non-string values returned by a contributor', () => { + const registry = new BashEnvRegistry(new Context(), { dshHome: './test-dsh-home' }) + registry.register({ + name: 'wrong-value-type', + variables: { DSH_STRING: { description: 'String fact.' } }, + resolve: () => ({ DSH_STRING: 42 }) as unknown as Record<'DSH_STRING', string>, + }) + + expect(() => registry.collect(execution())).toThrow(/wrong-value-type.*non-string.*DSH_STRING/) + }) + + it('removes an effect-scoped contributor when its plugin is disposed', async () => { + const ctx = new Context() + const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' }) + const fiber = await ctx.plugin({ + inject: ['bashEnv'], + apply(inner: Context) { + inner.bashEnv.register({ + name: 'temporary', + variables: { DSH_TEMPORARY: { description: 'Temporary fact.' } }, + resolve: () => ({ DSH_TEMPORARY: 'present' }), + }) + }, + }) + + expect(registry.collect(execution()).DSH_TEMPORARY).toBe('present') + await fiber.dispose() + expect(registry.collect(execution())).not.toHaveProperty('DSH_TEMPORARY') + }) + + it('returns an explicit contributor disposer', () => { + const registry = new BashEnvRegistry(new Context(), { dshHome: './test-dsh-home' }) + const dispose = registry.register({ + name: 'explicit-disposal', + variables: { DSH_EXPLICIT_DISPOSAL: { description: 'Explicitly disposed fact.' } }, + resolve: () => ({ DSH_EXPLICIT_DISPOSAL: 'present' }), + }) + + expect(registry.collect(execution()).DSH_EXPLICIT_DISPOSAL).toBe('present') + dispose() + expect(registry.collect(execution())).not.toHaveProperty('DSH_EXPLICIT_DISPOSAL') + }) +}) diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index 430b0c3f11..8a939588cd 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -1,4 +1,4 @@ -import { afterEach, describe, expect, it } from 'vitest' +import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import { existsSync, mkdtempSync, readFileSync, rmSync } from 'node:fs' import { tmpdir } from 'node:os' @@ -21,7 +21,7 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent * through the agent loop, exercising the same seams a live model would * (tool/call + tool/result session events, agent.inject notifications). */ -async function harness(adapter: MockAdapter, sessionRoot?: string) { +async function harness(adapter: MockAdapter, sessionRoot?: string, dshHome?: string) { const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(SessionStore) @@ -31,13 +31,16 @@ async function harness(adapter: MockAdapter, sessionRoot?: string) { await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) - await ctx.plugin(ToolBash) + await ctx.plugin(ToolBash, dshHome === undefined ? {} : { dshHome }) ctx.llm.registerAdapter(['mock'], adapter) return ctx } const dirs: string[] = [] -afterEach(() => { for (const dir of dirs.splice(0)) rmSync(dir, { recursive: true, force: true }) }) +afterEach(() => { + vi.unstubAllEnvs() + for (const dir of dirs.splice(0)) rmSync(dir, { recursive: true, force: true }) +}) function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { return new Promise((resolve) => { @@ -79,14 +82,16 @@ describe('bash tool through the agent loop', () => { it('first-turn bash receives session identity before the lazy JSONL file materializes', async () => { const root = mkdtempSync(join(tmpdir(), 'dsh-bash-session-env-')) dirs.push(root) + const dshHome = join(root, 'dsh-home') + vi.stubEnv('DSH_STALE_PARENT', 'stale') const adapter = new MockAdapter([ toolCallResponse('call-1', 'bash', { - command: 'printf \'%s\\n%s\\n\' "$DSH_SESSION_ID" "$DSH_SESSION_JSONL"; if [ -e "$DSH_SESSION_JSONL" ]; then printf \'present\\n\'; else printf \'absent\\n\'; fi', + command: 'printf \'%s\\n%s\\n%s\\n%s\\n%s\\n\' "$DSH_HOME" "$DSH_SHELL" "$DSH_SESSION_ID" "$DSH_SESSION_JSONL" "${DSH_STALE_PARENT-unset}"; if [ -e "$DSH_SESSION_JSONL" ]; then printf \'present\\n\'; else printf \'absent\\n\'; fi', description: 'inspect session environment', }), textResponse('Session environment inspected.'), ]) - const ctx = await harness(adapter, root) + const ctx = await harness(adapter, root, dshHome) const handle = ctx.agents.create({ agentId: AgentId('session-env'), sessionId: SessionId('session-env-id'), @@ -100,7 +105,7 @@ describe('bash tool through the agent loop', () => { await waitForIdle(ctx, agent) const result = findEvent(events(agent), 'tool/result') - expect(resultText(result)).toBe(`session-env-id\n${location?.path}\nabsent\n`) + expect(resultText(result)).toBe(`${dshHome}\n1\nsession-env-id\n${location?.path}\nunset\nabsent\n`) expect(existsSync(location!.path)).toBe(true) const header = JSON.parse(readFileSync(location!.path, 'utf8').split('\n')[0]!) as { type: string; id: string } expect(header).toMatchObject({ type: 'session', id: 'session-env-id' }) diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index 44eca86c0e..66639b39a0 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -892,6 +892,8 @@ describe('tool-owned UI presentation (presentCall / presentResult)', () => { }) describe('the model-facing bash tool builds its request from named args only (no {...args} forward)', () => { + const recordingDshHome = join(spillDir, 'dsh-home') + /** * Records every {@link BashExecRequest} the consumer hands to `resolve()`, so a * test can assert what the model-facing tool DID and DID NOT forward. The `bash` @@ -899,7 +901,7 @@ describe('the model-facing bash tool builds its request from named args only (no * model that power), so it must build its request from named args only and * never spread unknown tool-call keys into it. This guard's job is to catch a * future refactor that blindly forwards `...args` — which would silently thread - * model input into the post-scrub `env` merge — NOT to defend a trust boundary + * model input into the ordinary `env` channel — NOT to defend a trust boundary * (the credential scrub in dsh-bash-local is the security control; see the * bash-stdin-env RFC). Foreground `run()` returns a canned result; `start()` is * unused here. @@ -915,6 +917,7 @@ describe('the model-facing bash tool builds its request from named args only (no ...request.signal ? { signal: request.signal } : {}, ...request.stdin !== undefined ? { stdin: request.stdin } : {}, ...request.env !== undefined ? { env: request.env } : {}, + ...request.dshEnv !== undefined ? { dshEnv: request.dshEnv } : {}, owner: request.owner, sandboxMode: request.sandboxMode, } @@ -943,15 +946,15 @@ describe('the model-facing bash tool builds its request from named args only (no await ctx.plugin(SessionPersistenceJsonl, { root: join(spillDir, 'jsonl') }) } await ctx.plugin(RecordingBashExecutor) - await ctx.plugin(ToolBash) + await ctx.plugin(ToolBash, { dshHome: recordingDshHome }) return { ctx, bash: ctx.bash as RecordingBashExecutor } } - it('describes the trusted session variables to the model', async () => { + it('describes the managed harness environment namespace to the model', async () => { const { ctx } = await setupRecording() const description = ctx.tools.get('bash')?.description ?? '' - expect(description).toContain('DSH_SESSION_ID') - expect(description).toContain('DSH_SESSION_JSONL') + expect(description).toContain('$DSH_*') + expect(description).not.toContain('DSH_SESSION_JSONL') }) it('injects the session id and JSONL target path into a foreground request', async () => { @@ -966,9 +969,11 @@ describe('the model-facing bash tool builds its request from named args only (no agent, }) - expect(bash.requests[0]?.env).toEqual({ + expect(bash.requests[0]?.dshEnv).toEqual({ + DSH_HOME: recordingDshHome, DSH_SESSION_ID: 'request-fg', DSH_SESSION_JSONL: path, + DSH_SHELL: '1', }) }) @@ -989,13 +994,16 @@ describe('the model-facing bash tool builds its request from named args only (no agent, }) - expect(bash.requests[0]?.env).toEqual({ + expect(bash.requests[0]?.env).toBeUndefined() + expect(bash.requests[0]?.dshEnv).toEqual({ + DSH_HOME: recordingDshHome, DSH_SESSION_ID: 'request-bg', DSH_SESSION_JSONL: path, + DSH_SHELL: '1', }) }) - it('injects only the stable session id when no JSONL locator is available', async () => { + it('injects built-ins and the stable session id when no JSONL locator is available', async () => { const { ctx, bash } = await setupRecording() const agent = registerFakeAgent(ctx, 'request-id-only', () => undefined) const ambient = process.env.DSH_SESSION_ID @@ -1007,7 +1015,11 @@ describe('the model-facing bash tool builds its request from named args only (no agent, }) - expect(bash.requests[0]?.env).toEqual({ DSH_SESSION_ID: 'request-id-only' }) + expect(bash.requests[0]?.dshEnv).toEqual({ + DSH_HOME: recordingDshHome, + DSH_SESSION_ID: 'request-id-only', + DSH_SHELL: '1', + }) expect(process.env.DSH_SESSION_ID).toBe(ambient) }) @@ -1025,17 +1037,21 @@ describe('the model-facing bash tool builds its request from named args only (no }) } - expect(bash.requests.map(request => request.env)).toEqual([ + expect(bash.requests.map(request => request.dshEnv)).toEqual([ { + DSH_HOME: recordingDshHome, DSH_SESSION_ID: 'request-parent', DSH_SESSION_JSONL: ctx.sessionPersistence.locate(parent.session.header)?.path, + DSH_SHELL: '1', }, { + DSH_HOME: recordingDshHome, DSH_SESSION_ID: 'request-child', DSH_SESSION_JSONL: ctx.sessionPersistence.locate(child.session.header)?.path, + DSH_SHELL: '1', }, ]) - expect(bash.requests[0]?.env?.DSH_SESSION_JSONL).not.toBe(bash.requests[1]?.env?.DSH_SESSION_JSONL) + expect(bash.requests[0]?.dshEnv?.DSH_SESSION_JSONL).not.toBe(bash.requests[1]?.dshEnv?.DSH_SESSION_JSONL) }) it('does not forward env/stdin even when the model includes them as extra arguments', async () => { diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 257ccc2267..8323d13248 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -95,6 +95,15 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'onTaskDone(listener: BashTaskListener): () => void', ], }, + { + key: 'bashEnv', + summary: 'Registry (`ctx.bashEnv`) for trusted, per-execution `DSH_*` variables.', + methods: [ + 'register(contributor: BashEnvContributor): () => void', + 'collect(execution: ToolExecution): DshEnvironment', + 'list(): BashEnvVariableInfo[]', + ], + }, { key: 'codeRuntime', summary: 'Abstract code-execution service.', @@ -524,13 +533,25 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'AssembledSection', declaration: 'export interface AssembledSection {\n name: string;\n order: number;\n text: string;\n}', }, + { + name: 'BashEnvContributor', + declaration: 'export interface BashEnvContributor {\n name: string;\n variables: Readonly>;\n resolve(execution: ToolExecution): Readonly>>;\n}', + }, + { + name: 'BashEnvVariable', + declaration: 'export interface BashEnvVariable {\n description: string;\n}', + }, + { + name: 'BashEnvVariableInfo', + declaration: 'export interface BashEnvVariableInfo extends BashEnvVariable {\n contributor: string;\n key: `DSH_${string}`;\n}', + }, { name: 'BashExecRequest', - declaration: 'export interface BashExecRequest {\n command: string;\n workdir?: string | undefined;\n timeoutMs?: number | undefined;\n signal?: AbortSignal | undefined;\n stdin?: string | undefined;\n env?: Record | undefined;\n owner?: OwnerToken | undefined;\n sandboxMode?: SandboxMode | undefined;\n}', + declaration: 'export interface BashExecRequest {\n command: string;\n workdir?: string | undefined;\n timeoutMs?: number | undefined;\n signal?: AbortSignal | undefined;\n stdin?: string | undefined;\n env?: Record | undefined;\n dshEnv?: DshEnvironment | undefined;\n owner?: OwnerToken | undefined;\n sandboxMode?: SandboxMode | undefined;\n}', }, { name: 'BashExecSpec', - declaration: 'export interface BashExecSpec {\n command: string;\n workdir: string;\n timeoutMs: number;\n signal?: AbortSignal | undefined;\n stdin?: string | undefined;\n env?: Record | undefined;\n owner: OwnerToken | undefined;\n sandboxMode: SandboxMode | undefined;\n}', + declaration: 'export interface BashExecSpec {\n command: string;\n workdir: string;\n timeoutMs: number;\n signal?: AbortSignal | undefined;\n stdin?: string | undefined;\n env?: Record | undefined;\n dshEnv?: DshEnvironment | undefined;\n owner: OwnerToken | undefined;\n sandboxMode: SandboxMode | undefined;\n}', }, { name: 'BashRunResult', @@ -636,6 +657,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'DiffResultView', declaration: 'export interface DiffResultView {\n card: \'diff\';\n title?: string;\n diffs: FileDiff[];\n}', }, + { + name: 'DshEnvironment', + declaration: 'export type DshEnvironment = Readonly>;', + }, { name: 'FileDiff', declaration: 'export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n}', diff --git a/packages/core/agent-core/README.md b/packages/core/agent-core/README.md index 642b07b10d..ad63fdc5c0 100644 --- a/packages/core/agent-core/README.md +++ b/packages/core/agent-core/README.md @@ -39,11 +39,11 @@ This is the [interface/implementation/consumer seam](../../../docs/rfc/implement ```ts import type { Config } from '@deepseek-ai/dsh-agent-core' -// { agents?, persona?, toolOrder?, tools?, skills? } — the schema intersects the owner schemas, +// { agents?, persona?, toolOrder?, tools?, dshHome?, skills? } — the schema intersects the owner schemas, // so validation and defaulting can never drift from the owners. ``` -The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure. +The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry; `dshHome` to tool-bash's managed environment and the local skill provider; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. An absent top-level `dshHome` adopts `skills.local.dshHome`; supplying both with different resolved paths fails loudly. ## Why a code bundle, not a shared YAML include diff --git a/packages/core/agent-core/src/index.ts b/packages/core/agent-core/src/index.ts index d12ef3bad5..ba4904cbef 100644 --- a/packages/core/agent-core/src/index.ts +++ b/packages/core/agent-core/src/index.ts @@ -46,6 +46,7 @@ */ import type { Context } from 'cordis' +import { resolve as resolvePath } from 'node:path' import Timer from '@cordisjs/plugin-timer' import z from 'schemastery' import LlmService from '@deepseek-ai/dsh-llm' @@ -78,7 +79,8 @@ export interface SkillConfig { * bridge, simply omits it), `persona` and `toolOrder` to the system-prompt * plugin (the deployment's persona section and the explicit model-facing tool * order), the `tools` object to the tool registry (its presentation `mode`), - * and `skills` to the skill registry/local provider/tool consumer. Every field + * `dshHome` to the bash environment registry and local skill provider, and + * `skills` to the skill registry/local provider/tool consumer. Every field * is optional INPUT here because each owner's schema supplies the default; * the schema is the INTERSECTION of the owners' own schemas (with registry * schemas nested under their bundle keys), so validation and defaulting can @@ -93,6 +95,8 @@ export interface Config { toolOrder?: SystemPromptConfig['toolOrder'] /** The tool registry's config — its presentation `mode` (see dsh-tools' `Config`). */ tools?: ToolsConfig + /** DeepSeek Harness home directory shared by shell context and local skill discovery. */ + dshHome?: string /** Skill registry, local provider, and model-facing consumer config. */ skills?: SkillConfig } @@ -108,7 +112,7 @@ export const SkillConfigSchema: z = z.object({ export const Config = z.intersect([ AgentLoop.Config, SystemPrompt.Config, - z.object({ tools: ToolRegistry.Config, skills: SkillConfigSchema }), + z.object({ tools: ToolRegistry.Config, dshHome: z.string(), skills: SkillConfigSchema }), ]) as unknown as z /** @@ -121,6 +125,13 @@ export const Config = z.intersect([ * then the loop that drives them. */ export function apply(ctx: Context, config: Config): void { + const nestedDshHome = config.skills?.local?.dshHome + if (config.dshHome !== undefined && nestedDshHome !== undefined + && resolvePath(config.dshHome) !== resolvePath(nestedDshHome)) { + throw new Error('agent-core: dshHome and skills.local.dshHome must resolve to the same directory') + } + const dshHome = config.dshHome ?? nestedDshHome + ctx.plugin(Timer) ctx.plugin(LlmService) ctx.plugin(SessionStore) @@ -136,10 +147,14 @@ export function apply(ctx: Context, config: Config): void { }) ctx.plugin(ToolRegistry, config.tools ?? {}) ctx.plugin(SkillService, config.skills?.registry ?? {}) - ctx.plugin(SkillLocal, config.skills?.local ?? {}) + ctx.plugin(SkillLocal, Object.assign( + {}, + config.skills?.local, + dshHome === undefined ? {} : { dshHome }, + )) ctx.plugin(AgentRegistry) ctx.plugin(invariants) - ctx.plugin(toolBash) + ctx.plugin(toolBash, dshHome === undefined ? {} : { dshHome }) ctx.plugin(toolSkill, config.skills?.tool ?? {}) ctx.plugin(AgentLoop, { agents: config.agents ?? [] }) } diff --git a/packages/core/agent-core/tests/agent-core.spec.ts b/packages/core/agent-core/tests/agent-core.spec.ts index fb1bc7e1bd..5ed15ab72d 100644 --- a/packages/core/agent-core/tests/agent-core.spec.ts +++ b/packages/core/agent-core/tests/agent-core.spec.ts @@ -2,12 +2,24 @@ import { describe, expect, it } from 'vitest' import { mkdir, mkdtemp, writeFile } from 'node:fs/promises' import { join } from 'node:path' import { tmpdir } from 'node:os' -import { Context } from 'cordis' +import { Context, Service } from 'cordis' import Loader from '@cordisjs/plugin-loader' import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import * as agentCore from '../src/index.ts' import { AgentId } from '@deepseek-ai/dsh-agent' -import type { Message } from '@deepseek-ai/dsh-llm' +import { CallId, type Message } from '@deepseek-ai/dsh-llm' +import type { ToolExecution } from '@deepseek-ai/dsh-tools' + +/** Minimal service that lets the executor-less bundle activate tool-bash in config-forwarding tests. */ +class StubBashService extends Service { + constructor(ctx: Context) { + super(ctx, 'bash') + } + + onTaskDone(): () => void { + return () => undefined + } +} async function composePrefix(ctx: Context, cwd: string): Promise { const empty: Message[] = [] @@ -152,6 +164,39 @@ describe('dsh-agent-core bundle', () => { await ctx.fiber.dispose() }) + it('shares top-level dshHome between local skills and the managed bash environment', async () => { + const home = await mkdtemp(join(tmpdir(), 'dsh-agent-core-shared-home-')) + const agentsHome = await mkdtemp(join(tmpdir(), 'dsh-agent-core-shared-agents-')) + await mkdir(join(home, 'skills'), { recursive: true }) + await writeFile(join(home, 'skills', 'shared-skill.md'), '---\nname: shared-skill\ndescription: Shared home skill\n---\n\nShared body.\n') + + const ctx = new Context() + await ctx.plugin(StubBashService) + await ctx.plugin(agentCore, { + dshHome: home, + skills: { local: { agentsHome } }, + }) + await new Promise(resolve => setTimeout(resolve, 50)) + + expect((await ctx.skills.list()).map(skill => skill.name)).toEqual(['shared-skill']) + const execution: ToolExecution = { + callId: CallId('agent-core-dsh-home'), + name: 'bash', + arguments: { command: 'true' }, + } + expect(ctx.bashEnv.collect(execution)).toMatchObject({ DSH_HOME: home, DSH_SHELL: '1' }) + await ctx.fiber.dispose() + }) + + it('rejects conflicting global and nested DSH home directories', () => { + expect(() => { + agentCore.apply(new Context(), { + dshHome: '/global-dsh-home', + skills: { local: { dshHome: '/nested-dsh-home' } }, + }) + }).toThrow(/must resolve to the same directory/) + }) + it('uses the default skill config when apply is called directly without skills', async () => { await withIsolatedSkillHomes(async () => { const ctx = new Context() diff --git a/packages/ui/acp-agent/README.md b/packages/ui/acp-agent/README.md index d81c9cc091..a65c99c48e 100644 --- a/packages/ui/acp-agent/README.md +++ b/packages/ui/acp-agent/README.md @@ -27,6 +27,7 @@ Because the package wires no logger entry, an ACP leaf has **nothing to get wron | `model` | (required) | the per-session agent template the bridge creates agents from | | `persona` | — | the deployment persona template (may reference `{{model}}`/`{{cwd}}`), routed to `dsh-system-prompt` | | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | +| `dshHome` | `$DSH_HOME` or `~/.dsh` | Harness home exposed to model bash and used by local skill discovery | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | The leaf supplies the swappable backends: an LLM adapter (`llm-deepseek` for the real model, `llm-replay` for keyless snapshot replay) and a bash executor (`bash-local`). diff --git a/packages/ui/acp-agent/src/index.ts b/packages/ui/acp-agent/src/index.ts index 27b919f756..cd35d34b5a 100644 --- a/packages/ui/acp-agent/src/index.ts +++ b/packages/ui/acp-agent/src/index.ts @@ -58,6 +58,8 @@ export interface Config { toolOrder?: string[] /** Tool-registry config — its presentation `mode` (forwarded through agent-core; see dsh-tools). */ tools?: ToolsConfig + /** DeepSeek Harness home directory exposed to bash and used for local skill discovery. */ + dshHome?: string /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */ persistenceRoot?: string /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-core. */ @@ -72,6 +74,7 @@ export const Config: z = z.object({ // schemastery's native [] default would read as an invalid configured list. toolOrder: z.array(z.string()).default(undefined as unknown as string[]), tools: ToolRegistry.Config, + dshHome: z.string(), persistenceRoot: z.string().default('./.sessions'), skills: agentCore.SkillConfigSchema, }) @@ -88,6 +91,7 @@ export function apply(ctx: Context, config: Config): void { ...config.persona !== undefined ? { persona: config.persona } : {}, ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {}, ...config.tools !== undefined ? { tools: config.tools } : {}, + ...config.dshHome !== undefined ? { dshHome: config.dshHome } : {}, ...config.skills !== undefined ? { skills: config.skills } : {}, }) ctx.plugin(UserInteractionService) diff --git a/packages/ui/acp-agent/tests/acp-agent.spec.ts b/packages/ui/acp-agent/tests/acp-agent.spec.ts index 47cc399dfc..222ea66896 100644 --- a/packages/ui/acp-agent/tests/acp-agent.spec.ts +++ b/packages/ui/acp-agent/tests/acp-agent.spec.ts @@ -104,7 +104,8 @@ describe('dsh-acp-agent composition', () => { }) it('forwards skill config into agent-core', async () => { - const ctx = await mount({ model: 'mock', persona: 'hi', skills: await isolatedSkillsConfig(6) }) + const skills = await isolatedSkillsConfig(6) + const ctx = await mount({ model: 'mock', persona: 'hi', dshHome: skills.local!.dshHome!, skills }) ctx.skills.register({ name: 'acp-skill', description: 'ACP skill', source: 'runtime', content: 'body' }) expect(JSON.stringify(await composePrefix(ctx))).toContain('- `acp-skill`: ACP...') await ctx.fiber.dispose() diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 27f0d20be7..ece219c264 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -28,6 +28,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `model` | (required) | the pre-created `main` agent's model | | `persona` | — | the deployment persona template (may reference `{{model}}`), routed to `dsh-system-prompt` | | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | +| `dshHome` | `$DSH_HOME` or `~/.dsh` | Harness home exposed to model bash and used by local skill discovery | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 1037c28112..0a45cb368f 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -71,6 +71,8 @@ export interface Config { toolOrder?: string[] /** Tool-registry config — its presentation `mode` (forwarded through agent-core; see dsh-tools). */ tools?: ToolsConfig + /** DeepSeek Harness home directory exposed to bash and used for local skill discovery. */ + dshHome?: string /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */ persistenceRoot?: string /** stdin-chat banner printed once on start. Defaults to `'ready.'`. */ @@ -93,6 +95,7 @@ export const Config: z = z.object({ // schemastery's native [] default would read as an invalid configured list. toolOrder: z.array(z.string()).default(undefined as unknown as string[]), tools: ToolRegistry.Config, + dshHome: z.string(), persistenceRoot: z.string().default('./.sessions'), welcome: z.string().default('ready.'), skills: agentCore.SkillConfigSchema, @@ -112,6 +115,7 @@ export function apply(ctx: Context, config: Config): void { ...config.persona !== undefined ? { persona: config.persona } : {}, ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {}, ...config.tools !== undefined ? { tools: config.tools } : {}, + ...config.dshHome !== undefined ? { dshHome: config.dshHome } : {}, agents: [{ id: AgentId('main'), model: config.model, diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index c08115526f..0d88c50ea8 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -129,7 +129,8 @@ describe('dsh-stdio-agent app', () => { }) it('forwards skill config into agent-core', async () => { - const ctx = await mount({ model: 'mock', persona: 'hi', skills: await isolatedSkillsConfig(6) }) + const skills = await isolatedSkillsConfig(6) + const ctx = await mount({ model: 'mock', persona: 'hi', dshHome: skills.local!.dshHome!, skills }) ctx.skills.register({ name: 'stdio-skill', description: 'Stdio skill', source: 'runtime', content: 'body' }) expect(JSON.stringify(await composePrefix(ctx))).toContain('- `stdio-skill`: Std...') await ctx.fiber.dispose() diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 236f2ec4af..688c6b1f0c 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -75,31 +75,6 @@ importers: specifier: ^4.1.8 version: 4.1.8(@types/node@22.20.0)(@vitest/coverage-v8@4.1.8)(jsdom@29.1.1)(vite@8.0.16(@types/node@22.20.0)(esbuild@0.28.1)(jiti@2.7.0)(tsx@4.22.4)(yaml@2.9.0)) - packages/ui/user-approval: - dependencies: - schemastery: - specifier: ^3.18.0 - version: 3.18.0 - devDependencies: - '@deepseek-ai/dsh-agent': - specifier: workspace:^ - version: link:../../core/agent - '@deepseek-ai/dsh-brand': - specifier: workspace:^ - version: link:../../util/brand - '@deepseek-ai/dsh-llm': - specifier: workspace:^ - version: link:../../llm/llm - '@deepseek-ai/dsh-session': - specifier: workspace:^ - version: link:../../core/session - '@deepseek-ai/dsh-system-prompt': - specifier: workspace:^ - version: link:../../core/system-prompt - cordis: - specifier: ^4.0.0-rc.6 - version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) - packages/bash/bash: devDependencies: '@deepseek-ai/dsh-brand': @@ -157,6 +132,10 @@ importers: version: 0.0.0-test.0 packages/bash/tool-bash: + dependencies: + schemastery: + specifier: ^3.18.0 + version: 3.18.0 devDependencies: '@deepseek-ai/dsh-agent': specifier: workspace:^ @@ -164,9 +143,6 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop - '@deepseek-ai/dsh-user-approval': - specifier: workspace:^ - version: link:../../ui/user-approval '@deepseek-ai/dsh-bash': specifier: workspace:^ version: link:../bash @@ -200,6 +176,9 @@ importers: '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools + '@deepseek-ai/dsh-user-approval': + specifier: workspace:^ + version: link:../../ui/user-approval cordis: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) @@ -431,9 +410,6 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../agent - '@deepseek-ai/dsh-user-approval': - specifier: workspace:^ - version: link:../../ui/user-approval '@deepseek-ai/dsh-code-runtime': specifier: workspace:^ version: link:../../code-runtime/code-runtime @@ -446,6 +422,9 @@ importers: '@deepseek-ai/dsh-system-prompt': specifier: workspace:^ version: link:../system-prompt + '@deepseek-ai/dsh-user-approval': + specifier: workspace:^ + version: link:../../ui/user-approval cordis: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) @@ -1153,9 +1132,6 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop - '@deepseek-ai/dsh-user-approval': - specifier: workspace:^ - version: link:../user-approval '@deepseek-ai/dsh-bash': specifier: workspace:^ version: link:../../bash/bash @@ -1204,6 +1180,9 @@ importers: '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools + '@deepseek-ai/dsh-user-approval': + specifier: workspace:^ + version: link:../user-approval '@deepseek-ai/dsh-user-interaction': specifier: workspace:^ version: link:../user-interaction @@ -1328,6 +1307,31 @@ importers: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/ui/user-approval: + dependencies: + schemastery: + specifier: ^3.18.0 + version: 3.18.0 + devDependencies: + '@deepseek-ai/dsh-agent': + specifier: workspace:^ + version: link:../../core/agent + '@deepseek-ai/dsh-brand': + specifier: workspace:^ + version: link:../../util/brand + '@deepseek-ai/dsh-llm': + specifier: workspace:^ + version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + '@deepseek-ai/dsh-system-prompt': + specifier: workspace:^ + version: link:../../core/system-prompt + cordis: + specifier: ^4.0.0-rc.6 + version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/ui/user-interaction: devDependencies: '@deepseek-ai/dsh-agent': diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index ec92045069..b4647b7a6b 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -170,6 +170,13 @@ const SERVICE_ROLES: ServiceRole[] = [ consumers: ['tool-bash', 'hooks-claude', 'hooks-codex'], note: 'The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors replace bash-local without touching them.', }, + { + key: 'bashEnv', + pkg: 'tool-bash', + title: 'Managed bash environment registry', + mode: 'core', + note: 'Plugins declare effect-scoped DSH_* facts; tool-bash collects one trusted snapshot per execution and the executor rebuilds the namespace.', + }, { key: 'sandbox', pkg: 'sandbox', From 48e7bde3617dd5c84fb7f1c7692066e9bd530e3c Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sun, 12 Jul 2026 16:14:13 +0800 Subject: [PATCH 010/359] refactor(bash): centralize managed env prefix --- docs/cordis-catalog/services.md | 4 +- ...agent-session-identity-and-log-location.md | 2 +- packages/bash/bash-local/src/run.ts | 5 +- packages/bash/bash/README.md | 2 +- packages/bash/bash/src/index.ts | 3 +- packages/bash/bash/src/types.ts | 8 ++- packages/bash/tool-bash/src/index.ts | 51 ++++++++++--------- .../cordis/tool-cordis/src/api-catalog.ts | 10 ++-- 8 files changed, 51 insertions(+), 34 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 87ecaa328a..d25379adad 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -79,7 +79,7 @@ onTaskDone(listener: BashTaskListener): () => void Types: [BashExecRequest](../core-data-structures/bash.md) · [BashExecSpec](../core-data-structures/bash.md) · [BashRunResult](../core-data-structures/bash.md) · [BashTask](../core-data-structures/bash.md) · [BashTaskRead](../core-data-structures/bash.md) -Source: [`packages/bash/bash/src/index.ts:63`](../../packages/bash/bash/src/index.ts) +Source: [`packages/bash/bash/src/index.ts:64`](../../packages/bash/bash/src/index.ts) ## `ctx.bashEnv` — `BashEnvRegistry` @@ -93,7 +93,7 @@ list(): BashEnvVariableInfo[] Types: [ToolExecution](../core-data-structures/tools.md) -Source: [`packages/bash/tool-bash/src/index.ts:143`](../../packages/bash/tool-bash/src/index.ts) +Source: [`packages/bash/tool-bash/src/index.ts:147`](../../packages/bash/tool-bash/src/index.ts) ## `ctx.codeRuntime` — `CodeRuntime` (abstract seam) diff --git a/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md b/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md index 35968a3896..9dcd609b50 100644 --- a/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md +++ b/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md @@ -38,7 +38,7 @@ The registry rebuilds a trusted overlay for every foreground and background bash Session persistence remains the fact owner: JSONL does not depend on tool-bash or register shell variables itself, and hooks continue to consume `locate()` directly. Tool-bash is the translation layer from the persistence fact into a shell convention. Other plugins that need shell-visible facts depend on the registry and register their own keys; they do not modify `process.env`. -The bash seam carries the managed overlay separately as `BashExecRequest.dshEnv` / `BashExecSpec.dshEnv`. Ordinary `env` remains the general in-process plugin surface used by hooks, but cannot contain `DSH_*`; the local executor rejects that wrong channel, removes every inherited ambient `DSH_*`, applies its ordinary scrub/terminal environment/explicit `env`, and finally merges the trusted `dshEnv` snapshot. This guarantees that a missing value means absent now rather than inherited from an outer or previous harness. The model-facing tool still ignores model-supplied `env`/`stdin` arguments. +The bash seam exports `DSH_ENV_PREFIX` as the single namespace source and derives `DshEnvironmentKey` from its `typeof`. Tool-bash derives built-in names and model guidance from that constant, while executors use it for filtering and ordinary-env rejection. The seam carries the managed overlay separately as `BashExecRequest.dshEnv` / `BashExecSpec.dshEnv`. Ordinary `env` remains the general in-process plugin surface used by hooks, but cannot contain managed keys; the local executor rejects that wrong channel, removes every inherited ambient managed key, applies its ordinary scrub/terminal environment/explicit `env`, and finally merges the trusted `dshEnv` snapshot. This guarantees that a missing value means absent now rather than inherited from an outer or previous harness. The model-facing tool still ignores model-supplied `env`/`stdin` arguments. The bash tool description teaches only the durable convention: current harness environment facts are available through managed `$DSH_*` variables and may be inspected when needed. It does not enumerate persistence-specific keys or add a permanent system-prompt section. Tool schemas are already logged in request headers and tool output is logged as `tool/result`, so no new session event is required. diff --git a/packages/bash/bash-local/src/run.ts b/packages/bash/bash-local/src/run.ts index 47361b4e5e..9cd9ac2553 100644 --- a/packages/bash/bash-local/src/run.ts +++ b/packages/bash/bash-local/src/run.ts @@ -27,6 +27,7 @@ import { randomBytes } from 'node:crypto' import { closeSync, mkdtempSync, openSync, writeSync } from 'node:fs' import { tmpdir } from 'node:os' import { join } from 'node:path' +import { DSH_ENV_PREFIX } from '@deepseek-ai/dsh-bash' import type { CollectedOutput, DshEnvironment } from '@deepseek-ai/dsh-bash' /** @@ -69,10 +70,10 @@ export function childEnv( ): NodeJS.ProcessEnv { const env: NodeJS.ProcessEnv = {} for (const [key, value] of Object.entries(process.env)) { - if (!SENSITIVE_ENV_PATTERN.test(key) && !key.startsWith('DSH_')) env[key] = value + if (!SENSITIVE_ENV_PATTERN.test(key) && !key.startsWith(DSH_ENV_PREFIX)) env[key] = value } for (const key of Object.keys(extra ?? {})) { - if (key.startsWith('DSH_')) { + if (key.startsWith(DSH_ENV_PREFIX)) { throw new Error(`ordinary bash env cannot set reserved variable "${key}"; use dshEnv`) } } diff --git a/packages/bash/bash/README.md b/packages/bash/bash/README.md index 11a50c954a..97c2d00faf 100644 --- a/packages/bash/bash/README.md +++ b/packages/bash/bash/README.md @@ -34,4 +34,4 @@ Implementations subclass `BashExecutor`, implement the abstract methods, and cal The seam also owns the per-session mode override vocabulary (the sandbox RFC § Per-session mode switching): the log-only `'bash/sandbox-mode'` session event, the pure fold `effectiveSandboxMode(events)` (last event wins; `undefined` means "apply the executor default"), and THE write path `setSandboxMode(session, mode)` — the session log is the store, so an override survives restart by replay and two sessions can never see each other's mode. Writers must respect turn-enclosure: the ACP bridge anchors an idle switch at the next turn rather than appending between turns. The task id (`BashTaskId`) and the `owner` token (`OwnerToken`) are [branded](../../util/brand) — `OwnerToken` is a DISTINCT brand from `SessionId` (the seam never imports `dsh-session`; the `dsh-tool-bash` consumer is the single boundary that casts its `SessionId` into one). `run()` returns `BashRunResult` (exitCode, signal, timedOut, aborted, timeoutMs, stdout/stderr as `CollectedOutput`) and `start()`/`readOutput()` use `BashTask`/`BashTaskRead` for the background side. A sandboxing executor additionally stamps `sandbox` result facts on results and settled tasks (`BashSandboxInfo`: the mode it executed under, the conservative `denied` classification, and — for confined modes — the backend's `enforcement` completeness); the mode/enforcement vocabulary is owned by the [`dsh-sandbox`](../../sandbox/sandbox/) seam, and the facts are documented in [core-data-structures/bash.md](../../../docs/core-data-structures/bash.md). See `src/types.ts` for the full contracts. -`stdin` and ordinary `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its JSON payload and `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` values. `dshEnv` is a separate trusted overlay restricted by type to `DSH_*` keys; model bash uses it for the current snapshot collected by `ctx.bashEnv`. Implementations remove inherited `DSH_*`, reject those names in ordinary `env`, then merge `dshEnv`, so an omitted current fact cannot fall back to stale ambient state. The model-facing tool exposes none of these as parameters. All three remain optional on the resolved spec; absent means no input/overlay. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [the session environment RFC](../../../docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md). +`stdin` and ordinary `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its JSON payload and `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` values. `dshEnv` is a separate trusted overlay restricted by type to managed keys; the exported `DSH_ENV_PREFIX` is the single source for that namespace, its `DshEnvironmentKey` template type, executor scrubbing, registry validation, derived built-in names, and model guidance. Model bash uses the current snapshot collected by `ctx.bashEnv`. Implementations remove inherited managed keys, reject those names in ordinary `env`, then merge `dshEnv`, so an omitted current fact cannot fall back to stale ambient state. The model-facing tool exposes none of these as parameters. All three remain optional on the resolved spec; absent means no input/overlay. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [the session environment RFC](../../../docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md). diff --git a/packages/bash/bash/src/index.ts b/packages/bash/bash/src/index.ts index 6c9acedf20..207f475dcb 100644 --- a/packages/bash/bash/src/index.ts +++ b/packages/bash/bash/src/index.ts @@ -18,7 +18,7 @@ import { Context, Service } from 'cordis' import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' import type { BashExecRequest, BashExecSpec, BashRunResult, BashTask, BashTaskId, BashTaskListener, BashTaskRead, OwnerToken } from './types.ts' -export { BashTaskId, OwnerToken } from './types.ts' +export { BashTaskId, DSH_ENV_PREFIX, OwnerToken } from './types.ts' export { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from './session-mode.ts' export type { BashExecRequest, @@ -31,6 +31,7 @@ export type { BashTaskStatus, CollectedOutput, DshEnvironment, + DshEnvironmentKey, } from './types.ts' declare module 'cordis' { diff --git a/packages/bash/bash/src/types.ts b/packages/bash/bash/src/types.ts index ebc0d36898..479b968cfc 100644 --- a/packages/bash/bash/src/types.ts +++ b/packages/bash/bash/src/types.ts @@ -12,8 +12,14 @@ import type { SandboxEnforcement, SandboxMode } from '@deepseek-ai/dsh-sandbox' /** Identifies one background task within an executor (generated `bash-N`). */ export type BashTaskId = Branded<'BashTaskId'> +/** Namespace prefix reserved for DeepSeek Harness-managed child environment facts. */ +export const DSH_ENV_PREFIX = 'DSH_' as const + +/** One environment key inside the managed {@link DSH_ENV_PREFIX} namespace. */ +export type DshEnvironmentKey = `${typeof DSH_ENV_PREFIX}${string}` + /** Trusted DeepSeek Harness variables for one bash execution. */ -export type DshEnvironment = Readonly> +export type DshEnvironment = Readonly> /** * Brand a string as a {@link BashTaskId}. diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index 7ebf1621f3..08493d79c0 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -70,8 +70,8 @@ import type {} from '@deepseek-ai/dsh-system-prompt' // stays optional at runtime, same pattern as dsh-tools' ask routing). import type {} from '@deepseek-ai/dsh-user-approval' import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' -import { BashTaskId, OwnerToken, effectiveSandboxMode } from '@deepseek-ai/dsh-bash' -import type { BashRunResult, BashTask, CollectedOutput, DshEnvironment } from '@deepseek-ai/dsh-bash' +import { BashTaskId, DSH_ENV_PREFIX, OwnerToken, effectiveSandboxMode } from '@deepseek-ai/dsh-bash' +import type { BashRunResult, BashTask, CollectedOutput, DshEnvironment, DshEnvironmentKey } from '@deepseek-ai/dsh-bash' declare module 'cordis' { interface Context { @@ -108,13 +108,13 @@ export interface BashEnvContributor { /** Stable contributor name used in diagnostics and duplicate detection. */ name: string /** Complete set of `DSH_*` keys this contributor may return. */ - variables: Readonly> + variables: Readonly> /** * Resolve this contributor's available values for one tool execution. * @param execution - the bash tool execution and its optional calling agent. * @returns a partial map containing only keys declared in {@link variables}. */ - resolve(execution: ToolExecution): Readonly>> + resolve(execution: ToolExecution): Readonly>> } /** An enumerable declaration returned by {@link BashEnvRegistry.list}. */ @@ -122,15 +122,19 @@ export interface BashEnvVariableInfo extends BashEnvVariable { /** Contributor that owns the variable. */ contributor: string /** Declared `DSH_*` environment variable name. */ - key: `DSH_${string}` + key: DshEnvironmentKey } -const RESERVED_BASH_ENV_KEYS = new Set<`DSH_${string}`>([ - 'DSH_HOME', - 'DSH_SHELL', - 'DSH_SESSION_ID', +const DSH_HOME_KEY = `${DSH_ENV_PREFIX}HOME` as const +const DSH_SHELL_KEY = `${DSH_ENV_PREFIX}SHELL` as const +const DSH_SESSION_ID_KEY = `${DSH_ENV_PREFIX}SESSION_ID` as const +const DSH_SESSION_JSONL_KEY = `${DSH_ENV_PREFIX}SESSION_JSONL` as const +const RESERVED_BASH_ENV_KEYS = new Set([ + DSH_HOME_KEY, + DSH_SHELL_KEY, + DSH_SESSION_ID_KEY, ]) -const BASH_ENV_KEY = /^DSH_[A-Z][A-Z0-9_]*$/ +const BASH_ENV_KEY_SUFFIX = /^[A-Z][A-Z0-9_]*$/ /** * Registry (`ctx.bashEnv`) for trusted, per-execution `DSH_*` variables. @@ -142,7 +146,7 @@ const BASH_ENV_KEY = /^DSH_[A-Z][A-Z0-9_]*$/ */ export class BashEnvRegistry extends Service { private readonly contributors = new Map() - private readonly keyOwners = new Map<`DSH_${string}`, string>() + private readonly keyOwners = new Map() private readonly dshHome: string /** @@ -152,7 +156,7 @@ export class BashEnvRegistry extends Service { */ constructor(ctx: Context, config: Config = {}) { super(ctx, 'bashEnv') - this.dshHome = resolvePath(config.dshHome ?? process.env.DSH_HOME ?? join(homedir(), '.dsh')) + this.dshHome = resolvePath(config.dshHome ?? process.env[DSH_HOME_KEY] ?? join(homedir(), '.dsh')) } /** @@ -170,9 +174,10 @@ export class BashEnvRegistry extends Service { throw new Error(`bash env contributor "${contributor.name}" is already registered`) } - const variables = Object.entries(contributor.variables) as [`DSH_${string}`, BashEnvVariable][] + const variables = Object.entries(contributor.variables) as [DshEnvironmentKey, BashEnvVariable][] for (const [key, variable] of variables) { - if (!BASH_ENV_KEY.test(key)) { + if (!key.startsWith(DSH_ENV_PREFIX) + || !BASH_ENV_KEY_SUFFIX.test(key.slice(DSH_ENV_PREFIX.length))) { throw new Error(`bash env contributor "${contributor.name}" declared invalid key "${key}"`) } if (RESERVED_BASH_ENV_KEYS.has(key)) { @@ -203,18 +208,18 @@ export class BashEnvRegistry extends Service { * @returns an immutable environment overlay containing built-ins and current contributions. */ collect(execution: ToolExecution): DshEnvironment { - const values: Record<`DSH_${string}`, string> = { - DSH_HOME: this.dshHome, - DSH_SHELL: '1', + const values: Record = { + [DSH_HOME_KEY]: this.dshHome, + [DSH_SHELL_KEY]: '1', } if (execution.agent !== undefined) { - values.DSH_SESSION_ID = execution.agent.session.header.id + values[DSH_SESSION_ID_KEY] = execution.agent.session.header.id } for (const contributor of [...this.contributors.values()].sort((left, right) => left.name.localeCompare(right.name))) { const resolved = contributor.resolve(execution) for (const [rawKey, value] of Object.entries(resolved)) { - const key = rawKey as `DSH_${string}` + const key = rawKey as DshEnvironmentKey if (!Object.hasOwn(contributor.variables, key)) { throw new Error(`bash env contributor "${contributor.name}" returned undeclared key "${key}"`) } @@ -237,7 +242,7 @@ export class BashEnvRegistry extends Service { .flatMap(contributor => Object.entries(contributor.variables).map(([key, variable]) => ({ contributor: contributor.name, description: variable.description, - key: key as `DSH_${string}`, + key: key as DshEnvironmentKey, }))) .sort((left, right) => left.key.localeCompare(right.key)) } @@ -337,7 +342,7 @@ function bashDescription(escalationModes: readonly SandboxMode[]): string { const base = 'Execute a bash command (`bash -c`) and return its stdout/stderr. ' + 'Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — ' + 'pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. ' - + 'Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. ' + + `Current harness environment facts are exposed through managed \`$${DSH_ENV_PREFIX}*\` variables; inspect them when needed. ` + 'Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). ' + 'Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. ' + 'Set `run_in_background: true` for long-running commands: the call returns a task id immediately; ' @@ -579,7 +584,7 @@ export function apply(ctx: Context, config: Config = {}): void { bashEnv.register({ name: 'session-persistence', variables: { - DSH_SESSION_JSONL: { + [DSH_SESSION_JSONL_KEY]: { description: 'Absolute target path of the current session JSONL when the active persistence backend provides one.', }, }, @@ -587,7 +592,7 @@ export function apply(ctx: Context, config: Config = {}): void { const agent = execution.agent if (agent === undefined) return {} const location = ctx.get('sessionPersistence')?.locate(agent.session.header) - return location?.kind === 'jsonl' ? { DSH_SESSION_JSONL: location.path } : {} + return location?.kind === 'jsonl' ? { [DSH_SESSION_JSONL_KEY]: location.path } : {} }, }) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 8323d13248..dbdfb880da 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -535,7 +535,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'BashEnvContributor', - declaration: 'export interface BashEnvContributor {\n name: string;\n variables: Readonly>;\n resolve(execution: ToolExecution): Readonly>>;\n}', + declaration: 'export interface BashEnvContributor {\n name: string;\n variables: Readonly>;\n resolve(execution: ToolExecution): Readonly>>;\n}', }, { name: 'BashEnvVariable', @@ -543,7 +543,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'BashEnvVariableInfo', - declaration: 'export interface BashEnvVariableInfo extends BashEnvVariable {\n contributor: string;\n key: `DSH_${string}`;\n}', + declaration: 'export interface BashEnvVariableInfo extends BashEnvVariable {\n contributor: string;\n key: DshEnvironmentKey;\n}', }, { name: 'BashExecRequest', @@ -659,7 +659,11 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'DshEnvironment', - declaration: 'export type DshEnvironment = Readonly>;', + declaration: 'export type DshEnvironment = Readonly>;', + }, + { + name: 'DshEnvironmentKey', + declaration: 'export type DshEnvironmentKey = `${typeof DSH_ENV_PREFIX}${string}`;', }, { name: 'FileDiff', From 1aadce9fe7eaa24f66a210e772acd701ed06fc20 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sun, 12 Jul 2026 16:30:01 +0800 Subject: [PATCH 011/359] refactor(core): centralize DSH home resolution --- docs/config-catalog.md | 3 +- docs/cordis-catalog/services.md | 2 +- docs/module-graph.md | 11 +++++-- ...agent-session-identity-and-log-location.md | 4 +-- knip.json | 5 ++++ packages/README.md | 2 +- packages/bash/tool-bash/README.md | 2 +- packages/bash/tool-bash/package.json | 2 ++ packages/bash/tool-bash/src/index.ts | 11 ++++--- packages/bash/tool-bash/tsconfig.json | 3 ++ packages/core/agent-core/README.md | 2 +- packages/core/agent-core/package.json | 2 ++ packages/core/agent-core/src/index.ts | 14 ++++----- packages/core/agent-core/tsconfig.json | 3 ++ packages/skill/skill-local/README.md | 2 +- packages/skill/skill-local/package.json | 2 ++ packages/skill/skill-local/src/index.ts | 3 +- packages/skill/skill-local/tsconfig.json | 1 + packages/util/README.md | 3 ++ packages/util/home/README.md | 9 ++++++ packages/util/home/package.json | 30 +++++++++++++++++++ packages/util/home/src/index.ts | 23 ++++++++++++++ packages/util/home/tests/home.spec.ts | 26 ++++++++++++++++ packages/util/home/tsconfig.json | 9 ++++++ pnpm-lock.yaml | 15 ++++++++++ tsconfig.build.json | 1 + tsconfig.json | 1 + 27 files changed, 164 insertions(+), 27 deletions(-) create mode 100644 packages/util/home/README.md create mode 100644 packages/util/home/package.json create mode 100644 packages/util/home/src/index.ts create mode 100644 packages/util/home/tests/home.spec.ts create mode 100644 packages/util/home/tsconfig.json diff --git a/docs/config-catalog.md b/docs/config-catalog.md index b297595592..55b0551ac2 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -606,7 +606,7 @@ export interface Config { } ``` -Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-local/src/index.ts) +Source: [`packages/skill/skill-local/src/index.ts:40`](../packages/skill/skill-local/src/index.ts) ## `@deepseek-ai/dsh-stdio-agent` @@ -1184,6 +1184,7 @@ Imported as libraries by other packages; a `cordis.yml` cannot load them. - `@deepseek-ai/dsh-acp-snapshot` ([`packages/support/acp-snapshot/src/index.ts`](../packages/support/acp-snapshot/src/index.ts)) - `@deepseek-ai/dsh-app-boot` ([`packages/ui/app-boot/src/index.ts`](../packages/ui/app-boot/src/index.ts)) - `@deepseek-ai/dsh-brand` ([`packages/util/brand/src/index.ts`](../packages/util/brand/src/index.ts)) +- `@deepseek-ai/dsh-home` ([`packages/util/home/src/index.ts`](../packages/util/home/src/index.ts)) - `@deepseek-ai/dsh-hook-protocol` ([`packages/hooks/hook-protocol/src/index.ts`](../packages/hooks/hook-protocol/src/index.ts)) - `@deepseek-ai/dsh-subagent-inprocess` ([`packages/subagent/subagent-inprocess/src/index.ts`](../packages/subagent/subagent-inprocess/src/index.ts)) - `@deepseek-ai/dsh-subagent-subprocess` ([`packages/subagent/subagent-subprocess/src/index.ts`](../packages/subagent/subagent-subprocess/src/index.ts)) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index d25379adad..9094e3a351 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -93,7 +93,7 @@ list(): BashEnvVariableInfo[] Types: [ToolExecution](../core-data-structures/tools.md) -Source: [`packages/bash/tool-bash/src/index.ts:147`](../../packages/bash/tool-bash/src/index.ts) +Source: [`packages/bash/tool-bash/src/index.ts:146`](../../packages/bash/tool-bash/src/index.ts) ## `ctx.codeRuntime` — `CodeRuntime` (abstract seam) diff --git a/docs/module-graph.md b/docs/module-graph.md index 56c3a64f95..fe606ad78a 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -9,6 +9,7 @@ Inter-package dependencies among the `@deepseek-ai/dsh-*` harness packages, deri flowchart TD subgraph group_util["packages/util"] pkg_brand["brand"] + pkg_home["home"] pkg_timeout["timeout"] end subgraph group_llm["packages/llm"] @@ -133,6 +134,7 @@ flowchart TD pkg_fs_local --> pkg_fs pkg_fs_policy --> pkg_fs pkg_skill_local --> pkg_fs + pkg_skill_local --> pkg_home pkg_skill_local --> pkg_skill pkg_compact --> pkg_llm pkg_compact --> pkg_session @@ -188,6 +190,7 @@ flowchart TD pkg_agent_loop --> pkg_tools pkg_tool_bash --> pkg_agent pkg_tool_bash --> pkg_bash + pkg_tool_bash --> pkg_home pkg_tool_bash --> pkg_llm pkg_tool_bash --> pkg_sandbox pkg_tool_bash --> pkg_session_persistence @@ -244,6 +247,7 @@ flowchart TD pkg_tool_workflow --> pkg_workflow pkg_agent_core --> pkg_agent pkg_agent_core --> pkg_agent_loop + pkg_agent_core --> pkg_home pkg_agent_core --> pkg_invariants pkg_agent_core --> pkg_llm pkg_agent_core --> pkg_session @@ -309,6 +313,7 @@ flowchart TD | Package | Group | Depends on | | --- | --- | --- | | [`brand`](../packages/util/brand) | `util` | — | +| [`home`](../packages/util/home) | `util` | — | | [`timeout`](../packages/util/timeout) | `util` | — | | [`skill`](../packages/skill/skill) | `skill` | — | | [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | `subagent` | — | @@ -328,7 +333,7 @@ flowchart TD | [`bash`](../packages/bash/bash) | `bash` | [`brand`](../packages/util/brand), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session) | | [`fs-local`](../packages/fs/fs-local) | `fs` | [`fs`](../packages/fs/fs) | | [`fs-policy`](../packages/fs/fs-policy) | `fs` | [`fs`](../packages/fs/fs) | -| [`skill-local`](../packages/skill/skill-local) | `skill` | [`fs`](../packages/fs/fs), [`skill`](../packages/skill/skill) | +| [`skill-local`](../packages/skill/skill-local) | `skill` | [`fs`](../packages/fs/fs), [`home`](../packages/util/home), [`skill`](../packages/skill/skill) | | [`compact`](../packages/compact/compact) | `compact` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`web-fetch-local`](../packages/web/web-fetch-local) | `web` | [`timeout`](../packages/util/timeout), [`web`](../packages/web/web) | | [`web-search-deepseek`](../packages/web/web-search-deepseek) | `web` | [`web`](../packages/web/web) | @@ -349,7 +354,7 @@ flowchart TD | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) | | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) | | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | -| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | +| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`home`](../packages/util/home), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | | [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`tools`](../packages/core/tools) | @@ -362,7 +367,7 @@ flowchart TD | [`tool-ask-user`](../packages/ui/tool-ask-user) | `ui` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) | | [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | -| [`agent-core`](../packages/core/agent-core) | `core` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tools`](../packages/core/tools) | +| [`agent-core`](../packages/core/agent-core) | `core` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`home`](../packages/util/home), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tools`](../packages/core/tools) | | [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | diff --git a/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md b/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md index 9dcd609b50..9127d70207 100644 --- a/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md +++ b/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md @@ -31,7 +31,7 @@ The model-facing bash package owns a `ctx.bashEnv` registry. A contributor decla The registry rebuilds a trusted overlay for every foreground and background bash `ToolExecution`: -- `DSH_HOME` is always the absolute configured Harness home, resolved from tool-bash/agent-core `dshHome`, then ambient `$DSH_HOME`, then `~/.dsh`. +- `DSH_HOME` is always the absolute configured Harness home. The standalone [`@deepseek-ai/dsh-home`](../../../../packages/util/home/README.md) utility owns its precedence: explicit `dshHome`, then ambient `$DSH_HOME`, then `~/.dsh`. - `DSH_SHELL=1` is always present and identifies a model bash child managed by DeepSeek Harness. - `DSH_SESSION_ID` is present when the execution has an agent and equals `agent.session.header.id`. - The built-in persistence translator contributes `DSH_SESSION_JSONL` only when `ctx.sessionPersistence.locate(header)` returns `kind: 'jsonl'`. @@ -54,7 +54,7 @@ A fresh session receives its id before the first turn, so its first bash call ca Resume reuses the loaded header and therefore the same id and location. Fork and spawn create new session ids and locations. Parent and child calls resolve from their own `ToolExecution.agent`; each command receives an immutable snapshot even when calls overlap. A persistence service replacement affects later collections because the translator queries `ctx.get('sessionPersistence')` at execution time; the registry itself is effect-scoped and HMR-safe. -`dshHome` is session-independent deployment context. Agent-core routes one value to both tool-bash and local skill discovery; if top-level `dshHome` and `skills.local.dshHome` are both supplied and resolve differently, composition fails instead of exposing contradictory homes. Persistence may change independently without freezing its facts into the session prefix. +`dshHome` is session-independent deployment context. Agent-core resolves one value through `@deepseek-ai/dsh-home` and routes it to both tool-bash and local skill discovery; standalone consumers call the same resolver. If top-level `dshHome` and `skills.local.dshHome` are both supplied and resolve differently, composition fails instead of exposing contradictory homes. Persistence may change independently without freezing its facts into the session prefix. ## Testing diff --git a/knip.json b/knip.json index cf43b90e34..929b590874 100644 --- a/knip.json +++ b/knip.json @@ -31,6 +31,11 @@ "project": ["src/**/*.ts"], "ignoreDependencies": ["cordis"] }, + "packages/util/home": { + "entry": ["tests/**/*.spec.ts"], + "project": ["src/**/*.ts", "tests/**/*.ts"], + "ignoreDependencies": ["cordis"] + }, "packages/util/timeout": { "entry": ["tests/**/*.spec.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"], diff --git a/packages/README.md b/packages/README.md index 35c4652a1f..5c6fedd7f4 100644 --- a/packages/README.md +++ b/packages/README.md @@ -27,7 +27,7 @@ Packages are grouped by modular role at `packages///`. The group dir | [`session-persistence/`](session-persistence/README.md) | Persistence capability family: the seam + JSONL/SQLite backends | Product — stable surface | | [`ui/`](ui/README.md) | Editor/client integration surfaces: ACP bridge, app packages, user-approval and user-interaction seams, ask-user tool | Product — stable surface | | [`support/`](support/README.md) | Dev/test/example infrastructure (invariants, replay adapter, subagent mock) | Support — lower compatibility expectations | -| [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (the `Branded` primitive) | Support — small, stable, harness-dep-free | +| [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (branding, Harness home resolution, timeout classification) | Support — small, stable, harness-dep-free | The split is the point: a package's group says whether it is part of the product API or support/test/example infrastructure, so release and removal decisions do not treat every package as an equal public contract. New packages join an existing group; adding a new top-level group is a deliberate act (extend the group READMEs and this table). diff --git a/packages/bash/tool-bash/README.md b/packages/bash/tool-bash/README.md index ccbb1c0033..d728788da8 100644 --- a/packages/bash/tool-bash/README.md +++ b/packages/bash/tool-bash/README.md @@ -24,7 +24,7 @@ The plugin also contributes the `tool:bash` prompt section (order 105) — the c ### Managed shell environment -Every foreground and background model bash call receives a newly collected trusted `DSH_*` environment. `DSH_HOME` is the absolute Harness home (`dshHome` config, then ambient `$DSH_HOME`, then `~/.dsh`) and `DSH_SHELL=1` identifies the managed child. Agent calls additionally receive `DSH_SESSION_ID=agent.session.header.id`; when the active persistence seam locates a JSONL artifact they also receive `DSH_SESSION_JSONL=`. The JSONL path is a location hint: it may not exist before the first flush or contain the current buffered turn, and it is not an authorization credential. +Every foreground and background model bash call receives a newly collected trusted `DSH_*` environment. `DSH_HOME` is the absolute Harness home resolved by [`@deepseek-ai/dsh-home`](../../util/home/README.md) (`dshHome` config, then ambient `$DSH_HOME`, then `~/.dsh`) and `DSH_SHELL=1` identifies the managed child. Agent calls additionally receive `DSH_SESSION_ID=agent.session.header.id`; when the active persistence seam locates a JSONL artifact they also receive `DSH_SESSION_JSONL=`. The JSONL path is a location hint: it may not exist before the first flush or contain the current buffered turn, and it is not an authorization credential. `ctx.bashEnv` owns collection. Other plugins can register an effect-scoped contributor with a stable name, declared keys/descriptions, and `resolve(execution: ToolExecution)`; duplicate ownership and undeclared runtime keys fail loudly, while `list()` enumerates declarations without executing providers. Harness built-ins reserve `DSH_HOME`, `DSH_SHELL`, and `DSH_SESSION_ID`; tool-bash's persistence translator owns `DSH_SESSION_JSONL` by reading the backend-neutral `sessionPersistence.locate()` seam. diff --git a/packages/bash/tool-bash/package.json b/packages/bash/tool-bash/package.json index 003aadad74..e41f08f56d 100644 --- a/packages/bash/tool-bash/package.json +++ b/packages/bash/tool-bash/package.json @@ -25,6 +25,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-user-approval": "^0.0.1", "@deepseek-ai/dsh-bash": "^0.0.1", + "@deepseek-ai/dsh-home": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-session-persistence": "^0.0.1", "@deepseek-ai/dsh-sandbox": "^0.0.1", @@ -42,6 +43,7 @@ "@deepseek-ai/dsh-bash": "workspace:^", "@deepseek-ai/dsh-bash-local": "workspace:^", "@deepseek-ai/dsh-bash-sandbox": "workspace:^", + "@deepseek-ai/dsh-home": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-sandbox": "workspace:^", "@deepseek-ai/dsh-sandbox-local": "workspace:^", diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index 08493d79c0..712b381930 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -57,8 +57,7 @@ import { Service, type Context } from 'cordis' import z from 'schemastery' -import { homedir } from 'node:os' -import { isAbsolute, join, resolve as resolvePath } from 'node:path' +import { isAbsolute, resolve as resolvePath } from 'node:path' import { defineTool } from '@deepseek-ai/dsh-tools' import type { GenericCallView, TerminalCallView, ToolExecution, ToolResult, ToolResultView } from '@deepseek-ai/dsh-tools' import type { Agent } from '@deepseek-ai/dsh-agent' @@ -72,6 +71,7 @@ import type {} from '@deepseek-ai/dsh-user-approval' import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' import { BashTaskId, DSH_ENV_PREFIX, OwnerToken, effectiveSandboxMode } from '@deepseek-ai/dsh-bash' import type { BashRunResult, BashTask, CollectedOutput, DshEnvironment, DshEnvironmentKey } from '@deepseek-ai/dsh-bash' +import { DSH_HOME_ENV, resolveDshHome } from '@deepseek-ai/dsh-home' declare module 'cordis' { interface Context { @@ -125,12 +125,11 @@ export interface BashEnvVariableInfo extends BashEnvVariable { key: DshEnvironmentKey } -const DSH_HOME_KEY = `${DSH_ENV_PREFIX}HOME` as const const DSH_SHELL_KEY = `${DSH_ENV_PREFIX}SHELL` as const const DSH_SESSION_ID_KEY = `${DSH_ENV_PREFIX}SESSION_ID` as const const DSH_SESSION_JSONL_KEY = `${DSH_ENV_PREFIX}SESSION_JSONL` as const const RESERVED_BASH_ENV_KEYS = new Set([ - DSH_HOME_KEY, + DSH_HOME_ENV, DSH_SHELL_KEY, DSH_SESSION_ID_KEY, ]) @@ -156,7 +155,7 @@ export class BashEnvRegistry extends Service { */ constructor(ctx: Context, config: Config = {}) { super(ctx, 'bashEnv') - this.dshHome = resolvePath(config.dshHome ?? process.env[DSH_HOME_KEY] ?? join(homedir(), '.dsh')) + this.dshHome = resolveDshHome(config.dshHome) } /** @@ -209,7 +208,7 @@ export class BashEnvRegistry extends Service { */ collect(execution: ToolExecution): DshEnvironment { const values: Record = { - [DSH_HOME_KEY]: this.dshHome, + [DSH_HOME_ENV]: this.dshHome, [DSH_SHELL_KEY]: '1', } if (execution.agent !== undefined) { diff --git a/packages/bash/tool-bash/tsconfig.json b/packages/bash/tool-bash/tsconfig.json index d3bd550386..5f8f4752b5 100644 --- a/packages/bash/tool-bash/tsconfig.json +++ b/packages/bash/tool-bash/tsconfig.json @@ -29,6 +29,9 @@ { "path": "../../bash/bash" }, + { + "path": "../../util/home" + }, { "path": "../../core/system-prompt" }, diff --git a/packages/core/agent-core/README.md b/packages/core/agent-core/README.md index ad63fdc5c0..233a126561 100644 --- a/packages/core/agent-core/README.md +++ b/packages/core/agent-core/README.md @@ -43,7 +43,7 @@ import type { Config } from '@deepseek-ai/dsh-agent-core' // so validation and defaulting can never drift from the owners. ``` -The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry; `dshHome` to tool-bash's managed environment and the local skill provider; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. An absent top-level `dshHome` adopts `skills.local.dshHome`; supplying both with different resolved paths fails loudly. +The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. It resolves `dshHome` once through [`@deepseek-ai/dsh-home`](../../util/home/README.md) and forwards that absolute value to tool-bash's managed environment and local skill discovery. An absent top-level `dshHome` adopts `skills.local.dshHome`; supplying both with different resolved paths fails loudly. ## Why a code bundle, not a shared YAML include diff --git a/packages/core/agent-core/package.json b/packages/core/agent-core/package.json index 039a6ac505..749de25be9 100644 --- a/packages/core/agent-core/package.json +++ b/packages/core/agent-core/package.json @@ -26,6 +26,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-agent-loop": "^0.0.1", "@deepseek-ai/dsh-invariants": "^0.0.1", + "@deepseek-ai/dsh-home": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-skill": "^0.0.1", @@ -41,6 +42,7 @@ "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", + "@deepseek-ai/dsh-home": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-skill": "workspace:^", diff --git a/packages/core/agent-core/src/index.ts b/packages/core/agent-core/src/index.ts index ba4904cbef..2c0c92a4bc 100644 --- a/packages/core/agent-core/src/index.ts +++ b/packages/core/agent-core/src/index.ts @@ -46,7 +46,6 @@ */ import type { Context } from 'cordis' -import { resolve as resolvePath } from 'node:path' import Timer from '@cordisjs/plugin-timer' import z from 'schemastery' import LlmService from '@deepseek-ai/dsh-llm' @@ -60,6 +59,7 @@ import * as invariants from '@deepseek-ai/dsh-invariants' import * as toolBash from '@deepseek-ai/dsh-tool-bash' import * as toolSkill from '@deepseek-ai/dsh-tool-skill' import AgentLoop, { type Config as AgentLoopConfig } from '@deepseek-ai/dsh-agent-loop' +import { resolveDshHome } from '@deepseek-ai/dsh-home' export const name = 'agent-core' @@ -127,10 +127,10 @@ export const Config = z.intersect([ export function apply(ctx: Context, config: Config): void { const nestedDshHome = config.skills?.local?.dshHome if (config.dshHome !== undefined && nestedDshHome !== undefined - && resolvePath(config.dshHome) !== resolvePath(nestedDshHome)) { + && resolveDshHome(config.dshHome) !== resolveDshHome(nestedDshHome)) { throw new Error('agent-core: dshHome and skills.local.dshHome must resolve to the same directory') } - const dshHome = config.dshHome ?? nestedDshHome + const dshHome = resolveDshHome(config.dshHome ?? nestedDshHome) ctx.plugin(Timer) ctx.plugin(LlmService) @@ -147,14 +147,10 @@ export function apply(ctx: Context, config: Config): void { }) ctx.plugin(ToolRegistry, config.tools ?? {}) ctx.plugin(SkillService, config.skills?.registry ?? {}) - ctx.plugin(SkillLocal, Object.assign( - {}, - config.skills?.local, - dshHome === undefined ? {} : { dshHome }, - )) + ctx.plugin(SkillLocal, Object.assign({}, config.skills?.local, { dshHome })) ctx.plugin(AgentRegistry) ctx.plugin(invariants) - ctx.plugin(toolBash, dshHome === undefined ? {} : { dshHome }) + ctx.plugin(toolBash, { dshHome }) ctx.plugin(toolSkill, config.skills?.tool ?? {}) ctx.plugin(AgentLoop, { agents: config.agents ?? [] }) } diff --git a/packages/core/agent-core/tsconfig.json b/packages/core/agent-core/tsconfig.json index 4fd0a81e97..974c2aecc0 100644 --- a/packages/core/agent-core/tsconfig.json +++ b/packages/core/agent-core/tsconfig.json @@ -50,6 +50,9 @@ { "path": "../../support/invariants" }, + { + "path": "../../util/home" + }, { "path": "../../bash/tool-bash" } diff --git a/packages/skill/skill-local/README.md b/packages/skill/skill-local/README.md index c885416ff5..4214c55505 100644 --- a/packages/skill/skill-local/README.md +++ b/packages/skill/skill-local/README.md @@ -12,7 +12,7 @@ Requires `ctx.skills` (`inject: ['skills']`). | Field | Default | Meaning | |---|---|---| -| `dshHome` | `$DSH_HOME` or `~/.dsh` | DeepSeek Harness config root; scans `skills` under this directory. | +| `dshHome` | `$DSH_HOME` or `~/.dsh` | DeepSeek Harness config root resolved by [`@deepseek-ai/dsh-home`](../../util/home/README.md); scans `skills` under this directory. | | `agentsHome` | `$DSH_AGENTS_HOME` or `~/.agents` | Shared agent config root scanned for compatible skills. | | `customSkillDirs` | `[]` | Additional local skill roots scanned after project roots and before user roots. | diff --git a/packages/skill/skill-local/package.json b/packages/skill/skill-local/package.json index dcacc5960a..1e19cf891a 100644 --- a/packages/skill/skill-local/package.json +++ b/packages/skill/skill-local/package.json @@ -23,6 +23,7 @@ "license": "BSD-3-Clause", "peerDependencies": { "@deepseek-ai/dsh-fs": "^0.0.1", + "@deepseek-ai/dsh-home": "^0.0.1", "@deepseek-ai/dsh-skill": "^0.0.1", "cordis": "^4.0.0-rc.6" }, @@ -32,6 +33,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-fs": "workspace:^", + "@deepseek-ai/dsh-home": "workspace:^", "@deepseek-ai/dsh-skill": "workspace:^", "cordis": "^4.0.0-rc.6" } diff --git a/packages/skill/skill-local/src/index.ts b/packages/skill/skill-local/src/index.ts index 19a15f1de8..ee109fbb16 100644 --- a/packages/skill/skill-local/src/index.ts +++ b/packages/skill/skill-local/src/index.ts @@ -17,6 +17,7 @@ import z from 'schemastery' import type Schema from 'schemastery' import { parse as parseYaml } from 'yaml' import type { FileSystem, FsDirEntry, FsTarget } from '@deepseek-ai/dsh-fs' +import { resolveDshHome } from '@deepseek-ai/dsh-home' import { isSkillName, type SkillCandidate, @@ -92,7 +93,7 @@ export class LocalSkillProvider implements SkillProvider { private readonly customSkillDirs: string[] constructor(private readonly ctx: Context, config: Config = {}) { - this.dshHome = resolve(config.dshHome ?? process.env.DSH_HOME ?? join(homedir(), '.dsh')) + this.dshHome = resolveDshHome(config.dshHome) this.agentsHome = resolve(config.agentsHome ?? process.env.DSH_AGENTS_HOME ?? join(homedir(), '.agents')) this.customSkillDirs = (config.customSkillDirs ?? []).map(root => resolve(root)) } diff --git a/packages/skill/skill-local/tsconfig.json b/packages/skill/skill-local/tsconfig.json index 018f0a4a50..f51147abce 100644 --- a/packages/skill/skill-local/tsconfig.json +++ b/packages/skill/skill-local/tsconfig.json @@ -9,6 +9,7 @@ { "path": "../../../vendor/cosmokit" }, { "path": "../../../vendor/cordis" }, { "path": "../../../vendor/schemastery" }, + { "path": "../../util/home" }, { "path": "../../fs/fs" }, { "path": "../skill" } ] diff --git a/packages/util/README.md b/packages/util/README.md index 45afe7b0a9..256cc36e67 100644 --- a/packages/util/README.md +++ b/packages/util/README.md @@ -5,8 +5,11 @@ Zero-dependency primitives shared across the other groups. A package lands here | Package | Role | |---|---| | `brand/` | The type-only `Branded` nominal-typing primitive (no runtime code, no harness deps) | +| `home/` | Canonical `DSH_HOME` resolution from explicit config, environment, or `~/.dsh` (no harness deps) | | `timeout/` | The timing/classification half of a timeout — `clampTimeout`/`deadline`/`timeoutOf`/`TimeoutReason` (pure functions, no harness deps); termination stays in each capability | `dsh-brand` is the canonical case: it owns ONLY the `Branded` helper, so a capability package can brand the ids it owns (`dsh-bash`'s `BashTaskId`/`OwnerToken`, `dsh-session`'s `SessionId`, …) by depending on `dsh-brand` alone, without pulling in an unrelated package just to reach `Branded`. +`dsh-home` gives every package the same configurable Harness home without assigning that cross-cutting fact to bash, skills, or a composition bundle. It resolves an explicit value before `$DSH_HOME`, falls back to `~/.dsh`, and returns an absolute path without caching, creating, or mutating anything. + `dsh-timeout` follows the same shape for the timeout family: `dsh-bash` and `dsh-web-fetch-local` each fuse a caller's cancellation with a deadline and later classify "timed out" vs "cancelled" by depending on `dsh-timeout` alone. It deliberately owns only the timing/classification half — the *termination* (SIGKILL a process group, tear down a fetch socket) stays in each capability, because no shared layer can own every capability's kill (see [the timeout-library RFC](../../docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md)). diff --git a/packages/util/home/README.md b/packages/util/home/README.md new file mode 100644 index 0000000000..14d8fec1f8 --- /dev/null +++ b/packages/util/home/README.md @@ -0,0 +1,9 @@ +# @deepseek-ai/dsh-home + +`@deepseek-ai/dsh-home` is the single owner of DeepSeek Harness home-directory resolution. `resolveDshHome(configured?)` returns an absolute path using this precedence: + +1. The explicit `configured` path. +2. The `DSH_HOME` environment variable. +3. The `.dsh` directory under the current user's home directory. + +The resolver reads its inputs at call time. It does not cache a result, create the directory, or mutate `process.env`; consumers keep ownership of their own configuration fields and pass the configured value when resolving the shared home. diff --git a/packages/util/home/package.json b/packages/util/home/package.json new file mode 100644 index 0000000000..efeaf4832c --- /dev/null +++ b/packages/util/home/package.json @@ -0,0 +1,30 @@ +{ + "name": "@deepseek-ai/dsh-home", + "description": "Canonical DeepSeek Harness home-directory resolver", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "cordis": "^4.0.0-rc.6" + }, + "devDependencies": { + "cordis": "^4.0.0-rc.6" + } +} diff --git a/packages/util/home/src/index.ts b/packages/util/home/src/index.ts new file mode 100644 index 0000000000..4e3d56b54b --- /dev/null +++ b/packages/util/home/src/index.ts @@ -0,0 +1,23 @@ +/** + * Canonical DeepSeek Harness home-directory resolution. + * + * @module @deepseek-ai/dsh-home + */ + +import { homedir } from 'node:os' +import { join, resolve } from 'node:path' + +const DEFAULT_DSH_HOME_DIRNAME = '.dsh' + +/** Environment variable that overrides the default Harness home directory. */ +export const DSH_HOME_ENV = 'DSH_HOME' as const + +/** + * Resolve the DeepSeek Harness home directory without caching or mutating the environment. + * + * @param configured - Optional configured path, which takes precedence over the environment. + * @returns The absolute configured path, `$DSH_HOME`, or `~/.dsh`, in that order. + */ +export function resolveDshHome(configured?: string): string { + return resolve(configured ?? process.env[DSH_HOME_ENV] ?? join(homedir(), DEFAULT_DSH_HOME_DIRNAME)) +} diff --git a/packages/util/home/tests/home.spec.ts b/packages/util/home/tests/home.spec.ts new file mode 100644 index 0000000000..3ebde50bee --- /dev/null +++ b/packages/util/home/tests/home.spec.ts @@ -0,0 +1,26 @@ +import { homedir } from 'node:os' +import { join, resolve } from 'node:path' +import { afterEach, describe, expect, it, vi } from 'vitest' +import { DSH_HOME_ENV, resolveDshHome } from '@deepseek-ai/dsh-home' + +afterEach(() => vi.unstubAllEnvs()) + +describe('resolveDshHome', () => { + it('prefers an explicit configured path and resolves it absolutely', () => { + vi.stubEnv(DSH_HOME_ENV, './environment-home') + + expect(resolveDshHome('./configured-home')).toBe(resolve('./configured-home')) + }) + + it('uses DSH_HOME when no configured path is supplied', () => { + vi.stubEnv(DSH_HOME_ENV, './environment-home') + + expect(resolveDshHome()).toBe(resolve('./environment-home')) + }) + + it('defaults to the .dsh directory under the user home', () => { + vi.stubEnv(DSH_HOME_ENV, undefined) + + expect(resolveDshHome()).toBe(join(homedir(), '.dsh')) + }) +}) diff --git a/packages/util/home/tsconfig.json b/packages/util/home/tsconfig.json new file mode 100644 index 0000000000..9770ef25d6 --- /dev/null +++ b/packages/util/home/tsconfig.json @@ -0,0 +1,9 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": ["src"], + "references": [] +} diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 688c6b1f0c..0e7451343c 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -152,6 +152,9 @@ importers: '@deepseek-ai/dsh-bash-sandbox': specifier: workspace:^ version: link:../bash-sandbox + '@deepseek-ai/dsh-home': + specifier: workspace:^ + version: link:../../util/home '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm @@ -311,6 +314,9 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../agent-loop + '@deepseek-ai/dsh-home': + specifier: workspace:^ + version: link:../../util/home '@deepseek-ai/dsh-invariants': specifier: workspace:^ version: link:../../support/invariants @@ -773,6 +779,9 @@ importers: '@deepseek-ai/dsh-fs': specifier: workspace:^ version: link:../../fs/fs + '@deepseek-ai/dsh-home': + specifier: workspace:^ + version: link:../../util/home '@deepseek-ai/dsh-skill': specifier: workspace:^ version: link:../skill @@ -1350,6 +1359,12 @@ importers: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/util/home: + devDependencies: + cordis: + specifier: ^4.0.0-rc.6 + version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/util/timeout: devDependencies: cordis: diff --git a/tsconfig.build.json b/tsconfig.build.json index 8b2967b2bf..caf749cd4b 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -11,6 +11,7 @@ { "path": "./vendor/hmr" }, { "path": "./vendor/logger-console" }, { "path": "./packages/util/brand" }, + { "path": "./packages/util/home" }, { "path": "./packages/util/timeout" }, { "path": "./packages/llm/llm" }, { "path": "./packages/core/session" }, diff --git a/tsconfig.json b/tsconfig.json index 70780e1c17..808d07a2e1 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -22,6 +22,7 @@ { "path": "./vendor/hmr" }, { "path": "./vendor/logger-console" }, { "path": "./packages/util/brand" }, + { "path": "./packages/util/home" }, { "path": "./packages/util/timeout" }, { "path": "./packages/llm/llm" }, { "path": "./packages/core/session" }, From d4b52270717d8db207e0fac694a3964bf6d66916 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sun, 12 Jul 2026 17:03:11 +0800 Subject: [PATCH 012/359] fix(bash): validate managed env namespace --- ...7-10-agent-session-identity-and-log-location.md | 2 +- packages/bash/bash-local/README.md | 2 +- packages/bash/bash-local/src/run.ts | 14 ++++++++++---- packages/bash/bash-local/tests/run.spec.ts | 7 +++++++ packages/bash/bash/src/types.ts | 5 +++-- 5 files changed, 22 insertions(+), 8 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md b/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md index 9127d70207..118009dedb 100644 --- a/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md +++ b/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md @@ -38,7 +38,7 @@ The registry rebuilds a trusted overlay for every foreground and background bash Session persistence remains the fact owner: JSONL does not depend on tool-bash or register shell variables itself, and hooks continue to consume `locate()` directly. Tool-bash is the translation layer from the persistence fact into a shell convention. Other plugins that need shell-visible facts depend on the registry and register their own keys; they do not modify `process.env`. -The bash seam exports `DSH_ENV_PREFIX` as the single namespace source and derives `DshEnvironmentKey` from its `typeof`. Tool-bash derives built-in names and model guidance from that constant, while executors use it for filtering and ordinary-env rejection. The seam carries the managed overlay separately as `BashExecRequest.dshEnv` / `BashExecSpec.dshEnv`. Ordinary `env` remains the general in-process plugin surface used by hooks, but cannot contain managed keys; the local executor rejects that wrong channel, removes every inherited ambient managed key, applies its ordinary scrub/terminal environment/explicit `env`, and finally merges the trusted `dshEnv` snapshot. This guarantees that a missing value means absent now rather than inherited from an outer or previous harness. The model-facing tool still ignores model-supplied `env`/`stdin` arguments. +The bash seam exports `DSH_ENV_PREFIX` as the single namespace source and derives `DshEnvironmentKey` from its `typeof`. Tool-bash derives built-in names and model guidance from that constant, while executors use it for filtering and channel validation. The seam carries the managed overlay separately as `BashExecRequest.dshEnv` / `BashExecSpec.dshEnv`. Ordinary `env` remains the general in-process plugin surface used by hooks, but cannot contain managed keys; symmetrically, `dshEnv` cannot contain ordinary keys. The local executor rejects either wrong channel before spawn, removes every inherited ambient managed key, applies its ordinary scrub/terminal environment/explicit `env`, and finally merges the trusted `dshEnv` snapshot. This guarantees that a missing value means absent now rather than inherited from an outer or previous harness. The model-facing tool still ignores model-supplied `env`/`stdin` arguments. The bash tool description teaches only the durable convention: current harness environment facts are available through managed `$DSH_*` variables and may be inspected when needed. It does not enumerate persistence-specific keys or add a permanent system-prompt section. Tool schemas are already logged in request headers and tool output is logged as `tool/result`, so no new session event is required. diff --git a/packages/bash/bash-local/README.md b/packages/bash/bash-local/README.md index 9a00dc4a9b..2efc76d77d 100644 --- a/packages/bash/bash-local/README.md +++ b/packages/bash/bash-local/README.md @@ -22,7 +22,7 @@ Design surveyed against the bash tools of Claude Code, OpenCode, Codex, and pi; - **Spawn per call, no shell state** — every call is a fresh non-login `bash -c` (deterministic; no rc files). All four surveyed tools spawn per call. `XXX(stateful-shell)` in `src/run.ts` records the two proven stateful designs (Claude Code's cwd-only persistence; Codex's PTY exec sessions) for when real workflows demand them. - **Process-group kills with escalation** — children are spawned `detached` (own process group); kills send SIGTERM to the group, then SIGKILL after the `graceMs` grace (default 3s — OpenCode's escalation; pipelines and subshells die with the parent). ESRCH is tolerated; daemons that re-parent away from the group can still survive — same caveat as the surveyed tools. - **Tail-keep truncation + spill files** — output beyond `maxOutputBytes` keeps the in-memory TAIL (errors/results cluster at the end — pi/OpenCode rationale) while the FULL stream is appended to a temp file whose path is reported when available. If the final spill close reports a delayed writeback failure, the executor still returns the tail but withholds the path rather than advertising a possibly incomplete file. -- **Model-friendly env + credential/namespace scrub** — start with `process.env` minus credential-shaped vars (`*KEY*`/`*SECRET*`/`*TOKEN*`) and every `DSH_*`, then apply `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat`. Ordinary spec `env` is merged next and may restore caller-held credential-shaped values, but is rejected if it tries to set reserved `DSH_*`; the trusted spec `dshEnv` snapshot is merged last. This keeps ambient secrets out and prevents a nested/previous harness identity from surviving when the current registry omits it. The spec's `stdin`, when supplied, is written to the child and closed; with none supplied, fd 0 is `/dev/null`. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [the session environment RFC](../../../docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md). +- **Model-friendly env + credential/namespace scrub** — start with `process.env` minus credential-shaped vars (`*KEY*`/`*SECRET*`/`*TOKEN*`) and every `DSH_*`, then apply `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat`. Ordinary spec `env` is merged next and may restore caller-held credential-shaped values, but is rejected if it tries to set reserved `DSH_*`; the managed spec `dshEnv` snapshot is rejected if it contains ordinary names and otherwise merges last. This keeps ambient secrets out, catches wrong-channel plugin configuration before spawn, and prevents a nested/previous harness identity from surviving when the current registry omits it. The spec's `stdin`, when supplied, is written to the child and closed; with none supplied, fd 0 is `/dev/null`. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [the session environment RFC](../../../docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md). - **Background tasks** — `start()` returns immediately, no timeout applies (Claude Code detaches timeouts when backgrounding), `readOutput()` is incremental with whole-stream byte offsets, and disposal kills everything. The spec's opaque `owner` token is stored on the tracked task and returned by `ownerOf(id)` — the executor never interprets it (the consumer's access policy does), and because it lives with the task here it survives a `tool-bash` HMR reload. ## Sandboxing diff --git a/packages/bash/bash-local/src/run.ts b/packages/bash/bash-local/src/run.ts index 9cd9ac2553..6b1f2064c0 100644 --- a/packages/bash/bash-local/src/run.ts +++ b/packages/bash/bash-local/src/run.ts @@ -58,10 +58,11 @@ export const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i * `ENV_OVERRIDES` then forces model-friendly terminal values, ordinary `extra` * follows, and `dshEnv` merges last. Ordinary `extra` may restore a * credential-shaped name whose value the caller already holds, but cannot set - * the managed namespace. `dsh-tool-bash` builds both channels from trusted - * named fields and never forwards model-provided environment objects. + * the managed namespace; `dshEnv` rejects ordinary names symmetrically. + * `dsh-tool-bash` builds both channels from trusted named fields and never + * forwards model-provided environment objects. * @param extra - ordinary caller-supplied entries; `DSH_*` names are rejected. - * @param dshEnv - trusted managed `DSH_*` entries for the current execution. + * @param dshEnv - managed entries; names outside `DSH_*` are rejected. * @returns the environment to hand to `spawn` for the child process. */ export function childEnv( @@ -77,6 +78,11 @@ export function childEnv( throw new Error(`ordinary bash env cannot set reserved variable "${key}"; use dshEnv`) } } + for (const key of Object.keys(dshEnv ?? {})) { + if (!key.startsWith(DSH_ENV_PREFIX)) { + throw new Error(`managed bash env cannot set ordinary variable "${key}"; use env`) + } + } return { ...env, ...ENV_OVERRIDES, ...extra, ...dshEnv } } @@ -107,7 +113,7 @@ export interface SpawnSpec { * terminal overrides. `DSH_*` names are rejected and belong in `dshEnv`. */ env?: Record | undefined - /** Harness-owned `DSH_*` entries merged after ambient `DSH_*` removal. */ + /** Harness-owned entries; non-`DSH_*` names are rejected before spawn. */ dshEnv?: DshEnvironment | undefined } diff --git a/packages/bash/bash-local/tests/run.spec.ts b/packages/bash/bash-local/tests/run.spec.ts index 48f00a861b..1726e30743 100644 --- a/packages/bash/bash-local/tests/run.spec.ts +++ b/packages/bash/bash-local/tests/run.spec.ts @@ -4,6 +4,7 @@ import { dirname, join } from 'node:path' import { describe, expect, it, vi } from 'vitest' import { killGroup, OutputCollector, runBash } from '@deepseek-ai/dsh-bash-local' import type { RunningBash } from '@deepseek-ai/dsh-bash-local' +import type { DshEnvironment } from '@deepseek-ai/dsh-bash' const { failNextClose } = vi.hoisted(() => ({ failNextClose: { value: false } })) vi.mock('node:fs', async (importOriginal) => { @@ -392,6 +393,12 @@ describe('review fixes: env scrubbing and spill hardening', () => { .toThrow(/DSH_WRONG_CHANNEL.*dshEnv/) }) + it('rejects ordinary variables on the managed env channel', () => { + const invalid = { PATH: '/wrong-channel' } as unknown as DshEnvironment + expect(() => runBash(spec('true', { dshEnv: invalid }))) + .toThrow(/managed bash env.*PATH.*use env/) + }) + it('creates spill files with owner-only permissions and random names', async () => { const result = await runBash( spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { maxOutputBytes: 500 }), diff --git a/packages/bash/bash/src/types.ts b/packages/bash/bash/src/types.ts index 479b968cfc..a3a6bba116 100644 --- a/packages/bash/bash/src/types.ts +++ b/packages/bash/bash/src/types.ts @@ -125,7 +125,8 @@ export interface BashExecRequest { /** * Harness-owned `DSH_*` variables for this execution. Executors discard * ambient `DSH_*` entries before merging this snapshot, so an unavailable - * current fact cannot inherit a stale value from the harness process. + * current fact cannot inherit a stale value from the harness process, and + * reject non-`DSH_*` names supplied through this managed channel. */ dshEnv?: DshEnvironment | undefined /** @@ -182,7 +183,7 @@ export interface BashExecSpec { * ordinary extra environment. */ env?: Record | undefined - /** Trusted `DSH_*` snapshot carried through from {@link BashExecRequest.dshEnv}. */ + /** Managed `DSH_*` snapshot; implementations reject ordinary names. */ dshEnv?: DshEnvironment | undefined /** * Opaque owner token, REQUIRED-but-nullable (mirrors `workdir`/`timeoutMs` From 7ea1bf119f76455bdb084a380a9c5738877244a8 Mon Sep 17 00:00:00 2001 From: Dudu-0223 Date: Mon, 13 Jul 2026 11:02:21 +0800 Subject: [PATCH 013/359] feat(agent-loop): run safe tool calls in parallel --- docs/agent-lifecycle.md | 12 +- docs/architecture.md | 14 +- docs/config-catalog.md | 9 +- docs/cordis-catalog/services.md | 7 +- docs/core-data-structures/tools.md | 35 +- docs/rfc/INDEX.md | 1 + ...2026-07-10-parallel-tool-call-execution.md | 110 +++++ docs/tool-catalog.md | 2 +- examples/acp-agent/tests/acp.snapshot.ts | 1 + .../snapshots/both-mode-turn/session.jsonl | 2 +- .../both-mode-turn/system-prompt.golden.md | 4 +- .../code-mode-turn/system-prompt.golden.md | 4 +- .../snapshots/parallel-tool-calls/input.json | 7 + .../parallel-tool-calls/session.jsonl | 28 ++ .../parallel-tool-calls/stdout.golden.jsonl | 8 + .../parallel-tool-calls/workspace/a.txt | 1 + .../parallel-tool-calls/workspace/b.txt | 1 + .../tests/snapshots/skill-load/session.jsonl | 2 +- .../tests/snapshots/text-turn/session.jsonl | 2 +- .../escalation-approved/session.jsonl | 4 +- .../escalation-rejected/session.jsonl | 4 +- packages/bash/tool-bash/src/index.ts | 6 + .../cordis/tool-cordis/src/api-catalog.ts | 7 +- packages/core/agent-loop/README.md | 19 +- packages/core/agent-loop/src/constants.ts | 15 + packages/core/agent-loop/src/index.ts | 36 ++ packages/core/agent-loop/src/loop.ts | 78 +-- packages/core/agent-loop/src/tool-calls.ts | 326 ++++++++++++ .../core/agent-loop/tests/tool-calls.spec.ts | 462 ++++++++++++++++++ packages/core/tools/README.md | 16 +- packages/core/tools/src/index.ts | 216 ++++++-- packages/core/tools/src/schema.ts | 28 +- .../core/tools/tests/execution-mode.spec.ts | 133 +++++ packages/fs/tool-fs/README.md | 2 + packages/fs/tool-fs/src/read.ts | 5 + packages/fs/tool-fs/tests/tools.spec.ts | 10 + packages/subagent/README.md | 2 + packages/subagent/subagent/src/types.ts | 13 + packages/subagent/tool-subagent/README.md | 4 + packages/subagent/tool-subagent/src/index.ts | 12 +- .../tool-subagent/tests/tool-subagent.spec.ts | 9 + packages/web/tool-web/README.md | 2 + packages/web/tool-web/src/fetch.ts | 3 + packages/web/tool-web/src/search.ts | 3 + packages/web/tool-web/tests/tool-web.spec.ts | 4 + scripts/gen-cordis-catalog.ts | 1 + scripts/gen-doc-graphs.ts | 12 +- scripts/type-equiv.manifest.json | 1 + 48 files changed, 1542 insertions(+), 141 deletions(-) create mode 100644 docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md create mode 100644 examples/acp-agent/tests/snapshots/parallel-tool-calls/input.json create mode 100644 examples/acp-agent/tests/snapshots/parallel-tool-calls/session.jsonl create mode 100644 examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl create mode 100644 examples/acp-agent/tests/snapshots/parallel-tool-calls/workspace/a.txt create mode 100644 examples/acp-agent/tests/snapshots/parallel-tool-calls/workspace/b.txt create mode 100644 packages/core/agent-loop/src/constants.ts create mode 100644 packages/core/agent-loop/src/tool-calls.ts create mode 100644 packages/core/agent-loop/tests/tool-calls.spec.ts create mode 100644 packages/core/tools/tests/execution-mode.spec.ts diff --git a/docs/agent-lifecycle.md b/docs/agent-lifecycle.md index d6d9ab1ba7..05e8aea2d0 100644 --- a/docs/agent-lifecycle.md +++ b/docs/agent-lifecycle.md @@ -34,10 +34,14 @@ sequenceDiagram Session-->>SDK: session/event assistant/chunk* Driver->>Hooks: agent/step-result waterfall Driver->>Session: assistant/message - Driver->>Session: tool/call - Driver->>Tools: execute through pre and post waterfalls - Tools-->>Session: tool-owned events when applicable - Driver->>Session: tool/result and step/end + Driver->>Tools: group calls by executionMode + loop started tool calls (bounded pool) + Driver->>Session: tool/call pending audit + Driver->>Tools: ordered pre / pooled dispatch / ordered post + Tools-->>Session: tool-owned events when applicable + end + Driver->>Session: tool/result in model order + Driver->>Session: step/end Driver->>Hooks: agent/turn-continuation waterfall Driver->>Session: turn/end Driver->>Persistence: session/flush parallel checkpoint diff --git a/docs/architecture.md b/docs/architecture.md index c1755dc815..2752f35fec 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -81,11 +81,13 @@ forever: 'assistant/chunk' agent/step-result 'assistant/message' - each tool call: - 'tool/call' - tools/pre-execute -> tools/execute -> tools/post-execute - 'tool/result' - append post-tool context and steering + schedule tool calls by ctx.tools.executionMode (exclusive = barrier; + consecutive parallel-safe = one rolling-pool group, <= maxParallelToolCalls in flight): + each started call: + 'tool/call' + tools/pre-execute -> tools/execute -> tools/post-execute + 'tool/result' committed in model order (slot-buffered) + append post-tool context (model order) and steering 'step/end' agent/turn-continuation stop unless tools or continuation policy ask for another step @@ -97,6 +99,8 @@ Prompt assembly is single-path: `renderPrompt(assemble({ agent }))` IS the syste Post-tool context lands after all tool results so tool-call/result adjacency stays stable. Steering drains between steps; leftover steering after a turn is re-queued as ordinary input. +Tool-call scheduling groups exclusive barriers and bounded parallel-safe runs while preserving ordered results ([the parallel tool-call RFC](rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md)). + ### Failure Boundaries The turn is the containment boundary. A throwing listener, adapter error finish, or failed step ends the current turn with an error reason and reports live diagnostics through `agent/error`; it does not kill the driver loop. `cancel()` clears queued and steering work, aborts the active model/tool boundary when possible, and records the appropriate turn end. Disposal stops the loop, awaits quiescence, unregisters the agent, and lets service disposers drain. diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 75ca4a67d1..ebc4efde33 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -124,6 +124,11 @@ export interface Config { id: AgentId /** Optional workspace cwd for the config-created fresh session. */ cwd?: string + /** + * Maximum parallel-safe tool calls to run concurrently within one assistant + * step. Must be a positive integer; `1` preserves serial execution. + */ + maxParallelToolCalls?: number /** * If set, the config agent RESUMES this persisted session id instead of * starting a fresh `${id}-session-`. Sourced from an env var in @@ -144,7 +149,7 @@ export interface Config { Depends on: [`AgentId`](../packages/core/agent/src/index.ts) · [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:36`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:52`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` @@ -956,7 +961,7 @@ export interface Config { export type ToolPresentationMode = 'native' | 'code' | 'both' ``` -Source: [`packages/core/tools/src/index.ts:323`](../packages/core/tools/src/index.ts) +Source: [`packages/core/tools/src/index.ts:389`](../packages/core/tools/src/index.ts) ## `@deepseek-ai/dsh-user-approval` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index bd01d39792..75fe128826 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -21,7 +21,7 @@ createAgent(options: CreateAgentOptions): AgentHandle async resume(options: ResumeAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:70`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:91`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` @@ -266,12 +266,13 @@ Tool registry (`ctx.tools`): tool plugins register definitions; the agent loop e register(definition: ToolDefinition): () => void get(name: string): ToolDefinition | undefined schemas(): ToolSchema[] +executionMode(exec: ToolExecution): ToolExecutionMode async execute(exec: ToolExecution): Promise ``` -Types: [ToolDefinition](../core-data-structures/tools.md) · [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) +Types: [ToolDefinition](../core-data-structures/tools.md) · [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionMode](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) -Source: [`packages/core/tools/src/index.ts:349`](../../packages/core/tools/src/index.ts) +Source: [`packages/core/tools/src/index.ts:415`](../../packages/core/tools/src/index.ts) ## `ctx.userInteraction` — `UserInteractionService` diff --git a/docs/core-data-structures/tools.md b/docs/core-data-structures/tools.md index 96d3e79bdc..324af67289 100644 --- a/docs/core-data-structures/tools.md +++ b/docs/core-data-structures/tools.md @@ -6,7 +6,7 @@ Source: [`packages/core/tools/src/index.ts`](../../packages/core/tools/src/index ## `ToolDefinition` — a registered tool -A `ToolSchema` (the model-facing fields) plus the `execute` function and optional UI presenters. The registry holds these; the loop dispatches calls through them. The registry's `schemas()` builds the model-facing `ToolSchema[]` by an explicit allowlist — `execute`/`presentCall`/`presentResult` must never leak into a model request. +A `ToolSchema` (the model-facing fields) plus the `execute` function, host-only scheduler metadata, and optional UI presenters. The registry holds these; the loop dispatches calls through them. The registry's `schemas()` builds the model-facing `ToolSchema[]` by an explicit allowlist — `execute`/`timeoutMs`/`isConcurrencySafe`/`presentCall`/`presentResult` must never leak into a model request. ```ts type-equiv interface ToolDefinition extends ToolSchema { @@ -19,6 +19,31 @@ interface ToolDefinition extends ToolSchema { * cooperative implementation that can reach quiescence when the signal aborts. */ timeoutMs?: number + /** + * Optional synchronous, pure classification: may this call run concurrently + * with other tool calls in the same assistant step? The agent-loop scheduler + * calls it (via {@link ToolRegistry.executionMode}) to decide whether the call + * joins a parallel group or forms an exclusive barrier; a missing declaration, + * a thrown check, or any non-`true` return is treated as exclusive. Like + * `timeoutMs` it is host-only scheduler metadata — NEVER sent to the model, + * since `schemas()` whitelists only name/description/parameters. + * + * It may inspect the parsed `args` (`unknown` — a hand-rolled definition + * receives the raw parsed value; `defineTool` schema-validates first and + * returns `false` on invalid args, so an eventual `ToolArgsError` is produced + * only if the tool actually executes). The check performs no I/O and receives + * no live `Agent` or mutable `ToolExecution`. + * + * Declaring `true` is a contract: the tool body must NOT mutate the parent + * agent's session or other parent-owned async state during `execute` (no + * `exec.agent.session.append(...)`, no `agent.inject(...)`). Its only parent- + * step outputs are the returned content, `meta`, structured error, and + * `additionalContext` carried through the loop's ordered post-execute path. + * The narrow exception is a synchronous, side-effect-only recorder whose + * updates are commutative for concurrent calls by the same session (the + * `fs/observed` version recorder is the worked example). + */ + isConcurrencySafe?(args: unknown): boolean /** * Optional: how to present the PENDING state of one call in a UI, derived from * the call's `args` (parsed arguments, `unknown` — the tool validates/narrows @@ -97,6 +122,14 @@ interface ToolExecution { } ``` +The agent loop asks the registry for each pending call's execution mode and uses it to partition a step into exclusive barriers and rolling-pool parallel runs: + +```ts type-equiv +type ToolExecutionMode = + | { kind: 'parallel' } + | { kind: 'exclusive' } +``` + ```ts type-equiv interface ToolExecutionResult { callId: CallId diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index 8dc3b93b47..4b2c63b1c4 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -70,6 +70,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [The session prefix — request-only messages in front of the derived history](implemented/feature/2026-07-07-session-prefix.md) | 2026-07-07 | | [Repeat-tool-call guard plugin](implemented/feature/2026-07-08-repeat-tool-guard.md) | 2026-07-08 | | [The self-referential cordis toolset](implemented/feature/2026-07-08-self-referential-cordis-toolset.md) | 2026-07-08 | +| [Parallel tool-call execution by per-call safety](implemented/feature/2026-07-10-parallel-tool-call-execution.md) | 2026-07-10 | ### Simplification diff --git a/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md b/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md new file mode 100644 index 0000000000..e75dcd0a81 --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md @@ -0,0 +1,110 @@ +# RFC: Parallel tool-call execution by per-call safety + +Status: implemented + +## Problem + +The loop accepts an assistant message containing multiple `tool-call` blocks. Serial execution makes independent reads, web requests, and subagent delegations pay the sum of their wall-clock latency even though the model and adapters already represent sibling tool calls in one response. + +Concurrency cannot live in the model-facing JSON schema. `ctx.tools.schemas()` exposes only `name`, `description`, and `parameters`; scheduling is a host contract. The loop needs an internal per-call safety decision and must use it without hardcoding tool names. + +The hard constraint is replay. The session log remains the source of truth: the assistant message contains the model's calls in order, each started call has a `tool/call` audit event before its body runs, each model-facing result is a `tool/result`, and derived history sees results in the original call order. Live ACP and stdio surfaces may show several pending calls before the first result; that progress interleaving is not part of the model-history guarantee. + +## Decision + +`ToolDefinition` carries an optional host-only classifier: + +```text +export interface ToolDefinition extends ToolSchema { + execute(args: unknown, exec: ToolExecution): Promise + isConcurrencySafe?(args: unknown): boolean +} +``` + +`isConcurrencySafe` is synchronous, pure classification metadata. It may inspect parsed call arguments; `defineTool()` schema-validates those arguments before the typed callback runs, while hand-rolled definitions receive the raw parsed value. The callback performs no I/O and receives no live `Agent` or mutable `ToolExecution`. `defineTool()` validates arguments softly for `isConcurrencySafe`, matching the display-only `presentCall`/`presentResult` pattern: invalid args return `false`, and the ordinary `ToolArgsError` is produced only if the tool executes. + +The registry exposes the scheduling decision as a plain method: + +```text +export type ToolExecutionMode = + | { kind: 'parallel' } + | { kind: 'exclusive' } +``` + +```text +class ToolRegistry { + executionMode(exec: ToolExecution): ToolExecutionMode +} +``` + +`ctx.tools.executionMode(exec)` looks up the registered tool and calls `tool.isConcurrencySafe?.(exec.arguments)`. Unknown tools, missing declarations, malformed typed args, and thrown safety checks all resolve to `{ kind: 'exclusive' }`. The method is not a Cordis waterfall; it is the future insertion point if hook, MCP, or provider policy needs to downgrade a tool's baseline decision. The object-tagged union leaves room for future resource grouping, for example `{ kind: 'exclusive', group: 'session:...' }`. + +A parallel-safe declaration is a contract. The tool body must not mutate the parent agent's session or other parent-owned async state during `execute`; parent-session writes such as `exec.agent.session.append(...)`, `agent.inject(...)`, or other tool-owned parent events belong to exclusive tools unless the mutation moves behind the loop's ordered result path. The only parent-step outputs a parallel-safe call may produce are its returned content, `meta`, structured error, and `additionalContext` carried through the ordered post-execute path. The narrow exception is a synchronous, side-effect-only recorder whose updates are commutative for concurrent calls by the same session. `fs/observed` is the worked example: `read` emits it synchronously after a successful read, `dsh-fs-policy` records `WeakMap` state synchronously, same-target reads converge to an observed version, and write/edit remain exclusive barriers that re-check versions before mutating. + +## Scheduling + +The loop waits for the model stream to finish and logs one authoritative `assistant/message` before scheduling tools. Streaming tool execution is out of scope. + +For each assistant step, `packages/core/agent-loop/src/tool-calls.ts` parses each call's raw JSON arguments exactly once, creates one distinct `ToolExecution` object per call, asks `ctx.tools.executionMode(exec)`, and partitions calls into ordered groups. A group is either one exclusive call or a run of consecutive parallel calls. `loop.ts` calls the helper so the turn/step lifecycle remains readable. + +Parallelism is per agent. `AgentOptions.maxParallelToolCalls` is a positive integer, defaults to `DEFAULT_MAX_PARALLEL_TOOL_CALLS` (`10`), and is accepted through the config-created agent path. Setting it to `1` preserves serial execution for that agent. Both the TypeScript `AgentOptions` vocabulary and the `AgentLoop.Config` schemastery object validate the cap, so invalid `cordis.yml` values fail during config validation. + +Within a parallel group, execution uses a rolling pool: start calls in model order up to `maxParallelToolCalls`, and whenever one call settles, start the next unstarted call until the group is exhausted. A group larger than the cap is not truncated; the cap limits simultaneous in-flight calls only. + +Only the dispatch/body stage runs concurrently. Generic middleware that can shape ordering-sensitive state remains ordered: `tools/pre-execute` and `tools/post-execute` run in model call order. `@deepseek-ai/dsh-tools` exposes the symbol-keyed internal `TOOL_REGISTRY_SCHEDULER` view so `dsh-agent-loop` can split prepare, dispatch, and finalize without adding named staged service methods to `ctx.tools`; ordinary callers still use the one-call `execute(exec)` API. `tools/execute` around-dispatch listeners run with the dispatch they wrap, so wrappers must be reentrant across distinct `ToolExecution` objects. The shipped timeout policy is per-call: every call owns its mutable `exec` and deadline. + +Each started call appends its own `tool/call` immediately before its pre-execute gate and body can run. `tool/call` events remain in model order relative to started calls, but their log positions may interleave with sibling results: a later call's `tool/call` can appear before or after an earlier call's `tool/result` as the rolling pool replenishes. That is safe because `tool/call` is log-only; derived model history reads the assistant's `tool-call` blocks and the ordered `tool/result` events, pairing by `callId`. Settled dispatches are stored in model-order slots, and a commit cursor appends `tool/result` only while the next slot is ready. `additionalContext` is collected from those same slots and injected in model call order after normal completion of every started tool result in the step. + +If the parent signal is already aborted before a group starts, the group is not started and no `tool/call` audit records are appended for it. If the signal aborts while a parallel group is running, the pool stops replenishing, waits for only the already-started calls to settle, records their results in order, drops buffered `additionalContext`, and then raises the abort error so the existing `runTurn` catch path owns `turn/end` reason selection. This keeps every started call paired while avoiding audit records for calls that never began. + +Code Mode remains outside native scheduling. In `mode: 'code'`, the wire exposes only `run_code`, so the model emits one native tool call and the loop-level scheduler has nothing to parallelize. `run_code` stays exclusive, and its in-program dispatch queue remains serialized. In `mode: 'both'`, native sibling tool calls can form parallel groups normally, while calls made inside one `run_code` execution still follow Code Mode's own queue. + +## Tool declarations + +The shipped declarations are conservative: + +- `web_search`, `web_fetch`, filesystem `read`, and `subagent` return `true`. +- Filesystem `write`, filesystem `edit`, `todo_write`, `bash`, `bash_output`, `bash_kill`, `workflow`, `ask_user_question`, and Cordis mutation tools stay exclusive by omitting `isConcurrencySafe`. +- Bash stays exclusive until a bash-owned read-only classifier exists; the loop never infers shell safety. + +Subagent providers do not get an extra opt-in field. `SubagentProvider.start()` is part of the provider contract and must be safe to call concurrently for independent runs. A provider backed by a limited resource may queue internally, apply its own capacity limit, or return a typed failure for the affected run, but it must not require the parent agent loop to serialize every `subagent` tool call. Built-in spawn, fork, and ACP runs own a child session or process; fork seeds only the parent's completed-turn prefix, so concurrent forks inside the parent's open step all see the same stable prefix. + +Exclusive tools naturally form ordering barriers. A step such as `[read A, write A, read A]` becomes three ordered groups because `write` is exclusive, so the scheduler does not introduce a read/write race inside one assistant step. + +The subagent tool remains synchronous. Multiple subagent tool calls in one assistant message can run concurrently, but each tool result is still the child final answer. Background spawning plus later collection would be a separate tool vocabulary. + +## Testing + +Unit tests cover the classifier (`ToolDefinition.isConcurrencySafe`, `defineTool()` soft validation, `ToolRegistry.executionMode`, and schema projection), the loop scheduler (grouping, exclusive barriers, rolling-pool replenishment, `maxParallelToolCalls: 1`, distinct `ToolExecution` objects, ordered pre/post middleware, ordered `tool/result`, concrete `tool/call`/`tool/result` interleaving, ordered `additionalContext`, and abort/drop-context cases), and first-party safe declarations for filesystem read, web tools, and subagent. + +Snapshot coverage pins the transcript-facing ACP behavior for a multi-call step: several pending tool-call updates may precede model-ordered result updates. Code Mode tests and docs pin that `run_code` remains exclusive and that in-program dispatch stays serialized. No real-API e2e is required for this decision because scheduling is deterministic loop behavior with mocked tools and replayable snapshots, not provider-specific behavior. + +## Alternatives considered + +**Keep serial execution.** This keeps the loop simple and avoids new abort ordering cases, but it leaves obvious latency on the table for independent reads, web calls, and subagent delegations. The model and adapters already represent multiple tool calls in one assistant message, so serial execution is a host limitation rather than a protocol limitation. + +**Codex-style tool-level `supportsParallelToolCalls`.** A tool-level boolean is smaller, but it cannot express that the same tool is safe for some inputs and unsafe for others. Bash is the key example: a read-only command classifier can make `pwd` or `ls` parallel-safe without making `rm` or a long-lived background-task operation parallel-safe. + +**Parallelize the complete `ctx.tools.execute()` pipeline.** This preserves the existing one-call API in the loop, but it also runs `tools/pre-execute` and `tools/post-execute` concurrently. The shipped repeat-tool guard and hook bridges can carry ordering-sensitive state, so the shipped design keeps pre/post ordered and overlaps only dispatch/body work. + +**Expose a public staged API such as `prepare` / `dispatch` / `finalize`.** That names too much implementation surface before another consumer exists. The loop needs staged behavior, but `ToolRegistry` factors it through a symbol-keyed internal view while keeping `execute(exec)` as the public one-call API for ordinary callers. + +**Add a `tools/execution-mode` waterfall.** A Cordis seam would let hook bridges, provider policies, or MCP server metadata downgrade a tool's declaration. It is not needed for the conservative declaration set: raw and undeclared tools default exclusive, pre/post middleware stays ordered, and a non-reentrant around-dispatch wrapper can serialize internally. The `executionMode(exec)` method remains the insertion point if a real deployment needs policy-driven downgrades. + +**Start tools while the model is still streaming.** Claude Code has a streaming executor path, but this repo's log reconstruction and surface-pairing contracts make that a larger design. This decision waits for the assistant message to be assembled, so the log records one authoritative assistant message before scheduling tools. + +**Use fixed windows inside one parallel group.** Fixed windows would start `maxParallelToolCalls` calls, wait for all of them to settle, then start the next window. The rolling pool wins because slot-based result storage and a model-order commit cursor preserve the transcript contract without sacrificing avoidable latency. + +**Expose concurrency in the model-facing schema.** The model does not need a scheduler flag to request multiple calls; it already can emit multiple `tool-call` blocks. Sending host-only concurrency metadata would bloat requests and mix execution policy into the schema whose job is only argument shape and tool-choice guidance. + +## Consequences + +Parallel execution can expose latent shared-state bugs in tools that declare themselves safe too broadly. The default is exclusive, the shipped declarations are conservative, and input-sensitive tools such as bash stay exclusive until their owning package proves a narrower classifier. + +An around-dispatch plugin can also violate the contract even when the tool itself is safe. The scheduler limits that risk to `tools/execute`; shipped wrappers are per-call, and third-party wrappers with shared mutable state must serialize internally. + +Parallel groups change abort timing: a sibling call may have started in a case where the serial loop would not have reached it yet. The pool makes this explicit by logging only started calls, stopping replenishment on abort, draining those calls to results, and preventing later calls from starting. + +Concurrent subagents can compete for model quota, filesystem state, or external process resources. The provider contract requires concurrent `start()` safety, not unlimited capacity, and tool guidance still tells the model to parallelize only independent tasks with non-overlapping write scopes. + +The result-order rule can delay a fast result behind a slow sibling in the same group. That preserves the model transcript and replay contract. ACP and stdio still expose immediate pending-call progress, but completion updates stay model-ordered. diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 7713c1f278..e76a808b18 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -398,7 +398,7 @@ Source: [`packages/skill/tool-skill/src/index.ts`](../packages/skill/tool-skill/ ### `subagent` -Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. +Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. ```json { diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index eaa4e0381a..ed01a613ae 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -49,6 +49,7 @@ const SCENARIOS: Scenario[] = [ // Its system-prompt.golden.md and JSONL tool list pin the composed header. { name: 'text-turn', hasModelTurn: true, recorded: true, pinsHeader: true }, { name: 'tool-call-turn', hasModelTurn: true, recorded: true }, + { name: 'parallel-tool-calls', hasModelTurn: true, recorded: false }, { name: 'fs-terminal-card', hasModelTurn: true, recorded: true }, { name: 'todo-plan', hasModelTurn: true, recorded: true }, { name: 'skill-load', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'skill' }, diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index b49097188e..39d381f16a 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index 5dd8547aa8..47910b3214 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -76,14 +76,14 @@ declare const tools: { /** The exact skill name from the available skills list. */ name: string; }): Promise; - /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */ + /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. */ subagent(args: { /** A short (3-5 word) description of the delegated task, for display. */ description: string; /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */ prompt: string; }): Promise; - /** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */ + /** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. */ subagent_fork(args: { /** A short (3-5 word) description of the delegated task, for display. */ description: string; diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index 5dd8547aa8..47910b3214 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -76,14 +76,14 @@ declare const tools: { /** The exact skill name from the available skills list. */ name: string; }): Promise; - /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */ + /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. */ subagent(args: { /** A short (3-5 word) description of the delegated task, for display. */ description: string; /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */ prompt: string; }): Promise; - /** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */ + /** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. */ subagent_fork(args: { /** A short (3-5 word) description of the delegated task, for display. */ description: string; diff --git a/examples/acp-agent/tests/snapshots/parallel-tool-calls/input.json b/examples/acp-agent/tests/snapshots/parallel-tool-calls/input.json new file mode 100644 index 0000000000..e5356e4af5 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/parallel-tool-calls/input.json @@ -0,0 +1,7 @@ +{ + "steps": [ + { "op": "initialize" }, + { "op": "newSession" }, + { "op": "prompt", "text": "Use the read tool twice in the same assistant message: read a.txt and b.txt. Then reply DONE." } + ] +} diff --git a/examples/acp-agent/tests/snapshots/parallel-tool-calls/session.jsonl b/examples/acp-agent/tests/snapshots/parallel-tool-calls/session.jsonl new file mode 100644 index 0000000000..7d7e79974e --- /dev/null +++ b/examples/acp-agent/tests/snapshots/parallel-tool-calls/session.jsonl @@ -0,0 +1,28 @@ +{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}"} +{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Use the read tool twice in the same assistant message: read a.txt and b.txt. Then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_read_a","name":"read","argumentsDelta":"{\"file_path\":\"a.txt\"}"}}} +{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_read_a","name":"read","arguments":"{\"file_path\":\"a.txt\"}"}}}} +{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_read_b","name":"read","argumentsDelta":"{\"file_path\":\"b.txt\"}"}}} +{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_read_b","name":"read","arguments":"{\"file_path\":\"b.txt\"}"}}}} +{"type":"assistant/chunk","seq":10,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} +{"type":"assistant/chunk","seq":11,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":12,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_read_a","name":"read","arguments":"{\"file_path\":\"a.txt\"}"},{"type":"tool-call","id":"call_read_b","name":"read","arguments":"{\"file_path\":\"b.txt\"}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8,9,10,11],"surfaceOp":"append"} +{"type":"tool/call","seq":13,"time":0,"data":{"turn":1,"step":1,"callId":"call_read_a","name":"read","arguments":"{\"file_path\":\"a.txt\"}"}} +{"type":"tool/call","seq":14,"time":0,"data":{"turn":1,"step":1,"callId":"call_read_b","name":"read","arguments":"{\"file_path\":\"b.txt\"}"}} +{"type":"tool/result","seq":15,"time":0,"data":{"turn":1,"step":1,"callId":"call_read_a","content":[{"type":"text","text":"{{cwd}}/a.txt\nfile\n\n1: alpha\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[13],"surfaceOp":"append"} +{"type":"tool/result","seq":16,"time":0,"data":{"turn":1,"step":1,"callId":"call_read_b","content":[{"type":"text","text":"{{cwd}}/b.txt\nfile\n\n1: beta\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[14],"surfaceOp":"append"} +{"type":"step/end","seq":17,"time":0,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":18,"time":0,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":20,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"DONE"}}} +{"type":"assistant/chunk","seq":21,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}} +{"type":"assistant/chunk","seq":22,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":1}}}} +{"type":"assistant/chunk","seq":23,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":24,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"DONE"}],"usage":{"inputTokens":10,"outputTokens":1}},"sourceEventSeqs":[19,20,21,22,23],"surfaceOp":"append"} +{"type":"step/end","seq":25,"time":0,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":26,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl new file mode 100644 index 0000000000..91ca67746f --- /dev/null +++ b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl @@ -0,0 +1,8 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_a","title":"Read a.txt","kind":"read","status":"in_progress","locations":[{"path":"a.txt","line":1}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_b","title":"Read b.txt","kind":"read","status":"in_progress","locations":[{"path":"b.txt","line":1}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_read_a","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/a.txt\nfile\n\n1: alpha\n\n(End of file - total 1 lines)\n"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_read_b","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/b.txt\nfile\n\n1: beta\n\n(End of file - total 1 lines)\n"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}} +{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} diff --git a/examples/acp-agent/tests/snapshots/parallel-tool-calls/workspace/a.txt b/examples/acp-agent/tests/snapshots/parallel-tool-calls/workspace/a.txt new file mode 100644 index 0000000000..4a58007052 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/parallel-tool-calls/workspace/a.txt @@ -0,0 +1 @@ +alpha diff --git a/examples/acp-agent/tests/snapshots/parallel-tool-calls/workspace/b.txt b/examples/acp-agent/tests/snapshots/parallel-tool-calls/workspace/b.txt new file mode 100644 index 0000000000..65b2df87f7 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/parallel-tool-calls/workspace/b.txt @@ -0,0 +1 @@ +beta diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 645671709e..fde4a1f941 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index 324ef8d4eb..86240f9fe0 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl b/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl index 2ac9d27044..fef0ca3597 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl +++ b/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl @@ -114,8 +114,8 @@ {"type":"assistant/chunk","seq":112,"time":1783486771232,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":113,"time":1783486771236,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the command with sandbox_permissions set to workspace-write. They explicitly said they will approve the permission prompt. Let me proceed."},{"type":"tool-call","id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"usage":{"inputTokens":1255,"outputTokens":160,"cacheReadTokens":0,"reasoningTokens":34}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} {"type":"tool/call","seq":114,"time":1783486771236,"data":{"turn":1,"step":1,"callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}} -{"type":"approval/asked","seq":115,"time":1783486771238,"data":{"id":"3ec45405-5add-4929-a755-e8c077ec7a7e","toolName":"bash","callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}} -{"type":"approval/decided","seq":116,"time":1783486771243,"data":{"id":"3ec45405-5add-4929-a755-e8c077ec7a7e","outcome":"allowed-once"}} +{"type":"approval/asked","seq":115,"time":1783486771238,"data":{"id":"6c836429-f953-4505-8ead-2c70db64f4f8","toolName":"bash","callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}} +{"type":"approval/decided","seq":116,"time":1783486771243,"data":{"id":"6c836429-f953-4505-8ead-2c70db64f4f8","outcome":"allowed-once"}} {"type":"tool/result","seq":117,"time":1783486771442,"data":{"turn":1,"step":1,"callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[114],"surfaceOp":"append"} {"type":"step/end","seq":118,"time":1783486771443,"data":{"turn":1,"step":1}} {"type":"step/start","seq":119,"time":1783486771443,"data":{"turn":1,"step":2}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl b/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl index ee2586bc34..8380fc962c 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl +++ b/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl @@ -151,8 +151,8 @@ {"type":"assistant/chunk","seq":149,"time":1783486774569,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":150,"time":1783486774572,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the exact command `printf 'escalated\\n' > escalated.txt && cat escalated.txt` with `sandbox_permissions` set to `workspace-write` and the justification they specified. They explicitly say they will reject the permission prompt, so after rejection I should explain in one short sentence and stop."},{"type":"tool-call","id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"usage":{"inputTokens":1269,"outputTokens":197,"cacheReadTokens":0,"reasoningTokens":70}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"surfaceOp":"append"} {"type":"tool/call","seq":151,"time":1783486774572,"data":{"turn":1,"step":1,"callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}} -{"type":"approval/asked","seq":152,"time":1783486774574,"data":{"id":"ed977255-38a3-4c1d-9f4e-0e258ef86e94","toolName":"bash","callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}} -{"type":"approval/decided","seq":153,"time":1783486774578,"data":{"id":"ed977255-38a3-4c1d-9f4e-0e258ef86e94","outcome":"rejected"}} +{"type":"approval/asked","seq":152,"time":1783486774574,"data":{"id":"c6f486d0-2225-49d1-940e-1e82a877580f","toolName":"bash","callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}} +{"type":"approval/decided","seq":153,"time":1783486774578,"data":{"id":"c6f486d0-2225-49d1-940e-1e82a877580f","outcome":"rejected"}} {"type":"tool/result","seq":154,"time":1783486774579,"data":{"turn":1,"step":1,"callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"workspace-write\""}],"isError":true},"sourceEventSeqs":[151],"surfaceOp":"append"} {"type":"step/end","seq":155,"time":1783486774579,"data":{"turn":1,"step":1}} {"type":"step/start","seq":156,"time":1783486774580,"data":{"turn":1,"step":2}} diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index 31e6512ae0..f25d9a24dd 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -549,6 +549,12 @@ export function apply(ctx: Context): void { } } + // bash, bash_output, and bash_kill declare no `isConcurrencySafe`, so they + // default to exclusive: bash spawns/awaits a real process, bash_output reads a + // mutable per-task output cursor (a delta since last read), and bash_kill + // mutates task state. They stay exclusive until a bash-OWNED read-only command + // classifier can prove which invocations (e.g. `pwd`, `ls`) are side-effect- + // free; the loop never infers shell safety from a command string. ctx.tools.register(defineTool({ name: 'bash', description: bashDescription(escalationModes), diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 6b137abd39..d5a9fd026a 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -199,6 +199,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'register(definition: ToolDefinition): () => void', 'get(name: string): ToolDefinition | undefined', 'schemas(): ToolSchema[]', + 'executionMode(exec: ToolExecution): ToolExecutionMode', 'async execute(exec: ToolExecution): Promise', ], }, @@ -893,7 +894,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'ToolDefinition', - declaration: 'export interface ToolDefinition extends ToolSchema {\n execute(args: unknown, exec: ToolExecution): Promise;\n timeoutMs?: number;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n}', + declaration: 'export interface ToolDefinition extends ToolSchema {\n execute(args: unknown, exec: ToolExecution): Promise;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n}', }, { name: 'ToolErrorInfo', @@ -907,6 +908,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'ToolExecution', declaration: 'export interface ToolExecution {\n callId: CallId;\n name: string;\n arguments: unknown;\n agent?: Agent;\n signal?: AbortSignal;\n}', }, + { + name: 'ToolExecutionMode', + declaration: 'export type ToolExecutionMode = {\n kind: \'parallel\';\n} | {\n kind: \'exclusive\';\n};', + }, { name: 'ToolExecutionResult', declaration: 'export interface ToolExecutionResult {\n callId: CallId;\n content: ContentBlock[];\n isError: boolean;\n error?: ToolErrorInfo;\n additionalContext?: HookContext;\n meta?: unknown;\n}', diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 6137737457..7bbbbfea84 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -26,14 +26,15 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo ```ts interface Config { agents: Array<{ - id: string // required + id: string // required model?: string - cwd?: string // optional workspace cwd for the fresh session + cwd?: string // optional workspace cwd for the fresh session + maxParallelToolCalls?: number // positive integer; per-agent parallel tool-call cap (default 10) }> } ``` -Agents listed in config are auto-created at startup. `cwd` applies only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. There is no per-agent persona: the deployment persona is `dsh-system-prompt`'s own `persona` config, shared by every agent in the context. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from the `assemble({ agent })` context — runtime facts of the agents THIS loop drives, unlike the `harness:identity`/`deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` applies only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. `maxParallelToolCalls` (a positive integer, default `DEFAULT_MAX_PARALLEL_TOOL_CALLS` = `10`) bounds how many parallel-safe calls one assistant step runs at once; `1` restores fully serial execution. It is validated in the schema (`z.number().step(1).min(1)`), so a bad value fails config load rather than being silently dropped. There is no per-agent persona: the deployment persona is `dsh-system-prompt`'s own `persona` config, shared by every agent in the context. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from the `assemble({ agent })` context — runtime facts of the agents THIS loop drives, unlike the `harness:identity`/`deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Classes @@ -67,10 +68,12 @@ forever: stream llm.stream(freeze({header..., messages: prefix+boundary})) → session('assistant/chunk') message = waterfall agent/step-result session('assistant/message') - each tool-call: session('tool/call') - → tools.execute() [waterfall tools/pre-execute → dispatch → tools/post-execute] - → session('tool/result') - append buffered post-execute additionalContext as session('context/message')(s) + schedule tool-calls: group by tools.executionMode (exclusive call = barrier; + run of parallel-safe calls = one rolling-pool group, ≤ maxParallelToolCalls in flight) + each STARTED call: session('tool/call') ⟵ model-order per started call; log positions + → ordered tools/pre-execute → pooled dispatch/body → ordered tools/post-execute may interleave with sibling results as the pool replenishes + commit cursor appends session('tool/result') in MODEL order (slot-buffered) + append buffered post-execute additionalContext (model call order) as session('context/message')(s) drain steering → session('steering/message') cont = waterfall agent/turn-continuation → ContinuationDecision ({action:'continue', reason?} records reason as next-step steering) @@ -83,6 +86,8 @@ forever: Error containment: a throwing plugin ends the **turn**, never the loop. Dispose mid-turn emits `agent/status('disposed')` and ends with reason `disposed`. A step that hits the model's output-token ceiling makes the turn end `max-tokens` (the rule: any `max-tokens` step in the turn surfaces as `max-tokens`; `disposed`/`aborted`/`error` still take precedence) — distinct from a clean `completed` stop. +Tool scheduling: within one assistant step the loop partitions tool calls into ordered groups via `ctx.tools.executionMode` — an exclusive call is its own group (an ordering barrier), a run of consecutive parallel-safe calls is one group. A parallel group runs in a rolling pool: up to `maxParallelToolCalls` calls start in model order, and each settle starts the next until the group drains. Only dispatch/body overlaps — `tools/pre-execute`/`tools/post-execute` run in model call order, each STARTED call appends its own `tool/call` (whose log position may interleave with sibling `tool/result`s), and a model-order commit cursor appends `tool/result` from slot-buffered settlements so derived history stays model-ordered (pairing by the assistant message + `callId`). `additionalContext` from the group is injected in model call order after every result. Abort stops replenishment, drains only already-started calls to results, drops buffered context, and re-raises so `runTurn` owns the end reason; a group not yet started appends no `tool/call`. `maxParallelToolCalls: 1` is byte-for-byte the old serial path. + Cancellation: `agent.cancel()` is the single public stop primitive — it clears the queued + steering FIFOs, aborts the in-flight step, and drives a turn-scoped marker the driver checks at every point a turn could start or continue (right after the idle wait, after the `running` flip, before each step, and at the continuation gate) so a turn about to start is dropped. A cancelled turn ends `aborted`; a queued-but-not-started prompt never runs and cannot be batched into the cancelled turn. The marker is reset once per loop iteration, so a cancel governs exactly one turn and never leaks onto a later prompt. (The loop still aborts its own per-step `AbortController` directly on disposal and from `cancel()`; that controller is loop-internal, not a public verb.) ### What is NOT here diff --git a/packages/core/agent-loop/src/constants.ts b/packages/core/agent-loop/src/constants.ts new file mode 100644 index 0000000000..de18e0411e --- /dev/null +++ b/packages/core/agent-loop/src/constants.ts @@ -0,0 +1,15 @@ +/** + * Loop-level tunable defaults shared between the plugin entry (`index.ts`) and + * the tool-call scheduler (`tool-calls.ts`). Kept in a leaf module so importing + * a default never pulls in the service class or the scheduler. + * + * @module dsh-agent-loop/constants + */ + +/** + * Default cap on simultaneously in-flight tool calls within one assistant step, + * when {@link AgentOptions.maxParallelToolCalls} is unset. Matches the + * rolling-pool size Claude Code uses; a group larger than the cap is not + * truncated — the cap limits concurrency, not the group. + */ +export const DEFAULT_MAX_PARALLEL_TOOL_CALLS = 10 diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 4af0d464ec..3d256570c4 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -29,6 +29,22 @@ declare module 'cordis' { } } +declare module '@deepseek-ai/dsh-agent' { + interface AgentOptions { + /** + * Maximum tool calls this agent runs concurrently within one assistant step + * (a positive integer; defaults to {@link DEFAULT_MAX_PARALLEL_TOOL_CALLS}). + * The loop's rolling pool starts up to this many parallel-safe calls at once + * and replenishes as each settles; `1` preserves the fully serial path. + * A merge-extensible field — the loop owns it (it neither the agent nor the + * subagent seam sets it), read in `runStep` when scheduling a parallel group. + */ + maxParallelToolCalls?: number + } +} + +export { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from './constants.ts' + /** * Plugin config: the agents to create — or resume, via `resumeSessionId` — * declaratively at startup, so a cordis.yml deployment needs no code. @@ -40,6 +56,11 @@ export interface Config { id: AgentId /** Optional workspace cwd for the config-created fresh session. */ cwd?: string + /** + * Maximum parallel-safe tool calls to run concurrently within one assistant + * step. Must be a positive integer; `1` preserves serial execution. + */ + maxParallelToolCalls?: number /** * If set, the config agent RESUMES this persisted session id instead of * starting a fresh `${id}-session-`. Sourced from an env var in @@ -81,6 +102,9 @@ export class AgentLoop extends Service implements AgentFactory { model: z.string(), cwd: z.string(), resumeSessionId: z.string(), + // A positive integer; a bad value (0, negative, fractional) fails config + // validation here rather than being silently dropped from cordis.yml. + maxParallelToolCalls: z.number().step(1).min(1), })).default([]), }) as unknown as z @@ -144,6 +168,7 @@ export class AgentLoop extends Service implements AgentFactory { * @returns the running agent, owned by the calling fiber (no handle). */ create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent { + this.validateAgentOptions(options) this.assertAgentIdFree(id) // Config/programmatic path: prepare the session and let start() fold its // lifecycle into the agent's composite effect (so a fiber unload tears the @@ -168,6 +193,7 @@ export class AgentLoop extends Service implements AgentFactory { * @returns the handle whose dispose tears down exactly this agent. */ createAgent(options: CreateAgentOptions): AgentHandle { + this.validateAgentOptions(options.agentOptions ?? {}) // Check the agent id BEFORE preparing the session: register() would reject a // duplicate id only AFTER the session enters the store, leaving an orphaned // live session (and lazy persistence state) that blocks reuse of that id. @@ -196,6 +222,7 @@ export class AgentLoop extends Service implements AgentFactory { * @returns the handle for the agent resumed on the reconstructed session. */ async resume(options: ResumeAgentOptions): Promise { + this.validateAgentOptions(options.agentOptions ?? {}) // Read the service through `ctx.get('sessionPersistence')` — a direct // global-store lookup keyed by the isolate symbol — NOT // `this.ctx.sessionPersistence`. AgentLoop deliberately does NOT inject @@ -228,6 +255,7 @@ export class AgentLoop extends Service implements AgentFactory { * AgentLoop's static inject, so they resolve fine). */ private async resumeWith(persistence: SessionPersistence, options: ResumeAgentOptions): Promise { + this.validateAgentOptions(options.agentOptions ?? {}) this.assertAgentIdFree(options.agentId) const { meta, events } = await persistence.load(options.resumeSessionId) // Re-check the agent id AFTER the await: the pre-load check above can go @@ -267,6 +295,14 @@ export class AgentLoop extends Service implements AgentFactory { } } + /** Validate merge-extended options the loop owns before any session is prepared or loaded. */ + private validateAgentOptions(options: AgentOptions): void { + const { maxParallelToolCalls } = options + if (maxParallelToolCalls !== undefined && (!Number.isInteger(maxParallelToolCalls) || maxParallelToolCalls < 1)) { + throw new Error('maxParallelToolCalls must be a positive integer') + } + } + /** * Shared: construct a ReactLoopAgent over a PREPARED (not-yet-entered) * session, then build the ONE composite effect that owns the whole agent diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 33ddee8f64..87b82f7563 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -10,7 +10,7 @@ import type { Context } from 'cordis' import type { FinishReason, GenerateOptions, LlmCallConfig, Message } from '@deepseek-ai/dsh-llm' import { BlockAssembler, HarnessError, deepFreeze } from '@deepseek-ai/dsh-llm' -import type { ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' +import type { ContinuationDecision, PromptDecision } from '@deepseek-ai/dsh-agent' import { canonicalHeader } from '@deepseek-ai/dsh-session' import type { Session, TurnEndReason, TurnTrigger } from '@deepseek-ai/dsh-session' import { createTransmissionLog, recordRequestHeader } from './request-log.ts' @@ -18,6 +18,7 @@ import type { TransmissionLog } from './request-log.ts' import { renderPrompt } from '@deepseek-ai/dsh-system-prompt' import type { PromptAssembly } from '@deepseek-ai/dsh-system-prompt' import type {} from '@deepseek-ai/dsh-tools' +import { executeToolCalls } from './tool-calls.ts' import type { ReactLoopAgent } from './agent.ts' /** An Error with an optional machine-readable code (e.g., from LlmError or a throwing plugin). */ @@ -172,11 +173,12 @@ export interface LoopHandle { * session('assistant/chunk') * msg = waterfall agent/step-result ⟵ BEFORE the log append, so the * session('assistant/message' {content, usage?}) session records what actually ran - * each tool-call in msg (sequential, abort-checked): - * session('tool/call'); ctx.tools.execute() ⟵ tools/pre-execute (allow/deny/ask) - * → dispatch → tools/post-execute - * session('tool/result') - * append buffered post-execute additionalContext → session('context/message')(s) + * schedule tool-calls in msg by ctx.tools.executionMode (exclusive = barrier; + * consecutive parallel-safe = one rolling-pool group, ≤ maxParallelToolCalls in flight): + * each STARTED call: session('tool/call'); tools/pre-execute (MODEL order) + * → tools/execute dispatch/body (parallel pool) → tools/post-execute (MODEL order) + * session('tool/result') committed in MODEL order (slot-buffered) + * append buffered post-execute additionalContext (model order) → session('context/message')(s) * drain steering → session('steering/message') * session('step/end') ⟵ durable step boundary (no agent/* mirror) * cont = waterfall agent/turn-continuation ⟵ ContinuationDecision; default @@ -864,68 +866,26 @@ async function runStep( ) } - // --- Tool execution (sequential; parallel execution is a TODO) --- - // ToolRegistry.execute converts tool failures (including aborts) into - // isError results, so abort is re-checked around every call here. + // --- Tool execution (scheduled by per-call concurrency safety) --- + // executeToolCalls groups the step's calls by ctx.tools.executionMode and runs + // parallel-safe runs through a rolling pool. Only dispatch/body overlaps: + // tools/pre-execute and tools/post-execute run in model order, tool/result is + // committed in model order, and the returned additionalContext buffer is + // ordered the same way. Tool failures (including aborts) become isError + // results; the scheduler re-checks the shared signal around calls and throws + // the abort so this step's caller ends the turn. const toolCalls = message.content.filter(block => block.type === 'tool-call') // Per-step buffer of `additionalContext` attached by tools/post-execute // listeners. Appended as context/message(s) only AFTER every tool/result for // the step, so a multi-call step keeps tool-call/result adjacency // (interleaving context between a call's result and the next call's would // break the pairing the next model request relies on). - const pendingContext: HookContext[] = [] - for (const call of toolCalls) { - /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ - if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) - const callEvent = session.append('tool/call', { turn, step, callId: call.id, name: call.name, arguments: call.arguments }) - let parsedArguments: unknown - try { - parsedArguments = call.arguments ? JSON.parse(call.arguments) : {} - } catch { - parsedArguments = call.arguments - } - // TODO(pre-tool-input-rewrite): tools/pre-execute deliberately cannot rewrite - // `arguments` — tool/call (the audit record) and assistant/message (the - // model-history source) are logged BEFORE execute, and live consumers (ACP, - // tool-bash presentation) read the pre-execution args, so an execution-only - // rewrite would desync the UI from what ran. Designing that consistently is - // its own proposed RFC (docs/rfc/proposed/feature/…-pre-tool-input-rewrite.md). - const result = await ctx.tools.execute({ - callId: call.id, - name: call.name, - arguments: parsedArguments, - agent, - signal, - }) - session.append('tool/result', { - turn, step, - // The correlation id MUST be the loop's authoritative call.id (the - // model-transcript id that deriveMessages turns into toolCallId), NOT - // result.callId — a post-execute waterfall listener returning a - // mismatched id would otherwise orphan the call↔result pairing in the - // next model request. A listener-internal id, if ever needed, belongs in - // a separate diagnostic field, never overloaded onto callId. - callId: call.id, - content: result.content, - isError: result.isError, - ...result.error ? { error: result.error } : {}, - // The tool's private presentation payload (e.g. a result-time diff), - // persisted so a UI bridge reproduces the card on replay. - ...result.meta !== undefined ? { meta: result.meta } : {}, - }, { surfaceOp: 'append', sourceEventSeqs: [callEvent.seq] }) - // Buffer (don't append yet) any post-execute additionalContext for this call. - if (result.additionalContext) pendingContext.push(result.additionalContext) - // signal CAN flip during the await above (abort() inside a tool); - // the analyzer can't see through the await boundary. - /* v8 ignore start -- signal.reason default unreachable: cancel()/disposal always set it */ - // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition - if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) - /* v8 ignore stop */ - } + const pendingContext = await executeToolCalls(ctx, agent, turn, step, toolCalls, signal) // Append buffered post-execute context AFTER every tool/result, preserving // tool-call/result adjacency across the whole batch. inject() appends into the - // open turn (a context/message at its chronological position). + // open turn (a context/message at its chronological position). The scheduler + // returns the buffer in model call order. for (const context of pendingContext) { agent.inject(context.content, { source: context.source }) } diff --git a/packages/core/agent-loop/src/tool-calls.ts b/packages/core/agent-loop/src/tool-calls.ts new file mode 100644 index 0000000000..69ec2b0751 --- /dev/null +++ b/packages/core/agent-loop/src/tool-calls.ts @@ -0,0 +1,326 @@ +/** + * The agent loop's per-step tool-call scheduler. `runStep` (loop.ts) hands it + * the assistant message's `tool-call` blocks; this module parses each call's + * arguments once, classifies it via `ctx.tools.executionMode`, partitions the + * calls into ordered groups (one exclusive call, or a run of consecutive + * parallel-safe calls), and executes each group — a parallel group through a + * rolling pool bounded by the agent's `maxParallelToolCalls`. + * + * The session log stays the source of truth and is reconstructable regardless + * of dispatch timing: each STARTED call appends its own `tool/call` before its + * body runs, `tool/result` events are appended in MODEL order (slot-buffered + * behind a commit cursor), and buffered `additionalContext` is injected in model + * call order after every result. A `tool/call`'s log position may interleave + * with a sibling's `tool/result` as the pool replenishes; that is safe because + * `tool/call` is log-only and derived history pairs the assistant message's + * `tool-call` blocks with the ordered `tool/result`s by `callId`. + * + * @module dsh-agent-loop/tool-calls + */ + +import type { Context } from 'cordis' +import { assertNever, type ToolCallBlock } from '@deepseek-ai/dsh-llm' +import type { HookContext } from '@deepseek-ai/dsh-agent' +import type { Session } from '@deepseek-ai/dsh-session' +import { TOOL_REGISTRY_SCHEDULER, type ToolExecution, type ToolExecutionResult } from '@deepseek-ai/dsh-tools' +import type { ReactLoopAgent } from './agent.ts' +import { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from './constants.ts' + +/** One tool call after argument parsing, ready to schedule. */ +interface PlannedCall { + /** The model-transcript call (authoritative `id`/`name`/raw `arguments`). */ + block: ToolCallBlock + /** The distinct per-call execution object handed to the tool pipeline. */ + exec: ToolExecution +} + +/** A settled call's slot, filled in model order before ordered finalization. */ +interface Slot { + /** The raw dispatch/pre result. */ + result: ToolExecutionResult + /** Whether the result still needs ordered `tools/post-execute` finalization. */ + needsPost: boolean +} + +/** + * Execute one assistant step's tool calls, honoring per-call concurrency safety. + * + * Appends `tool/call` (per started call) and `tool/result` (in model order) to + * the session, and returns the ordered `additionalContext` buffer for the loop + * to inject after the batch. On abort it drains only already-started calls to + * results, drops buffered context, and throws the abort error so `runTurn` owns + * the turn-end reason. + * + * @param ctx - the loop context (reaches `ctx.tools`). + * @param agent - the agent being driven (owns the session, options, and is + * passed to each `ToolExecution`). + * @param turn - the current turn number (for the session events). + * @param step - the current step number (for the session events). + * @param toolCalls - the assistant message's `tool-call` blocks, in model order. + * @param signal - the step's abort signal (shared by every call). + * @returns the per-step `additionalContext` buffer in model call order. + */ +export async function executeToolCalls( + ctx: Context, + agent: ReactLoopAgent, + turn: number, + step: number, + toolCalls: ToolCallBlock[], + signal: AbortSignal, +): Promise { + const { session, options } = agent + const maxParallel = options.maxParallelToolCalls ?? DEFAULT_MAX_PARALLEL_TOOL_CALLS + + // Plan: parse each call's raw JSON arguments exactly once, and build one + // distinct ToolExecution per call so a `tools/execute` wrapper that mutates + // `exec` in place (e.g. replacing exec.signal with a per-call deadline) cannot + // race through a shared payload. + const planned: PlannedCall[] = toolCalls.map(block => ({ + block, + exec: { + callId: block.id, + name: block.name, + arguments: parseArguments(block.arguments), + agent, + signal, + }, + })) + + // Partition into ordered groups: an exclusive call is its own group (a + // barrier), a run of consecutive parallel-safe calls is one group. Grouping + // uses executionMode so an exclusive tool between two reads splits them into + // separate ordered groups (no read/write race inside one assistant step). + const groups = groupByMode(ctx, planned) + + const pendingContext: HookContext[] = [] + for (const group of groups) { + // Groups are never empty (groupByMode only pushes non-empty runs/singletons). + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- non-empty group + const first = group[0]! + if (group.length === 1 && ctx.tools.executionMode(first.exec).kind === 'exclusive') { + await runExclusive(ctx, session, turn, step, first, signal, pendingContext) + } else { + await runParallelGroup(ctx, session, turn, step, group, signal, maxParallel, pendingContext) + } + } + return pendingContext +} + +/** Parse a model-produced raw arguments string, falling back to the raw string on invalid JSON (empty ⇒ `{}`). */ +function parseArguments(raw: string): unknown { + try { + return raw ? JSON.parse(raw) : {} + } catch { + return raw + } +} + +/** + * Group planned calls into ordered runs: each exclusive call is a singleton + * group; consecutive parallel-safe calls coalesce into one group. `executionMode` + * is queried once per call here and again by the caller to pick the exclusive + * fast-path — both reads are pure and cheap. + */ +function groupByMode(ctx: Context, planned: PlannedCall[]): PlannedCall[][] { + const groups: PlannedCall[][] = [] + let run: PlannedCall[] = [] + const flush = (): void => { + if (run.length > 0) { + groups.push(run) + run = [] + } + } + for (const call of planned) { + if (ctx.tools.executionMode(call.exec).kind === 'parallel') { + run.push(call) + } else { + flush() + groups.push([call]) + } + } + flush() + return groups +} + +/** + * The exclusive single-call path keeps the public one-call pipeline sequential: + * abort-check, `tool/call`, pre/dispatch/post via `ctx.tools.execute`, + * `tool/result`, buffer context, post-await abort-check. + */ +async function runExclusive( + ctx: Context, + session: Session, + turn: number, + step: number, + call: PlannedCall, + signal: AbortSignal, + pendingContext: HookContext[], +): Promise { + /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ + if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) + const callSeq = appendToolCall(session, turn, step, call.block) + const result = await ctx.tools.execute(call.exec) + appendToolResult(session, turn, step, call.block, result, callSeq) + if (result.additionalContext) pendingContext.push(result.additionalContext) + // signal CAN flip during the await above (abort() inside a tool); the analyzer + // can't see through the await boundary. + /* v8 ignore start -- signal.reason default unreachable: cancel()/disposal always set it */ + // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition + if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) + /* v8 ignore stop */ +} + +/** + * The rolling-pool path for a group of parallel-safe calls. Starts calls in + * model order up to `maxParallel`, and whenever one settles starts the next + * unstarted call until the group is exhausted. Settled dispatches land in + * model-order slots; a commit cursor appends `tool/result` (and collects + * `additionalContext`) only while the next slot is ready, so the log stays + * model-ordered regardless of completion order. + * + * Abort: an already-aborted signal starts nothing and throws before any + * `tool/call`. An abort mid-group stops replenishment, awaits only the started + * calls, commits their results in order, drops buffered context, and throws. + */ +async function runParallelGroup( + ctx: Context, + session: Session, + turn: number, + step: number, + group: PlannedCall[], + signal: AbortSignal, + maxParallel: number, + pendingContext: HookContext[], +): Promise { + /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ + if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) + + const slots: (Slot | undefined)[] = group.map(() => undefined) + // callSeqs[i] is the `tool/call` event seq for started slot i (its provenance + // for the matching tool/result). A slot is only committed after it is started, + // so its callSeq is always set by then. + const callSeqs: number[] = group.map(() => -1) + let nextToStart = 0 + let committed = 0 + let started = 0 + let aborted: boolean = signal.aborted + + // Advance the commit cursor over contiguous settled slots: run post-execute in + // model order, append each tool/result, and collect its additionalContext. + const commitReady = async (): Promise => { + while (committed < group.length) { + const slot = slots[committed] + if (slot === undefined) break + const call = group[committed] + const result = slot.needsPost + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- bounded index + ? await ctx.tools[TOOL_REGISTRY_SCHEDULER].finalize(call!.exec, slot.result) + : slot.result + // committed < group.length, so call and its callSeq (set at start) exist. + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- bounded index + appendToolResult(session, turn, step, call!.block, result, callSeqs[committed]!) + if (result.additionalContext) pendingContext.push(result.additionalContext) + committed++ + } + } + + const inFlight = new Map>() + + const startCall = async (index: number): Promise => { + // index is always < group.length (bounded by every caller). + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- bounded index + const call = group[index]! + callSeqs[index] = appendToolCall(session, turn, step, call.block) + started++ + const prepared = await ctx.tools[TOOL_REGISTRY_SCHEDULER].prepare(call.exec) + switch (prepared.kind) { + case 'dispatch': { + const promise = ctx.tools[TOOL_REGISTRY_SCHEDULER].dispatch(call.exec).then((result) => { + slots[index] = { result, needsPost: true } + return index + }) + inFlight.set(index, promise) + break + } + case 'post-result': + slots[index] = { result: prepared.result, needsPost: true } + break + case 'final-result': + slots[index] = { result: prepared.result, needsPost: false } + break + /* v8 ignore next -- closed-union exhaustiveness guard */ + default: + assertNever(prepared, 'tool-call scheduler prepare result') + } + } + + const fillPool = async (): Promise => { + while (!aborted && nextToStart < group.length && inFlight.size < maxParallel) { + await startCall(nextToStart) + nextToStart++ + await commitReady() + // The signal CAN flip while an ordered pre-execute listener is running. + if (signal.aborted) aborted = true + } + } + + // Prime the pool up to the cap. Ordered pre-execute listeners may be async; + // dispatch/body is the only stage that overlaps across in-flight calls. + await fillPool() + while (inFlight.size > 0) { + const settledIndex = await Promise.race(inFlight.values()) + inFlight.delete(settledIndex) + // Commit every contiguous settled slot now available. + await commitReady() + // The signal CAN flip during the await above (abort() inside a tool); the + // analyzer can't see through the await boundary. An abort stops the pool + // from starting any further calls, but already-started calls still drain. + // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition + if (signal.aborted) aborted = true + await fillPool() + } + + if (aborted) { + // Every started call has settled and committed in order; buffered context + // from this aborted step is dropped (not injected). Raise the abort so the + // existing runTurn catch owns turn/end reason selection. Unstarted calls + // beyond the cap never appended a tool/call. + /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ + throw new Error(String(signal.reason ?? 'aborted')) + } + // A defensive check the started count matches what we committed — a parallel + // group with no abort commits every started slot, and started === group.length. + /* v8 ignore next -- unreachable: a non-aborted group starts and commits all calls */ + if (committed !== started) throw new Error('tool-call scheduler: uncommitted settled calls') +} + +/** Append the `tool/call` audit event for one started call; returns its seq (the tool/result's provenance). */ +function appendToolCall(session: Session, turn: number, step: number, block: ToolCallBlock): number { + const event = session.append('tool/call', { turn, step, callId: block.id, name: block.name, arguments: block.arguments }) + return event.seq +} + +/** Append one call's `tool/result`, keyed by the authoritative model-transcript call id and provenanced to its `tool/call`. */ +function appendToolResult( + session: Session, + turn: number, + step: number, + block: ToolCallBlock, + result: ToolExecutionResult, + callSeq: number, +): void { + session.append('tool/result', { + turn, step, + // The correlation id MUST be the loop's authoritative call.id (the + // model-transcript id deriveMessages turns into toolCallId), NOT + // result.callId — a post-execute listener returning a mismatched id would + // otherwise orphan the call↔result pairing in the next model request. + callId: block.id, + content: result.content, + isError: result.isError, + ...result.error ? { error: result.error } : {}, + // The tool's private presentation payload (e.g. a result-time diff), + // persisted so a UI bridge reproduces the card on replay. + ...result.meta !== undefined ? { meta: result.meta } : {}, + }, { surfaceOp: 'append', sourceEventSeqs: [callSeq] }) +} diff --git a/packages/core/agent-loop/tests/tool-calls.spec.ts b/packages/core/agent-loop/tests/tool-calls.spec.ts new file mode 100644 index 0000000000..af4e68f9a7 --- /dev/null +++ b/packages/core/agent-loop/tests/tool-calls.spec.ts @@ -0,0 +1,462 @@ +/** + * The per-step tool-call scheduler (`tool-calls.ts`): grouping by + * `ctx.tools.executionMode`, the rolling pool for parallel groups, model-order + * `tool/result` commit despite out-of-order settlement, interleaved `tool/call` + * audit records, ordered `tools/pre-execute`/`tools/post-execute`, + * model-ordered `additionalContext`, and abort behavior. + * + * Tools are mocked and deterministic — no real API, no snapshot here (the + * transcript-facing live-order behavior is pinned by the ACP snapshot goldens). + */ + +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import { CallId, StreamChunk } from '@deepseek-ai/dsh-llm' +import SessionStore, { SessionEvent, SessionId } from '@deepseek-ai/dsh-session' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import LlmService from '@deepseek-ai/dsh-llm' +import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools' +import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { MockAdapter, textResponse } from './mock-adapter.ts' + +async function harness(adapter: MockAdapter) { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt, { persona: '' }) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentLoop, { agents: [] }) + ctx.llm.registerAdapter(['mock'], adapter) + return ctx +} + +function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { + return new Promise((resolve) => { + const dispose = ctx.on('agent/status', (subject, status) => { + if (subject === agent && status === 'idle') { dispose(); resolve() } + }) + }) +} + +function events(agent: ReactLoopAgent): SessionEvent[] { + return [...agent.session.events] +} + +/** An assistant message with N tool-call blocks named `name` (ids c1..cN, arg = index). */ +function multiCall(calls: { id: string; name: string; args: object }[]): StreamChunk[] { + const chunks: StreamChunk[] = [] + calls.forEach((call, index) => { + chunks.push( + { type: 'block-start', index, blockType: 'tool-call' }, + { type: 'block-end', index, block: { type: 'tool-call', id: CallId(call.id), name: call.name, arguments: JSON.stringify(call.args) } }, + ) + }) + chunks.push( + { type: 'usage', usage: { inputTokens: 5, outputTokens: 5 } }, + { type: 'finish', reason: { kind: 'tool-calls' } }, + ) + return chunks +} + +/** A parallel-safe tool whose calls block until the test releases them by callId. */ +function gatedParallelTool(name: string) { + const gates = new Map void>() + const started: string[] = [] + const tool = defineTool({ + name, + description: `gated ${name}`, + parameters: { id: { type: 'string', required: true } }, + isConcurrencySafe: () => true, + async execute(args) { + started.push(args.id) + await new Promise((resolve) => { gates.set(args.id, resolve) }) + return [{ type: 'text', text: `done-${args.id}` }] + }, + }) + return { + tool, + started, + /** Release one in-flight call by its arg id (its `execute` resolves). */ + release(id: string) { gates.get(id)?.(); gates.delete(id) }, + pending() { return [...gates.keys()] }, + } +} + +/** Poll until `predicate` holds, letting microtasks/timers drain between checks. */ +async function until(predicate: () => boolean): Promise { + for (let i = 0; i < 1000 && !predicate(); i++) await new Promise(r => setTimeout(r, 0)) + if (!predicate()) throw new Error('until: condition never held') +} + +describe('tool-call scheduler: grouping and barriers', () => { + it('runs parallel-safe siblings concurrently (all start before any completes)', async () => { + const adapter = new MockAdapter([ + multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }, { id: 'c3', name: 'p', args: { id: '3' } }]), + textResponse('done'), + ]) + const ctx = await harness(adapter) + const gated = gatedParallelTool('p') + ctx.tools.register(gated.tool) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + + agent.send([{ type: 'text', text: 'go' }]) + // All three start before any is released — proof of concurrency. + await until(() => gated.started.length === 3) + expect(gated.started).toEqual(['1', '2', '3']) + gated.release('1'); gated.release('2'); gated.release('3') + await waitForIdle(ctx, agent) + }) + + it('an exclusive call between two parallel-safe calls forms a barrier (3 groups)', async () => { + // read A (safe), write A (exclusive), read A (safe) → the write must not + // overlap either read. The exclusive tool records whether a read was still + // in flight when it ran. + const order: string[] = [] + const adapter = new MockAdapter([ + multiCall([ + { id: 'c1', name: 'r', args: { id: 'A1' } }, + { id: 'c2', name: 'w', args: { id: 'A2' } }, + { id: 'c3', name: 'r', args: { id: 'A3' } }, + ]), + textResponse('done'), + ]) + const ctx = await harness(adapter) + ctx.tools.register(defineTool({ + name: 'r', description: 'read', parameters: { id: { type: 'string', required: true } }, + isConcurrencySafe: () => true, + async execute(args) { order.push(`r-start-${args.id}`); order.push(`r-end-${args.id}`); return [{ type: 'text', text: 'r' }] }, + })) + ctx.tools.register(defineTool({ + name: 'w', description: 'write', parameters: { id: { type: 'string', required: true } }, + async execute(args) { order.push(`w-${args.id}`); return [{ type: 'text', text: 'w' }] }, + })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + + // The write ran strictly between the two reads (barrier ordering). + expect(order).toEqual(['r-start-A1', 'r-end-A1', 'w-A2', 'r-start-A3', 'r-end-A3']) + }) +}) + +describe('tool-call scheduler: model-order results despite out-of-order settlement', () => { + it('commits tool/result in model order even when a later call settles first', async () => { + const adapter = new MockAdapter([ + multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]), + textResponse('done'), + ]) + const ctx = await harness(adapter) + const gated = gatedParallelTool('p') + ctx.tools.register(gated.tool) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + + agent.send([{ type: 'text', text: 'go' }]) + await until(() => gated.started.length === 2) + // Release the SECOND call first; its result must NOT be committed until the + // first commits (the commit cursor holds it in a slot). + gated.release('2') + await new Promise(r => setTimeout(r, 5)) + const beforeFirst = events(agent).filter(e => e.type === 'tool/result') + expect(beforeFirst).toEqual([]) + gated.release('1') + await waitForIdle(ctx, agent) + + const results = events(agent).filter(e => e.type === 'tool/result') + expect(results.map(e => e.data.callId)).toEqual([CallId('c1'), CallId('c2')]) + }) + + it('derived history pairs calls in model order regardless of tool/call log interleaving', async () => { + const adapter = new MockAdapter([ + multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]), + textResponse('done'), + ]) + const ctx = await harness(adapter) + const gated = gatedParallelTool('p') + ctx.tools.register(gated.tool) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await until(() => gated.started.length === 2) + gated.release('2'); gated.release('1') + await waitForIdle(ctx, agent) + + // deriveMessages pairs the assistant tool-call blocks with tool-result + // blocks by callId — model order, independent of log interleaving. + const messages = agent.session.deriveMessages() + const toolResults = messages.flatMap(m => m.content.filter(b => b.type === 'tool-result')) + expect(toolResults.map(b => b.toolCallId)).toEqual([CallId('c1'), CallId('c2')]) + }) +}) + +describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => { + it('rejects invalid programmatic maxParallelToolCalls values before creating agents', async () => { + const ctx = await harness(new MockAdapter([])) + + expect(() => ctx.agentLoop.create(AgentId('bad-zero'), { model: 'mock', maxParallelToolCalls: 0 })) + .toThrow('maxParallelToolCalls must be a positive integer') + expect(() => ctx.agentLoop.createAgent({ + agentId: AgentId('bad-fractional'), + sessionId: SessionId('bad-fractional-session'), + agentOptions: { model: 'mock', maxParallelToolCalls: 1.5 }, + })).toThrow('maxParallelToolCalls must be a positive integer') + }) + + it('starts at most the cap, replenishing as calls settle', async () => { + const adapter = new MockAdapter([ + multiCall([1, 2, 3, 4].map(n => ({ id: `c${n}`, name: 'p', args: { id: String(n) } }))), + textResponse('done'), + ]) + const ctx = await harness(adapter) + const gated = gatedParallelTool('p') + ctx.tools.register(gated.tool) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock', maxParallelToolCalls: 2 }) + + agent.send([{ type: 'text', text: 'go' }]) + // Only 2 start initially (the cap). + await until(() => gated.started.length === 2) + await new Promise(r => setTimeout(r, 5)) + expect(gated.started).toEqual(['1', '2']) + // Releasing one starts the next in model order. + gated.release('1') + await until(() => gated.started.length === 3) + expect(gated.started).toEqual(['1', '2', '3']) + expect(events(agent) + .filter(e => e.type === 'tool/call' || e.type === 'tool/result') + .map(e => `${e.type}:${String(e.data.callId)}`) + .slice(0, 4)) + .toEqual(['tool/call:c1', 'tool/call:c2', 'tool/result:c1', 'tool/call:c3']) + gated.release('2'); gated.release('3') + await until(() => gated.started.length === 4) + gated.release('4') + await waitForIdle(ctx, agent) + expect(events(agent).filter(e => e.type === 'tool/result').map(e => e.data.callId)) + .toEqual([CallId('c1'), CallId('c2'), CallId('c3'), CallId('c4')]) + }) + + it('maxParallelToolCalls: 1 is fully serial (no second start before the first settles)', async () => { + const adapter = new MockAdapter([ + multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]), + textResponse('done'), + ]) + const ctx = await harness(adapter) + const gated = gatedParallelTool('p') + ctx.tools.register(gated.tool) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock', maxParallelToolCalls: 1 }) + agent.send([{ type: 'text', text: 'go' }]) + await until(() => gated.started.length === 1) + await new Promise(r => setTimeout(r, 5)) + expect(gated.started).toEqual(['1']) + gated.release('1') + await until(() => gated.started.length === 2) + gated.release('2') + await waitForIdle(ctx, agent) + }) +}) + +describe('tool-call scheduler: ordered middleware and additionalContext', () => { + it('tools/pre-execute and tools/post-execute observe model call order', async () => { + const adapter = new MockAdapter([ + multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }, { id: 'c3', name: 'p', args: { id: '3' } }]), + textResponse('done'), + ]) + const ctx = await harness(adapter) + const gated = gatedParallelTool('p') + ctx.tools.register(gated.tool) + const pre: string[] = [] + const post: string[] = [] + ctx.on('tools/pre-execute', async (exec, next): Promise => { pre.push(String(exec.callId)); return next() }) + ctx.on('tools/post-execute', async (exec, _result, next): Promise => { post.push(String(exec.callId)); return next() }) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + + agent.send([{ type: 'text', text: 'go' }]) + await until(() => gated.started.length === 3) + // Settle in reverse; post-execute (ordered by the commit cursor) still fires + // in model order because post runs on the commit path, not on dispatch. + gated.release('3'); gated.release('2'); gated.release('1') + await waitForIdle(ctx, agent) + + expect(pre).toEqual([CallId('c1'), CallId('c2'), CallId('c3')].map(String)) + expect(post).toEqual([CallId('c1'), CallId('c2'), CallId('c3')].map(String)) + }) + + it('injects additionalContext in model call order, not settlement order', async () => { + const adapter = new MockAdapter([ + multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]), + textResponse('done'), + ]) + const ctx = await harness(adapter) + const gated = gatedParallelTool('p') + ctx.tools.register(gated.tool) + ctx.on('tools/post-execute', async (exec, _result): Promise => + ({ kind: 'accept', additionalContext: { content: [{ type: 'text', text: `ctx-${exec.callId}` }], source: { kind: 'plugin', plugin: 'p' } } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + + agent.send([{ type: 'text', text: 'go' }]) + await until(() => gated.started.length === 2) + gated.release('2'); gated.release('1') + await waitForIdle(ctx, agent) + + const log = events(agent) + // Both tool/results precede both context/messages, and context is model-ordered. + const contextTexts = log.filter(e => e.type === 'context/message') + .map(e => (e.data.content[0] as { text: string }).text) + expect(contextTexts).toEqual(['ctx-c1', 'ctx-c2']) + const lastResult = log.findLastIndex(e => e.type === 'tool/result') + const firstContext = log.findIndex(e => e.type === 'context/message') + expect(lastResult).toBeLessThan(firstContext) + }) + + it('keeps pre-produced deny/error results ordered without dispatching those calls', async () => { + const adapter = new MockAdapter([ + multiCall([ + { id: 'c1', name: 'p', args: { id: '1' } }, + { id: 'c2', name: 'p', args: { id: '2' } }, + { id: 'c3', name: 'p', args: { id: '3' } }, + ]), + textResponse('done'), + ]) + const ctx = await harness(adapter) + const gated = gatedParallelTool('p') + ctx.tools.register(gated.tool) + const post: string[] = [] + ctx.on('tools/pre-execute', async (exec, next): Promise => { + if (exec.callId === CallId('c2')) return { kind: 'deny', reason: 'blocked by policy' } + if (exec.callId === CallId('c3')) throw new Error('pre exploded') + return next() + }) + ctx.on('tools/post-execute', async (exec, _result, next): Promise => { + post.push(String(exec.callId)) + return next() + }) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + + agent.send([{ type: 'text', text: 'go' }]) + await until(() => gated.started.length === 1) + gated.release('1') + await waitForIdle(ctx, agent) + + expect(gated.started).toEqual(['1']) + expect(post).toEqual(['c1', 'c2']) + const results = events(agent).filter(e => e.type === 'tool/result') + expect(results.map(e => e.data.callId)).toEqual([CallId('c1'), CallId('c2'), CallId('c3')]) + expect((results[1]!.data.content[0] as { text: string }).text).toContain('blocked by policy') + expect((results[2]!.data.content[0] as { text: string }).text).toContain('pre exploded') + }) +}) + +describe('tool-call scheduler: abort handling', () => { + it('starts no calls when the signal is already aborted before a parallel group', async () => { + const adapter = new MockAdapter([ + multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]), + textResponse('should never be requested'), + ]) + const ctx = await harness(adapter) + const gated = gatedParallelTool('p') + ctx.tools.register(gated.tool) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + ctx.on('session/event', (session, event) => { + if (session === agent.session && event.type === 'assistant/message') { + ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('already aborted') + } + }) + + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + + expect(gated.started).toEqual([]) + expect(events(agent).filter(e => e.type === 'tool/call')).toEqual([]) + expect(events(agent).filter(e => e.type === 'tool/result')).toEqual([]) + }) + + it('stops starting siblings when abort fires during ordered pre-execute', async () => { + const adapter = new MockAdapter([ + multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]), + textResponse('should never be requested'), + ]) + const ctx = await harness(adapter) + const gated = gatedParallelTool('p') + ctx.tools.register(gated.tool) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + ctx.on('tools/pre-execute', async (exec, next): Promise => { + if (exec.callId === CallId('c1')) { + ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('pre cancelled') + } + return next() + }) + + agent.send([{ type: 'text', text: 'go' }]) + await until(() => gated.started.length === 1) + await new Promise(r => setTimeout(r, 5)) + expect(gated.started).toEqual(['1']) + gated.release('1') + await waitForIdle(ctx, agent) + + expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId)) + .toEqual([CallId('c1')]) + expect(events(agent).filter(e => e.type === 'tool/result').map(e => e.data.callId)) + .toEqual([CallId('c1')]) + }) + + it('stops replenishing after abort, commits started results, and drops buffered additionalContext', async () => { + const adapter = new MockAdapter([ + multiCall([1, 2, 3, 4].map(n => ({ id: `c${n}`, name: 'p', args: { id: String(n) } }))), + textResponse('should never be requested'), + ]) + const ctx = await harness(adapter) + const gated = gatedParallelTool('p') + ctx.tools.register(gated.tool) + ctx.on('tools/post-execute', async (exec, _result, next): Promise => ({ + ...await next(), + additionalContext: { content: [{ type: 'text', text: `ctx-${exec.callId}` }], source: { kind: 'plugin', plugin: 'p' } }, + })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock', maxParallelToolCalls: 2 }) + + agent.send([{ type: 'text', text: 'go' }]) + await until(() => gated.started.length === 2) + ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('stop now') + gated.release('1') + gated.release('2') + await waitForIdle(ctx, agent) + + expect(gated.started).toEqual(['1', '2']) + expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId)) + .toEqual([CallId('c1'), CallId('c2')]) + expect(events(agent).filter(e => e.type === 'tool/result').map(e => e.data.callId)) + .toEqual([CallId('c1'), CallId('c2')]) + expect(events(agent).filter(e => e.type === 'context/message')).toEqual([]) + }) + + it('does not run an exclusive barrier after a parallel group aborts', async () => { + const adapter = new MockAdapter([ + multiCall([ + { id: 'c1', name: 'p', args: { id: '1' } }, + { id: 'c2', name: 'p', args: { id: '2' } }, + { id: 'c3', name: 'x', args: { id: '3' } }, + ]), + textResponse('should never be requested'), + ]) + const ctx = await harness(adapter) + const gated = gatedParallelTool('p') + const exclusive: string[] = [] + ctx.tools.register(gated.tool) + ctx.tools.register(defineTool({ + name: 'x', + description: 'exclusive', + parameters: { id: { type: 'string', required: true } }, + async execute(args) { exclusive.push(args.id); return [{ type: 'text', text: 'x' }] }, + })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock', maxParallelToolCalls: 2 }) + + agent.send([{ type: 'text', text: 'go' }]) + await until(() => gated.started.length === 2) + ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('stop before barrier') + gated.release('1') + gated.release('2') + await waitForIdle(ctx, agent) + + expect(exclusive).toEqual([]) + expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId)) + .toEqual([CallId('c1'), CallId('c2')]) + }) +}) diff --git a/packages/core/tools/README.md b/packages/core/tools/README.md index 0bf1c4bf08..5ae46fe098 100644 --- a/packages/core/tools/README.md +++ b/packages/core/tools/README.md @@ -19,6 +19,7 @@ tools: - `ctx.tools.get(name: string): ToolDefinition | undefined` - `ctx.tools.schemas(): ToolSchema[]` Schemas of all registered tools (without the `execute` functions). The shipped tools' schemas are catalogued in [docs/tool-catalog.md](../../../docs/tool-catalog.md), generated by booting each tool plugin and harvesting this method (see [the tool-schema-catalog RFC](../../../docs/rfc/implemented/process/2026-07-02-tool-schema-catalog.md)). - `ctx.tools.execute(exec: ToolExecution): Promise` Execute one tool call through the `tools/pre-execute` → `tools/execute` → `tools/post-execute` pipeline. +- `ctx.tools.executionMode(exec: ToolExecution): ToolExecutionMode` Classify how one call may be scheduled relative to its step-siblings — `{ kind: 'parallel' }` only when the registered tool's `isConcurrencySafe(exec.arguments)` returns `true`, else `{ kind: 'exclusive' }` (unknown tool, no declaration, non-`true`, or a thrown check). The agent-loop scheduler uses it to group calls; host-only, never model-visible. ### Injected services @@ -35,8 +36,9 @@ tools: ### Key types -- `ToolDefinition` — `ToolSchema` + `execute(args, exec): Promise` (the bare array is the model-facing content; the object form additionally attaches an opaque, JSON-serializable `meta` presentation payload persisted on the `tool/result` event and handed back to `presentResult`), plus optional `presentCall(args)` / `presentResult(args, result)` for tool-owned UI presentation (see below). It also carries an optional cooperative timeout budget `timeoutMs?: number` (ms) enforced by `@deepseek-ai/dsh-timeout-policy`, never sent to the model. +- `ToolDefinition` — `ToolSchema` + `execute(args, exec): Promise` (the bare array is the model-facing content; the object form additionally attaches an opaque, JSON-serializable `meta` presentation payload persisted on the `tool/result` event and handed back to `presentResult`), plus optional `presentCall(args)` / `presentResult(args, result)` for tool-owned UI presentation (see below). It also carries an optional cooperative timeout budget `timeoutMs?: number` (ms) enforced by `@deepseek-ai/dsh-timeout-policy`, and an optional synchronous `isConcurrencySafe(args): boolean` concurrency classifier read by `executionMode` — both host-only scheduler metadata, never sent to the model. - `ToolExecution` — one pending tool call: `{ callId, name, arguments, agent?, signal? }`. +- `ToolExecutionMode` — `{ kind: 'parallel' } | { kind: 'exclusive' }`, returned by `executionMode`. Object-tagged (not a bare boolean) so a future resource-grouping dimension (e.g. `{ kind: 'exclusive', group: 'session:...' }`) can extend a variant without a breaking change. - `ToolExecutionResult` — outcome: `{ callId, content, isError, error?, additionalContext?, meta? }`. On failure with a `HarnessError`, `error: { name, code }` carries the structured failure class alongside the model-facing text (the loop forwards it onto the `tool/result` session event for retry/sandbox plugins and replay). `additionalContext` (a `HookContext`) ferries any `tools/post-execute` context up to the loop, which buffers it and appends it as a `context/message` after all `tool/result`s in the step. `meta` is the tool's opaque presentation payload from a successful `execute` (the object return form); the loop forwards it onto the `tool/result` session event for result-card rendering. - `PreToolDecision` — `{kind:'allow'}` | `{kind:'deny', reason}` | `{kind:'ask', reason?}`. Input rewrite (changing `arguments`) is deliberately NOT offered (it would desync the pre-execution audit/history/UI from what ran — its own proposed RFC); `ask` is serviced by [`ctx.approval`](../../ui/user-approval/README.md) when a deployment mounts it (`allowed-once` proceeds to dispatch; `rejected`/`cancelled`/`unavailable` deny with distinct reasons) and degrades to `deny` when none is mounted or the execution carries no agent. - `PostToolDecision` — `{kind:'accept', content?, additionalContext?}` (keep the call successful, optionally replacing the model-facing content) | `{kind:'block', feedback, additionalContext?}` (turn it into an `isError` whose content is the corrective feedback). Output replacement is clean because `tool/result` is logged AFTER `execute()` returns. @@ -83,6 +85,8 @@ See `defineTool`, `validateArgs`, `ToolArgsError`, `SchemaSpec`, `InferArgs`, an `defineTool` also validates an optional `timeoutMs` at definition time when present: it must be a positive finite number, or the helper throws — the budget is attached to the produced `ToolDefinition` (for `@deepseek-ai/dsh-timeout-policy`) and never reaches the model. +`defineTool` also accepts an optional `isConcurrencySafe(args): boolean` — the per-call concurrency classifier the agent-loop scheduler reads via `executionMode`. `args` is the typed `InferArgs` shape. It is soft-validated exactly like the presenters: an arg mismatch yields `false` (the conservative exclusive default), never the hard `ToolArgsError`. Declaring `true` is a contract — the tool body must not mutate parent-owned async state (`exec.agent.session.append`, `agent.inject`) during `execute`; its only ordered outputs are the returned content, `meta`, error, and `additionalContext`. The one exception is a synchronous, side-effect-only commutative recorder (the `fs/observed` version recorder is the worked example); anything richer stays exclusive. Host-only, never model-visible. + ### Structured-output schema subset A separate vocabulary for callers that DEMAND a machine-readable value from an agent — the subagent seam's `SubagentStartRequest.outputSchema` (and, by extension, a workflow's `agent({ schema })`). Unlike `SchemaSpec` (the author-facing DSL for tool parameters), a `StructuredOutputSchema` is an object-rooted **raw JSON Schema subset** as data: it travels verbatim to the model as a forced tool's `parameters`, and the produced value is validated against it. @@ -133,12 +137,16 @@ const bash = defineTool({ Under `mode: code` (or `both`) the registry turns the tool surface into a programming API, per the [Code Mode RFC](../../../docs/rfc/implemented/feature/2026-06-15-code-mode.md): the model writes a TypeScript program (the body of an async function) and passes it to the ONE wire tool `run_code`; the program runs in `ctx.codeRuntime` (the [code-execution seam](../../code-runtime/README.md) — the shipped backend is a worker thread) with one async binding per registered tool (`await tools.bash({...})`), and ONLY what it prints or returns re-enters the model's context. - **The SDK section** (`tools:sdk`, order 150): a lazy prompt section regenerating, at each assembly, a `declare const tools: {...}` TypeScript declaration of every registered tool except `run_code` (exotic names via quoted keys), plus fixed usage instructions. Deterministic — lexicographic tool order, byte-identical text for an unchanged tool set (prefix-cache-friendly). The codegen (`jsonSchemaToTs`, exported) is TOTAL: constructs outside the `defineTool` subset degrade to `unknown`, never throw. -- **The dispatch bridge** (`run_code`'s execute): every binding call is JSON-normalized BEFORE dispatch (a value that does not survive — `BigInt`, circulars — rejects that one call, so the dispatched form and the logged form are the same JSON value by construction), serialized through a per-run queue (even `Promise.all` executes the underlying `ctx.tools.execute()` calls one at a time in submission order — the tool contract carries no concurrency-safety metadata yet), gated by `tools/pre-execute`/`tools/post-execute` like any native call (a deny reaches the program as a binding rejection), and logged as one `tool/code-dispatch` session event (log-only: `deriveMessages()` never surfaces it) with the deterministic sub-id `:code:`. A failed sub-call REJECTS the program-side promise with the tool's error text — real code error handling, no bespoke envelope. A sub-call's `additionalContext` is deliberately DROPPED (no safe outlet mid-run without breaking tool-call/result adjacency; deferred until a real hook needs it through Code Mode). +- **The dispatch bridge** (`run_code`'s execute): every binding call is JSON-normalized BEFORE dispatch (a value that does not survive — `BigInt`, circulars — rejects that one call, so the dispatched form and the logged form are the same JSON value by construction), serialized through a per-run queue (even `Promise.all` executes the underlying `ctx.tools.execute()` calls one at a time in submission order — Code Mode's in-program dispatch stays serial even though native sibling calls parallelize; lifting that is follow-up work for the Code Mode bridge), gated by `tools/pre-execute`/`tools/post-execute` like any native call (a deny reaches the program as a binding rejection), and logged as one `tool/code-dispatch` session event (log-only: `deriveMessages()` never surfaces it) with the deterministic sub-id `:code:`. A failed sub-call REJECTS the program-side promise with the tool's error text — real code error handling, no bespoke envelope. A sub-call's `additionalContext` is deliberately DROPPED (no safe outlet mid-run without breaking tool-call/result adjacency; deferred until a real hook needs it through Code Mode). - **Settlement discipline**: the bridge owns a run-scoped abort that follows the outer signal in and fires when the run settles for any reason, so a budget expiry aborts an in-flight sub-tool instead of orphaning it; the bridge then drains its queue BEFORE returning, so every `tool/code-dispatch` lands inside the open turn. A failed run throws `CodeRunFailedError` (`code: 'CODE_RUN_FAILED'`, message = the failure kind + captured logs), which the pipeline converts to a structured `isError` the model self-corrects from. The wire collapse is the registry's own contribution (`systemPrompt.tools()` is mode-aware), so the logged `request/header` records it for free — under `code`, the assembled tool list is exactly `[run_code]`, pinned by tests and the snapshot goldens. Try it: `pnpm run demo:code-mode` ([the coding-agent example's Code Mode overlay](../../../examples/coding-agent/README.md#code-mode)); `pnpm run demo:code-mode acp` serves the same mode over ACP instead of the REPL. +### Parallel execution + +A `ToolDefinition` declares per-call concurrency safety via `isConcurrencySafe(args)`; the registry's `executionMode(exec)` turns that into `{ kind: 'parallel' | 'exclusive' }`. The agent loop groups a step's calls by mode — a run of consecutive parallel calls executes in a rolling pool (bounded by the agent's `maxParallelToolCalls`), an exclusive call runs alone as an ordering barrier. Only dispatch/body overlaps; `tools/pre-execute` and `tools/post-execute` still observe model call order, and `tool/result` events are appended in model order (see [`dsh-agent-loop`](../agent-loop/README.md)). The conservative first declarations: `web_search`, `web_fetch`, filesystem `read`, and `subagent` are parallel-safe; `write`/`edit`/`todo_write`/`bash`/`bash_output`/`bash_kill` stay exclusive. `run_code` stays exclusive and its in-program dispatch stays serial. + ### What is NOT here (TODO) -- **Tool shapes review** — when real tools land (e.g. a concurrency-safety hint for parallel execution); phase 1 executes tool calls sequentially. -- **Parallel execution** — the loop currently iterates tool calls sequentially. +- **A `tools/execution-mode` waterfall** — `executionMode` is a plain method today; a Cordis seam letting hook/MCP/provider policy downgrade a tool's baseline decision is the future insertion point, not needed for the conservative first declaration set. +- **A bash read-only classifier** — `bash`/`bash_output`/`bash_kill` stay exclusive until the bash package can prove which commands are read-only; the loop never infers shell safety. diff --git a/packages/core/tools/src/index.ts b/packages/core/tools/src/index.ts index b624f468bb..26bf72c7e6 100644 --- a/packages/core/tools/src/index.ts +++ b/packages/core/tools/src/index.ts @@ -136,11 +136,6 @@ declare module 'cordis' { } } -// TODO(review): revisit these shapes when the first real tools and -// sandbox/permission plugins land (e.g. a concurrency-safety hint for -// parallel execution — Claude Code partitions read-only tools; phase 1 -// executes sequentially). - /** * What a tool's `execute` returns. The bare {@link ContentBlock}`[]` form is the * common case (model-facing content only); the object form additionally attaches @@ -163,6 +158,31 @@ export interface ToolDefinition extends ToolSchema { * cooperative implementation that can reach quiescence when the signal aborts. */ timeoutMs?: number + /** + * Optional synchronous, pure classification: may this call run concurrently + * with other tool calls in the same assistant step? The agent-loop scheduler + * calls it (via {@link ToolRegistry.executionMode}) to decide whether the call + * joins a parallel group or forms an exclusive barrier; a missing declaration, + * a thrown check, or any non-`true` return is treated as exclusive. Like + * `timeoutMs` it is host-only scheduler metadata — NEVER sent to the model, + * since `schemas()` whitelists only name/description/parameters. + * + * It may inspect the parsed `args` (`unknown` — a hand-rolled definition + * receives the raw parsed value; `defineTool` schema-validates first and + * returns `false` on invalid args, so an eventual `ToolArgsError` is produced + * only if the tool actually executes). The check performs no I/O and receives + * no live `Agent` or mutable `ToolExecution`. + * + * Declaring `true` is a contract: the tool body must NOT mutate the parent + * agent's session or other parent-owned async state during `execute` (no + * `exec.agent.session.append(...)`, no `agent.inject(...)`). Its only parent- + * step outputs are the returned content, `meta`, structured error, and + * `additionalContext` carried through the loop's ordered post-execute path. + * The narrow exception is a synchronous, side-effect-only recorder whose + * updates are commutative for concurrent calls by the same session (the + * `fs/observed` version recorder is the worked example). + */ + isConcurrencySafe?(args: unknown): boolean /** * Optional: how to present the PENDING state of one call in a UI, derived from * the call's `args` (parsed arguments, `unknown` — the tool validates/narrows @@ -209,6 +229,53 @@ export interface ToolExecution { signal?: AbortSignal } +/** + * How a single tool call may be scheduled relative to its siblings in one + * assistant step, as decided by {@link ToolRegistry.executionMode}. `parallel` + * calls may run concurrently within a rolling pool; an `exclusive` call runs + * alone and forms an ordering barrier. Object-tagged (rather than a bare + * boolean) so a future resource-grouping dimension can extend a variant — e.g. + * `{ kind: 'exclusive', group: 'session:...' }` — without a breaking change. + */ +export type ToolExecutionMode = + | { kind: 'parallel' } + | { kind: 'exclusive' } + +/** + * Internal result of the scheduler-owned `tools/pre-execute` stage. Exported + * only so `dsh-agent-loop` can split ordered middleware from concurrent + * dispatch without exposing named staged service methods on `ctx.tools`. + * @internal + */ +export type ScheduledToolPreparation = + | { kind: 'dispatch' } + | { kind: 'post-result'; result: ToolExecutionResult } + | { kind: 'final-result'; result: ToolExecutionResult } + +/** + * Internal scheduler view of the registry pipeline. `dsh-agent-loop` uses this + * symbol-keyed entry point to keep `tools/pre-execute` and `tools/post-execute` + * ordered while overlapping only `tools/execute` dispatch/body. Ordinary + * callers use {@link ToolRegistry.execute}; this symbol is not a plugin seam. + * @internal + */ +export interface ToolRegistryScheduler { + /** Run the ordered pre-execute gate and decide what stage follows. */ + prepare(exec: ToolExecution): Promise + /** Run only the around-dispatch/body stage. */ + dispatch(exec: ToolExecution): Promise + /** Run ordered post-execute finalization for a dispatch/pre result. */ + finalize(exec: ToolExecution, result: ToolExecutionResult): Promise +} + +/** + * Symbol-keyed internal scheduler entry point on {@link ToolRegistry}. The + * generated service catalog deliberately skips computed members, so this does + * not create a named public staged API. + * @internal + */ +export const TOOL_REGISTRY_SCHEDULER: unique symbol = Symbol('@deepseek-ai/dsh-tools.scheduler') + /** Structured error metadata for a failed tool call (alongside the model-facing text). */ export interface ToolErrorInfo { name: string @@ -239,7 +306,6 @@ export interface ToolExecutionResult { * text in `content` is always present; this is extra structure for code. */ error?: ToolErrorInfo - /** /** * Extra model-facing context a `tools/post-execute` listener attached for the * NEXT request (Claude Code's PostToolUse `additionalContext`). It is NOT part @@ -353,6 +419,13 @@ export class ToolRegistry extends Service { mode: z.union(['native', 'code', 'both'] as const).default('native'), }) + /** Internal staged view consumed by `dsh-agent-loop`'s parallel scheduler. */ + readonly [TOOL_REGISTRY_SCHEDULER]: ToolRegistryScheduler = { + prepare: exec => this.prepareScheduledExecution(exec), + dispatch: exec => this.dispatchScheduledExecution(exec), + finalize: (exec, result) => this.finalizeScheduledExecution(exec, result), + } + private store = new Map() private readonly mode: ToolPresentationMode @@ -472,23 +545,47 @@ export class ToolRegistry extends Service { } /** - * Execute one tool call through the `tools/pre-execute` → `tools/execute` - * (around dispatch) → `tools/post-execute` pipeline. `pre-execute` is the gate - * (allow/deny), `tools/execute` wraps core dispatch (a timeout/retry/metrics - * seam), and `post-execute` is the inspect/transform seam; core dispatch sits - * as the base `next()` of the `tools/execute` waterfall. The whole thing is - * wrapped in one outer try/catch so a throwing listener (in any waterfall) - * becomes an `isError` result instead of failing the turn; the tool body ALSO - * keeps its own inner try/catch, so a thrown tool becomes an `isError` result - * that `tools/execute` and `post-execute` listeners can still inspect. If the - * tool is not registered, the result is an `isError` carrying a `UNKNOWN_TOOL` - * structured error. A thrown {@link HarnessError} surfaces its `{ name, code }` - * on the result. - * @param exec - the call to run (name, parsed arguments, caller agent, signal). - * @returns the final result after every waterfall; failures resolve as - * `isError` results, never rejections. + * Classify how one pending call may be scheduled relative to its siblings in + * the same assistant step. Looks up the registered tool and calls its + * `isConcurrencySafe(exec.arguments)` classifier. The default is exclusive: + * an unknown tool, a tool with no `isConcurrencySafe` declaration, a check + * that returns any non-`true` value, and a check that THROWS all resolve to + * `{ kind: 'exclusive' }` — only an explicit `true` yields `{ kind: 'parallel' }`. + * + * This is a plain method, not a cordis waterfall: the conservative first + * declaration set needs no policy-driven downgrade, and the method boundary + * leaves room to introduce a `tools/execution-mode` seam later if a real + * deployment needs hook, MCP, or provider policy to override a tool's baseline + * decision. + * @param exec - the call to classify (its `name` selects the tool, its parsed + * `arguments` feed the classifier). No I/O runs and `exec` is not mutated. + * @returns `{ kind: 'parallel' }` only when the registered tool's check + * returns `true`; `{ kind: 'exclusive' }` otherwise. */ - async execute(exec: ToolExecution): Promise { + executionMode(exec: ToolExecution): ToolExecutionMode { + const tool = this.store.get(exec.name) + if (!tool?.isConcurrencySafe) return { kind: 'exclusive' } + try { + return tool.isConcurrencySafe(exec.arguments) ? { kind: 'parallel' } : { kind: 'exclusive' } + } catch { + // A thrown classifier is a tool-authoring bug, not a scheduling signal: + // fail closed to exclusive so a broken check can never widen concurrency. + return { kind: 'exclusive' } + } + } + + /** + * Run the ordered `tools/pre-execute` gate for the agent-loop scheduler. This + * is an internal factoring point, not a plugin seam; ordinary callers use + * {@link execute}, which still performs the full sequential pipeline. A + * non-allow decision returns a result that still needs ordered post-execute + * finalization; a throwing pre listener returns a final error result. + * @param exec - the call to prepare. + * @returns whether the scheduler should dispatch the tool, post-process a + * pre-produced result, or use a final error result as-is. + * @internal + */ + private async prepareScheduledExecution(exec: ToolExecution): Promise { try { // --- Gate: tools/pre-execute. An `ask` resolves through the approval // seam (or degrades) to allow/deny before the shared deny path. --- @@ -503,16 +600,27 @@ export class ToolRegistry extends Service { content: [{ type: 'text', text: `Error: ${decision.reason}` }], isError: true, } - return await this.postExecute(exec, denied) + return { kind: 'post-result', result: denied } } + return { kind: 'dispatch' } + } catch (error: unknown) { + return { kind: 'final-result', result: toolErrorResult(exec.callId, error) } + } + } - // --- Around-dispatch: tools/execute. The base `next` is the dispatch- - // with-normalization thunk — the tool body's own try/catch turns a throw - // into an isError result so a wrapper (and post-execute) can inspect it; - // an unknown tool routes through the same catch. A `tools/execute` listener - // (e.g. a timeout plugin) wraps this thunk: it may mutate `exec` before - // delegating and inspect the normalized result after. --- - const result = await this.ctx.waterfall( + /** + * Run only the concurrent dispatch/body stage for the agent-loop scheduler. + * The `tools/execute` around-dispatch waterfall wraps the normalized tool body + * here; ordered pre/post remain the scheduler's responsibility. Ordinary + * callers use {@link execute}. + * @param exec - the already-prepared call to dispatch. + * @returns the raw dispatch result before `tools/post-execute`; failures are + * normalized into `isError` results. + * @internal + */ + private async dispatchScheduledExecution(exec: ToolExecution): Promise { + try { + return await this.ctx.waterfall( this, 'tools/execute', exec, async (): Promise => { try { @@ -530,11 +638,7 @@ export class ToolRegistry extends Service { } }, ) - - return await this.postExecute(exec, result) } catch (error: unknown) { - // Outer backstop: a throwing pre/post-execute listener (or the waterfall - // machinery) becomes an isError result, never a turn failure. return toolErrorResult(exec.callId, error) } } @@ -577,6 +681,50 @@ export class ToolRegistry extends Service { } } + /** + * Run the ordered `tools/post-execute` finalization stage for the agent-loop + * scheduler. This is an internal factoring point paired with + * {@link prepareScheduledExecution} and {@link dispatchScheduledExecution}; + * ordinary callers use {@link execute}. + * @param exec - the call whose dispatch result is being finalized. + * @param result - the dispatch result or pre-produced denial result. + * @returns the final tool result after post-execute; throwing listeners are + * normalized into `isError` results. + * @internal + */ + private async finalizeScheduledExecution(exec: ToolExecution, result: ToolExecutionResult): Promise { + try { + return await this.postExecute(exec, result) + } catch (error: unknown) { + return toolErrorResult(exec.callId, error) + } + } + + /** + * Execute one tool call through the `tools/pre-execute` → `tools/execute` + * (around dispatch) → `tools/post-execute` pipeline. `pre-execute` is the gate + * (allow/deny), `tools/execute` wraps core dispatch (a timeout/retry/metrics + * seam), and `post-execute` is the inspect/transform seam; core dispatch sits + * as the base `next()` of the `tools/execute` waterfall. The staged scheduler + * helpers above are internal factoring points for the agent loop; this public + * one-call API remains the sequential composition direct callers use. Failures + * in any stage resolve as `isError` results instead of failing the turn. If the + * tool is not registered, the result is an `isError` carrying a `UNKNOWN_TOOL` + * structured error. A thrown {@link HarnessError} surfaces its `{ name, code }` + * on the result. + * @param exec - the call to run (name, parsed arguments, caller agent, signal). + * @returns the final result after every waterfall; failures resolve as + * `isError` results, never rejections. + */ + async execute(exec: ToolExecution): Promise { + const prepared = await this.prepareScheduledExecution(exec) + if (prepared.kind === 'final-result') return prepared.result + const result = prepared.kind === 'post-result' + ? prepared.result + : await this.dispatchScheduledExecution(exec) + return await this.finalizeScheduledExecution(exec, result) + } + /** * Run the `tools/post-execute` waterfall over a dispatched `result` and apply * its {@link PostToolDecision}: `accept` keeps the call successful (replacing diff --git a/packages/core/tools/src/schema.ts b/packages/core/tools/src/schema.ts index 1a428ffd40..a3ea4e1d32 100644 --- a/packages/core/tools/src/schema.ts +++ b/packages/core/tools/src/schema.ts @@ -302,6 +302,16 @@ export interface DefineToolOptions { * is never sent to the model. */ timeoutMs?: number + /** + * Optional synchronous concurrency-safety classifier (see + * {@link ToolDefinition.isConcurrencySafe}). `args` is the typed, schema- + * validated shape — zero casts. Validated SOFTLY, mirroring the presenters: + * on an arg mismatch the produced classifier returns `false` (the conservative + * exclusive default) instead of the hard {@link ToolArgsError} the execute path + * raises, since replay/scheduling may feed older-schema args. Host-only — never + * sent to the model. + */ + isConcurrencySafe?(args: InferArgs): boolean /** * Tool execution function. `args` is typed as {@link InferArgs} — zero * casts needed. Returns either a bare {@link ContentBlock}`[]` (model-facing @@ -357,9 +367,9 @@ export interface DefineToolOptions { * execute body, and optional presenters. * @returns a registry-ready {@link ToolDefinition}: its `execute` validates the * raw args first (throwing {@link ToolArgsError} on mismatch, which the - * registry turns into an isError result), and its presenters validate softly - * (returning undefined on mismatch, since replay may feed them older-schema - * args). + * registry turns into an isError result), and its presenters and + * `isConcurrencySafe` classifier validate softly (returning undefined/`false` + * on mismatch, since replay/scheduling may feed them older-schema args). */ export function defineTool(options: DefineToolOptions): ToolDefinition { // Object-literal execute methods don't use `this`; the reference is safe. @@ -369,6 +379,8 @@ export function defineTool(options: DefineToolOptions): const userPresentCall = options.presentCall // eslint-disable-next-line @typescript-eslint/unbound-method const userPresentResult = options.presentResult + // eslint-disable-next-line @typescript-eslint/unbound-method + const userIsConcurrencySafe = options.isConcurrencySafe if (options.timeoutMs !== undefined && (!Number.isFinite(options.timeoutMs) || options.timeoutMs <= 0)) { throw new Error(`defineTool(${options.name}): timeoutMs must be a positive finite number`) } @@ -403,5 +415,15 @@ export function defineTool(options: DefineToolOptions): return userPresentResult(args as InferArgs, result) } } + // Concurrency classification is host-only scheduler metadata (never sent to + // the model) and, like the presenters, may run against replay/scheduling args + // from an older schema — so it validates SOFTLY: an arg mismatch returns + // `false` (conservative exclusive default), never the hard ToolArgsError. + if (userIsConcurrencySafe) { + tool.isConcurrencySafe = (args: unknown): boolean => { + if (validateArgs(options.parameters, args).length > 0) return false + return userIsConcurrencySafe(args as InferArgs) + } + } return tool } diff --git a/packages/core/tools/tests/execution-mode.spec.ts b/packages/core/tools/tests/execution-mode.spec.ts new file mode 100644 index 0000000000..443581d239 --- /dev/null +++ b/packages/core/tools/tests/execution-mode.spec.ts @@ -0,0 +1,133 @@ +/** + * Per-call concurrency classification: `ToolDefinition.isConcurrencySafe`, + * `defineTool()`'s soft-validated forwarding of it, and the registry's + * `executionMode(exec)` decision. Also proves the classifier never leaks into + * the model-facing `schemas()` projection. + */ + +import { describe, expect, expectTypeOf, it } from 'vitest' +import { Context } from 'cordis' +import { CallId } from '@deepseek-ai/dsh-llm' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry, { + defineTool, + type ToolDefinition, + type ToolExecution, + type ToolExecutionMode, +} from '@deepseek-ai/dsh-tools' + +async function setup() { + const ctx = new Context() + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + return ctx +} + +function exec(name: string, args: unknown): ToolExecution { + return { callId: CallId('c1'), name, arguments: args } +} + +describe('ToolRegistry.executionMode', () => { + it('returns parallel only when the registered tool declares isConcurrencySafe → true', async () => { + const ctx = await setup() + ctx.tools.register(defineTool({ + name: 'safe', + description: 'parallel-safe', + parameters: {}, + isConcurrencySafe: () => true, + async execute() { return [] }, + })) + expect(ctx.tools.executionMode(exec('safe', {}))).toEqual({ kind: 'parallel' }) + }) + + it('defaults to exclusive for a tool with no isConcurrencySafe declaration', async () => { + const ctx = await setup() + ctx.tools.register(defineTool({ + name: 'plain', + description: 'no declaration', + parameters: {}, + async execute() { return [] }, + })) + expect(ctx.tools.executionMode(exec('plain', {}))).toEqual({ kind: 'exclusive' }) + }) + + it('returns exclusive for an unknown tool', async () => { + const ctx = await setup() + expect(ctx.tools.executionMode(exec('nonexistent', {}))).toEqual({ kind: 'exclusive' }) + }) + + it('returns exclusive when the classifier returns false for these args', async () => { + const ctx = await setup() + // Input-sensitive: safe to read, unsafe to write — the same tool differs by args. + ctx.tools.register(defineTool({ + name: 'rw', + description: 'read or write', + parameters: { mode: { type: 'string', required: true } }, + isConcurrencySafe: args => args.mode === 'read', + async execute() { return [] }, + })) + expect(ctx.tools.executionMode(exec('rw', { mode: 'read' }))).toEqual({ kind: 'parallel' }) + expect(ctx.tools.executionMode(exec('rw', { mode: 'write' }))).toEqual({ kind: 'exclusive' }) + }) + + it('a defineTool classifier soft-fails to exclusive on invalid args (no ToolArgsError)', async () => { + const ctx = await setup() + // The typed classifier would read args.mode, but the required arg is missing: + // soft validation returns false (exclusive) rather than throwing, matching the + // presenter pattern. Executing the same bad args WOULD raise ToolArgsError. + ctx.tools.register(defineTool({ + name: 'needs-mode', + description: 'requires mode', + parameters: { mode: { type: 'string', required: true } }, + isConcurrencySafe: () => true, + async execute() { return [] }, + })) + expect(ctx.tools.executionMode(exec('needs-mode', {}))).toEqual({ kind: 'exclusive' }) + }) + + it('a thrown classifier fails closed to exclusive (raw definition)', async () => { + const ctx = await setup() + // A hand-rolled ToolDefinition (not via defineTool) whose check throws. + const raw: ToolDefinition = { + name: 'thrower', + description: 'classifier throws', + parameters: { type: 'object', properties: {} }, + isConcurrencySafe() { throw new Error('boom') }, + async execute() { return [] }, + } + ctx.tools.register(raw) + expect(ctx.tools.executionMode(exec('thrower', {}))).toEqual({ kind: 'exclusive' }) + }) + + it('a raw definition (no defineTool) receives the raw parsed value', async () => { + const ctx = await setup() + let seen: unknown + ctx.tools.register({ + name: 'raw-safe', + description: 'raw', + parameters: { type: 'object', properties: {} }, + isConcurrencySafe(args) { seen = args; return true }, + async execute() { return [] }, + }) + expect(ctx.tools.executionMode(exec('raw-safe', { anything: 1 }))).toEqual({ kind: 'parallel' }) + expect(seen).toEqual({ anything: 1 }) + }) + + it('isConcurrencySafe never reaches the model-facing schemas() projection', async () => { + const ctx = await setup() + ctx.tools.register(defineTool({ + name: 'safe', + description: 'parallel-safe', + parameters: { x: { type: 'string', required: true } }, + isConcurrencySafe: () => true, + async execute() { return [] }, + })) + const schema = ctx.tools.schemas()[0] as unknown as Record + expect(Object.keys(schema).sort()).toEqual(['description', 'name', 'parameters']) + expect(schema.isConcurrencySafe).toBeUndefined() + }) + + it('ToolExecutionMode is the object-tagged union', () => { + expectTypeOf().toEqualTypeOf<{ kind: 'parallel' } | { kind: 'exclusive' }>() + }) +}) diff --git a/packages/fs/tool-fs/README.md b/packages/fs/tool-fs/README.md index fedd1ff7a2..5817c0eb95 100644 --- a/packages/fs/tool-fs/README.md +++ b/packages/fs/tool-fs/README.md @@ -46,4 +46,6 @@ The tool passes `exec` (the tool-execution context) as the opaque `actor` on eve `fs/observed` fires AFTER the read/write/edit already succeeded, via a plain `ctx.emit`. A listener is contractually a synchronous, side-effect-only recorder (`@deepseek-ai/dsh-fs-policy`'s is a `WeakMap.set`); the tool does not guard the emit, so a listener that throws would surface as the tool's `isError` result — async or fallible observation does not belong on this event. +This is exactly why `read` declares `isConcurrencySafe: () => true` while `write`/`edit` do not: `read`'s only side effect is that synchronous commutative recorder (same-target concurrent reads converge to one observed version), so the agent loop may run sibling reads in parallel. `write`/`edit` mutate the filesystem and stay exclusive barriers — the provider re-checks the observed version inside its per-target lock before mutating, so a stale read never corrupts (it only forces a re-read). See the [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md). + The read rendering (line windowing + output formatting) lives in `src/read-render.ts` (Cordis-free, independently unit-tested); `src/read.ts`/`write.ts`/`edit.ts` are the tool executors and `src/index.ts` composes them. diff --git a/packages/fs/tool-fs/src/read.ts b/packages/fs/tool-fs/src/read.ts index 039d8742e9..dc43177726 100644 --- a/packages/fs/tool-fs/src/read.ts +++ b/packages/fs/tool-fs/src/read.ts @@ -92,6 +92,11 @@ export function applyReadTool(ctx: Context, caps: ReadToolCaps): void { offset: { type: 'number', description: '1-based first line to return. Defaults to 1.' }, limit: { type: 'number', description: `Maximum number of lines to return. Defaults to ${caps.limit}.` }, }, + // Read-only. Its one side effect is the synchronous, commutative `fs/observed` + // version recorder (a WeakMap write; see below and the fs-policy plugin), so + // concurrent same-target reads converge to one observed version. write/edit + // stay exclusive barriers and re-check versions in-lock before mutating. + isConcurrencySafe: () => true, async execute(args, exec): Promise { const input = parseReadArgs(args, caps.limit) const cwd = sessionCwd(exec) diff --git a/packages/fs/tool-fs/tests/tools.spec.ts b/packages/fs/tool-fs/tests/tools.spec.ts index 53f912cce2..e394e45452 100644 --- a/packages/fs/tool-fs/tests/tools.spec.ts +++ b/packages/fs/tool-fs/tests/tools.spec.ts @@ -106,6 +106,16 @@ describe('registration', () => { expect(ctx.tools.schemas().map(s => s.name).sort()).toEqual(['edit', 'read', 'write']) }) + it('declares read parallel-safe while write/edit remain exclusive', async () => { + const { ctx } = await setup() + expect(ctx.tools.executionMode({ callId: CallId('read-safe'), name: 'read', arguments: { file_path: 'a.txt' } })) + .toEqual({ kind: 'parallel' }) + expect(ctx.tools.executionMode({ callId: CallId('write-exclusive'), name: 'write', arguments: { file_path: 'a.txt', content: 'x' } })) + .toEqual({ kind: 'exclusive' }) + expect(ctx.tools.executionMode({ callId: CallId('edit-exclusive'), name: 'edit', arguments: { file_path: 'a.txt', old_string: 'x', new_string: 'y' } })) + .toEqual({ kind: 'exclusive' }) + }) + it('registers prompt sections for each tool', async () => { const { ctx } = await setup() const prompt = renderPrompt(await ctx.systemPrompt.assemble()) diff --git a/packages/subagent/README.md b/packages/subagent/README.md index 87930167e9..eb491b8f77 100644 --- a/packages/subagent/README.md +++ b/packages/subagent/README.md @@ -14,4 +14,6 @@ The subagent seam: an agent delegating work to a child agent. Like the [bash](.. The interface lives at `subagent/subagent/`. The in-process `subagent-spawn` / `subagent-fork` backends share the `subagent-inprocess` driver (a pure library — both depend on it, neither on the other), the out-of-process `subagent-acp` backend builds on the `subagent-subprocess` library (the credential env scrub, the dispose ladder, isolated config dirs) and ships alongside them here; the test-only `dsh-subagent-mock` (in [support](../support/README.md)) is separate. All **product** packages except the mock. +`SubagentProvider.start()` must be safe to call concurrently for independent runs: the `subagent` tool is parallel-safe, so one parent step may issue several subagent calls at once. Each backend reads the parent synchronously at start (a snapshot, never mutated or re-read during the run) — `fork` seeds each child from the parent's completed-turn prefix, which the open in-flight turn cannot change, so concurrent forks inside one open step all see the same stable prefix. A resource-limited provider may queue or cap internally, but must not require the loop to serialize every call. + The proposal and design rationale: [docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md](../../docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md). diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index fb512c0bdb..cb19b27d34 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -182,6 +182,19 @@ export interface SubagentProvider { * Start a child run. The service has already validated that every requested * start-time capability is supported, so an implementation may assume e.g. * `request.maxDepth` is honorable when present. + * + * MUST be safe to call concurrently for independent runs: the `subagent` tool + * is parallel-safe, so a parent step may issue several subagent calls at once, + * each invoking `start()` before an earlier run settles. An implementation + * reads the parent SYNCHRONOUSLY at start (a snapshot — never mutating or + * re-reading it during the run) so concurrent starts inside the parent's one + * open step all observe the same stable state; the fork backend seeds each + * child from the parent's completed-turn prefix, which the open in-flight turn + * cannot change. A provider backed by a limited resource may queue internally, + * apply its own capacity cap, or return a typed failure for the affected run — + * but it must NOT require the parent loop to serialize every `subagent` call. + * @param request - the start request (prompt, parent, and any start-time options). + * @returns the started {@link SubagentRun}. */ start(request: SubagentStartRequest): SubagentRun } diff --git a/packages/subagent/tool-subagent/README.md b/packages/subagent/tool-subagent/README.md index 6fe26d3083..936965bc72 100644 --- a/packages/subagent/tool-subagent/README.md +++ b/packages/subagent/tool-subagent/README.md @@ -21,3 +21,7 @@ The tool description and the `prompt` parameter description are DERIVED from the `execute` starts a run on the configured provider and **awaits `run.result` inside a `try/finally` that always `dispose()`s the run** — the owned child agent/session is torn down on every path (success, error, abort), never leaked. The tool's abort signal (`exec.signal`) is bridged to `run.cancel()`. A non-`completed` stop reason (aborted/error/max-tokens/refusal) maps to an `isError` tool result rather than returning partial output as success. Background / poll collection is deferred (see the [RFC](../../../docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md)); this cut blocks the parent turn until the child finishes. + +## Concurrency + +The tool declares `isConcurrencySafe: () => true`: each call starts an independent child run and returns only its final answer, touching no parent-agent state, and `SubagentProvider.start()` is contractually concurrent-safe for independent runs (see [subagent/](../README.md)). So the agent loop may run several `subagent` calls from one assistant step in parallel, and the tool description tells the model it may issue independent tasks together when their work scopes do not overlap. The subagent tool stays synchronous (one result = the child's final answer); background spawning + later collection is separate future work. diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index f48ef4345e..e487d49046 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -119,7 +119,8 @@ export function providerWording(inherits: boolean): { description: string; promp + 'completed turns so far (it does not see the current in-flight turn), returning only its final ' + 'result. Use this when the subtask builds on this conversation\'s context — a follow-up analysis, ' + 'a review, a continuation — without consuming this conversation\'s context for the work itself. ' - + 'You receive only its final answer, not its intermediate steps.', + + 'You receive only its final answer, not its intermediate steps. You may issue several subagent ' + + 'calls in one message to run independent tasks concurrently when their work scopes do not overlap.', promptDescription: 'The task for the subagent. It already sees this conversation\'s completed turns, so build on them ' + 'freely and state only what is new.', @@ -131,7 +132,8 @@ export function providerWording(inherits: boolean): { description: string; promp + 'and return its final result. Use this to offload focused, independent work — research, a scoped ' + 'implementation, an analysis — so it does not consume this conversation\'s context. The subagent ' + 'runs to completion and you receive only its final answer, not its intermediate steps. Give it a ' - + 'complete, standalone prompt: it does not see this conversation.', + + 'complete, standalone prompt: it does not see this conversation. You may issue several subagent ' + + 'calls in one message to run independent tasks concurrently when their work scopes do not overlap.', promptDescription: 'The complete, self-contained task for the subagent. It does not share this ' + 'conversation\'s context, so include everything it needs.', @@ -165,6 +167,12 @@ export function apply(ctx: Context, config: Config): void { description: wording.promptDescription, }, }, + // Each call starts an independent child run and returns only its final + // answer; the tool touches no parent-agent state. SubagentProvider.start() + // is contractually safe to call concurrently for independent runs (a + // resource-limited provider queues internally), so sibling subagent calls + // may run in parallel. + isConcurrencySafe: () => true, async execute(args, exec): Promise { const parent = exec.agent if (!parent) { diff --git a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts index 611069ef76..f08521ef20 100644 --- a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts +++ b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts @@ -68,6 +68,15 @@ describe('dsh-tool-subagent', () => { expect(Object.keys(props).sort()).toEqual(['description', 'prompt']) }) + it('declares each subagent call parallel-safe through the shared tool scheduler contract', async () => { + const ctx = await setup({ provider: 'mock' }) + expect(ctx.tools.executionMode({ + callId: CallId('subagent-safe'), + name: 'subagent', + arguments: { description: 'do work', prompt: 'Reply OK' }, + })).toEqual({ kind: 'parallel' }) + }) + it.each([ { stopReason: 'aborted' as const, fragment: 'cancelled' }, { stopReason: 'error' as const, fragment: 'failed' }, diff --git a/packages/web/tool-web/README.md b/packages/web/tool-web/README.md index ab1326a21e..858b91e397 100644 --- a/packages/web/tool-web/README.md +++ b/packages/web/tool-web/README.md @@ -11,6 +11,8 @@ Each tool is registered independently; a product that wants only one disables th | `web_search` | `query` (string) | Discovery. Returns an optional answer plus source URLs. `max_results` is **not** model-facing — the tool sets the bound (the `searchMaxResults` config, default 8) and passes it to the seam. | | `web_fetch` | `url` (string) | Retrieves a specific URL. HTML bodies are rendered to markdown-ish text; text bodies pass through. A non-2xx status is reported, not an error. The tool-call timeout is deployment policy (`dsh-timeout-policy`), not a model argument. | +Both tools declare `isConcurrencySafe: () => true` — they are read-only (fetch a provider/URL, return content, mutate no parent-agent state), so the agent loop may run sibling web calls in parallel. + ## Config | Key | Default | Meaning | diff --git a/packages/web/tool-web/src/fetch.ts b/packages/web/tool-web/src/fetch.ts index 571ce00797..9246134fc7 100644 --- a/packages/web/tool-web/src/fetch.ts +++ b/packages/web/tool-web/src/fetch.ts @@ -99,6 +99,9 @@ export function applyWebFetchTool(ctx: Context, timeoutMs: number): void { url: { type: 'string', required: true, description: 'The HTTP(S) URL to fetch.' }, }, timeoutMs, + // Read-only: fetching a URL returns content and mutates no parent-agent + // state — safe to run concurrently with sibling calls. + isConcurrencySafe: () => true, async execute(args, exec): Promise { const input = parseFetchArgs(args) const result = await ctx.web.fetch( diff --git a/packages/web/tool-web/src/search.ts b/packages/web/tool-web/src/search.ts index a7587d328b..c4e715e51e 100644 --- a/packages/web/tool-web/src/search.ts +++ b/packages/web/tool-web/src/search.ts @@ -109,6 +109,9 @@ export function applyWebSearchTool(ctx: Context, maxResults: number, timeoutMs: query: { type: 'string', required: true, description: 'The search query.' }, }, timeoutMs, + // Read-only: a search hits the provider and returns content, mutating no + // parent-agent state — safe to run concurrently with sibling calls. + isConcurrencySafe: () => true, async execute(args, exec): Promise { const input = parseSearchArgs(args) const result = await ctx.web.search( diff --git a/packages/web/tool-web/tests/tool-web.spec.ts b/packages/web/tool-web/tests/tool-web.spec.ts index 4bb2728df7..543bd8e234 100644 --- a/packages/web/tool-web/tests/tool-web.spec.ts +++ b/packages/web/tool-web/tests/tool-web.spec.ts @@ -166,6 +166,10 @@ describe('tool-web registration', () => { const names = ctx.tools.schemas().map(s => s.name) expect(names).toContain('web_search') expect(names).toContain('web_fetch') + expect(ctx.tools.executionMode({ callId: CallId('search-safe'), name: 'web_search', arguments: { query: 'q' } })) + .toEqual({ kind: 'parallel' }) + expect(ctx.tools.executionMode({ callId: CallId('fetch-safe'), name: 'web_fetch', arguments: { url: 'https://a.test' } })) + .toEqual({ kind: 'parallel' }) await fiber.dispose() expect(ctx.tools.schemas().map(s => s.name)).not.toContain('web_search') }) diff --git a/scripts/gen-cordis-catalog.ts b/scripts/gen-cordis-catalog.ts index 7c6666542b..951e5789fa 100644 --- a/scripts/gen-cordis-catalog.ts +++ b/scripts/gen-cordis-catalog.ts @@ -91,6 +91,7 @@ export const LINK_MAP: Record = { TurnEndReason: 'session.md', ToolDefinition: 'tools.md', ToolExecution: 'tools.md', + ToolExecutionMode: 'tools.md', ToolExecutionResult: 'tools.md', ApprovalOutcome: 'approval.md', ApprovalPolicy: 'approval.md', diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index ec92045069..72470f5707 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -674,10 +674,14 @@ function renderLifecycle(): string { ` Session-->>SDK: ${mermaidCode('session/event')} ${mermaidCode('assistant/chunk')}*`, ` Driver->>Hooks: ${mermaidCode('agent/step-result')} waterfall`, ` Driver->>Session: ${mermaidCode('assistant/message')}`, - ` Driver->>Session: ${mermaidCode('tool/call')}`, - ' Driver->>Tools: execute through pre and post waterfalls', - ' Tools-->>Session: tool-owned events when applicable', - ` Driver->>Session: ${mermaidCode('tool/result')} and ${mermaidCode('step/end')}`, + ' Driver->>Tools: group calls by executionMode', + ' loop started tool calls (bounded pool)', + ` Driver->>Session: ${mermaidCode('tool/call')} pending audit`, + ' Driver->>Tools: ordered pre / pooled dispatch / ordered post', + ' Tools-->>Session: tool-owned events when applicable', + ' end', + ` Driver->>Session: ${mermaidCode('tool/result')} in model order`, + ` Driver->>Session: ${mermaidCode('step/end')}`, ` Driver->>Hooks: ${mermaidCode('agent/turn-continuation')} waterfall`, ` Driver->>Session: ${mermaidCode('turn/end')}`, ` Driver->>Persistence: ${mermaidCode('session/flush')} parallel checkpoint`, diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index e87d945497..3f2443ab79 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -40,6 +40,7 @@ { "doc": "docs/core-data-structures/tools.md", "symbol": "SchemaSpec", "source": "packages/core/tools/src/schema.ts" }, { "doc": "docs/core-data-structures/tools.md", "symbol": "InferArgs", "source": "packages/core/tools/src/schema.ts" }, { "doc": "docs/core-data-structures/tools.md", "symbol": "ToolExecution", "source": "packages/core/tools/src/index.ts" }, + { "doc": "docs/core-data-structures/tools.md", "symbol": "ToolExecutionMode", "source": "packages/core/tools/src/index.ts" }, { "doc": "docs/core-data-structures/tools.md", "symbol": "ToolExecutionResult", "source": "packages/core/tools/src/index.ts" }, { "doc": "docs/core-data-structures/tools.md", "symbol": "PreToolDecision", "source": "packages/core/tools/src/index.ts" }, { "doc": "docs/core-data-structures/tools.md", "symbol": "PostToolDecision", "source": "packages/core/tools/src/index.ts" }, From fdf5e08548a8350c3ffb53eafc44c1d43ef65725 Mon Sep 17 00:00:00 2001 From: Dudu-0223 Date: Mon, 13 Jul 2026 11:55:51 +0800 Subject: [PATCH 014/359] test(tool-fs): cover stale read observation fail-closed --- packages/fs/tool-fs/tests/integration.spec.ts | 29 +++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/packages/fs/tool-fs/tests/integration.spec.ts b/packages/fs/tool-fs/tests/integration.spec.ts index c0973197eb..3ee23a2590 100644 --- a/packages/fs/tool-fs/tests/integration.spec.ts +++ b/packages/fs/tool-fs/tests/integration.spec.ts @@ -398,6 +398,35 @@ describe('signal, concurrency, and the fs/observed contract', () => { expect(onDisk === 'ONE value here' || onDisk === 'base TWO here').toBe(true) }) + it('a stale observed version from an older read fails closed at edit CAS', async () => { + await writeFile(join(dir, 'a.txt'), 'older content\n') + const target = await ctx.fs.resolve('a.txt') + const firstInfo = await ctx.fs.stat(target) + if (!firstInfo) throw new Error('expected first stat') + + expect((await callOwned('read', { file_path: 'a.txt' })).isError).toBe(false) + + await writeFile(join(dir, 'a.txt'), 'newer current content\n') + const secondInfo = await ctx.fs.stat(target) + if (!secondInfo) throw new Error('expected second stat') + expect(secondInfo.version).not.toBe(firstInfo.version) + expect((await callOwned('read', { file_path: 'a.txt' })).isError).toBe(false) + + // Simulate an older concurrent read finishing last and overwriting the + // observed-state WeakMap with the stale version it saw before the external + // file change. The provider's in-lock CAS is still the safety boundary. + ctx.emit('fs/observed', target, firstInfo.version, { agent: { session } }) + + const edit = await callOwned('edit', { + file_path: 'a.txt', + old_string: 'newer', + new_string: 'edited', + }) + expect(edit.isError).toBe(true) + expect(edit.error).toMatchObject({ code: 'FS_STALE_VERSION' }) + expect(await readFile(join(dir, 'a.txt'), 'utf8')).toBe('newer current content\n') + }) + it('a throwing fs/observed listener surfaces as isError, but the mutation already hit disk', async () => { // fs/observed is a plain ctx.emit AFTER the write succeeded; a throwing // listener cannot roll the write back — it only turns the tool result into From 320de5466afa2de305064f25e9d7f2ce4c3fd245 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Mon, 13 Jul 2026 13:44:01 +0800 Subject: [PATCH 015/359] feat(session-query): add relationship tracing (round 1) --- docs/architecture.md | 2 +- docs/capability-seams.md | 4 +- docs/config-catalog.md | 2 +- docs/cordis-catalog/services.md | 6 +- docs/core-data-structures/core.md | 2 +- docs/core-data-structures/session-query.md | 54 ++- docs/rfc/INDEX.md | 1 + .../2026-07-10-session-query-service.md | 13 +- .../2026-07-13-session-query-tracing.md | 34 ++ ...026-07-10-sqlite-session-query-provider.md | 6 +- packages/README.md | 2 +- .../cordis/tool-cordis/src/api-catalog.ts | 20 +- packages/session-query/README.md | 6 +- .../session-query/session-query/README.md | 12 +- .../session-query/session-query/package.json | 2 +- .../session-query/session-query/src/config.ts | 6 +- .../session-query/session-query/src/index.ts | 54 +-- .../session-query/src/tracing.ts | 277 +++++++++++++ .../session-query/session-query/src/types.ts | 58 ++- .../session-query/tests/tracing.spec.ts | 376 ++++++++++++++++++ scripts/gen-doc-graphs.ts | 4 +- scripts/type-equiv.manifest.json | 4 + 22 files changed, 885 insertions(+), 60 deletions(-) create mode 100644 docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md create mode 100644 packages/session-query/session-query/src/tracing.ts create mode 100644 packages/session-query/session-query/tests/tracing.spec.ts diff --git a/docs/architecture.md b/docs/architecture.md index 0b8cb6e304..79d59981e8 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -35,7 +35,7 @@ Composition is preferred over inheritance. `packages/core/` is a repository grou | `ctx.subagents` | [`subagent/`](../packages/subagent/README.md) | named delegation providers | | `ctx.workflows` | [`workflow/`](../packages/workflow/README.md) | script-driven multi-agent orchestration | | `ctx.sessionPersistence` | [`session-persistence/`](../packages/session-persistence/README.md) | durable storage for session logs | -| `ctx.sessionQuery` | [`session-query/`](../packages/session-query/README.md) | live-preferred logical-corpus and exact-event reads | +| `ctx.sessionQuery` | [`session-query/`](../packages/session-query/README.md) | live-preferred exact reads and relationship traces | ## Event diff --git a/docs/capability-seams.md b/docs/capability-seams.md index dd7e3f2379..15887725e1 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -25,7 +25,7 @@ flowchart LR pkg_session_persistence_jsonl["session-persistence-jsonl"] pkg_session_persistence_sqlite["session-persistence-sqlite"] pkg_acp["acp"] - svc_sessionQuery["ctx.sessionQuery
Exact session-history reads"] + svc_sessionQuery["ctx.sessionQuery
Exact session-history reads and traces"] pkg_system_prompt["system-prompt"] svc_systemPrompt["ctx.systemPrompt
System prompt assembly registry"] pkg_tools["tools"] @@ -181,7 +181,7 @@ flowchart LR | `ctx.llm` | `seam` | [`llm`](../packages/llm/llm) | [`llm-deepseek`](../packages/llm/llm-deepseek), [`llm-pi-ai`](../packages/llm/llm-pi-ai), [`llm-replay`](../packages/support/llm-replay) | [`agent-loop`](../packages/core/agent-loop), [`compact-basic`](../packages/compact/compact-basic) | - | Adapters register provider implementations; the loop and compaction call the provider-neutral stream service. | | `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. | | `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`session-query`](../packages/session-query/session-query) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. | -| `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | - | - | - | Resolves live and optional persisted logs into one logical corpus for exact reads. | +| `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | - | - | - | Resolves live and optional persisted logs into one logical corpus for exact reads and relationship traces. | | `ctx.systemPrompt` | `core` | [`system-prompt`](../packages/core/system-prompt) | - | [`agent-loop`](../packages/core/agent-loop), [`tools`](../packages/core/tools), [`tool-fs`](../packages/fs/tool-fs), [`tool-web`](../packages/web/tool-web) | - | Collects prompt sections and model-facing tool schemas for each step. | | `ctx.tools` | `core` | [`tools`](../packages/core/tools) | - | [`agent-loop`](../packages/core/agent-loop), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tool-bash`](../packages/bash/tool-bash), [`tool-cordis`](../packages/cordis/tool-cordis), [`tool-fs`](../packages/fs/tool-fs), [`tool-skill`](../packages/skill/tool-skill), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-todo`](../packages/todo/tool-todo), [`tool-web`](../packages/web/tool-web), [`acp`](../packages/ui/acp) | - | Registers tool definitions, exposes schemas to the prompt, and routes calls through tools/pre-execute and tools/post-execute. | | `ctx.userInteraction` | `seam` | [`user-interaction`](../packages/ui/user-interaction) | [`stdio-agent`](../packages/ui/stdio-agent), [`acp`](../packages/ui/acp) | [`tool-ask-user`](../packages/ui/tool-ask-user), [`stdio-agent`](../packages/ui/stdio-agent), [`acp`](../packages/ui/acp) | - | UI front doors provide the active human-answer provider; tool-ask-user pauses a tool call on the provider-neutral ask() promise. | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 6193ff8449..608046d053 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -578,7 +578,7 @@ Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:5 Requires: `sessions` ```ts config-catalog -/** Configuration for exact session-query reads. */ +/** Configuration for exact session-query reads and traces. */ export interface Config { /** Maximum accepted raw read context on either side. Defaults to 50. */ readWindowMax?: number diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index d8e4cbb107..666dbb0b33 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -203,15 +203,17 @@ Source: [`packages/session-persistence/session-persistence/src/index.ts:102`](.. ## `ctx.sessionQuery` — `SessionQueryService` -Live-preferred logical-corpus and exact-event read service. +Live-preferred logical-corpus exact-read and relationship-tracing service. ```ts cordis-catalog listSessions(): Promise async listEvents(sessionId: SessionId): Promise +async traceSession(sessionId: SessionId): Promise +async traceEvent(request: SessionEventTraceRequest): Promise async readEvent(request: SessionEventReadRequest): Promise ``` -Source: [`packages/session-query/session-query/src/index.ts:35`](../../packages/session-query/session-query/src/index.ts) +Source: [`packages/session-query/session-query/src/index.ts:38`](../../packages/session-query/session-query/src/index.ts) ## `ctx.sessions` — `SessionStore` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 6a2cbcfa60..b2d07b229c 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -18,7 +18,7 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t | [llm-streaming.md](llm-streaming.md) | the `StreamChunk` wire protocol + adapter contract, `BlockAssembler`, the `LlmAdapter` seam | | [session.md](session.md) | the full `SessionEventMap` variant catalog, `TurnTrigger`/`TurnEndReason`, `deriveMessages()`, the turn-enclosure invariant | | [persistence.md](persistence.md) | the durability seam: `SessionPersistence`, JSONL + SQLite backends, `session/flush`, crash recovery, `SessionHeader` | -| [session-query.md](session-query.md) | logical session/event records and bounded exact-event reads | +| [session-query.md](session-query.md) | logical records, bounded exact-event reads, and relationship traces | | [tools.md](tools.md) | `ToolDefinition` full fields, the schema DSL, `ToolExecution`/`ToolResult`, tool-presentation UI types, the `tools/pre-execute`/`tools/post-execute` pipeline | | [user-interaction.md](user-interaction.md) | the UI-backed human question/answer seam: `AskUserQuestionRequest`, answer/options vocabulary, provider API, error taxonomy | | [approval.md](approval.md) | the one-shot user-approval seam: `ApprovalRequest`, `ApprovalOutcome`, per-session policy, audit and answerer contracts | diff --git a/docs/core-data-structures/session-query.md b/docs/core-data-structures/session-query.md index ded8ca3f7e..71fb956dcb 100644 --- a/docs/core-data-structures/session-query.md +++ b/docs/core-data-structures/session-query.md @@ -1,6 +1,6 @@ # Session Query -Exact reads over the live-preferred logical session corpus. The [package contract](../../packages/session-query/session-query) owns source precedence, dynamic optional persistence, cloning, surface classification, bounded windows, and typed failures. Full-text search is a separate proposed SQLite phase. +Exact reads and relationship traces over the live-preferred logical session corpus. The [package contract](../../packages/session-query/session-query) owns source precedence, dynamic optional persistence, cloning, surface classification, bounded windows, tracing validation, and typed failures. Full-text search is a separate proposed SQLite package. Source: [`packages/session-query/session-query/src/types.ts`](../../packages/session-query/session-query/src/types.ts) @@ -30,6 +30,34 @@ export interface SessionEventRecord { } ``` +## Session lineage + +`SessionLineageTrace` carries known parents in immediate-to-outward order and a forest of recursively nested direct descendants. The completeness discriminant makes a known root and a missing parent mutually exclusive. + +```ts type-equiv +export interface SessionLineageNode { + session: SessionRecord + descendants: SessionLineageNode[] +} +``` + +```ts type-equiv +export type SessionLineageTrace = { + target: SessionRecord + ancestors: SessionRecord[] + descendants: SessionLineageNode[] +} & ( + | { + complete: true + root: SessionRecord + } + | { + complete: false + unresolvedParentId: SessionId + } +) +``` + ## Bounded event reads The request addresses one raw seq and optional neighboring counts. The result carries a `SessionHeader` rather than availability flags so a known live target can remain independent of persistence health. @@ -53,6 +81,28 @@ export interface SessionEventWindow { } ``` +## Event relationships + +Event traces distinguish positional surface replacement from logged provenance. Every seq list contains direct links except `replacementChain`, which follows immediate replacers from the target to the final positional replacement. + +```ts type-equiv +export interface SessionEventTraceRequest { + sessionId: SessionId + seq: number +} +``` + +```ts type-equiv +export interface SessionEventTrace { + target: SessionEventRecord + replacedBy?: number + replacementChain: number[] + replacedEventSeqs: number[] + sourceEventSeqs: number[] + derivedEventSeqs: number[] +} +``` + ## Errors The closed code union distinguishes request validation, missing targets, malformed surface logs, optional-backend failure, and contradictory source metadata. @@ -61,6 +111,8 @@ The closed code union distinguishes request validation, missing targets, malform export type SessionQueryErrorCode = | 'SESSION_QUERY_EVENT_NOT_FOUND' | 'SESSION_QUERY_INVALID_CONFIG' + | 'SESSION_QUERY_INVALID_LINEAGE' + | 'SESSION_QUERY_INVALID_PROVENANCE' | 'SESSION_QUERY_INVALID_SURFACE' | 'SESSION_QUERY_INVALID_WINDOW' | 'SESSION_QUERY_PERSISTENCE_FAILED' diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index c202cc358c..d6bbed97ea 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -72,6 +72,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Repeat-tool-call guard plugin](implemented/feature/2026-07-08-repeat-tool-guard.md) | 2026-07-08 | | [The self-referential cordis toolset](implemented/feature/2026-07-08-self-referential-cordis-toolset.md) | 2026-07-08 | | [Exact session query service](implemented/feature/2026-07-10-session-query-service.md) | 2026-07-10 | +| [Session query relationship tracing](implemented/feature/2026-07-13-session-query-tracing.md) | 2026-07-13 | ### Simplification diff --git a/docs/rfc/implemented/feature/2026-07-10-session-query-service.md b/docs/rfc/implemented/feature/2026-07-10-session-query-service.md index 7e13256669..ebc201f102 100644 --- a/docs/rfc/implemented/feature/2026-07-10-session-query-service.md +++ b/docs/rfc/implemented/feature/2026-07-10-session-query-service.md @@ -4,13 +4,13 @@ Status: implemented ## Problem -Session history exists in two places: current `SessionStore` objects and an optional persistence backend. Consumers that need exact inspection would otherwise duplicate live-versus-persisted precedence, persistence lifecycle handling, raw-event surface classification, and defensive cloning. Durable state can lag the live log between checkpoints, so persistence alone is not a truthful current source. +Session history exists in two places: current `SessionStore` objects and an optional persistence backend. Consumers that need exact inspection would otherwise duplicate live-versus-persisted precedence, persistence lifecycle handling, raw-event surface classification, relationship tracing, and defensive cloning. Durable state can lag the live log between checkpoints, so persistence alone is not a truthful current source. Full-text search is related but materially larger. Designing provider registration, extraction, synchronization, invalidation, ranking, and cursor contracts before a real backend exists creates two speculative state machines: one in the interface service and another in the eventual database package. ## Decision -`@deepseek-ai/dsh-session-query` owns `ctx.sessionQuery`, a small trusted exact-read service over one logical corpus. It exposes `listSessions()`, `listEvents(sessionId)`, and bounded `readEvent(request)`. It does not expose filters, lineage or provenance traversals, text extractors, search requests, provider registration, or derived-index synchronization. +`@deepseek-ai/dsh-session-query` owns `ctx.sessionQuery`, a small trusted exact-inspection service over one logical corpus. It exposes `listSessions()`, `listEvents(sessionId)`, bounded `readEvent(request)`, `traceSession(sessionId)`, and `traceEvent(request)`. It does not expose filters, text extractors, search requests, provider registration, or derived-index synchronization. The separate [tracing decision](2026-07-13-session-query-tracing.md) owns lineage and event-relationship semantics. The service observes the optional `ctx.sessionPersistence` binding dynamically but retains no persisted cache or invalidation listener. Each cross-corpus list asks the active backend for authoritative metadata, then overlays a fresh live-store list. Matching ids become one `SessionRecord`: the live header wins and `live`/`persisted` independently report source availability. Immutable header disagreement is `SESSION_QUERY_SOURCE_CONFLICT`. @@ -18,13 +18,13 @@ An exact target read first checks the live store and snapshots the live header a ## Surface semantics -`dsh-session` exports `foldSurface(events)`, and `SurfaceManager` uses the same transition functions for its incremental cache. The fold returns detached current nodes and each replacement's actual removed seqs. `listEvents()` uses that result to classify every raw event as `current`, `shadowed`, or `log-only`, so inspection cannot disagree with model-history derivation about positional replacement semantics. +`dsh-session` exports `foldSurface(events)`, and `SurfaceManager` uses the same transition functions for its incremental cache. The fold returns detached current nodes and each replacement's actual removed seqs. `listEvents()` and `traceEvent()` use that result to classify every raw event, so inspection cannot disagree with model-history derivation about positional replacement semantics. `readEvent()` returns the complete target plus raw neighbors by contiguous seq. `before` and `after` default to zero and are independently bounded by `readWindowMax`, default 50. The result carries a cloned `SessionHeader`, not a source-availability record, because determining a live target's persisted flag would violate the guarantee that live exact reads do not depend on persistence health. ## Security boundary -The service is context-wide trusted infrastructure, not an authorization layer. A future model-facing history tool or human UI applies explicit caller/session scope. This phase adds no model-facing tool and changes no transcript or snapshot surface. +The service is context-wide trusted infrastructure, not an authorization layer. A future model-facing history tool or human UI applies explicit caller/session scope. The service adds no model-facing tool and changes no transcript or snapshot surface. ## Alternatives considered @@ -32,10 +32,9 @@ The service is context-wide trusted infrastructure, not an authorization layer. - **Query only persistence** — rejected because checkpoints can lag the current live log. - **Cache persisted metadata and listen for writes/removals** — rejected because exact reads can ask the authoritative sources directly, while cache invalidation adds lifecycle and concurrency state before scale requires it. - **Define a provider-neutral search protocol now** — rejected because no provider consumes it. The first SQLite FTS package should own one reconciliation/transaction state machine; a smaller shared seam can be extracted later only when a second implementation proves the boundary. -- **Include lineage, provenance, and generic filters in phase one** — rejected because no current consumer requires them and canonical logs remain sufficient to add them with evidence later. ## Consequences -Phase one has one source-resolution state variable: the currently mounted persistence service. There are no provider queues, fingerprints, extractor registries, observation generations, or derived index updates. Exact reads remain usable in live-only deployments and deterministic when persistence is present. +The service has one source-resolution state variable: the currently mounted persistence service. There are no provider queues, fingerprints, extractor registries, observation generations, or derived index updates. Exact reads and event traces remain usable in live-only deployments and deterministic when persistence is present. -Cross-corpus listing and persisted exact reads perform backend I/O on each call. That is deliberate: correctness comes from current authoritative state, and scale-oriented search belongs to the phase-two database. Full-text search is unavailable until that package defines and implements its complete contract. +Cross-corpus listing, lineage tracing, and persisted event operations perform backend I/O on each call. That is deliberate: correctness comes from current authoritative state, and scale-oriented search belongs to the proposed database package. Full-text search is unavailable until that package defines and implements its complete contract. diff --git a/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md b/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md new file mode 100644 index 0000000000..cb09531fc6 --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md @@ -0,0 +1,34 @@ +# RFC: Session query relationship tracing + +Status: implemented + +## Problem + +Session relationships are encoded across immutable headers, positional surface operations, and logged provenance arrays. A consumer reconstructing those relationships directly would need to duplicate corpus precedence, surface folding, malformed-log handling, deterministic lineage ordering, and cloning. Positional replacement and provenance are different graphs, so collapsing them into one generic edge type would also lose meaning. + +## Decision + +`ctx.sessionQuery` exposes `traceSession(sessionId)` and `traceEvent({ sessionId, seq })` alongside its exact reads. Both are one-shot views over the existing live-preferred corpus: session tracing consumes one complete corpus listing, while event tracing consumes one loaded logical log and one canonical surface fold. The service retains no lineage, reverse-index, or replacement state after a call. + +`SessionLineageTrace` returns the target, known parents in immediate-to-outward order, and recursive descendant trees whose siblings sort by creation time and then session id. `complete: true` carries the known root; `complete: false` carries the first unresolved parent id. A cycle connected to the target fails with `SESSION_QUERY_INVALID_LINEAGE`. + +`SessionEventTrace` keeps positional and provenance relationships separate. `replacedBy` is the immediate positional replacer, `replacementChain` follows replacers to the final node, and `replacedEventSeqs` lists the actual surface nodes directly removed by the target. `sourceEventSeqs` preserves direct logged source order, while `derivedEventSeqs` lists later direct reverse references in log order. Provenance is not expanded transitively. + +## Validation boundary + +Event tracing checks target existence before surface analysis. Before returning a trace it validates the whole loaded log: only surface event types carry provenance, present arrays are nonempty and duplicate-free, every source is a known earlier seq, and every positional replacement names all surface nodes it removed. Provenance failures use `SESSION_QUERY_INVALID_PROVENANCE`; positional fold failures keep `SESSION_QUERY_INVALID_SURFACE`. `listEvents()` remains a surface-classification operation and does not acquire trace-specific provenance rejection. + +All returned records and arrays are detached. A known live event trace never consults persistence; persisted event traces preserve the exact-read list/load consistency check. Session lineage is necessarily a cross-corpus operation and therefore preserves cross-corpus persistence failure semantics. + +## Alternatives considered + +- **Expose standalone tracing helpers** — rejected because the source-precedence and detachment boundary belongs to `ctx.sessionQuery`; public helpers would invite callers to bypass it. +- **Combine replacement and provenance edges** — rejected because a positional replacement can shadow surface nodes while also citing non-surface construction inputs, and consumers need to distinguish those meanings. +- **Return transitive provenance closure** — rejected because it obscures logged direct evidence, increases result size, and lets one malformed distant edge alter otherwise local output. +- **Best-effort traces over malformed provenance** — rejected because a structurally plausible partial graph would look authoritative. Exact inspection fails loudly when the canonical relationship contract is broken. + +## Consequences + +Consumers receive deterministic relationship views without a cache or second corpus. Event tracing performs whole-log validation and allocation on each call, while lineage tracing lists the complete logical corpus on each call. Those costs keep the source of truth explicit and are separate from the content-bearing full-text-search and filtering API. + +The feature has unit and service-level coverage but no snapshot or end-to-end fixture because it introduces no model-facing consumer, transcript change, or cross-process protocol. diff --git a/docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md b/docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md index acfdf23bee..36216f74d8 100644 --- a/docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md +++ b/docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md @@ -4,7 +4,7 @@ Status: proposed ## Problem -The exact-read `ctx.sessionQuery` service deliberately has no derived index. Large persisted histories need full-text search without scanning every event on every query, while current live sessions need an overlay newer than the last durability checkpoint. Search also needs concrete ranking, snippets, filters, pagination, cancellation, and rebuild behavior. +The exact-read `ctx.sessionQuery` service deliberately has no derived index. Large persisted histories need full-text search without scanning every event on every query, while current live sessions need an overlay newer than the last durability checkpoint. Search also needs concrete ranking, snippets, pagination, cancellation, and rebuild behavior. Splitting those concerns across a speculative provider coordinator and a database implementation would create two coupled reconciliation state machines. The first real implementation should own the source observation, extraction, SQLite transaction, generation, and query as one lifecycle. @@ -20,7 +20,7 @@ Persisted documents survive restarts. Live overrides are connection-local and sh The implementation must define both cross-session and within-session scopes from executable use cases. Each searchable event is one document with session metadata, event metadata, surface classification, normalized semantic text, and a bounded plain-text snippet. Session results group by their strongest matching event; numeric backend scores remain private. -Filters compile to parameterized SQL before ranking. Query syntax is treated as data. Ordering includes stable tie fields. Opaque cursors bind to normalized request shape and the smallest relevant generation; unrelated session changes should not invalidate a within-session cursor. Cancellation must stop caller waiting and interrupt SQLite work where the runtime permits. +Search returns content-bearing result records rather than metadata-only headers. Chainable filters operate on that exact result shape and are designed and implemented with the search API instead of becoming a provider-specific pre-ranking contract. Query syntax is treated as data. Ordering includes stable tie fields. Opaque cursors bind to normalized request shape and the smallest relevant generation; unrelated session changes should not invalidate a within-session cursor. Cancellation must stop caller waiting and interrupt SQLite work where the runtime permits. Tokenizer choice remains an implementation experiment. FTS5 trigram supports substring recall but rejects useful terms shorter than three characters and increases index size; the proposal must benchmark that tradeoff against the default Unicode tokenizer before making it contract. @@ -41,7 +41,7 @@ Reconciliation may use stable fingerprints to avoid rewriting unchanged persiste - Restart tests cover unchanged, new, changed, and deleted persisted sessions without rebuilding the whole index. - Reopening preserves persisted rows and removes live rows; live rows shadow and then reveal their persisted base. -- Tests cover both search scopes, metadata filters, surface defaults, snippets, escaping, deterministic ties, pagination, scoped stale cursors, cancellation, dynamic persistence mount/unmount, and recovery after a failed transaction. +- Tests cover both search scopes, content-bearing results, chainable result filters, surface defaults, snippets, escaping, deterministic ties, pagination, scoped stale cursors, cancellation, dynamic persistence mount/unmount, and recovery after a failed transaction. - A schema mismatch resets only the derived database. - A keyless end-to-end test combines a real persistence backend with the real SQLite search package. - The RFC is amended to the measured tokenizer and public API actually implemented before moving to `implemented/`. diff --git a/packages/README.md b/packages/README.md index 64eaba8ad5..62dfe68fc8 100644 --- a/packages/README.md +++ b/packages/README.md @@ -25,7 +25,7 @@ Packages are grouped by modular role at `packages///`. The group dir | [`cordis/`](cordis/README.md) | Self-referential runtime toolset: inspect the live runtime's plugins and services, mount/unmount model-written plugins ([design](../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)) | Product — stable surface | | [`hooks/`](hooks/README.md) | Hook bridges + the shared Claude Code / Codex wire-protocol library | Product — stable surface | | [`session-persistence/`](session-persistence/README.md) | Persistence capability family: the seam + JSONL/SQLite backends | Product — stable surface | -| [`session-query/`](session-query/README.md) | Session retrieval family: logical corpus, surface records, and bounded exact reads | Product — stable surface | +| [`session-query/`](session-query/README.md) | Session retrieval family: logical corpus, exact reads, lineage, and event relationships | Product — stable surface | | [`ui/`](ui/README.md) | Editor/client integration surfaces: ACP bridge, app packages, user-approval and user-interaction seams, ask-user tool | Product — stable surface | | [`support/`](support/README.md) | Dev/test/example infrastructure (invariants, replay adapter, subagent mock) | Support — lower compatibility expectations | | [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (the `Branded` primitive) | Support — small, stable, harness-dep-free | diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 80530025ad..3f491f8ad3 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -151,10 +151,12 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ }, { key: 'sessionQuery', - summary: 'Live-preferred logical-corpus and exact-event read service.', + summary: 'Live-preferred logical-corpus exact-read and relationship-tracing service.', methods: [ 'listSessions(): Promise', 'async listEvents(sessionId: SessionId): Promise', + 'async traceSession(sessionId: SessionId): Promise', + 'async traceEvent(request: SessionEventTraceRequest): Promise', 'async readEvent(request: SessionEventReadRequest): Promise', ], }, @@ -780,6 +782,14 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'SessionEventSurface', declaration: 'export type SessionEventSurface = \'current\' | \'shadowed\' | \'log-only\';', }, + { + name: 'SessionEventTrace', + declaration: 'export interface SessionEventTrace {\n target: SessionEventRecord;\n replacedBy?: number;\n replacementChain: number[];\n replacedEventSeqs: number[];\n sourceEventSeqs: number[];\n derivedEventSeqs: number[];\n}', + }, + { + name: 'SessionEventTraceRequest', + declaration: 'export interface SessionEventTraceRequest {\n sessionId: SessionId;\n seq: number;\n}', + }, { name: 'SessionEventType', declaration: 'export type SessionEventType = keyof SessionEventMap;', @@ -800,6 +810,14 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'SessionId', declaration: 'export type SessionId = Branded<\'SessionId\'>;', }, + { + name: 'SessionLineageNode', + declaration: 'export interface SessionLineageNode {\n session: SessionRecord;\n descendants: SessionLineageNode[];\n}', + }, + { + name: 'SessionLineageTrace', + declaration: 'export type SessionLineageTrace = {\n target: SessionRecord;\n ancestors: SessionRecord[];\n descendants: SessionLineageNode[];\n} & ({\n complete: true;\n root: SessionRecord;\n} | {\n complete: false;\n unresolvedParentId: SessionId;\n});', + }, { name: 'SessionRecord', declaration: 'export interface SessionRecord {\n header: SessionHeader;\n live: boolean;\n persisted: boolean;\n}', diff --git a/packages/session-query/README.md b/packages/session-query/README.md index 8b0c06a30c..4c4b1c75c4 100644 --- a/packages/session-query/README.md +++ b/packages/session-query/README.md @@ -1,9 +1,9 @@ # session-query/ — session retrieval capability family -Trusted exact reads over live and durable session logs. Phase one contains one interface package that owns `ctx.sessionQuery`, logical-corpus precedence, surface classification, and bounded event reads. +Trusted exact reads and relationship traces over live and durable session logs. The family contains one interface package that owns `ctx.sessionQuery`, logical-corpus precedence, surface classification, bounded event reads, lineage, and direct event relationships. | Package | Role | ctx key | |---|---|---| -| [`session-query/`](session-query/README.md) | Logical-corpus and exact-event read service | `ctx.sessionQuery` | +| [`session-query/`](session-query/README.md) | Logical-corpus exact-read and relationship-tracing service | `ctx.sessionQuery` | -The family is independent of compaction: it reads the canonical session log but does not participate in compaction policy or execution. Full-text search remains proposed as a phase-two SQLite package rather than a speculative provider seam in this interface package. +The family is independent of compaction: it reads canonical lineage, surface operations, and logged provenance but does not participate in compaction policy or execution. Full-text search remains a proposed SQLite package rather than a speculative provider seam in this interface package. diff --git a/packages/session-query/session-query/README.md b/packages/session-query/session-query/README.md index 55f9b32fcd..f85ade5984 100644 --- a/packages/session-query/session-query/README.md +++ b/packages/session-query/session-query/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-session-query -Exact session-history retrieval through `ctx.sessionQuery`. The service presents live `ctx.sessions` and an optional, dynamically mounted `ctx.sessionPersistence` as one logical corpus. Matching ids produce one record: live events win, while `live` and `persisted` report both source availabilities. Conflicting immutable headers fail with `SESSION_QUERY_SOURCE_CONFLICT`. +Exact session-history retrieval and relationship tracing through `ctx.sessionQuery`. The service presents live `ctx.sessions` and an optional, dynamically mounted `ctx.sessionPersistence` as one logical corpus. Matching ids produce one record: live events win, while `live` and `persisted` report both source availabilities. Conflicting immutable headers fail with `SESSION_QUERY_SOURCE_CONFLICT`. This is trusted context-wide infrastructure. It performs no caller authorization; a future model tool or UI must constrain which sessions its caller may inspect. @@ -9,10 +9,14 @@ This is trusted context-wide infrastructure. It performs no caller authorization - `listSessions()` reads current persistence metadata, merges live records with live precedence, and returns cloned records in deterministic newest-first order. - `listEvents(sessionId)` loads the live-preferred raw log and classifies each event as `current`, `shadowed`, or `log-only` with the shared `dsh-session` surface fold. - `readEvent(request)` returns a cloned header, the full target event, and a bounded raw-seq window. `before` and `after` default to zero and may not exceed `readWindowMax`. +- `traceSession(sessionId)` reads the corpus once and returns immediate-to-outward ancestors plus deterministic recursive descendant trees. `complete: false` identifies the first missing parent; a target-connected cycle fails with `SESSION_QUERY_INVALID_LINEAGE`. +- `traceEvent(request)` loads the logical log once and returns direct positional replacements and direct logged provenance. `replacementChain` follows positional replacers to the final replacement; provenance links remain non-transitive. -Persistence is optional and may mount or unmount dynamically. A cross-corpus list fails with `SESSION_QUERY_PERSISTENCE_FAILED` while mounted persistence is unreadable. A read targeting a known live session does not consult persistence, so durable backend health cannot make current in-memory history unreadable. Persisted exact reads list before loading, and reject a metadata mismatch rather than combining inconsistent observations. +Persistence is optional and may mount or unmount dynamically. Cross-corpus listing and lineage tracing fail with `SESSION_QUERY_PERSISTENCE_FAILED` while mounted persistence is unreadable. An event read or trace targeting a known live session does not consult persistence, so durable backend health cannot make current in-memory history unreadable. Persisted event operations list before loading and reject a metadata mismatch rather than combining inconsistent observations. -`SessionQueryError.code` is a closed union: `SESSION_QUERY_EVENT_NOT_FOUND`, `SESSION_QUERY_INVALID_CONFIG`, `SESSION_QUERY_INVALID_SURFACE`, `SESSION_QUERY_INVALID_WINDOW`, `SESSION_QUERY_PERSISTENCE_FAILED`, `SESSION_QUERY_SESSION_NOT_FOUND`, and `SESSION_QUERY_SOURCE_CONFLICT`. +`traceEvent()` validates the whole loaded log before returning relationships: provenance arrays are nonempty and duplicate-free, references name known earlier events, only surface event types carry sources, and each positional replacement names every surface node it removed. Provenance violations fail with `SESSION_QUERY_INVALID_PROVENANCE`; positional fold failures remain `SESSION_QUERY_INVALID_SURFACE`. `listEvents()` only needs surface classification and deliberately does not enforce the trace-specific provenance contract. + +`SessionQueryError.code` is a closed union: `SESSION_QUERY_EVENT_NOT_FOUND`, `SESSION_QUERY_INVALID_CONFIG`, `SESSION_QUERY_INVALID_LINEAGE`, `SESSION_QUERY_INVALID_PROVENANCE`, `SESSION_QUERY_INVALID_SURFACE`, `SESSION_QUERY_INVALID_WINDOW`, `SESSION_QUERY_PERSISTENCE_FAILED`, `SESSION_QUERY_SESSION_NOT_FOUND`, and `SESSION_QUERY_SOURCE_CONFLICT`. ## Configuration @@ -20,4 +24,4 @@ Persistence is optional and may mount or unmount dynamically. A cross-corpus lis |---|---:|---| | `readWindowMax` | `50` | Maximum `before` or `after` raw-event count. | -This phase deliberately has no filters, lineage/provenance traversal, extraction registry, search-provider protocol, index synchronization, or model-facing tool. Full-text search belongs beside its first real implementation; the proposed SQLite package and its single transaction/reconciliation owner are described in the [phase-two RFC](../../../docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md). +The service has no filters, extraction registry, search-provider protocol, index synchronization, or model-facing tool. The [tracing decision](../../../docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md) owns relationship semantics. Content-bearing full-text-search results and their chainable filters belong together in the proposed [SQLite search package](../../../docs/rfc/proposed/feature/2026-07-10-sqlite-session-query-provider.md). diff --git a/packages/session-query/session-query/package.json b/packages/session-query/session-query/package.json index 9f78d4f1db..d096058fa5 100644 --- a/packages/session-query/session-query/package.json +++ b/packages/session-query/session-query/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-session-query", - "description": "Live-preferred exact session-history retrieval service (ctx.sessionQuery)", + "description": "Live-preferred exact session-history retrieval and tracing service (ctx.sessionQuery)", "version": "0.0.1", "private": true, "type": "module", diff --git a/packages/session-query/session-query/src/config.ts b/packages/session-query/session-query/src/config.ts index 2736f68cbd..a6d0ab10fa 100644 --- a/packages/session-query/session-query/src/config.ts +++ b/packages/session-query/session-query/src/config.ts @@ -5,16 +5,18 @@ import { HarnessError } from '@deepseek-ai/dsh-llm' /** Default maximum `before`/`after` raw-event window. */ export const SESSION_QUERY_READ_WINDOW_MAX = 50 -/** Configuration for exact session-query reads. */ +/** Configuration for exact session-query reads and traces. */ export interface Config { /** Maximum accepted raw read context on either side. Defaults to 50. */ readWindowMax?: number } -/** Stable machine-routable failure taxonomy for exact session reads. */ +/** Stable machine-routable failure taxonomy for exact session reads and traces. */ export type SessionQueryErrorCode = | 'SESSION_QUERY_EVENT_NOT_FOUND' | 'SESSION_QUERY_INVALID_CONFIG' + | 'SESSION_QUERY_INVALID_LINEAGE' + | 'SESSION_QUERY_INVALID_PROVENANCE' | 'SESSION_QUERY_INVALID_SURFACE' | 'SESSION_QUERY_INVALID_WINDOW' | 'SESSION_QUERY_PERSISTENCE_FAILED' diff --git a/packages/session-query/session-query/src/index.ts b/packages/session-query/session-query/src/index.ts index 828fe2ec88..c468f31696 100644 --- a/packages/session-query/session-query/src/index.ts +++ b/packages/session-query/session-query/src/index.ts @@ -1,17 +1,19 @@ /** - * Exact session-history reads over live and optionally persisted logs. + * Exact session-history reads and traces over live and optionally persisted logs. * * @module @deepseek-ai/dsh-session-query */ import { Context, Service } from 'cordis' import z from 'schemastery' -import { foldSurface } from '@deepseek-ai/dsh-session' -import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session' +import type { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEventReadRequest, SessionEventRecord, + SessionEventTrace, + SessionEventTraceRequest, SessionEventWindow, + SessionLineageTrace, SessionRecord, } from './types.ts' import { @@ -20,6 +22,7 @@ import { type Config, } from './config.ts' import { SessionCorpus } from './corpus.ts' +import { eventRecords, traceEventLog, traceLineage } from './tracing.ts' export type * from './types.ts' export type { Config, SessionQueryErrorCode } from './config.ts' @@ -31,7 +34,7 @@ declare module 'cordis' { } } -/** Live-preferred logical-corpus and exact-event read service. */ +/** Live-preferred logical-corpus exact-read and relationship-tracing service. */ export class SessionQueryService extends Service { static inject = ['sessions'] static Config: z = z.object({ @@ -71,6 +74,26 @@ export class SessionQueryService extends Service { return eventRecords(sessionId, loaded.events) } + /** + * Trace known ancestry and descendants from one corpus observation. + * @param sessionId - logical session id to trace. + * @returns a complete lineage or an explicit unresolved parent boundary. + */ + async traceSession(sessionId: SessionId): Promise { + const records = await this._corpus.listSessions() + return traceLineage(records, sessionId) + } + + /** + * Trace one event's direct positional and provenance relationships. + * @param request - target session id and event seq. + * @returns direct links plus the target's positional replacement chain. + */ + async traceEvent(request: SessionEventTraceRequest): Promise { + const loaded = await this._corpus.load(request.sessionId) + return traceEventLog(request.sessionId, loaded.events, request.seq) + } + /** * Read one full event plus a bounded raw-log context window. * @param request - target session/seq and context sizes. @@ -110,27 +133,4 @@ export class SessionQueryService extends Service { } } -function eventRecords(sessionId: SessionId, events: readonly SessionEvent[]): SessionEventRecord[] { - let folded: ReturnType - try { - folded = foldSurface(events) - } catch (error: unknown) { - throw new SessionQueryError( - /* v8 ignore next -- foldSurface throws Error instances */ - `invalid session surface: ${error instanceof Error ? error.message : 'unknown error'}`, - 'SESSION_QUERY_INVALID_SURFACE', - { cause: error }, - ) - } - const current = new Set(folded.nodes.map(node => node.seq)) - const shadowed = new Set(folded.replacements.flatMap(replacement => replacement.shadowedSeqs)) - return events.map(event => ({ - sessionId, - seq: event.seq, - type: event.type, - time: event.time, - surface: current.has(event.seq) ? 'current' : shadowed.has(event.seq) ? 'shadowed' : 'log-only', - })) -} - export default SessionQueryService diff --git a/packages/session-query/session-query/src/tracing.ts b/packages/session-query/session-query/src/tracing.ts new file mode 100644 index 0000000000..8efa2922b6 --- /dev/null +++ b/packages/session-query/session-query/src/tracing.ts @@ -0,0 +1,277 @@ +/** One-shot session-lineage and event-relationship tracing helpers. */ + +import { foldSurface, isSurfaceEligibleType } from '@deepseek-ai/dsh-session' +import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session' +import { SessionQueryError } from './config.ts' +import type { + SessionEventRecord, + SessionEventTrace, + SessionLineageNode, + SessionLineageTrace, + SessionRecord, +} from './types.ts' + +interface EventLogAnalysis { + records: SessionEventRecord[] + replacedBy: Map + replacedEventSeqs: Map +} + +/** + * Classify a raw event log with one canonical surface fold. + * @param sessionId - owner of the event log. + * @param events - detached raw event log. + * @returns lightweight records in ascending log order. + */ +export function eventRecords( + sessionId: SessionId, + events: readonly SessionEvent[], +): SessionEventRecord[] { + return analyzeEventLog(sessionId, events).records +} + +/** + * Trace one target after one canonical surface fold and whole-log validation. + * @param sessionId - owner of the event log. + * @param events - detached raw event log. + * @param seq - target event seq. + * @returns direct surface and provenance relationships. + */ +export function traceEventLog( + sessionId: SessionId, + events: readonly SessionEvent[], + seq: number, +): SessionEventTrace { + const target = events[seq] + if (target === undefined || target.seq !== seq) { + throw new SessionQueryError( + `session "${sessionId}" has no event at seq ${seq}`, + 'SESSION_QUERY_EVENT_NOT_FOUND', + ) + } + + const analysis = analyzeEventLog(sessionId, events) + validateProvenance(events, analysis.replacedEventSeqs) + + const replacementChain: number[] = [] + let replacement = analysis.replacedBy.get(seq) + while (replacement !== undefined) { + replacementChain.push(replacement) + replacement = analysis.replacedBy.get(replacement) + } + + const sourceEventSeqs = eventSources(target) + const derivedEventSeqs: number[] = [] + for (const event of events) { + if (event.seq <= seq) continue + if (eventSources(event).includes(seq)) derivedEventSeqs.push(event.seq) + } + + // The target check above proves the parallel record exists at this index. + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + const targetRecord = analysis.records[seq]! + const replacedBy = analysis.replacedBy.get(seq) + return { + target: { ...targetRecord }, + ...replacedBy === undefined ? {} : { replacedBy }, + replacementChain, + replacedEventSeqs: [...(analysis.replacedEventSeqs.get(seq) ?? [])], + sourceEventSeqs: [...sourceEventSeqs], + derivedEventSeqs, + } +} + +/** + * Trace one target's known ancestry and recursively known descendants. + * @param records - complete logical corpus from one observation. + * @param sessionId - target session id. + * @returns complete or explicitly partial lineage. + */ +export function traceLineage( + records: readonly SessionRecord[], + sessionId: SessionId, +): SessionLineageTrace { + const byId = new Map(records.map(record => [record.header.id, record])) + const target = byId.get(sessionId) + if (target === undefined) { + throw new SessionQueryError( + `session "${sessionId}" not found`, + 'SESSION_QUERY_SESSION_NOT_FOUND', + ) + } + + const ancestors: SessionRecord[] = [] + const ancestrySeen = new Set([sessionId]) + let unresolvedParentId: SessionId | undefined + let parentId = target.header.parentSession + while (parentId !== undefined) { + if (ancestrySeen.has(parentId)) lineageCycle(parentId) + ancestrySeen.add(parentId) + const parent = byId.get(parentId) + if (parent === undefined) { + unresolvedParentId = parentId + break + } + ancestors.push(parent) + parentId = parent.header.parentSession + } + + const childrenByParent = new Map() + for (const record of records) { + const parent = record.header.parentSession + if (parent === undefined) continue + const children = childrenByParent.get(parent) ?? [] + children.push(record) + childrenByParent.set(parent, children) + } + for (const children of childrenByParent.values()) children.sort(compareSessionsAscending) + + const descendants = buildDescendants(childrenByParent, sessionId) + const common = { + target: cloneRecord(target), + ancestors: ancestors.map(cloneRecord), + descendants, + } + if (unresolvedParentId !== undefined) { + return { ...common, complete: false, unresolvedParentId } + } + return { + ...common, + complete: true, + root: cloneRecord(ancestors.at(-1) ?? target), + } +} + +function analyzeEventLog( + sessionId: SessionId, + events: readonly SessionEvent[], +): EventLogAnalysis { + const folded = safeFold(events) + const current = new Set(folded.nodes.map(node => node.seq)) + const shadowed = new Set() + const replacedBy = new Map() + const replacedEventSeqs = new Map() + for (const replacement of folded.replacements) { + const removed = [...replacement.shadowedSeqs] + replacedEventSeqs.set(replacement.seq, removed) + for (const removedSeq of removed) { + shadowed.add(removedSeq) + replacedBy.set(removedSeq, replacement.seq) + } + } + return { + records: events.map(event => ({ + sessionId, + seq: event.seq, + type: event.type, + time: event.time, + surface: current.has(event.seq) + ? 'current' + : shadowed.has(event.seq) ? 'shadowed' : 'log-only', + })), + replacedBy, + replacedEventSeqs, + } +} + +function validateProvenance( + events: readonly SessionEvent[], + replacedEventSeqs: ReadonlyMap, +): void { + for (const event of events) { + const sources = rawEventSources(event) + if (sources === undefined) continue + if (!isSurfaceEligibleType(event.type)) { + invalidProvenance(`non-surface event at seq ${event.seq} carries sourceEventSeqs`) + } + if (!Array.isArray(sources) || sources.length === 0) { + invalidProvenance(`event at seq ${event.seq} has an empty or invalid sourceEventSeqs`) + } + const unique = new Set() + for (const source of sources as unknown[]) { + if (unique.has(source)) { + invalidProvenance(`event at seq ${event.seq} repeats source seq ${String(source)}`) + } + unique.add(source) + if ( + typeof source !== 'number' + || !Number.isInteger(source) + || source < 0 + || source >= event.seq + || events[source]?.seq !== source + ) { + invalidProvenance(`event at seq ${event.seq} references unknown or non-earlier source seq ${String(source)}`) + } + } + } + + for (const [replacementSeq, removedSeqs] of replacedEventSeqs) { + // The fold reports only replacement events from the input log. + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + const replacement = events.find(event => event.seq === replacementSeq)! + const sources = rawEventSources(replacement) + if (!Array.isArray(sources)) { + invalidProvenance(`replacement at seq ${replacementSeq} omits its shadowed surface sources`) + } + const sourceSet = new Set(sources as unknown[]) + for (const removedSeq of removedSeqs) { + if (!sourceSet.has(removedSeq)) { + invalidProvenance(`replacement at seq ${replacementSeq} omits shadowed surface seq ${removedSeq}`) + } + } + } +} + +function rawEventSources(event: SessionEvent): unknown { + return (event as SessionEvent & { sourceEventSeqs?: unknown }).sourceEventSeqs +} + +function eventSources(event: SessionEvent): number[] { + const sources = rawEventSources(event) + return Array.isArray(sources) ? sources as number[] : [] +} + +function safeFold(events: readonly SessionEvent[]): ReturnType { + try { + return foldSurface(events) + } catch (error: unknown) { + throw new SessionQueryError( + /* v8 ignore next -- foldSurface throws Error instances */ + `invalid session surface: ${error instanceof Error ? error.message : 'unknown error'}`, + 'SESSION_QUERY_INVALID_SURFACE', + { cause: error }, + ) + } +} + +function buildDescendants( + childrenByParent: ReadonlyMap, + sessionId: SessionId, +): SessionLineageNode[] { + return (childrenByParent.get(sessionId) ?? []).map(child => ({ + session: cloneRecord(child), + descendants: buildDescendants(childrenByParent, child.header.id), + })) +} + +function compareSessionsAscending(a: SessionRecord, b: SessionRecord): number { + return a.header.createdAt - b.header.createdAt || a.header.id.localeCompare(b.header.id) +} + +function cloneRecord(record: SessionRecord): SessionRecord { + return { ...record, header: structuredClone(record.header) } +} + +function lineageCycle(id: SessionId): never { + throw new SessionQueryError( + `session lineage contains a cycle at "${id}"`, + 'SESSION_QUERY_INVALID_LINEAGE', + ) +} + +function invalidProvenance(message: string): never { + throw new SessionQueryError( + `invalid session provenance: ${message}`, + 'SESSION_QUERY_INVALID_PROVENANCE', + ) +} diff --git a/packages/session-query/session-query/src/types.ts b/packages/session-query/session-query/src/types.ts index 5c49695dda..38f0225ee4 100644 --- a/packages/session-query/session-query/src/types.ts +++ b/packages/session-query/session-query/src/types.ts @@ -1,5 +1,6 @@ /** - * Public records for exact reads over the live-preferred logical session corpus. + * Public records for exact reads and relationship traces over the + * live-preferred logical session corpus. * * @module @deepseek-ai/dsh-session-query/types */ @@ -33,6 +34,61 @@ export interface SessionEventRecord { surface: SessionEventSurface } +/** Recursive descendant node in a session-lineage trace. */ +export interface SessionLineageNode { + /** Detached logical-corpus record for this descendant. */ + session: SessionRecord + /** Direct children, each carrying its own recursive descendants. */ + descendants: SessionLineageNode[] +} + +/** Known ancestry and descendants for one logical session. */ +export type SessionLineageTrace = { + /** Detached record for the session that was traced. */ + target: SessionRecord + /** Known parents from the immediate parent outward. */ + ancestors: SessionRecord[] + /** Complete known descendant trees rooted at the target's direct children. */ + descendants: SessionLineageNode[] +} & ( + | { + /** The complete parent chain is present in the logical corpus. */ + complete: true + /** Detached record at the top of the complete lineage. */ + root: SessionRecord + } + | { + /** The parent chain leaves the visible logical corpus. */ + complete: false + /** First parent id that is not present in the logical corpus. */ + unresolvedParentId: SessionId + } +) + +/** Request for direct surface and provenance relationships around one event. */ +export interface SessionEventTraceRequest { + /** Session that owns the target event. */ + sessionId: SessionId + /** Target event seq. */ + seq: number +} + +/** Direct surface and provenance relationships for one event. */ +export interface SessionEventTrace { + /** Lightweight target record. */ + target: SessionEventRecord + /** Immediate positional replacement event, when the target was shadowed. */ + replacedBy?: number + /** Positional replacers from the immediate replacement to the final replacement. */ + replacementChain: number[] + /** Surface nodes directly removed when the target itself performed a replacement. */ + replacedEventSeqs: number[] + /** Direct logged provenance sources in their recorded order. */ + sourceEventSeqs: number[] + /** Later events that directly name the target as a provenance source, in log order. */ + derivedEventSeqs: number[] +} + /** Request for one event plus raw neighboring log context. */ export interface SessionEventReadRequest { /** Session that owns the target event. */ diff --git a/packages/session-query/session-query/tests/tracing.spec.ts b/packages/session-query/session-query/tests/tracing.spec.ts new file mode 100644 index 0000000000..3128cb243f --- /dev/null +++ b/packages/session-query/session-query/tests/tracing.spec.ts @@ -0,0 +1,376 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import SessionStore, { SESSION_FORMAT_VERSION, SessionId } from '@deepseek-ai/dsh-session' +import type { Session, SessionEvent, SessionHeader, SessionId as SessionIdType } from '@deepseek-ai/dsh-session' +import SessionPersistence from '@deepseek-ai/dsh-session-persistence' +import SessionQueryService, { type SessionQueryErrorCode } from '@deepseek-ai/dsh-session-query' + +function header(id: string, createdAt = 1, extra: Partial = {}): SessionHeader { + return { version: SESSION_FORMAT_VERSION, id: SessionId(id), createdAt, ...extra } +} + +function appendEvent(seq: number, sources?: number[]): SessionEvent { + return { + type: 'user/message', + seq, + time: seq + 1, + data: { content: [{ type: 'text', text: `event ${seq}` }], source: { kind: 'user' } }, + surfaceOp: 'append', + ...sources === undefined ? {} : { sourceEventSeqs: sources }, + } +} + +class TracePersistence extends SessionPersistence { + static entries = new Map() + static listCalls = 0 + static loadCalls = 0 + static listFailure: Error | undefined + static loadFailure: Error | undefined + static afterList: (() => void) | undefined + + static reset(entries: readonly { meta: SessionHeader; events: SessionEvent[] }[] = []): void { + this.entries = new Map(entries.map(entry => [entry.meta.id, structuredClone(entry)])) + this.listCalls = 0 + this.loadCalls = 0 + this.listFailure = undefined + this.loadFailure = undefined + this.afterList = undefined + } + + create(meta: SessionHeader): Promise { + TracePersistence.entries.set(meta.id, { meta: structuredClone(meta), events: [] }) + return Promise.resolve() + } + + append(id: SessionIdType, events: readonly SessionEvent[]): Promise { + const entry = TracePersistence.entries.get(id) + if (entry === undefined) return Promise.reject(new Error('missing test session')) + entry.events.push(...structuredClone(events)) + return Promise.resolve() + } + + load(id: SessionIdType): Promise<{ meta: SessionHeader; events: SessionEvent[] }> { + TracePersistence.loadCalls += 1 + if (TracePersistence.loadFailure !== undefined) return Promise.reject(TracePersistence.loadFailure) + const entry = TracePersistence.entries.get(id) + if (entry === undefined) return Promise.reject(new Error('missing test session')) + return Promise.resolve(structuredClone(entry)) + } + + list(): Promise { + TracePersistence.listCalls += 1 + if (TracePersistence.listFailure !== undefined) return Promise.reject(TracePersistence.listFailure) + const result = [...TracePersistence.entries.values()].map(entry => structuredClone(entry.meta)) + TracePersistence.afterList?.() + return Promise.resolve(result) + } +} + +async function queryContext(): Promise { + const ctx = new Context() + await ctx.plugin(SessionStore) + await ctx.plugin(SessionQueryService) + return ctx +} + +function expectCode(code: SessionQueryErrorCode): Error { + return expect.objectContaining({ code }) as Error +} + +function appendTraceEvents(session: Session): void { + session.append('assistant/chunk', { + turn: 1, + step: 1, + chunk: { type: 'text-delta', index: 0, text: 'draft' }, + }) + session.append( + 'user/message', + { content: [{ type: 'text', text: 'original' }], source: { kind: 'user' } }, + { surfaceOp: 'append', sourceEventSeqs: [0] }, + ) + session.append( + 'assistant/message', + { turn: 1, step: 1, content: [{ type: 'text', text: 'summary one' }] }, + { surfaceOp: { op: 'replace', start: 1, end: 1 }, sourceEventSeqs: [1, 0] }, + ) + session.append( + 'context/message', + { content: [{ type: 'text', text: 'context' }], source: { kind: 'plugin', plugin: 'test' } }, + { surfaceOp: 'append' }, + ) + session.append( + 'assistant/message', + { turn: 1, step: 2, content: [{ type: 'text', text: 'summary two' }] }, + { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [0, 2] }, + ) +} + +describe('session lineage tracing', () => { + it('returns complete ancestry, deterministic descendant trees, and detached records', async () => { + const ctx = await queryContext() + const root = ctx.sessions.create(SessionId('root'), { meta: { createdAt: 0 } }) + const parent = ctx.sessions.create(SessionId('parent'), { + meta: { createdAt: 1, parentSession: root.id }, + }) + const target = ctx.sessions.create(SessionId('target'), { + meta: { createdAt: 2, parentSession: parent.id }, + }) + ctx.sessions.create(SessionId('b'), { meta: { createdAt: 4, parentSession: target.id } }) + const childA = ctx.sessions.create(SessionId('a'), { + meta: { createdAt: 4, parentSession: target.id }, + }) + ctx.sessions.create(SessionId('older'), { meta: { createdAt: 3, parentSession: target.id } }) + ctx.sessions.create(SessionId('grandchild'), { + meta: { createdAt: 5, parentSession: childA.id }, + }) + + const trace = await ctx.sessionQuery.traceSession(target.id) + expect(trace.complete).toBe(true) + if (!trace.complete) throw new Error('expected complete lineage') + expect(trace.ancestors.map(record => record.header.id)).toEqual([parent.id, root.id]) + expect(trace.root.header.id).toBe(root.id) + expect(trace.descendants.map(node => node.session.header.id)) + .toEqual([SessionId('older'), SessionId('a'), SessionId('b')]) + expect(trace.descendants[1]?.descendants.map(node => node.session.header.id)) + .toEqual([SessionId('grandchild')]) + + trace.target.header.createdAt = 99 + trace.ancestors[0]!.header.createdAt = 99 + trace.root.header.createdAt = 99 + trace.descendants[0]!.session.header.createdAt = 99 + const repeated = await ctx.sessionQuery.traceSession(target.id) + expect(repeated.target.header.createdAt).toBe(2) + expect(repeated.ancestors[0]?.header.createdAt).toBe(1) + expect(repeated.descendants[0]?.session.header.createdAt).toBe(3) + }) + + it('represents root and unresolved-parent traces explicitly', async () => { + const ctx = await queryContext() + const root = ctx.sessions.create(SessionId('root'), { meta: { createdAt: 1 } }) + const partial = ctx.sessions.create(SessionId('partial'), { + meta: { createdAt: 2, parentSession: SessionId('outside') }, + }) + + await expect(ctx.sessionQuery.traceSession(root.id)).resolves.toMatchObject({ + complete: true, + root: { header: { id: root.id } }, + ancestors: [], + }) + await expect(ctx.sessionQuery.traceSession(partial.id)).resolves.toMatchObject({ + complete: false, + unresolvedParentId: SessionId('outside'), + ancestors: [], + }) + }) + + it('rejects target-connected cycles and missing targets', async () => { + const ctx = await queryContext() + ctx.sessions.create(SessionId('a'), { + meta: { createdAt: 1, parentSession: SessionId('b') }, + }) + ctx.sessions.create(SessionId('b'), { + meta: { createdAt: 2, parentSession: SessionId('a') }, + }) + + await expect(ctx.sessionQuery.traceSession(SessionId('a'))) + .rejects.toThrow(expectCode('SESSION_QUERY_INVALID_LINEAGE')) + await expect(ctx.sessionQuery.traceSession(SessionId('missing'))) + .rejects.toThrow(expectCode('SESSION_QUERY_SESSION_NOT_FOUND')) + }) + + it('uses one cross-corpus observation and preserves persistence failure semantics', async () => { + const durable = header('durable') + TracePersistence.reset([{ meta: durable, events: [appendEvent(0)] }]) + const ctx = await queryContext() + await ctx.plugin(TracePersistence) + + await expect(ctx.sessionQuery.traceSession(durable.id)).resolves.toMatchObject({ + target: { live: false, persisted: true }, + complete: true, + }) + expect(TracePersistence.listCalls).toBe(1) + expect(TracePersistence.loadCalls).toBe(0) + + TracePersistence.listFailure = new Error('unavailable') + await expect(ctx.sessionQuery.traceSession(durable.id)) + .rejects.toThrow(expectCode('SESSION_QUERY_PERSISTENCE_FAILED')) + }) +}) + +describe('session event tracing', () => { + it('returns direct replacement and provenance links in their contract order', async () => { + const ctx = await queryContext() + const session = ctx.sessions.create(SessionId('trace')) + appendTraceEvents(session) + + const original = await ctx.sessionQuery.traceEvent({ sessionId: session.id, seq: 1 }) + expect(original.target).toMatchObject({ + sessionId: session.id, + seq: 1, + type: 'user/message', + surface: 'shadowed', + }) + expect(original).toMatchObject({ + replacedBy: 2, + replacementChain: [2, 4], + replacedEventSeqs: [], + sourceEventSeqs: [0], + derivedEventSeqs: [2], + }) + await expect(ctx.sessionQuery.traceEvent({ sessionId: session.id, seq: 2 })) + .resolves.toMatchObject({ + replacedBy: 4, + replacementChain: [4], + replacedEventSeqs: [1], + sourceEventSeqs: [1, 0], + derivedEventSeqs: [4], + }) + await expect(ctx.sessionQuery.traceEvent({ sessionId: session.id, seq: 0 })) + .resolves.toMatchObject({ + target: { surface: 'log-only' }, + replacementChain: [], + sourceEventSeqs: [], + derivedEventSeqs: [1, 2, 4], + }) + await expect(ctx.sessionQuery.traceEvent({ sessionId: session.id, seq: 4 })) + .resolves.toMatchObject({ + replacementChain: [], + replacedEventSeqs: [2], + sourceEventSeqs: [0, 2], + derivedEventSeqs: [], + }) + }) + + it('returns fresh trace arrays and target records', async () => { + const ctx = await queryContext() + const session = ctx.sessions.create(SessionId('detached')) + appendTraceEvents(session) + + const first = await ctx.sessionQuery.traceEvent({ sessionId: session.id, seq: 2 }) + first.target.time = -1 + first.replacementChain.push(99) + first.replacedEventSeqs.push(99) + first.sourceEventSeqs.push(99) + first.derivedEventSeqs.push(99) + const repeated = await ctx.sessionQuery.traceEvent({ sessionId: session.id, seq: 2 }) + expect(repeated.target.time).not.toBe(-1) + expect(repeated.replacementChain).toEqual([4]) + expect(repeated.replacedEventSeqs).toEqual([1]) + expect(repeated.sourceEventSeqs).toEqual([1, 0]) + expect(repeated.derivedEventSeqs).toEqual([4]) + }) + + it('loads persisted logs once, prefers live logs, and preserves failures and conflicts', async () => { + const durable = header('shared', 1, { cwd: '/same' }) + TracePersistence.reset([{ meta: durable, events: [appendEvent(0)] }]) + const ctx = await queryContext() + await ctx.plugin(TracePersistence) + + await expect(ctx.sessionQuery.traceEvent({ sessionId: durable.id, seq: 0 })) + .resolves.toMatchObject({ target: { type: 'user/message', surface: 'current' } }) + expect([TracePersistence.listCalls, TracePersistence.loadCalls]).toEqual([1, 1]) + + const live = ctx.sessions.create(durable.id, { meta: { createdAt: 1, cwd: '/same' } }) + live.append( + 'context/message', + { content: [{ type: 'text', text: 'live' }], source: { kind: 'plugin', plugin: 'test' } }, + { surfaceOp: 'append' }, + ) + TracePersistence.listFailure = new Error('list unavailable') + TracePersistence.loadFailure = new Error('load unavailable') + await expect(ctx.sessionQuery.traceEvent({ sessionId: durable.id, seq: 0 })) + .resolves.toMatchObject({ target: { type: 'context/message' } }) + expect([TracePersistence.listCalls, TracePersistence.loadCalls]).toEqual([1, 1]) + + TracePersistence.reset([{ meta: durable, events: [appendEvent(0)] }]) + const failedCtx = await queryContext() + await failedCtx.plugin(TracePersistence) + TracePersistence.listFailure = new Error('list unavailable') + await expect(failedCtx.sessionQuery.traceEvent({ sessionId: durable.id, seq: 0 })) + .rejects.toThrow(expectCode('SESSION_QUERY_PERSISTENCE_FAILED')) + TracePersistence.listFailure = undefined + TracePersistence.loadFailure = new Error('load unavailable') + await expect(failedCtx.sessionQuery.traceEvent({ sessionId: durable.id, seq: 0 })) + .rejects.toThrow(expectCode('SESSION_QUERY_PERSISTENCE_FAILED')) + TracePersistence.loadFailure = undefined + TracePersistence.afterList = () => { + TracePersistence.entries.get(durable.id)!.meta.cwd = '/changed' + } + await expect(failedCtx.sessionQuery.traceEvent({ sessionId: durable.id, seq: 0 })) + .rejects.toThrow(expectCode('SESSION_QUERY_SOURCE_CONFLICT')) + }) + + it('checks target existence before surface or provenance analysis', async () => { + const bad = header('bad-target') + const malformed: SessionEvent[] = [appendEvent(0), { + type: 'assistant/message', + seq: 1, + time: 2, + data: { turn: 1, step: 1, content: [] }, + surfaceOp: { op: 'replace', start: 9, end: 9 }, + sourceEventSeqs: [], + }] + TracePersistence.reset([{ meta: bad, events: malformed }]) + const ctx = await queryContext() + await ctx.plugin(TracePersistence) + + await expect(ctx.sessionQuery.traceEvent({ sessionId: bad.id, seq: 9 })) + .rejects.toThrow(expectCode('SESSION_QUERY_EVENT_NOT_FOUND')) + await expect(ctx.sessionQuery.traceEvent({ sessionId: bad.id, seq: 0 })) + .rejects.toThrow(expectCode('SESSION_QUERY_INVALID_SURFACE')) + }) + + it.each([ + ['non-surface sources', [ + { type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }, sourceEventSeqs: [0] }, + ]], + ['invalid source array', [ + { ...appendEvent(0), sourceEventSeqs: 'invalid' }, + ]], + ['empty sources', [ + appendEvent(0, []), + ]], + ['duplicate sources', [ + appendEvent(0), + appendEvent(1, [0, 0]), + ]], + ['missing earlier source', [ + appendEvent(0), + appendEvent(1, [-1]), + ]], + ['future source', [ + appendEvent(0, [1]), + appendEvent(1), + ]], + ['replacement without sources', [ + appendEvent(0), + { ...appendEvent(1), surfaceOp: { op: 'replace', start: 0, end: 0 } }, + ]], + ['replacement missing a shadowed source', [ + { type: 'assistant/chunk', seq: 0, time: 1, data: { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'draft' } } }, + appendEvent(1), + { ...appendEvent(2, [0]), surfaceOp: { op: 'replace', start: 1, end: 1 } }, + ]], + ] as const)('rejects invalid whole-log provenance: %s', async (_name, rawEvents) => { + const durable = header('invalid-provenance') + const events = structuredClone(rawEvents) as unknown as SessionEvent[] + TracePersistence.reset([{ meta: durable, events }]) + const ctx = await queryContext() + await ctx.plugin(TracePersistence) + + await expect(ctx.sessionQuery.traceEvent({ sessionId: durable.id, seq: 0 })) + .rejects.toThrow(expectCode('SESSION_QUERY_INVALID_PROVENANCE')) + }) + + it('keeps listEvents tolerant of malformed provenance alone', async () => { + const durable = header('list-regression') + TracePersistence.reset([{ meta: durable, events: [appendEvent(0), appendEvent(1, [0, 0])] }]) + const ctx = await queryContext() + await ctx.plugin(TracePersistence) + + await expect(ctx.sessionQuery.listEvents(durable.id)).resolves.toMatchObject([ + { seq: 0, surface: 'current' }, + { seq: 1, surface: 'current' }, + ]) + }) +}) diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index a815bf6a13..0e25b16d64 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -115,9 +115,9 @@ const SERVICE_ROLES: ServiceRole[] = [ { key: 'sessionQuery', pkg: 'session-query', - title: 'Exact session-history reads', + title: 'Exact session-history reads and traces', mode: 'seam', - note: 'Resolves live and optional persisted logs into one logical corpus for exact reads.', + note: 'Resolves live and optional persisted logs into one logical corpus for exact reads and relationship traces.', }, { key: 'systemPrompt', diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index e8faa2499d..cf4f3d7402 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -40,9 +40,13 @@ { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionEventSurface", "source": "packages/session-query/session-query/src/types.ts" }, { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionRecord", "source": "packages/session-query/session-query/src/types.ts" }, { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionEventRecord", "source": "packages/session-query/session-query/src/types.ts" }, + { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionLineageNode", "source": "packages/session-query/session-query/src/types.ts" }, + { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionLineageTrace", "source": "packages/session-query/session-query/src/types.ts" }, { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionQueryErrorCode", "source": "packages/session-query/session-query/src/config.ts" }, { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionEventReadRequest", "source": "packages/session-query/session-query/src/types.ts" }, { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionEventWindow", "source": "packages/session-query/session-query/src/types.ts" }, + { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionEventTraceRequest", "source": "packages/session-query/session-query/src/types.ts" }, + { "doc": "docs/core-data-structures/session-query.md", "symbol": "SessionEventTrace", "source": "packages/session-query/session-query/src/types.ts" }, { "doc": "docs/core-data-structures/tools.md", "symbol": "ToolDefinition", "source": "packages/core/tools/src/index.ts" }, { "doc": "docs/core-data-structures/tools.md", "symbol": "SchemaProp", "source": "packages/core/tools/src/schema.ts" }, From 8e019f2a65644c43d73997a16a9e8ef672ad9277 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Mon, 13 Jul 2026 13:53:03 +0800 Subject: [PATCH 016/359] fix(session-query): avoid deep lineage recursion (round 2) --- .../session-query/src/tracing.ts | 24 +++++++++++++++---- .../session-query/tests/tracing.spec.ts | 21 ++++++++++++++++ 2 files changed, 41 insertions(+), 4 deletions(-) diff --git a/packages/session-query/session-query/src/tracing.ts b/packages/session-query/session-query/src/tracing.ts index 8efa2922b6..d14822844d 100644 --- a/packages/session-query/session-query/src/tracing.ts +++ b/packages/session-query/session-query/src/tracing.ts @@ -248,10 +248,26 @@ function buildDescendants( childrenByParent: ReadonlyMap, sessionId: SessionId, ): SessionLineageNode[] { - return (childrenByParent.get(sessionId) ?? []).map(child => ({ - session: cloneRecord(child), - descendants: buildDescendants(childrenByParent, child.header.id), - })) + const descendants: SessionLineageNode[] = [] + const stack = [{ sessionId, descendants }] + while (stack.length > 0) { + // The length guard proves a frame exists. + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + const frame = stack.pop()! + const nodes: SessionLineageNode[] = [] + for (const child of childrenByParent.get(frame.sessionId) ?? []) { + const node = { session: cloneRecord(child), descendants: [] } + nodes.push(node) + frame.descendants.push(node) + } + for (let index = nodes.length - 1; index >= 0; index -= 1) { + // The loop bounds prove this indexed node exists. + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + const node = nodes[index]! + stack.push({ sessionId: node.session.header.id, descendants: node.descendants }) + } + } + return descendants } function compareSessionsAscending(a: SessionRecord, b: SessionRecord): number { diff --git a/packages/session-query/session-query/tests/tracing.spec.ts b/packages/session-query/session-query/tests/tracing.spec.ts index 3128cb243f..9f4752feee 100644 --- a/packages/session-query/session-query/tests/tracing.spec.ts +++ b/packages/session-query/session-query/tests/tracing.spec.ts @@ -195,6 +195,27 @@ describe('session lineage tracing', () => { await expect(ctx.sessionQuery.traceSession(durable.id)) .rejects.toThrow(expectCode('SESSION_QUERY_PERSISTENCE_FAILED')) }) + + it('constructs deeply nested descendants without consuming the JavaScript call stack', async () => { + const ctx = await queryContext() + const root = ctx.sessions.create(SessionId('deep-0'), { meta: { createdAt: 0 } }) + let parent = root + for (let depth = 1; depth < 3_000; depth += 1) { + parent = ctx.sessions.create(SessionId(`deep-${depth}`), { + meta: { createdAt: depth, parentSession: parent.id }, + }) + } + + const trace = await ctx.sessionQuery.traceSession(root.id) + expect(trace.complete).toBe(true) + let node = trace.descendants[0] + for (let depth = 1; depth < 3_000; depth += 1) { + if (node === undefined) throw new Error(`lineage ended before depth ${depth}`) + if (depth === 2_999) expect(node.session.header.id).toBe(SessionId('deep-2999')) + node = node.descendants[0] + } + expect(node).toBeUndefined() + }) }) describe('session event tracing', () => { From be0d44183d3c35dc6665833aeaaf89c0499baeb5 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Mon, 13 Jul 2026 14:01:34 +0800 Subject: [PATCH 017/359] perf(session-query): keep provenance validation linear (round 3) --- packages/session-query/session-query/src/tracing.ts | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/packages/session-query/session-query/src/tracing.ts b/packages/session-query/session-query/src/tracing.ts index d14822844d..d0c7f200cb 100644 --- a/packages/session-query/session-query/src/tracing.ts +++ b/packages/session-query/session-query/src/tracing.ts @@ -206,9 +206,10 @@ function validateProvenance( } for (const [replacementSeq, removedSeqs] of replacedEventSeqs) { - // The fold reports only replacement events from the input log. + // Canonical logs guarantee events[i].seq === i, and the fold reports only + // replacement events from this input log. // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const replacement = events.find(event => event.seq === replacementSeq)! + const replacement = events[replacementSeq]! const sources = rawEventSources(replacement) if (!Array.isArray(sources)) { invalidProvenance(`replacement at seq ${replacementSeq} omits its shadowed surface sources`) From 7351f0799580494b161424f3f8afe5d631f13704 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Mon, 13 Jul 2026 14:17:52 +0800 Subject: [PATCH 018/359] refactor(session-query): inline tracing failures --- .../session-query/session-query/src/index.ts | 2 + .../session-query/src/tracing.ts | 76 ++++++++++--------- 2 files changed, 43 insertions(+), 35 deletions(-) diff --git a/packages/session-query/session-query/src/index.ts b/packages/session-query/session-query/src/index.ts index c468f31696..e5659c554a 100644 --- a/packages/session-query/session-query/src/index.ts +++ b/packages/session-query/session-query/src/index.ts @@ -78,6 +78,7 @@ export class SessionQueryService extends Service { * Trace known ancestry and descendants from one corpus observation. * @param sessionId - logical session id to trace. * @returns a complete lineage or an explicit unresolved parent boundary. + * @throws when corpus resolution fails, the target is absent, or its known ancestry cycles. */ async traceSession(sessionId: SessionId): Promise { const records = await this._corpus.listSessions() @@ -88,6 +89,7 @@ export class SessionQueryService extends Service { * Trace one event's direct positional and provenance relationships. * @param request - target session id and event seq. * @returns direct links plus the target's positional replacement chain. + * @throws when source resolution fails, the target is absent, or surface/provenance validation fails. */ async traceEvent(request: SessionEventTraceRequest): Promise { const loaded = await this._corpus.load(request.sessionId) diff --git a/packages/session-query/session-query/src/tracing.ts b/packages/session-query/session-query/src/tracing.ts index d0c7f200cb..c7cfd89b9a 100644 --- a/packages/session-query/session-query/src/tracing.ts +++ b/packages/session-query/session-query/src/tracing.ts @@ -105,7 +105,12 @@ export function traceLineage( let unresolvedParentId: SessionId | undefined let parentId = target.header.parentSession while (parentId !== undefined) { - if (ancestrySeen.has(parentId)) lineageCycle(parentId) + if (ancestrySeen.has(parentId)) { + throw new SessionQueryError( + `session lineage contains a cycle at "${parentId}"`, + 'SESSION_QUERY_INVALID_LINEAGE', + ) + } ancestrySeen.add(parentId) const parent = byId.get(parentId) if (parent === undefined) { @@ -146,7 +151,17 @@ function analyzeEventLog( sessionId: SessionId, events: readonly SessionEvent[], ): EventLogAnalysis { - const folded = safeFold(events) + let folded: ReturnType + try { + folded = foldSurface(events) + } catch (error: unknown) { + throw new SessionQueryError( + /* v8 ignore next -- foldSurface throws Error instances */ + `invalid session surface: ${error instanceof Error ? error.message : 'unknown error'}`, + 'SESSION_QUERY_INVALID_SURFACE', + { cause: error }, + ) + } const current = new Set(folded.nodes.map(node => node.seq)) const shadowed = new Set() const replacedBy = new Map() @@ -182,15 +197,24 @@ function validateProvenance( const sources = rawEventSources(event) if (sources === undefined) continue if (!isSurfaceEligibleType(event.type)) { - invalidProvenance(`non-surface event at seq ${event.seq} carries sourceEventSeqs`) + throw new SessionQueryError( + `invalid session provenance: non-surface event at seq ${event.seq} carries sourceEventSeqs`, + 'SESSION_QUERY_INVALID_PROVENANCE', + ) } if (!Array.isArray(sources) || sources.length === 0) { - invalidProvenance(`event at seq ${event.seq} has an empty or invalid sourceEventSeqs`) + throw new SessionQueryError( + `invalid session provenance: event at seq ${event.seq} has an empty or invalid sourceEventSeqs`, + 'SESSION_QUERY_INVALID_PROVENANCE', + ) } const unique = new Set() for (const source of sources as unknown[]) { if (unique.has(source)) { - invalidProvenance(`event at seq ${event.seq} repeats source seq ${String(source)}`) + throw new SessionQueryError( + `invalid session provenance: event at seq ${event.seq} repeats source seq ${String(source)}`, + 'SESSION_QUERY_INVALID_PROVENANCE', + ) } unique.add(source) if ( @@ -200,7 +224,10 @@ function validateProvenance( || source >= event.seq || events[source]?.seq !== source ) { - invalidProvenance(`event at seq ${event.seq} references unknown or non-earlier source seq ${String(source)}`) + throw new SessionQueryError( + `invalid session provenance: event at seq ${event.seq} references unknown or non-earlier source seq ${String(source)}`, + 'SESSION_QUERY_INVALID_PROVENANCE', + ) } } } @@ -212,12 +239,18 @@ function validateProvenance( const replacement = events[replacementSeq]! const sources = rawEventSources(replacement) if (!Array.isArray(sources)) { - invalidProvenance(`replacement at seq ${replacementSeq} omits its shadowed surface sources`) + throw new SessionQueryError( + `invalid session provenance: replacement at seq ${replacementSeq} omits its shadowed surface sources`, + 'SESSION_QUERY_INVALID_PROVENANCE', + ) } const sourceSet = new Set(sources as unknown[]) for (const removedSeq of removedSeqs) { if (!sourceSet.has(removedSeq)) { - invalidProvenance(`replacement at seq ${replacementSeq} omits shadowed surface seq ${removedSeq}`) + throw new SessionQueryError( + `invalid session provenance: replacement at seq ${replacementSeq} omits shadowed surface seq ${removedSeq}`, + 'SESSION_QUERY_INVALID_PROVENANCE', + ) } } } @@ -232,19 +265,6 @@ function eventSources(event: SessionEvent): number[] { return Array.isArray(sources) ? sources as number[] : [] } -function safeFold(events: readonly SessionEvent[]): ReturnType { - try { - return foldSurface(events) - } catch (error: unknown) { - throw new SessionQueryError( - /* v8 ignore next -- foldSurface throws Error instances */ - `invalid session surface: ${error instanceof Error ? error.message : 'unknown error'}`, - 'SESSION_QUERY_INVALID_SURFACE', - { cause: error }, - ) - } -} - function buildDescendants( childrenByParent: ReadonlyMap, sessionId: SessionId, @@ -278,17 +298,3 @@ function compareSessionsAscending(a: SessionRecord, b: SessionRecord): number { function cloneRecord(record: SessionRecord): SessionRecord { return { ...record, header: structuredClone(record.header) } } - -function lineageCycle(id: SessionId): never { - throw new SessionQueryError( - `session lineage contains a cycle at "${id}"`, - 'SESSION_QUERY_INVALID_LINEAGE', - ) -} - -function invalidProvenance(message: string): never { - throw new SessionQueryError( - `invalid session provenance: ${message}`, - 'SESSION_QUERY_INVALID_PROVENANCE', - ) -} From 75de01f06da916ca155bf481414b705680c20435 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Mon, 13 Jul 2026 14:46:43 +0800 Subject: [PATCH 019/359] refactor(session): centralize surface provenance validation --- docs/config-catalog.md | 2 +- .../2026-07-13-session-query-tracing.md | 2 +- packages/core/session/README.md | 1 + packages/core/session/src/index.ts | 2 +- packages/core/session/src/surface.ts | 45 ++++++++ packages/core/session/tests/surface.spec.ts | 62 ++++++++++- .../session-query/session-query/README.md | 2 +- .../session-query/src/tracing.ts | 85 +++------------ packages/support/invariants/README.md | 1 + packages/support/invariants/src/index.ts | 100 ++++++++---------- 10 files changed, 171 insertions(+), 131 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 608046d053..055a66b926 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -359,7 +359,7 @@ export interface Config { } ``` -Source: [`packages/support/invariants/src/index.ts:45`](../packages/support/invariants/src/index.ts) +Source: [`packages/support/invariants/src/index.ts:52`](../packages/support/invariants/src/index.ts) ## `@deepseek-ai/dsh-llm-deepseek` diff --git a/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md b/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md index cb09531fc6..fa2f7a7e33 100644 --- a/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md +++ b/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md @@ -16,7 +16,7 @@ Session relationships are encoded across immutable headers, positional surface o ## Validation boundary -Event tracing checks target existence before surface analysis. Before returning a trace it validates the whole loaded log: only surface event types carry provenance, present arrays are nonempty and duplicate-free, every source is a known earlier seq, and every positional replacement names all surface nodes it removed. Provenance failures use `SESSION_QUERY_INVALID_PROVENANCE`; positional fold failures keep `SESSION_QUERY_INVALID_SURFACE`. `listEvents()` remains a surface-classification operation and does not acquire trace-specific provenance rejection. +Event tracing checks target existence before surface analysis. Before returning a trace it validates the whole loaded log through `dsh-session`'s shared provenance checker: only surface event types carry provenance, present arrays are nonempty and duplicate-free, every source is a known earlier seq, and every positional replacement names all surface nodes it removed. Provenance failures use `SESSION_QUERY_INVALID_PROVENANCE`; positional fold failures keep `SESSION_QUERY_INVALID_SURFACE`. `listEvents()` remains a surface-classification operation and does not acquire trace-specific provenance rejection. All returned records and arrays are detached. A known live event trace never consults persistence; persisted event traces preserve the exact-read list/load consistency check. Session lineage is necessarily a cross-corpus operation and therefore preserves cross-corpus persistence failure semantics. diff --git a/packages/core/session/README.md b/packages/core/session/README.md index 99be514fe9..db3952b1a3 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -48,6 +48,7 @@ Plain class (not a Cordis Service). Create via `ctx.sessions.create()`. - `SurfaceIntent` — `{ surfaceOp: SurfaceOp; sourceEventSeqs?: number[] }`, the required third parameter to `session.append()` for surface-eligible types. - `SurfaceNode` — `{ seq: number; prev: number | null; next: number | null }`, one node in the surface linked list. - `foldSurface(events)` — replay the canonical surface transitions into detached current nodes and actual replacement ranges, rejecting surface-eligible events that lack their mandatory marker. `SurfaceManager` shares the same transitions while retaining its incremental cache. +- `validateSurfaceProvenance(event, knownSeqs, shadowedSeqs?)` — pure provenance-contract check shared by incremental invariant listeners and exact readers. It returns the first violation instead of choosing a caller's error taxonomy. - `isSurfaceEvent(event)` / `isSurfaceEligibleType(type)` — the first narrows a `SessionEvent` to a fully-formed surface node (type is surface-eligible AND `surfaceOp` present); the second is the type-only check (is this one of the five `SurfaceEventType` values?), used to detect a surface-eligible event MISSING its marker — e.g. when validating a seed/load log. ### Request-header reconstruction (`request-header.ts`) diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index ebbf28d63e..2357649eb6 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -21,7 +21,7 @@ export { isJsonValue } from './json.ts' export type { JsonValue } from './json.ts' export { interruptedTurnClosers } from './repair.ts' export type { SurfaceFoldReplacement, SurfaceFoldResult, SurfaceNode } from './surface.ts' -export { foldSurface, isSurfaceEvent, isSurfaceEligibleType } from './surface.ts' +export { foldSurface, isSurfaceEvent, isSurfaceEligibleType, validateSurfaceProvenance } from './surface.ts' export { isToolPairingBalanced } from './tool-pairing.ts' export { applyHeaderDelta, canonicalHeader, diffHeader, foldRequestHeader, headerEquals } from './request-header.ts' diff --git a/packages/core/session/src/surface.ts b/packages/core/session/src/surface.ts index 3e4ce6d89c..8124f05fe6 100644 --- a/packages/core/session/src/surface.ts +++ b/packages/core/session/src/surface.ts @@ -81,6 +81,51 @@ export interface SurfaceFoldResult { replacements: SurfaceFoldReplacement[] } +/** + * Validate one event's logged provenance against the preceding log and the + * surface nodes it actually shadows. + * @param event - event whose optional `sourceEventSeqs` is being checked. + * @param knownSeqs - seqs preceding `event` in the same log. + * @param shadowedSeqs - surface nodes directly removed by this event. + * @returns the first contract violation, or `undefined` when provenance is valid. + */ +export function validateSurfaceProvenance( + event: SessionEvent, + knownSeqs: ReadonlySet, + shadowedSeqs: readonly number[] = [], +): string | undefined { + const sources = (event as SessionEvent & { sourceEventSeqs?: unknown }).sourceEventSeqs + if (sources !== undefined && !isSurfaceEligibleType(event.type)) { + return `${event.type} cannot carry sourceEventSeqs (non-surface event)` + } + if (sources !== undefined && !Array.isArray(sources)) { + return `sourceEventSeqs on event at seq ${event.seq} must be an array when present` + } + if (Array.isArray(sources) && sources.length === 0) { + return 'sourceEventSeqs must not be empty when present' + } + + const unique = new Set() + for (const source of sources ?? []) { + if (unique.has(source)) return 'sourceEventSeqs must not contain duplicates' + unique.add(source) + if (typeof source !== 'number' || !Number.isInteger(source) || source < 0) { + return `sourceEventSeqs contains invalid seq ${String(source)}` + } + if (source >= event.seq) { + return `sourceEventSeqs must reference earlier events: ${source} >= current seq ${event.seq}` + } + if (!knownSeqs.has(source)) return `sourceEventSeqs references unknown seq ${source}` + } + + const sourceSet = new Set(sources ?? []) + const missing = shadowedSeqs.filter(seq => !sourceSet.has(seq)) + if (missing.length > 0) { + return `surface replace: sourceEventSeqs must include every shadowed surface node; missing ${missing.join(', ')}` + } + return undefined +} + /** Mutable state shared by the incremental manager and the full-log fold. */ interface SurfaceFoldState { nodes: SurfaceNode[] diff --git a/packages/core/session/tests/surface.spec.ts b/packages/core/session/tests/surface.spec.ts index 1260b450a4..fe471c29ad 100644 --- a/packages/core/session/tests/surface.spec.ts +++ b/packages/core/session/tests/surface.spec.ts @@ -1,6 +1,13 @@ import { describe, expect, it } from 'vitest' import type { SessionEvent, SurfaceEvent, SurfaceEventType } from '@deepseek-ai/dsh-session' -import { Session, SessionId, foldSurface, isSurfaceEligibleType, isSurfaceEvent } from '@deepseek-ai/dsh-session' +import { + Session, + SessionId, + foldSurface, + isSurfaceEligibleType, + isSurfaceEvent, + validateSurfaceProvenance, +} from '@deepseek-ai/dsh-session' import { CallId } from '@deepseek-ai/dsh-llm' /** Build a minimal session with turn boundaries and a single user message. */ @@ -13,6 +20,59 @@ function surfaceSession(): Session { return s } +function provenanceEvent(seq: number, sourceEventSeqs: unknown): SessionEvent { + return { + type: 'user/message', + seq, + time: seq, + data: { content: [], source: { kind: 'user' } }, + surfaceOp: 'append', + sourceEventSeqs, + } as unknown as SessionEvent +} + +describe('validateSurfaceProvenance', () => { + it('accepts absent or valid provenance and complete replacement coverage', () => { + expect(validateSurfaceProvenance(provenanceEvent(0, undefined), new Set())) + .toBeUndefined() + expect(validateSurfaceProvenance(provenanceEvent(2, [0, 1]), new Set([0, 1]), [1])) + .toBeUndefined() + }) + + it('rejects provenance on a non-surface event', () => { + const event = { + type: 'turn/start', + seq: 1, + time: 1, + data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }, + sourceEventSeqs: [0], + } as unknown as SessionEvent + expect(validateSurfaceProvenance(event, new Set([0]))) + .toMatch(/cannot carry sourceEventSeqs/) + }) + + it.each([ + ['a non-array', 1, 'invalid', new Set([0]), [], /must be an array/], + ['an empty array', 1, [], new Set([0]), [], /must not be empty/], + ['duplicates', 1, [0, 0], new Set([0]), [], /must not contain duplicates/], + ['a non-number', 1, ['0'], new Set([0]), [], /invalid seq 0/], + ['a fractional number', 1, [0.5], new Set([0]), [], /invalid seq 0\.5/], + ['a negative number', 1, [-1], new Set([0]), [], /invalid seq -1/], + ['a self reference', 1, [1], new Set([0]), [], /must reference earlier events/], + ['an unknown earlier seq', 2, [1], new Set([0]), [], /references unknown seq 1/], + ['incomplete replacement coverage', 2, [0], new Set([0, 1]), [0, 1], /missing 1/], + ] as const)( + 'returns the first violation for %s', + (_name, seq, sources, knownSeqs, shadowedSeqs, expected) => { + expect(validateSurfaceProvenance( + provenanceEvent(seq, sources), + knownSeqs, + shadowedSeqs, + )).toMatch(expected) + }, + ) +}) + describe('SurfaceManager', () => { it('shares exact nodes and nested replacement ranges with foldSurface', () => { const s = new Session(SessionId('shared-fold')) diff --git a/packages/session-query/session-query/README.md b/packages/session-query/session-query/README.md index f85ade5984..003fc9a839 100644 --- a/packages/session-query/session-query/README.md +++ b/packages/session-query/session-query/README.md @@ -14,7 +14,7 @@ This is trusted context-wide infrastructure. It performs no caller authorization Persistence is optional and may mount or unmount dynamically. Cross-corpus listing and lineage tracing fail with `SESSION_QUERY_PERSISTENCE_FAILED` while mounted persistence is unreadable. An event read or trace targeting a known live session does not consult persistence, so durable backend health cannot make current in-memory history unreadable. Persisted event operations list before loading and reject a metadata mismatch rather than combining inconsistent observations. -`traceEvent()` validates the whole loaded log before returning relationships: provenance arrays are nonempty and duplicate-free, references name known earlier events, only surface event types carry sources, and each positional replacement names every surface node it removed. Provenance violations fail with `SESSION_QUERY_INVALID_PROVENANCE`; positional fold failures remain `SESSION_QUERY_INVALID_SURFACE`. `listEvents()` only needs surface classification and deliberately does not enforce the trace-specific provenance contract. +`traceEvent()` validates the whole loaded log with `dsh-session`'s shared provenance checker before returning relationships: provenance arrays are nonempty and duplicate-free, references name known earlier events, only surface event types carry sources, and each positional replacement names every surface node it removed. Provenance violations fail with `SESSION_QUERY_INVALID_PROVENANCE`; positional fold failures remain `SESSION_QUERY_INVALID_SURFACE`. `listEvents()` only needs surface classification and deliberately does not enforce the trace-specific provenance contract. `SessionQueryError.code` is a closed union: `SESSION_QUERY_EVENT_NOT_FOUND`, `SESSION_QUERY_INVALID_CONFIG`, `SESSION_QUERY_INVALID_LINEAGE`, `SESSION_QUERY_INVALID_PROVENANCE`, `SESSION_QUERY_INVALID_SURFACE`, `SESSION_QUERY_INVALID_WINDOW`, `SESSION_QUERY_PERSISTENCE_FAILED`, `SESSION_QUERY_SESSION_NOT_FOUND`, and `SESSION_QUERY_SOURCE_CONFLICT`. diff --git a/packages/session-query/session-query/src/tracing.ts b/packages/session-query/session-query/src/tracing.ts index c7cfd89b9a..8327877ee3 100644 --- a/packages/session-query/session-query/src/tracing.ts +++ b/packages/session-query/session-query/src/tracing.ts @@ -1,6 +1,6 @@ /** One-shot session-lineage and event-relationship tracing helpers. */ -import { foldSurface, isSurfaceEligibleType } from '@deepseek-ai/dsh-session' +import { foldSurface, validateSurfaceProvenance } from '@deepseek-ai/dsh-session' import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session' import { SessionQueryError } from './config.ts' import type { @@ -51,7 +51,21 @@ export function traceEventLog( } const analysis = analyzeEventLog(sessionId, events) - validateProvenance(events, analysis.replacedEventSeqs) + const knownSeqs = new Set() + for (const event of events) { + const violation = validateSurfaceProvenance( + event, + knownSeqs, + analysis.replacedEventSeqs.get(event.seq), + ) + if (violation !== undefined) { + throw new SessionQueryError( + `invalid session provenance: ${violation}`, + 'SESSION_QUERY_INVALID_PROVENANCE', + ) + } + knownSeqs.add(event.seq) + } const replacementChain: number[] = [] let replacement = analysis.replacedBy.get(seq) @@ -189,73 +203,6 @@ function analyzeEventLog( } } -function validateProvenance( - events: readonly SessionEvent[], - replacedEventSeqs: ReadonlyMap, -): void { - for (const event of events) { - const sources = rawEventSources(event) - if (sources === undefined) continue - if (!isSurfaceEligibleType(event.type)) { - throw new SessionQueryError( - `invalid session provenance: non-surface event at seq ${event.seq} carries sourceEventSeqs`, - 'SESSION_QUERY_INVALID_PROVENANCE', - ) - } - if (!Array.isArray(sources) || sources.length === 0) { - throw new SessionQueryError( - `invalid session provenance: event at seq ${event.seq} has an empty or invalid sourceEventSeqs`, - 'SESSION_QUERY_INVALID_PROVENANCE', - ) - } - const unique = new Set() - for (const source of sources as unknown[]) { - if (unique.has(source)) { - throw new SessionQueryError( - `invalid session provenance: event at seq ${event.seq} repeats source seq ${String(source)}`, - 'SESSION_QUERY_INVALID_PROVENANCE', - ) - } - unique.add(source) - if ( - typeof source !== 'number' - || !Number.isInteger(source) - || source < 0 - || source >= event.seq - || events[source]?.seq !== source - ) { - throw new SessionQueryError( - `invalid session provenance: event at seq ${event.seq} references unknown or non-earlier source seq ${String(source)}`, - 'SESSION_QUERY_INVALID_PROVENANCE', - ) - } - } - } - - for (const [replacementSeq, removedSeqs] of replacedEventSeqs) { - // Canonical logs guarantee events[i].seq === i, and the fold reports only - // replacement events from this input log. - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const replacement = events[replacementSeq]! - const sources = rawEventSources(replacement) - if (!Array.isArray(sources)) { - throw new SessionQueryError( - `invalid session provenance: replacement at seq ${replacementSeq} omits its shadowed surface sources`, - 'SESSION_QUERY_INVALID_PROVENANCE', - ) - } - const sourceSet = new Set(sources as unknown[]) - for (const removedSeq of removedSeqs) { - if (!sourceSet.has(removedSeq)) { - throw new SessionQueryError( - `invalid session provenance: replacement at seq ${replacementSeq} omits shadowed surface seq ${removedSeq}`, - 'SESSION_QUERY_INVALID_PROVENANCE', - ) - } - } - } -} - function rawEventSources(event: SessionEvent): unknown { return (event as SessionEvent & { sourceEventSeqs?: unknown }).sourceEventSeqs } diff --git a/packages/support/invariants/README.md b/packages/support/invariants/README.md index 94c2682f9d..95ea6261ee 100644 --- a/packages/support/invariants/README.md +++ b/packages/support/invariants/README.md @@ -31,6 +31,7 @@ await ctx.plugin(Invariants, { freeze: false }) // assert contract, don't freez Session log (per session): - **`seq` strictly increases** — the spine of replay equivalence. +- **surface provenance is valid** — `sourceEventSeqs` uses the shared `dsh-session` checker for type eligibility, nonempty unique earlier references, and complete replacement coverage. - **turns pair and nest** — `turn/start` opens a turn, `turn/end` closes the matching one; no overlapping turns. - **steps nest in turns** — `step/start` opens a step in the open turn; `step/end` closes the matching step. - **chunks belong to an open step** — `step/start` precedes its `assistant/chunk`s. diff --git a/packages/support/invariants/src/index.ts b/packages/support/invariants/src/index.ts index 8147a6deb6..fb56519906 100644 --- a/packages/support/invariants/src/index.ts +++ b/packages/support/invariants/src/index.ts @@ -7,7 +7,8 @@ * `session/event`, and `agent/status`. It is **off in production**: enable it * in tests and the demos, where a contract violation should be a loud failure, * not a subtle one. It doubles as executable documentation of the event - * taxonomy: the assertions below ARE the contract. + * taxonomy: these assertions and the shared session validators they invoke + * are the contract. * * Why runtime assertions instead of compile-time deep-readonly types? See * the dev-invariants RFC. Briefly: a `DeepReadonly` is high type-noise across @@ -23,7 +24,13 @@ import type { Context } from 'cordis' import { HarnessError } from '@deepseek-ai/dsh-llm' import type { CallId, GenerateOptions } from '@deepseek-ai/dsh-llm' import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent' -import { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' +import { + Session, + SessionId, + foldRequestHeader, + isSurfaceEligibleType, + validateSurfaceProvenance, +} from '@deepseek-ai/dsh-session' import type { SessionEvent, SurfaceEventType } from '@deepseek-ai/dsh-session' export const name = 'invariants' @@ -121,71 +128,50 @@ function checkEvent(trace: SessionTrace, event: SessionEvent): void { trace.lastSeq = event.seq // --- Surface invariants --- - // Surface metadata (sourceEventSeqs, surfaceOp) is only valid on - // surface-eligible event types. The compiler enforces this at append() - // call sites; this runtime check catches casts and persisted data. - const SURFACE_TYPES = new Set(['user/message', 'assistant/message', 'tool/result', 'context/message', 'steering/message']) // Cast to surface-eligible event type so we can access surfaceOp and // sourceEventSeqs (optional on SessionEvent, mandatory on SurfaceEvent). // SurfaceEvent's mandatory surfaceOp is too strict here — we need to // CHECK whether surface metadata is present, not assume it. const se = event as SessionEvent - if (!SURFACE_TYPES.has(event.type)) { - if (se.sourceEventSeqs !== undefined) { - throw new InvariantError(`${event.type} cannot carry sourceEventSeqs (non-surface event)`) - } - if (se.surfaceOp !== undefined) { - throw new InvariantError(`${event.type} cannot carry surfaceOp (non-surface event)`) - } - } - if (se.sourceEventSeqs !== undefined) { - if (se.sourceEventSeqs.length === 0) { - throw new InvariantError('sourceEventSeqs must not be empty when present') - } - const unique = new Set(se.sourceEventSeqs) - if (unique.size !== se.sourceEventSeqs.length) { - throw new InvariantError('sourceEventSeqs must not contain duplicates') - } - for (const ref of se.sourceEventSeqs) { - if (ref >= event.seq) { - throw new InvariantError(`sourceEventSeqs must reference earlier events: ${ref} >= current seq ${event.seq}`) - } - if (!trace.knownSeqs.has(ref)) { - throw new InvariantError(`sourceEventSeqs references unknown seq ${ref}`) - } - } + if (!isSurfaceEligibleType(event.type) && se.surfaceOp !== undefined) { + throw new InvariantError(`${event.type} cannot carry surfaceOp (non-surface event)`) } + // Fold this event into the tracked surface linked list, validating the // replace contract as we go. `append` adds a tail node; `replace` shadows a // positional range — every shadowed node must appear in sourceEventSeqs. - if (se.surfaceOp !== undefined) { - if (se.surfaceOp === 'append') { - trace.surface.push(event.seq) - } else { - const { start, end } = se.surfaceOp - const startIdx = trace.surface.indexOf(start) - if (startIdx === -1) { - throw new InvariantError(`surface replace: start seq ${start} is not on the surface`) - } - const endIdx = trace.surface.indexOf(end) - if (endIdx === -1) { - throw new InvariantError(`surface replace: end seq ${end} is not on the surface`) - } - if (startIdx > endIdx) { - throw new InvariantError(`surface replace: start seq ${start} (pos ${startIdx}) is after end seq ${end} (pos ${endIdx}) on the surface`) - } - // Every node the replace shadows (surface positions [startIdx, endIdx] - // inclusive) must appear in sourceEventSeqs — the provenance contract. - const shadowed = trace.surface.slice(startIdx, endIdx + 1) - const recorded = new Set(se.sourceEventSeqs ?? []) - const missing = shadowed.filter(seq => !recorded.has(seq)) - if (missing.length > 0) { - throw new InvariantError(`surface replace: sourceEventSeqs must include every shadowed surface node; missing ${missing.join(', ')}`) - } - // Apply the replace to the tracked surface: the new node takes the - // range's position so order stays in sync for later replaces. - trace.surface.splice(startIdx, shadowed.length, event.seq) + let replacement: { startIdx: number; shadowed: number[] } | undefined + if (se.surfaceOp !== undefined && se.surfaceOp !== 'append') { + const { start, end } = se.surfaceOp + const startIdx = trace.surface.indexOf(start) + if (startIdx === -1) { + throw new InvariantError(`surface replace: start seq ${start} is not on the surface`) } + const endIdx = trace.surface.indexOf(end) + if (endIdx === -1) { + throw new InvariantError(`surface replace: end seq ${end} is not on the surface`) + } + if (startIdx > endIdx) { + throw new InvariantError(`surface replace: start seq ${start} (pos ${startIdx}) is after end seq ${end} (pos ${endIdx}) on the surface`) + } + replacement = { startIdx, shadowed: trace.surface.slice(startIdx, endIdx + 1) } + } + + const provenanceViolation = validateSurfaceProvenance( + event, + trace.knownSeqs, + replacement?.shadowed, + ) + if (provenanceViolation !== undefined) { + throw new InvariantError(provenanceViolation) + } + + if (se.surfaceOp === 'append') { + trace.surface.push(event.seq) + } else if (replacement !== undefined) { + // The new node takes the replaced range's position so order stays in sync + // for later replacements. + trace.surface.splice(replacement.startIdx, replacement.shadowed.length, event.seq) } // Boundary/step-scoped events have explicit cases; every OTHER event type — From 84e6f72ef57083cb968fa3473a75bc1caa3b1f79 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Mon, 13 Jul 2026 16:05:11 +0800 Subject: [PATCH 020/359] fix(session-query): reject misplaced surface ops --- docs/cordis-catalog/services.md | 2 +- .../2026-07-13-session-query-tracing.md | 2 +- packages/core/session/README.md | 4 +- packages/core/session/src/index.ts | 57 ++----- packages/core/session/src/surface.ts | 139 +++++++++++++----- packages/core/session/tests/session.spec.ts | 11 +- packages/core/session/tests/surface.spec.ts | 42 ++++-- .../session-query/session-query/README.md | 2 +- .../session-query/src/tracing.ts | 6 +- .../session-query/tests/tracing.spec.ts | 17 +++ packages/support/invariants/README.md | 2 +- packages/support/invariants/src/index.ts | 12 +- 12 files changed, 182 insertions(+), 114 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 20420a96b7..e3f2f8ffd0 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -232,7 +232,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:590`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:557`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` diff --git a/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md b/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md index fa2f7a7e33..ff2e9b7c23 100644 --- a/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md +++ b/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md @@ -16,7 +16,7 @@ Session relationships are encoded across immutable headers, positional surface o ## Validation boundary -Event tracing checks target existence before surface analysis. Before returning a trace it validates the whole loaded log through `dsh-session`'s shared provenance checker: only surface event types carry provenance, present arrays are nonempty and duplicate-free, every source is a known earlier seq, and every positional replacement names all surface nodes it removed. Provenance failures use `SESSION_QUERY_INVALID_PROVENANCE`; positional fold failures keep `SESSION_QUERY_INVALID_SURFACE`. `listEvents()` remains a surface-classification operation and does not acquire trace-specific provenance rejection. +Event tracing checks target existence before surface analysis. Before returning a trace it validates the whole loaded log through `dsh-session`'s shared surface-metadata checker: surface markers obey event-type eligibility, provenance belongs only to surface event types, present arrays are nonempty and duplicate-free, every source is a known earlier seq, and every positional replacement names all surface nodes it removed. Surface-marker and positional-fold failures use `SESSION_QUERY_INVALID_SURFACE`; provenance failures use `SESSION_QUERY_INVALID_PROVENANCE`. `listEvents()` remains a surface-classification operation and does not acquire trace-specific provenance rejection. All returned records and arrays are detached. A known live event trace never consults persistence; persisted event traces preserve the exact-read list/load consistency check. Session lineage is necessarily a cross-corpus operation and therefore preserves cross-corpus persistence failure semantics. diff --git a/packages/core/session/README.md b/packages/core/session/README.md index c575777ccd..fc7e6d4300 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -49,8 +49,8 @@ Durable values need one accepted representation, not a check followed by a secon - `SurfaceOp` — how a surface node entered the linked list: `'append'` (normal tail append) or `{ op: 'replace', start, end }` (replace nodes from `start` through `end` inclusive — both must be valid surface node seqs; `start === end` replaces a single node). Used by compaction to shadow old nodes without deleting them. - `SurfaceIntent` — `{ surfaceOp: SurfaceOp; sourceEventSeqs?: number[] }`, the required third parameter to `session.append()` for surface-eligible types. - `SurfaceNode` — `{ seq: number; prev: number | null; next: number | null }`, one node in the surface linked list. -- `foldSurface(events)` — replay the canonical surface transitions into detached current nodes and actual replacement ranges, rejecting surface-eligible events that lack their mandatory marker. `SurfaceManager` shares the same transitions while retaining its incremental cache. -- `validateSurfaceProvenance(event, knownSeqs, shadowedSeqs?)` — pure provenance-contract check shared by incremental invariant listeners and exact readers. It returns the first violation instead of choosing a caller's error taxonomy. +- `foldSurface(events)` — replay the canonical surface transitions into detached current nodes and actual replacement ranges, rejecting misplaced, missing, malformed, or positionally invalid `surfaceOp` metadata while leaving provenance validation to callers. `SurfaceManager` shares the same transitions while retaining its incremental cache. +- `validateSurfaceMetadata(event, knownSeqs?, shadowedSeqs?)` — canonical structural and provenance check shared by session acceptance, surface folding, incremental invariants, and exact readers. It tags violations as `surface` or `provenance` so callers retain their error taxonomy; omit `knownSeqs` for local shape validation only. - `isSurfaceEvent(event)` / `isSurfaceEligibleType(type)` — the first narrows a `SessionEvent` to a fully-formed surface node (type is surface-eligible AND `surfaceOp` present); the second is the type-only check (is this one of the five `SurfaceEventType` values?), used to detect a surface-eligible event MISSING its marker — e.g. when validating a seed/load log. ### Request-header reconstruction (`request-header.ts`) diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index 87a5cff8a6..88b3c15aff 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -15,7 +15,7 @@ import type { ContentBlock, Message, MessageSource } from '@deepseek-ai/dsh-llm' import { SESSION_FORMAT_VERSION, SessionId } from './types.ts' import type { CreateSessionOptions, EpochHeader, SessionEvent, SessionEventMap, SessionEventType, SessionHeader, SurfaceIntent, SurfaceEventType } from './types.ts' import { snapshotJsonValue } from './json.ts' -import { SurfaceManager, isSurfaceEligibleType } from './surface.ts' +import { SurfaceManager, validateSurfaceMetadata } from './surface.ts' import { foldRequestHeader } from './request-header.ts' export * from './types.ts' @@ -23,7 +23,7 @@ export { isJsonValue, snapshotJsonValue } from './json.ts' export type { JsonValue } from './json.ts' export { interruptedTurnClosers } from './repair.ts' export type { SurfaceFoldReplacement, SurfaceFoldResult, SurfaceNode } from './surface.ts' -export { foldSurface, isSurfaceEvent, isSurfaceEligibleType, validateSurfaceProvenance } from './surface.ts' +export { foldSurface, isSurfaceEvent, isSurfaceEligibleType, validateSurfaceMetadata } from './surface.ts' export { isToolPairingBalanced } from './tool-pairing.ts' export { applyHeaderDelta, canonicalHeader, diffHeader, foldRequestHeader, headerEquals } from './request-header.ts' @@ -157,43 +157,6 @@ function snapshotSessionHeader(id: SessionId, source?: SessionHeader): SessionHe return deepFreeze(record as unknown as SessionHeader) } -/** Validate the runtime shape of surface metadata after its JSON snapshot. */ -function assertSurfaceMetadataShape( - type: string, - surfaceOp: unknown, - sourceEventSeqs: unknown, -): void { - const eligible = isSurfaceEligibleType(type) - if (!eligible) { - if (surfaceOp !== undefined || sourceEventSeqs !== undefined) { - throw new Error(`session event "${type}" is not surface-eligible and cannot carry surface metadata`) - } - return - } - if (surfaceOp === undefined) { - throw new Error(`session event "${type}" is surface-eligible and requires a surfaceOp marker`) - } - if (surfaceOp !== 'append') { - if (surfaceOp === null || typeof surfaceOp !== 'object' || Array.isArray(surfaceOp)) { - throw new Error(`session event "${type}" carries an invalid surfaceOp`) - } - const op = surfaceOp as Record - const keys = Object.keys(op) - if (keys.length !== 3 || !Object.hasOwn(op, 'op') || !Object.hasOwn(op, 'start') || !Object.hasOwn(op, 'end') - || op['op'] !== 'replace' - || typeof op['start'] !== 'number' || !Number.isSafeInteger(op['start']) || op['start'] < 0 - || typeof op['end'] !== 'number' || !Number.isSafeInteger(op['end']) || op['end'] < 0) { - throw new Error(`session event "${type}" carries an invalid replace surfaceOp`) - } - } - if (sourceEventSeqs !== undefined) { - if (!Array.isArray(sourceEventSeqs) - || sourceEventSeqs.some(seq => typeof seq !== 'number' || !Number.isSafeInteger(seq) || seq < 0)) { - throw new Error(`session event "${type}" sourceEventSeqs must contain non-negative safe integers`) - } - } -} - /** Validate the fixed event envelope after one-pass JSON materialization. */ function assertSessionEventEnvelope(value: Record, index: number): asserts value is SessionEvent { const event = value @@ -312,12 +275,15 @@ export class Session { // this at compile time via its typed overload; a seed arrives as raw // SessionEvent[] (replay/fork/load), bypassing that, so re-check at // runtime here rather than silently resuming with empty history. - const structural = snapshot as SessionEvent & { surfaceOp?: unknown; sourceEventSeqs?: unknown } + let violation: ReturnType try { - assertSurfaceMetadataShape(snapshot.type, structural.surfaceOp, structural.sourceEventSeqs) + violation = validateSurfaceMetadata(snapshot) } catch (error: unknown) { throw new Error(`invalid seed event at index ${index}: ${error instanceof Error ? error.message : 'invalid surface metadata'}`) } + if (violation !== undefined) { + throw new Error(`invalid seed event at index ${index}: ${violation.message}`) + } return deepFreeze(snapshot) }) } @@ -392,11 +358,12 @@ export class Session { if (surfaceMetadataSnapshot === undefined) { throw new Error(`session event "${type}" carries non-JSON-serializable surface metadata`) } - assertSurfaceMetadataShape( + const surfaceViolation = validateSurfaceMetadata({ type, - (surfaceMetadataSnapshot as { surfaceOp?: unknown }).surfaceOp, - (surfaceMetadataSnapshot as { sourceEventSeqs?: unknown }).sourceEventSeqs, - ) + seq: this.log.length, + ...(surfaceMetadataSnapshot as { surfaceOp?: unknown; sourceEventSeqs?: unknown }), + }) + if (surfaceViolation !== undefined) throw new Error(surfaceViolation.message) const entry = attachments.get(this) if (entry?.appending) { diff --git a/packages/core/session/src/surface.ts b/packages/core/session/src/surface.ts index 8124f05fe6..c8642d18fc 100644 --- a/packages/core/session/src/surface.ts +++ b/packages/core/session/src/surface.ts @@ -82,46 +82,110 @@ export interface SurfaceFoldResult { } /** - * Validate one event's logged provenance against the preceding log and the - * surface nodes it actually shadows. - * @param event - event whose optional `sourceEventSeqs` is being checked. - * @param knownSeqs - seqs preceding `event` in the same log. + * Validate one event's surface metadata through the canonical structural and + * provenance contract. Structural validation always runs; when `knownSeqs` is + * supplied, provenance must additionally name unique known earlier events and + * cover every shadowed surface node. The tagged result lets callers retain + * their own surface-versus-provenance error taxonomy. + * @param event - event whose `surfaceOp` and `sourceEventSeqs` are being checked. + * @param knownSeqs - seqs preceding `event`, or `undefined` for local shape validation only. * @param shadowedSeqs - surface nodes directly removed by this event. - * @returns the first contract violation, or `undefined` when provenance is valid. + * @returns the first tagged contract violation, or `undefined` when valid. */ -export function validateSurfaceProvenance( - event: SessionEvent, - knownSeqs: ReadonlySet, +export function validateSurfaceMetadata( + event: Pick & { + surfaceOp?: unknown + sourceEventSeqs?: unknown + }, + knownSeqs?: ReadonlySet, shadowedSeqs: readonly number[] = [], -): string | undefined { - const sources = (event as SessionEvent & { sourceEventSeqs?: unknown }).sourceEventSeqs - if (sources !== undefined && !isSurfaceEligibleType(event.type)) { - return `${event.type} cannot carry sourceEventSeqs (non-surface event)` +): { kind: 'surface' | 'provenance'; message: string } | undefined { + const eligible = isSurfaceEligibleType(event.type) + const surfaceOp = event.surfaceOp + const sources = event.sourceEventSeqs + + if (!eligible && surfaceOp !== undefined) { + return { + kind: 'surface', + message: `session event "${event.type}" is not surface-eligible and cannot carry surfaceOp`, + } + } + if (eligible && surfaceOp === undefined) { + return { + kind: 'surface', + message: `session event "${event.type}" is surface-eligible and requires a surfaceOp marker`, + } + } + if (surfaceOp !== undefined && surfaceOp !== 'append') { + if (surfaceOp === null || typeof surfaceOp !== 'object' || Array.isArray(surfaceOp)) { + return { + kind: 'surface', + message: `session event "${event.type}" carries an invalid surfaceOp`, + } + } + const op = surfaceOp as Record + const keys = Object.keys(op) + if (keys.length !== 3 || !Object.hasOwn(op, 'op') || !Object.hasOwn(op, 'start') || !Object.hasOwn(op, 'end') + || op['op'] !== 'replace' + || typeof op['start'] !== 'number' || !Number.isSafeInteger(op['start']) || op['start'] < 0 + || typeof op['end'] !== 'number' || !Number.isSafeInteger(op['end']) || op['end'] < 0) { + return { + kind: 'surface', + message: `session event "${event.type}" carries an invalid replace surfaceOp`, + } + } + } + + if (sources !== undefined && !eligible) { + return { + kind: 'provenance', + message: `${event.type} cannot carry sourceEventSeqs (non-surface event)`, + } } if (sources !== undefined && !Array.isArray(sources)) { - return `sourceEventSeqs on event at seq ${event.seq} must be an array when present` + return { + kind: 'provenance', + message: `sourceEventSeqs on event at seq ${event.seq} must be an array when present`, + } } - if (Array.isArray(sources) && sources.length === 0) { - return 'sourceEventSeqs must not be empty when present' + if (Array.isArray(sources) + && sources.some(source => typeof source !== 'number' || !Number.isSafeInteger(source) || source < 0)) { + return { + kind: 'provenance', + message: `session event "${event.type}" sourceEventSeqs must contain non-negative safe integers`, + } + } + if (knownSeqs === undefined) return + + const sourceSeqs = sources as number[] | undefined + if (sourceSeqs !== undefined && sourceSeqs.length === 0) { + return { kind: 'provenance', message: 'sourceEventSeqs must not be empty when present' } } - const unique = new Set() - for (const source of sources ?? []) { - if (unique.has(source)) return 'sourceEventSeqs must not contain duplicates' + const unique = new Set() + for (const source of sourceSeqs ?? []) { + if (unique.has(source)) { + return { kind: 'provenance', message: 'sourceEventSeqs must not contain duplicates' } + } unique.add(source) - if (typeof source !== 'number' || !Number.isInteger(source) || source < 0) { - return `sourceEventSeqs contains invalid seq ${String(source)}` - } if (source >= event.seq) { - return `sourceEventSeqs must reference earlier events: ${source} >= current seq ${event.seq}` + return { + kind: 'provenance', + message: `sourceEventSeqs must reference earlier events: ${source} >= current seq ${event.seq}`, + } + } + if (!knownSeqs.has(source)) { + return { kind: 'provenance', message: `sourceEventSeqs references unknown seq ${source}` } } - if (!knownSeqs.has(source)) return `sourceEventSeqs references unknown seq ${source}` } - const sourceSet = new Set(sources ?? []) + const sourceSet = new Set(sourceSeqs ?? []) const missing = shadowedSeqs.filter(seq => !sourceSet.has(seq)) if (missing.length > 0) { - return `surface replace: sourceEventSeqs must include every shadowed surface node; missing ${missing.join(', ')}` + return { + kind: 'provenance', + message: `surface replace: sourceEventSeqs must include every shadowed surface node; missing ${missing.join(', ')}`, + } } return undefined } @@ -147,25 +211,26 @@ function applySurfaceEvent( state: SurfaceFoldState, event: SessionEvent, ): SurfaceFoldReplacement | undefined { + const violation = validateSurfaceMetadata(event) + if (violation?.kind === 'surface') throw new Error(violation.message) if (!isSurfaceEligibleType(event.type)) return - if (!isSurfaceEvent(event)) { - throw new Error(`surface event "${event.type}" (seq ${event.seq}) carries no surfaceOp marker`) - } + // The canonical metadata validation above proves this runtime shape. + const surfaceEvent = event as SurfaceEvent - if (event.surfaceOp === 'append') { + if (surfaceEvent.surfaceOp === 'append') { const tail = state.nodes.length > 0 ? state.nodes[state.nodes.length - 1] : undefined - const node: SurfaceNode = { seq: event.seq, prev: tail?.seq ?? null, next: null } - if (tail) tail.next = event.seq + const node: SurfaceNode = { seq: surfaceEvent.seq, prev: tail?.seq ?? null, next: null } + if (tail) tail.next = surfaceEvent.seq state.nodes.push(node) - state.nodeBySeq.set(event.seq, node) + state.nodeBySeq.set(surfaceEvent.seq, node) return } return { - seq: event.seq, - start: event.surfaceOp.start, - end: event.surfaceOp.end, - shadowedSeqs: replaceSurface(state, event.seq, event.surfaceOp), + seq: surfaceEvent.seq, + start: surfaceEvent.surfaceOp.start, + end: surfaceEvent.surfaceOp.end, + shadowedSeqs: replaceSurface(state, surfaceEvent.seq, surfaceEvent.surfaceOp), } } @@ -215,7 +280,7 @@ function replaceSurface( * models cannot disagree with `deriveMessages()` about replacement ranges. * @param events - session events in contiguous seq order. * @returns the current surface and every positional replacement. - * @throws when a surface-eligible event lacks its mandatory `surfaceOp`, or a + * @throws when an event violates the `surfaceOp` type/marker contract, or a * replacement names nodes that are absent or reversed on the current surface. */ export function foldSurface(events: readonly SessionEvent[]): SurfaceFoldResult { diff --git a/packages/core/session/tests/session.spec.ts b/packages/core/session/tests/session.spec.ts index 2204fc9027..fe44de871f 100644 --- a/packages/core/session/tests/session.spec.ts +++ b/packages/core/session/tests/session.spec.ts @@ -313,10 +313,13 @@ describe('Session', () => { expect(event.surfaceOp).toEqual({ op: 'replace', start: 0, end: 0 }) }) - it('adds seed context when surface validation throws a non-Error value', () => { + it.each([ + ['an Error', new Error('validator failed'), 'validator failed'], + ['a non-Error value', 'validator failed', 'invalid surface metadata'], + ] as const)('adds seed context when surface validation throws %s', (_name, failure, expected) => { const originalHasOwn = Object.hasOwn const hasOwn = vi.spyOn(Object, 'hasOwn').mockImplementation((object: object, property: PropertyKey): boolean => { - if ((object as Record)['op'] === 'replace') throw 'validator failed' + if ((object as Record)['op'] === 'replace') throw failure return originalHasOwn(object, property) }) const seed = [{ @@ -329,7 +332,7 @@ describe('Session', () => { try { expect(() => new Session(SessionId('seed-non-error-metadata-failure'), seed)) - .toThrow('invalid seed event at index 0: invalid surface metadata') + .toThrow(`invalid seed event at index 0: ${expected}`) } finally { hasOwn.mockRestore() } @@ -468,7 +471,7 @@ describe('Session', () => { 'turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }, { surfaceOp: 'append' }, - )).toThrow(/not surface-eligible and cannot carry surface metadata/) + )).toThrow(/not surface-eligible and cannot carry surfaceOp/) expect(() => new Session(SessionId('non-surface-metadata-seed'), [{ type: 'turn/start', seq: 0, diff --git a/packages/core/session/tests/surface.spec.ts b/packages/core/session/tests/surface.spec.ts index fe471c29ad..fa7b1ff3ce 100644 --- a/packages/core/session/tests/surface.spec.ts +++ b/packages/core/session/tests/surface.spec.ts @@ -6,7 +6,7 @@ import { foldSurface, isSurfaceEligibleType, isSurfaceEvent, - validateSurfaceProvenance, + validateSurfaceMetadata, } from '@deepseek-ai/dsh-session' import { CallId } from '@deepseek-ai/dsh-llm' @@ -31,11 +31,11 @@ function provenanceEvent(seq: number, sourceEventSeqs: unknown): SessionEvent { } as unknown as SessionEvent } -describe('validateSurfaceProvenance', () => { +describe('validateSurfaceMetadata', () => { it('accepts absent or valid provenance and complete replacement coverage', () => { - expect(validateSurfaceProvenance(provenanceEvent(0, undefined), new Set())) + expect(validateSurfaceMetadata(provenanceEvent(0, undefined), new Set())) .toBeUndefined() - expect(validateSurfaceProvenance(provenanceEvent(2, [0, 1]), new Set([0, 1]), [1])) + expect(validateSurfaceMetadata(provenanceEvent(2, [0, 1]), new Set([0, 1]), [1])) .toBeUndefined() }) @@ -47,28 +47,33 @@ describe('validateSurfaceProvenance', () => { data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }, sourceEventSeqs: [0], } as unknown as SessionEvent - expect(validateSurfaceProvenance(event, new Set([0]))) - .toMatch(/cannot carry sourceEventSeqs/) + expect(validateSurfaceMetadata(event, new Set([0]))) + .toEqual({ + kind: 'provenance', + message: 'turn/start cannot carry sourceEventSeqs (non-surface event)', + }) }) it.each([ ['a non-array', 1, 'invalid', new Set([0]), [], /must be an array/], ['an empty array', 1, [], new Set([0]), [], /must not be empty/], ['duplicates', 1, [0, 0], new Set([0]), [], /must not contain duplicates/], - ['a non-number', 1, ['0'], new Set([0]), [], /invalid seq 0/], - ['a fractional number', 1, [0.5], new Set([0]), [], /invalid seq 0\.5/], - ['a negative number', 1, [-1], new Set([0]), [], /invalid seq -1/], + ['a non-number', 1, ['0'], new Set([0]), [], /non-negative safe integers/], + ['a fractional number', 1, [0.5], new Set([0]), [], /non-negative safe integers/], + ['a negative number', 1, [-1], new Set([0]), [], /non-negative safe integers/], ['a self reference', 1, [1], new Set([0]), [], /must reference earlier events/], ['an unknown earlier seq', 2, [1], new Set([0]), [], /references unknown seq 1/], ['incomplete replacement coverage', 2, [0], new Set([0, 1]), [0, 1], /missing 1/], ] as const)( 'returns the first violation for %s', (_name, seq, sources, knownSeqs, shadowedSeqs, expected) => { - expect(validateSurfaceProvenance( + const violation = validateSurfaceMetadata( provenanceEvent(seq, sources), knownSeqs, shadowedSeqs, - )).toMatch(expected) + ) + expect(violation?.kind).toBe('provenance') + expect(violation?.message).toMatch(expected) }, ) }) @@ -124,7 +129,20 @@ describe('SurfaceManager', () => { } expect(() => foldSurface([malformed])) - .toThrow(/surface event "user\/message" \(seq 0\) carries no surfaceOp marker/) + .toThrow(/surface-eligible and requires a surfaceOp marker/) + }) + + it('foldSurface rejects surfaceOp on a non-surface event', () => { + const malformed = { + type: 'turn/start', + seq: 0, + time: 1, + data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }, + surfaceOp: 'append', + } as unknown as SessionEvent + + expect(() => foldSurface([malformed])) + .toThrow(/not surface-eligible and cannot carry surfaceOp/) }) it('rebuilds a linked list from surfaceOp: append markers', () => { diff --git a/packages/session-query/session-query/README.md b/packages/session-query/session-query/README.md index 003fc9a839..2dcdec085e 100644 --- a/packages/session-query/session-query/README.md +++ b/packages/session-query/session-query/README.md @@ -14,7 +14,7 @@ This is trusted context-wide infrastructure. It performs no caller authorization Persistence is optional and may mount or unmount dynamically. Cross-corpus listing and lineage tracing fail with `SESSION_QUERY_PERSISTENCE_FAILED` while mounted persistence is unreadable. An event read or trace targeting a known live session does not consult persistence, so durable backend health cannot make current in-memory history unreadable. Persisted event operations list before loading and reject a metadata mismatch rather than combining inconsistent observations. -`traceEvent()` validates the whole loaded log with `dsh-session`'s shared provenance checker before returning relationships: provenance arrays are nonempty and duplicate-free, references name known earlier events, only surface event types carry sources, and each positional replacement names every surface node it removed. Provenance violations fail with `SESSION_QUERY_INVALID_PROVENANCE`; positional fold failures remain `SESSION_QUERY_INVALID_SURFACE`. `listEvents()` only needs surface classification and deliberately does not enforce the trace-specific provenance contract. +`traceEvent()` validates the whole loaded log with `dsh-session`'s shared surface-metadata checker before returning relationships: surface markers obey event-type eligibility, provenance arrays are nonempty and duplicate-free, references name known earlier events, and each positional replacement names every surface node it removed. Surface-marker and positional-fold violations fail with `SESSION_QUERY_INVALID_SURFACE`; provenance violations use `SESSION_QUERY_INVALID_PROVENANCE`. `listEvents()` only needs surface classification and deliberately does not enforce the trace-specific provenance contract. `SessionQueryError.code` is a closed union: `SESSION_QUERY_EVENT_NOT_FOUND`, `SESSION_QUERY_INVALID_CONFIG`, `SESSION_QUERY_INVALID_LINEAGE`, `SESSION_QUERY_INVALID_PROVENANCE`, `SESSION_QUERY_INVALID_SURFACE`, `SESSION_QUERY_INVALID_WINDOW`, `SESSION_QUERY_PERSISTENCE_FAILED`, `SESSION_QUERY_SESSION_NOT_FOUND`, and `SESSION_QUERY_SOURCE_CONFLICT`. diff --git a/packages/session-query/session-query/src/tracing.ts b/packages/session-query/session-query/src/tracing.ts index 8327877ee3..09d3ed65f6 100644 --- a/packages/session-query/session-query/src/tracing.ts +++ b/packages/session-query/session-query/src/tracing.ts @@ -1,6 +1,6 @@ /** One-shot session-lineage and event-relationship tracing helpers. */ -import { foldSurface, validateSurfaceProvenance } from '@deepseek-ai/dsh-session' +import { foldSurface, validateSurfaceMetadata } from '@deepseek-ai/dsh-session' import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session' import { SessionQueryError } from './config.ts' import type { @@ -53,14 +53,14 @@ export function traceEventLog( const analysis = analyzeEventLog(sessionId, events) const knownSeqs = new Set() for (const event of events) { - const violation = validateSurfaceProvenance( + const violation = validateSurfaceMetadata( event, knownSeqs, analysis.replacedEventSeqs.get(event.seq), ) if (violation !== undefined) { throw new SessionQueryError( - `invalid session provenance: ${violation}`, + `invalid session provenance: ${violation.message}`, 'SESSION_QUERY_INVALID_PROVENANCE', ) } diff --git a/packages/session-query/session-query/tests/tracing.spec.ts b/packages/session-query/session-query/tests/tracing.spec.ts index 8dd67e4893..0a8b8e6da1 100644 --- a/packages/session-query/session-query/tests/tracing.spec.ts +++ b/packages/session-query/session-query/tests/tracing.spec.ts @@ -390,6 +390,23 @@ describe('session event tracing', () => { .rejects.toThrow(expectCode('SESSION_QUERY_INVALID_PROVENANCE')) }) + it('rejects surfaceOp on a non-surface event as an invalid surface', async () => { + const durable = header('invalid-non-surface-op') + const events = [{ + type: 'turn/start', + seq: 0, + time: 1, + data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }, + surfaceOp: 'append', + }] as unknown as SessionEvent[] + TracePersistence.reset([{ meta: durable, events }]) + const ctx = await queryContext() + await ctx.plugin(TracePersistence) + + await expect(ctx.sessionQuery.traceEvent({ sessionId: durable.id, seq: 0 })) + .rejects.toThrow(expectCode('SESSION_QUERY_INVALID_SURFACE')) + }) + it('keeps listEvents tolerant of malformed provenance alone', async () => { const durable = header('list-regression') TracePersistence.reset([{ meta: durable, events: [appendEvent(0), appendEvent(1, [0, 0])] }]) diff --git a/packages/support/invariants/README.md b/packages/support/invariants/README.md index 8e19cfd79c..2fe2db1f6c 100644 --- a/packages/support/invariants/README.md +++ b/packages/support/invariants/README.md @@ -28,7 +28,7 @@ await ctx.plugin(Invariants) Session log (per session): - **`seq` strictly increases** — the spine of replay equivalence. -- **surface provenance is valid** — `sourceEventSeqs` uses the shared `dsh-session` checker for type eligibility, nonempty unique earlier references, and complete replacement coverage. +- **surface metadata is valid** — `surfaceOp` and `sourceEventSeqs` use the shared `dsh-session` checker for type eligibility, structural shape, nonempty unique earlier references, and complete replacement coverage. - **turns pair and nest** — `turn/start` opens a turn, `turn/end` closes the matching one; no overlapping turns. - **steps nest in turns** — `step/start` opens a step in the open turn; `step/end` closes the matching step. - **chunks belong to an open step** — `step/start` precedes its `assistant/chunk`s. diff --git a/packages/support/invariants/src/index.ts b/packages/support/invariants/src/index.ts index 9a3c67b97e..b2fa15080f 100644 --- a/packages/support/invariants/src/index.ts +++ b/packages/support/invariants/src/index.ts @@ -26,8 +26,7 @@ import { Session, SessionId, foldRequestHeader, - isSurfaceEligibleType, - validateSurfaceProvenance, + validateSurfaceMetadata, } from '@deepseek-ai/dsh-session' import type { SessionEvent, SurfaceEventType } from '@deepseek-ai/dsh-session' @@ -131,9 +130,8 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr // SurfaceEvent's mandatory surfaceOp is too strict here — we need to // CHECK whether surface metadata is present, not assume it. const se = event as SessionEvent - if (!isSurfaceEligibleType(event.type) && se.surfaceOp !== undefined) { - throw new InvariantError(`${event.type} cannot carry surfaceOp (non-surface event)`) - } + const metadataViolation = validateSurfaceMetadata(event) + if (metadataViolation !== undefined) throw new InvariantError(metadataViolation.message) // Fold this event into the tracked surface linked list, validating the // replace contract as we go. `append` adds a tail node; `replace` shadows a @@ -160,13 +158,13 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr } } - const provenanceViolation = validateSurfaceProvenance( + const provenanceViolation = validateSurfaceMetadata( event, trace.knownSeqs, shadowed, ) if (provenanceViolation !== undefined) { - throw new InvariantError(provenanceViolation) + throw new InvariantError(provenanceViolation.message) } // Boundary/step-scoped events have explicit cases; every OTHER event type — From ca2dd34291447a68faad44a4b3bcb16dc417f6e3 Mon Sep 17 00:00:00 2001 From: Dudu-0223 Date: Mon, 13 Jul 2026 17:31:01 +0800 Subject: [PATCH 021/359] fix(agent-loop): fail closed on invalid parallel scheduling --- packages/core/agent-loop/src/tool-calls.ts | 8 +++++++ .../core/agent-loop/tests/tool-calls.spec.ts | 21 +++++++++++++++++++ packages/core/tools/src/index.ts | 3 ++- .../core/tools/tests/execution-mode.spec.ts | 13 ++++++++++++ 4 files changed, 44 insertions(+), 1 deletion(-) diff --git a/packages/core/agent-loop/src/tool-calls.ts b/packages/core/agent-loop/src/tool-calls.ts index a187283701..ae6f44d4dc 100644 --- a/packages/core/agent-loop/src/tool-calls.ts +++ b/packages/core/agent-loop/src/tool-calls.ts @@ -144,6 +144,13 @@ function groupByMode(ctx: Context, planned: PlannedCall[]): PlannedCall[][] { return groups } +/** Validate the live per-agent cap at the point it controls dispatch. */ +function assertMaxParallelToolCalls(maxParallel: number): void { + if (!Number.isInteger(maxParallel) || maxParallel < 1) { + throw new Error('maxParallelToolCalls must be a positive integer') + } +} + /** * The exclusive single-call path keeps the public one-call pipeline sequential: * abort-check, `tool/call`, pre/dispatch/post via `ctx.tools.execute`, @@ -196,6 +203,7 @@ async function runParallelGroup( ): Promise { /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) + assertMaxParallelToolCalls(maxParallel) const slots: (Slot | undefined)[] = group.map(() => undefined) // callSeqs[i] is the `tool/call` event seq for started slot i (its provenance diff --git a/packages/core/agent-loop/tests/tool-calls.spec.ts b/packages/core/agent-loop/tests/tool-calls.spec.ts index d664946bc4..cd4e202b9b 100644 --- a/packages/core/agent-loop/tests/tool-calls.spec.ts +++ b/packages/core/agent-loop/tests/tool-calls.spec.ts @@ -202,6 +202,27 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => })).rejects.toThrow('maxParallelToolCalls must be a positive integer') }) + it('fails loud if maxParallelToolCalls is mutated invalid after agent creation', async () => { + const adapter = new MockAdapter([ + multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]), + textResponse('must not run after unanswered tool calls'), + ]) + const ctx = await harness(adapter) + const gated = gatedParallelTool('p') + ctx.tools.register(gated.tool) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock', maxParallelToolCalls: 2 }) + ;(agent.options as { maxParallelToolCalls: number }).maxParallelToolCalls = 0 + + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + + expect(gated.started).toEqual([]) + expect(adapter.requests).toHaveLength(1) + expect(events(agent).filter(e => e.type === 'tool/call' || e.type === 'tool/result')).toEqual([]) + const turnEnd = events(agent).findLast(e => e.type === 'turn/end') + expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind).toBe('error') + }) + it('starts at most the cap, replenishing as calls settle', async () => { const adapter = new MockAdapter([ multiCall([1, 2, 3, 4].map(n => ({ id: `c${n}`, name: 'p', args: { id: String(n) } }))), diff --git a/packages/core/tools/src/index.ts b/packages/core/tools/src/index.ts index 92a6c20d92..f2eac7349b 100644 --- a/packages/core/tools/src/index.ts +++ b/packages/core/tools/src/index.ts @@ -971,7 +971,8 @@ export class ToolRegistry extends Service { const tool = this.get(exec.name, exec.agent) if (!tool?.isConcurrencySafe) return { kind: 'exclusive' } try { - return tool.isConcurrencySafe(exec.arguments) ? { kind: 'parallel' } : { kind: 'exclusive' } + const concurrencySafe: unknown = tool.isConcurrencySafe(exec.arguments) + return concurrencySafe === true ? { kind: 'parallel' } : { kind: 'exclusive' } } catch { return { kind: 'exclusive' } } diff --git a/packages/core/tools/tests/execution-mode.spec.ts b/packages/core/tools/tests/execution-mode.spec.ts index b4c686188b..ca33baa143 100644 --- a/packages/core/tools/tests/execution-mode.spec.ts +++ b/packages/core/tools/tests/execution-mode.spec.ts @@ -99,6 +99,19 @@ describe('ToolRegistry.executionMode', () => { expect(ctx.tools.executionMode(exec('thrower', {}))).toEqual({ kind: 'exclusive' }) }) + it('a truthy non-boolean classifier result fails closed to exclusive (raw definition)', async () => { + const ctx = await setup() + const raw = { + name: 'truthy', + description: 'classifier returns a truthy string', + parameters: { type: 'object', properties: {} }, + isConcurrencySafe() { return 'yes' }, + async execute() { return [] }, + } as unknown as ToolDefinition + ctx.tools.register(raw) + expect(ctx.tools.executionMode(exec('truthy', {}))).toEqual({ kind: 'exclusive' }) + }) + it('a raw definition (no defineTool) receives the raw parsed value', async () => { const ctx = await setup() let seen: unknown From 8c8e5fdd2432657dd5f530ace53e90a10114697a Mon Sep 17 00:00:00 2001 From: Dudu-0223 Date: Mon, 13 Jul 2026 19:14:36 +0800 Subject: [PATCH 022/359] fix(agent-loop): validate parallel cap before logging calls --- ...2026-07-10-parallel-tool-call-execution.md | 2 ++ packages/core/agent-loop/src/loop.ts | 12 +++++++++--- packages/core/agent-loop/src/tool-calls.ts | 19 +++++++++++++++++-- .../core/agent-loop/tests/tool-calls.spec.ts | 1 + 4 files changed, 29 insertions(+), 5 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md b/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md index 0dd497f441..c8cd96622a 100644 --- a/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md +++ b/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md @@ -101,6 +101,8 @@ Snapshot coverage pins the transcript-facing ACP behavior for a multi-call step: Parallel execution can expose latent shared-state bugs in tools that declare themselves safe too broadly. The default is exclusive, the shipped declarations are conservative, and input-sensitive tools such as bash stay exclusive until their owning package proves a narrower classifier. +Tool registration changes are a scheduling boundary. A call classified against one tool definition can become unsafe if an earlier exclusive tool replaces that definition before dispatch, so registry-mutating tools stay exclusive and scheduler changes that cross such barriers must either reclassify against the live registry view or bind dispatch to the classified definition. + An around-dispatch plugin can also violate the contract even when the tool itself is safe. The scheduler limits that risk to `tools/execute`; shipped wrappers are per-call, and third-party wrappers with shared mutable state must serialize internally. Parallel groups change abort timing: a sibling call may have started in a case where the serial loop would not have reached it yet. The pool makes this explicit by logging only started calls, stopping replenishment on abort, draining those calls to results, and preventing later calls from starting. diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 2c9c38fb1f..fbc1722391 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -19,7 +19,7 @@ import type { TransmissionLog } from './request-log.ts' import { renderPrompt } from '@deepseek-ai/dsh-system-prompt' import type { PromptAssembly } from '@deepseek-ai/dsh-system-prompt' import type {} from '@deepseek-ai/dsh-tools' -import { executeToolCalls } from './tool-calls.ts' +import { executeToolCalls, resolveMaxParallelToolCalls } from './tool-calls.ts' import type { ReactLoopAgent } from './agent.ts' import type { Inbox } from './inbox.ts' @@ -858,6 +858,11 @@ async function runStep( // // sourceEventSeqs records the assistant/chunk provenance, but is omitted when // no chunks streamed (the surface invariant rejects an empty sourceEventSeqs). + const toolCalls = message.content.filter(block => block.type === 'tool-call') + const scheduling = toolCalls.length > 0 + ? { maxParallel: resolveMaxParallelToolCalls(agent.options.maxParallelToolCalls) } + : undefined + if (message.content.length > 0 || assembler.usage) { session.append( 'assistant/message', @@ -874,13 +879,14 @@ async function runStep( // ordered the same way. Tool failures (including aborts) become isError // results; the scheduler re-checks the shared signal around calls and throws // the abort so this step's caller ends the turn. - const toolCalls = message.content.filter(block => block.type === 'tool-call') // Per-step buffer of `additionalContext` attached by tools/post-execute // listeners. Appended as context/message(s) only AFTER every tool/result for // the step, so a multi-call step keeps tool-call/result adjacency // (interleaving context between a call's result and the next call's would // break the pairing the next model request relies on). - const pendingContext = await executeToolCalls(ctx, agent, turn, step, toolCalls, signal) + const pendingContext = scheduling !== undefined + ? await executeToolCalls(ctx, agent, turn, step, toolCalls, signal, scheduling.maxParallel) + : [] // Append buffered post-execute context AFTER every tool/result, preserving // tool-call/result adjacency across the whole batch. inject() appends into the diff --git a/packages/core/agent-loop/src/tool-calls.ts b/packages/core/agent-loop/src/tool-calls.ts index ae6f44d4dc..6ee1dc5906 100644 --- a/packages/core/agent-loop/src/tool-calls.ts +++ b/packages/core/agent-loop/src/tool-calls.ts @@ -60,6 +60,7 @@ interface Slot { * @param step - the current step number (for the session events). * @param toolCalls - the assistant message's `tool-call` blocks, in model order. * @param signal - the step's abort signal (shared by every call). + * @param maxParallel - the already-validated cap snapshot for parallel groups. * @returns the per-step `additionalContext` buffer in model call order. */ export async function executeToolCalls( @@ -69,9 +70,9 @@ export async function executeToolCalls( step: number, toolCalls: ToolCallBlock[], signal: AbortSignal, + maxParallel: number, ): Promise { - const { session, options } = agent - const maxParallel = options.maxParallelToolCalls ?? DEFAULT_MAX_PARALLEL_TOOL_CALLS + const { session } = agent // Plan: parse each call's raw JSON arguments exactly once, and build one // distinct ToolExecution per call so a `tools/execute` wrapper that mutates @@ -108,6 +109,20 @@ export async function executeToolCalls( return pendingContext } +/** + * Resolve and validate the per-step parallel dispatch cap before the assistant + * tool-call message is logged, so invalid mutable options fail without leaving + * dangling model-visible tool calls in the session transcript. + * + * @param maxParallelToolCalls - the live agent option value. + * @returns the positive integer cap to use for this step. + */ +export function resolveMaxParallelToolCalls(maxParallelToolCalls: number | undefined): number { + const maxParallel = maxParallelToolCalls ?? DEFAULT_MAX_PARALLEL_TOOL_CALLS + assertMaxParallelToolCalls(maxParallel) + return maxParallel +} + /** Parse a model-produced raw arguments string, falling back to the raw string on invalid JSON (empty ⇒ `{}`). */ function parseArguments(raw: string): unknown { try { diff --git a/packages/core/agent-loop/tests/tool-calls.spec.ts b/packages/core/agent-loop/tests/tool-calls.spec.ts index cd4e202b9b..987b358720 100644 --- a/packages/core/agent-loop/tests/tool-calls.spec.ts +++ b/packages/core/agent-loop/tests/tool-calls.spec.ts @@ -218,6 +218,7 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => expect(gated.started).toEqual([]) expect(adapter.requests).toHaveLength(1) + expect(events(agent).some(e => e.type === 'assistant/message')).toBe(false) expect(events(agent).filter(e => e.type === 'tool/call' || e.type === 'tool/result')).toEqual([]) const turnEnd = events(agent).findLast(e => e.type === 'turn/end') expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind).toBe('error') From 1123e946c0f5f1966c995debd83adf9c42b50f82 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Mon, 13 Jul 2026 23:56:10 +0800 Subject: [PATCH 023/359] refactor: simplify session log representation --- docs/cordis-catalog/events.md | 10 +- docs/cordis-catalog/services.md | 2 +- docs/core-data-structures/core.md | 4 +- docs/core-data-structures/session.md | 37 +--- docs/event-producer-consumer.md | 8 +- docs/persistence-catalog.md | 44 ++-- docs/rfc/INDEX.md | 4 +- .../2026-06-18-session-surface.md | 17 +- .../2026-07-05-reconstructable-requests.md | 15 +- .../2026-06-18-compaction-capability-seam.md | 4 +- .../feature/2026-06-29-todo-write-tool.md | 2 +- .../feature/2026-07-06-explicit-tool-order.md | 2 +- .../implemented/feature/2026-07-06-sandbox.md | 6 +- .../feature/2026-07-07-session-prefix.md | 11 +- ...6-07-08-self-referential-cordis-toolset.md | 4 +- ...-12-simplify-session-log-representation.md | 33 +++ ...-request-header-content-in-one-scenario.md | 6 +- .../2026-07-08-shared-acp-snapshot-package.md | 2 +- ...-12-simplify-session-log-representation.md | 36 ---- docs/tool-catalog.md | 4 +- .../sandbox-acp-agent/tests/acp.snapshot.ts | 6 +- .../snapshots/mode-switching/session.jsonl | 2 +- .../mode-switching/system-prompt.golden.md | 11 +- packages/bash/bash/src/session-mode.ts | 2 +- packages/compact/compact-basic/src/index.ts | 23 +-- .../compact-basic/tests/compact-basic.spec.ts | 112 +++++----- .../tests/compact-loop-repro.spec.ts | 12 +- packages/core/agent-loop/src/loop.ts | 6 +- packages/core/agent-loop/src/request-log.ts | 21 +- .../agent-loop/tests/interception.spec.ts | 6 +- .../core/agent-loop/tests/request-log.spec.ts | 23 +-- .../tests/request-reconstruction.spec.ts | 23 ++- packages/core/agent/src/types.ts | 2 +- packages/core/session/README.md | 11 +- packages/core/session/src/index.ts | 22 +- packages/core/session/src/request-header.ts | 189 +++-------------- packages/core/session/src/surface.ts | 63 ++---- packages/core/session/src/tool-pairing.ts | 23 +-- packages/core/session/src/types.ts | 77 ++----- .../core/session/tests/derived-cache.spec.ts | 2 +- .../core/session/tests/request-header.spec.ts | 193 ++++-------------- packages/core/session/tests/session.spec.ts | 4 +- packages/core/session/tests/surface.spec.ts | 45 +--- .../core/session/tests/tool-pairing.spec.ts | 24 +-- packages/llm/llm/src/call-config.ts | 4 +- packages/llm/llm/tests/call-config.spec.ts | 2 +- .../tests/jsonl.spec.ts | 17 +- .../tests/sqlite.spec.ts | 17 ++ .../session-persistence/src/coordinator.ts | 11 + packages/support/acp-snapshot/README.md | 2 +- .../support/acp-snapshot/src/normalize.ts | 36 +--- packages/support/acp-snapshot/src/suite.ts | 132 ++++-------- .../fixtures/suite/pin-turn/behavior.json | 2 +- .../fixtures/suite/pin-turn/session.jsonl | 2 +- .../suite/pin-turn/system-prompt.golden.md | 4 +- .../acp-snapshot/tests/normalize.spec.ts | 96 ++------- .../support/acp-snapshot/tests/suite.spec.ts | 51 ++--- packages/support/invariants/README.md | 2 +- packages/support/invariants/src/index.ts | 8 +- .../invariants/tests/invariants.spec.ts | 4 +- packages/ui/user-approval/README.md | 2 +- packages/ui/user-approval/src/index.ts | 6 +- scripts/gen-tool-catalog.ts | 2 +- scripts/type-equiv.manifest.json | 1 - 64 files changed, 522 insertions(+), 1032 deletions(-) create mode 100644 docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md delete mode 100644 docs/rfc/proposed/simplification/2026-07-12-simplify-session-log-representation.md diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index acbd39b8fa..5a3398f9a8 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -89,7 +89,7 @@ Source: [`packages/core/agent/src/types.ts:360`](../../packages/core/agent/src/t ### `agent/request` — waterfall -Waterfall: shape the step's call configuration — model switching, sampling overrides — by returning a replacement LlmCallConfig (the frozen seed is the config the loop would otherwise use). Config is ALL a listener shapes here: every request is a pure function of the session log (the reconstructability RFC), so model-visible content flows through the log channels — `inject()`, steering, prompt-submit `additionalContext`, prompt sections via `system-prompt/assemble`, or the header-logged session prefix via agent/session-prefix — never through request mutation, and the loop records whatever config the request actually uses as a `request/header*` event before dispatch. The step's messages are already snapshotted when this fires (the `step/start` boundary): an `inject()` from a listener here lands in the log but joins the NEXT request. For surface mutation that must precede the snapshot (compaction), use agent/pre-step. Call `next()` to delegate, or return an LlmCallConfig without it to short-circuit. +Waterfall: shape the step's call configuration — model switching, sampling overrides — by returning a replacement LlmCallConfig (the frozen seed is the config the loop would otherwise use). Config is ALL a listener shapes here: every request is a pure function of the session log (the reconstructability RFC), so model-visible content flows through the log channels — `inject()`, steering, prompt-submit `additionalContext`, prompt sections via `system-prompt/assemble`, or the header-logged session prefix via agent/session-prefix — never through request mutation, and the loop records whatever config the request actually uses as a `request/header` event before dispatch. The step's messages are already snapshotted when this fires (the `step/start` boundary): an `inject()` from a listener here lands in the log but joins the NEXT request. For surface mutation that must precede the snapshot (compaction), use agent/pre-step. Call `next()` to delegate, or return an LlmCallConfig without it to short-circuit. ```ts cordis-catalog 'agent/request'(this: Scoped, agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise): Promise @@ -251,7 +251,7 @@ A session was created in the store. A synchronous listener throw vetoes publicat 'session/created'(this: Scoped, session: Session): void ``` -Source: [`packages/core/session/src/index.ts:52`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:51`](../../packages/core/session/src/index.ts) ### `session/disposed` — emit @@ -261,7 +261,7 @@ A previously announced session left the store. Emitted exactly once on normal de 'session/disposed'(this: Scoped, session: Session): void ``` -Source: [`packages/core/session/src/index.ts:64`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:63`](../../packages/core/session/src/index.ts) ### `session/event` — emit @@ -273,7 +273,7 @@ An event was appended to a session log (sync, fire-and-forget). This is the per- Types: [SessionEvent](../core-data-structures/core.md) -Source: [`packages/core/session/src/index.ts:83`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:82`](../../packages/core/session/src/index.ts) ### `session/flush` — parallel @@ -283,7 +283,7 @@ Awaited durability checkpoint. The agent loop awaits `ctx.sessions.flush(session 'session/flush'(this: Scoped, session: Session): Promise | void ``` -Source: [`packages/core/session/src/index.ts:101`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:100`](../../packages/core/session/src/index.ts) ## `skill/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 13de873d0c..ecb68913df 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -218,7 +218,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:590`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:592`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 757c74f399..168d727c8d 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -201,7 +201,7 @@ The model-facing `ToolSchema` is the wire shape; the registered `ToolDefinition` ### The request envelope: `LlmCallConfig` and the logged header -Requests are built by the loop, not shaped per call: the non-history half of a request — the `EpochHeader`: this call configuration plus the rendered system prompt, the tool schemas in the authoritative returned assembly order (initially canonicalized by dsh-system-prompt's `toolOrder` config, or lexicographically when unset), and the session prefix — is logged session state (`request/header` snapshot and delta events, [session.md](session.md#the-request-header-events-requestheader-and-requestheader-delta)), so every conversation request is a pure function of the session log ([reconstructability RFC](../rfc/implemented/architecture/2026-07-05-reconstructable-requests.md)). The `agent/request` waterfall receives a frozen `LlmCallConfig` seed and a listener returns a replacement to switch model or sampling; the `agent/session-prefix` waterfall — fired once per loop instance — composes the request-only messages fronting the derived history (recorded as the header's `messagePrefix`) — the loop logs whatever the request actually uses. Loop-built requests arrive at `llm/stream` deep-frozen; mutation throws. +Requests are built by the loop, not shaped per call: the non-history half of a request — the `EpochHeader`: this call configuration plus the rendered system prompt, the tool schemas in the authoritative returned assembly order (initially canonicalized by dsh-system-prompt's `toolOrder` config, or lexicographically when unset), and the session prefix — is logged as full `request/header` snapshots ([session.md](session.md#the-request-header-event-requestheader)), so every conversation request is a pure function of the session log ([reconstructability RFC](../rfc/implemented/architecture/2026-07-05-reconstructable-requests.md)). The `agent/request` waterfall receives a frozen `LlmCallConfig` seed and a listener returns a replacement to switch model or sampling; the `agent/session-prefix` waterfall — fired once per loop instance — composes the request-only messages fronting the derived history (recorded as the header's `messagePrefix`) — the loop logs whatever the request actually uses. Loop-built requests arrive at `llm/stream` deep-frozen; mutation throws. On the wire, a loop-built request reads in this order: the `system` slot (the rendered prompt assembly) → `messagePrefix` (the frozen session prefix) → the derived history — the boundary snapshot, whose tail is the newest `user/message` on a turn's first step and the previous step's tool results on later steps. The prefix never enters the derived history; its durable record is the header events, and the dev invariant recomputes exactly this equation against every loop-built request. @@ -244,7 +244,7 @@ type SessionEvent = { }[T] ``` -The fifteen event variants (`turn/start`, `turn/end`, `step/start`, `step/end`, `user/message`, `prompt/blocked`, `context/message`, `assistant/chunk`, `assistant/message`, `tool/call`, `tool/result`, `steering/message`, `todo/write`, `request/header`, `request/header-delta`), the `deriveMessages()` projection rules, the `TurnTrigger`/`TurnEndReason` reasons, and the turn-enclosure invariant are on **[session.md](session.md)**. How the log is made durable — the `SessionPersistence` seam, JSONL/SQLite backends, the `session/flush` checkpoint, crash recovery, and `SessionHeader` — is on **[persistence.md](persistence.md)**. +The fourteen event variants (`turn/start`, `turn/end`, `step/start`, `step/end`, `user/message`, `prompt/blocked`, `context/message`, `assistant/chunk`, `assistant/message`, `tool/call`, `tool/result`, `steering/message`, `todo/write`, `request/header`), the `deriveMessages()` projection rules, the `TurnTrigger`/`TurnEndReason` reasons, and the turn-enclosure invariant are on **[session.md](session.md)**. How the log is made durable — the `SessionPersistence` seam, JSONL/SQLite backends, the `session/flush` checkpoint, crash recovery, and `SessionHeader` — is on **[persistence.md](persistence.md)**. ## The agent handle diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index 1b12c3fc48..47517f53c3 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -64,25 +64,14 @@ interface SessionEventMap { * Full snapshot of the {@link EpochHeader} the NEXT request is built under, * with the {@link RequestHeaderReason} it was recorded whole. Appended by * the loop inside the step, before dispatch, on a loop instance's first - * request-building step (`'initial'`/`'resume'`) or when a delta failed its - * round-trip guard (`'fallback'`); always records what the request actually - * used, post-`agent/request`. Anchors the header fold: reconstruction reads - * the latest snapshot and applies the deltas after it. NOT a + * request-building step (`'initial'`/`'resume'`) or when a later request's + * header changes (`'change'`); always records what the request actually + * used, post-`agent/request`. Reconstruction reads the latest snapshot. NOT a * {@link SurfaceEventType}: it produces no LLM message — it is the request * envelope, logged so every request is a pure function of the session log * (the reconstructability RFC). */ 'request/header': { header: EpochHeader; reason: RequestHeaderReason } - /** - * Amendment to the folded {@link EpochHeader}: system line-trim, name-keyed - * tools delta, whole replacement config, or whole replacement session - * prefix (an EMPTY array encodes the transition to "none"). The - * writer verifies `applyHeaderDelta(previous, delta)` reproduces the new - * header exactly and falls back to a `'fallback'` `request/header` snapshot - * when it cannot, so a logged delta ALWAYS round-trips. NOT a - * {@link SurfaceEventType}. - */ - 'request/header-delta': { system?: SystemDelta; tools?: ToolsDelta; config?: LlmCallConfig; messagePrefix?: Message[] } } ``` @@ -97,9 +86,9 @@ export interface TodoItem { } ``` -### The request header events: `request/header` and `request/header-delta` +### The request header event: `request/header` -The request envelope — the `EpochHeader` (call config + rendered system prompt + assembled tool schemas + the session prefix) — is logged session state, so every conversation request is a pure function of the log (the reconstructability RFC). A `request/header` snapshot (reason `'initial' | 'resume' | 'fallback'`) anchors the fold at conversation birth, process boundaries, and delta-encoding fallbacks; `request/header-delta` events amend it mid-run. `foldRequestHeader(events)` reconstructs the header any request was built under; the writer round-trip-verifies every delta before logging it, so a well-formed log always folds. Neither is a `SurfaceEventType` — they produce no LLM message. +The request envelope — the `EpochHeader` (call config + rendered system prompt + assembled tool schemas + the session prefix) — is logged session state, so every conversation request is a pure function of the log (the reconstructability RFC). A full `request/header` snapshot with reason `'initial'` or `'resume'` records each loop-instance boundary; a later changed request records another full snapshot with reason `'change'`. `foldRequestHeader(events)` reconstructs the header by selecting the latest snapshot. The event is not a `SurfaceEventType`: it produces no LLM message. ```ts type-equiv export interface EpochHeader { @@ -120,7 +109,7 @@ export interface EpochHeader { } ``` -Canonical form: an empty system prompt, an empty tool list, and an empty session prefix are ABSENT fields, matching how requests are built. `messagePrefix` is the durable record of the `agent/session-prefix` waterfall's product (the request is `messagePrefix + derived history`); composed once per loop instance and anchored by that instance's snapshot, so the loop never produces a prefix delta in practice — the delta arm (whole-array replacement, an empty array encoding the transition back to absence) exists for codec totality. The other delta payloads (`SystemDelta` — a common-prefix/suffix line trim; `ToolsDelta` — name-keyed added/removed/changed) live beside the events in [`packages/core/session/src/types.ts`](../../packages/core/session/src/types.ts). +Canonical form: an empty system prompt, an empty tool list, and an empty session prefix are absent fields, matching how requests are built. `messagePrefix` is the durable record of the `agent/session-prefix` waterfall's product (the request is `messagePrefix + derived history`); it is composed once per loop instance and included in every full snapshot that instance records. Legacy v0 logs containing the removed `request/header-delta` format are rejected at seed and persistence-load boundaries rather than replayed incompletely. ## `SessionEvent` — one log entry @@ -152,7 +141,7 @@ type SessionEvent = { ## Surface types -The five message-producing types (`SurfaceEventType` — `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`) carry surface metadata declaring how they join the derived surface linked list. See the [session surface RFC](../rfc/implemented/architecture/2026-06-18-session-surface.md). +The five message-producing types (`SurfaceEventType` — `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`) carry surface metadata declaring how they join the ordered derived surface. See the [session surface RFC](../rfc/implemented/architecture/2026-06-18-session-surface.md). ### `SurfaceEventType` — the message-producing subset of event types @@ -173,7 +162,7 @@ export type SurfaceOp = | { op: 'replace'; start: number; end: number } ``` -`'append'` is the normal tail-append path. `replace` shadows surface nodes from `start` through `end` inclusive (both must be valid surface node seqs; `start === end` replaces a single node) and inserts the new node in their place. +`'append'` is the normal tail-append path. `replace` shadows surface entries from `start` through `end` inclusive (both must be valid surface seqs; `start === end` replaces a single entry) and inserts the new event in their place. ### `SurfaceIntent` — the parameter to `session.append()` @@ -186,16 +175,6 @@ export interface SurfaceIntent { Required for `SurfaceEventType` events — every message-producing event must declare how it joins the surface, the sole source of derived history. Non-surface types reject it at compile time. -### `SurfaceNode` — a node in the surface linked list - -```ts type-equiv -export interface SurfaceNode { - seq: number - prev: number | null - next: number | null -} -``` - ## Derived history: `deriveMessages()` and `deriveEventMessage()` `Session.deriveMessages()` projects the event log into the `Message[]` the model sees — cached (each surface node projected once, when first seen; a surface rewrite rebuilds) and frozen (a fresh array per call over shared, deep-frozen messages, so mutating logged history through a projection is unrepresentable). `deriveEventMessage(event)` is the per-node pure function the fold applies — public so external reconstructors and the dev invariant project a log prefix with exactly the same rules and cannot disagree with the cache. The projection rules: diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index a8810a01fe..10720c8abc 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -25,10 +25,10 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:138`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:109`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | -| `session/created` | `emit` | [`packages/core/session/src/index.ts:52`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`session-persistence`](../packages/session-persistence/session-persistence) | -| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:64`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | -| `session/event` | `emit` | [`packages/core/session/src/index.ts:83`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) | -| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:101`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | +| `session/created` | `emit` | [`packages/core/session/src/index.ts:51`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`session-persistence`](../packages/session-persistence/session-persistence) | +| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:63`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | +| `session/event` | `emit` | [`packages/core/session/src/index.ts:82`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) | +| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:100`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | | `skill/provider-added` | `emit` | [`packages/skill/skill/src/index.ts:131`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - | | `skill/provider-removed` | `emit` | [`packages/skill/skill/src/index.ts:137`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - | | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:90`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index 245d25fa5f..7971f84c71 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -37,7 +37,7 @@ Source: [`packages/ui/user-approval/src/index.ts:95`](../packages/ui/user-approv #### `approval/policy` — log-only -The session's approval policy was switched — log-only, durable, replayable, never in the model transcript (the model learns the policy from the prompt section and the narrator's notices). The LAST such event is the session's override (effectiveApprovalPolicy); who asked for it is derivable from position (an event after the log's last `request/header*` was a runtime switch by the user). +The session's approval policy was switched — log-only, durable, replayable, never in the model transcript (the model learns the policy from the prompt section and the narrator's notices). The LAST such event is the session's override (effectiveApprovalPolicy); who asked for it is derivable from position (an event after the log's last `request/header` was a runtime switch by the user). ```ts persistence-catalog 'approval/policy': { policy: ApprovalPolicy } @@ -57,7 +57,7 @@ Raw stream chunk — token-level replay fidelity. Types: [StreamChunk](core-data-structures/llm-streaming.md) -Source: [`packages/core/session/src/types.ts:322`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:287`](../packages/core/session/src/types.ts) #### `assistant/message` — surface @@ -69,13 +69,13 @@ Assembled assistant message for one step (derived history uses this). Carries th Types: [ContentBlock](core-data-structures/core.md) · [TokenUsage](core-data-structures/llm-streaming.md) -Source: [`packages/core/session/src/types.ts:329`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:294`](../packages/core/session/src/types.ts) ### `bash/*` #### `bash/sandbox-mode` — log-only -The session's sandbox mode was switched — log-only (like `approval/*`; NOT a surface event, carries no `surfaceOp`): durable and replayable, never in the model transcript. The LAST such event is the session's override (effectiveSandboxMode); who asked for it is derivable from position (an event after the log's last `request/header*` was a runtime switch by the user; see the tool layer's narrator). +The session's sandbox mode was switched — log-only (like `approval/*`; NOT a surface event, carries no `surfaceOp`): durable and replayable, never in the model transcript. The LAST such event is the session's override (effectiveSandboxMode); who asked for it is derivable from position (an event after the log's last `request/header` was a runtime switch by the user; see the tool layer's narrator). ```ts persistence-catalog 'bash/sandbox-mode': { mode: SandboxMode } @@ -129,7 +129,7 @@ In-session context injection (file-change notices, subdir AGENTS.md, skill conte Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:320`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:285`](../packages/core/session/src/types.ts) ### `hook/*` @@ -165,29 +165,19 @@ A queued prompt an `agent/prompt-submit` listener VETOED — the durable record Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:314`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:279`](../packages/core/session/src/types.ts) ### `request/*` #### `request/header` — log-only -Full snapshot of the EpochHeader the NEXT request is built under, with the RequestHeaderReason it was recorded whole. Appended by the loop inside the step, before dispatch, on a loop instance's first request-building step (`'initial'`/`'resume'`) or when a delta failed its round-trip guard (`'fallback'`); always records what the request actually used, post-`agent/request`. Anchors the header fold: reconstruction reads the latest snapshot and applies the deltas after it. NOT a SurfaceEventType: it produces no LLM message — it is the request envelope, logged so every request is a pure function of the session log (the reconstructability RFC). +Full snapshot of the EpochHeader the NEXT request is built under, with the RequestHeaderReason it was recorded whole. Appended by the loop inside the step, before dispatch, on a loop instance's first request-building step (`'initial'`/`'resume'`) or when a later request's header changes (`'change'`); always records what the request actually used, post-`agent/request`. Reconstruction reads the latest snapshot. NOT a SurfaceEventType: it produces no LLM message — it is the request envelope, logged so every request is a pure function of the session log (the reconstructability RFC). ```ts persistence-catalog 'request/header': { header: EpochHeader; reason: RequestHeaderReason } ``` -Source: [`packages/core/session/src/types.ts:374`](../packages/core/session/src/types.ts) - -#### `request/header-delta` — log-only - -Amendment to the folded EpochHeader: at least one of a SystemDelta, a ToolsDelta, a whole replacement LlmCallConfig (four scalars — not worth diffing), or a whole replacement session prefix (`messagePrefix` — small advisory content, replaced whole; an EMPTY array encodes the transition to "none", mirroring the canonical form's absent field — the loop never produces one in practice: the prefix is composed once per instance and anchored by that instance's snapshot, so this arm exists for codec totality). Appended by the loop inside the step, before dispatch, when the header for this request differs from the fold of the log so far; the writer verifies `applyHeaderDelta(previous, delta)` reproduces the new header exactly and falls back to a `'fallback'` `request/header` snapshot when it cannot, so a logged delta ALWAYS round-trips. NOT a SurfaceEventType. - -```ts persistence-catalog -'request/header-delta': { system?: SystemDelta; tools?: ToolsDelta; config?: LlmCallConfig; messagePrefix?: Message[] } -``` - -Source: [`packages/core/session/src/types.ts:391`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:338`](../packages/core/session/src/types.ts) ### `steering/*` @@ -201,7 +191,7 @@ Steering content injected between steps of a running turn. Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:347`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:312`](../packages/core/session/src/types.ts) ### `step/*` @@ -213,7 +203,7 @@ Closes step `step` of turn `turn`. 'step/end': { turn: number; step: number } ``` -Source: [`packages/core/session/src/types.ts:301`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:266`](../packages/core/session/src/types.ts) #### `step/start` — log-only @@ -223,7 +213,7 @@ Opens step `step` of turn `turn` — one model call plus the tool executions it 'step/start': { turn: number; step: number } ``` -Source: [`packages/core/session/src/types.ts:299`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:264`](../packages/core/session/src/types.ts) ### `todo/*` @@ -239,7 +229,7 @@ NOT a SurfaceEventType: it produces no LLM message and never reaches `deriveMess Types: [TodoItem](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:361`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:326`](../packages/core/session/src/types.ts) ### `tool/*` @@ -253,7 +243,7 @@ The model requested one tool invocation: `name` with the raw `arguments` JSON st Types: [CallId](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:335`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:300`](../packages/core/session/src/types.ts) #### `tool/code-dispatch` — log-only @@ -277,7 +267,7 @@ A completed tool call's model-facing result, plus an optional tool-private `meta Types: [CallId](core-data-structures/core.md) · [ContentBlock](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:345`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:310`](../packages/core/session/src/types.ts) ### `turn/*` @@ -291,7 +281,7 @@ Closes turn `turn` with the TurnEndReason that ended it. The loop fires the awai Types: [TurnEndReason](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:297`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:262`](../packages/core/session/src/types.ts) #### `turn/start` — log-only @@ -303,7 +293,7 @@ Opens turn `turn`. `trigger` records what started it — a drained message batch Types: [TurnTrigger](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:291`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:256`](../packages/core/session/src/types.ts) ### `user/*` @@ -317,4 +307,4 @@ A user-visible prompt (queued message drained at turn start). Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:303`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:268`](../packages/core/session/src/types.ts) diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index ec91aee492..5f534ae2f2 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -21,7 +21,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | | [Drop unconsumed skill provider events](proposed/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 | | [Prune unused web seam fields](proposed/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 | -| [Simplify session-log representation](proposed/simplification/2026-07-12-simplify-session-log-representation.md) | 2026-07-12 | ### Architecture @@ -100,6 +99,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Share the app bins' boot glue instead of maintaining twin copies](implemented/simplification/2026-07-04-share-app-bin-boot-glue.md) | 2026-07-04 | | [Tighten the hook-protocol contract — dialect, discarded fields, double defaults, and lib-owned `hook/result` semantics](implemented/simplification/2026-07-04-tighten-hook-protocol-contract.md) | 2026-07-04 | | [Trim unreachable ACP bridge surface — the branding knobs and the kind-sniffing fallback](implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md) | 2026-07-04 | +| [Simplify session-log representation](implemented/simplification/2026-07-12-simplify-session-log-representation.md) | 2026-07-12 | ### Architecture @@ -119,7 +119,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Every session event is enclosed in a turn](implemented/architecture/2026-06-15-turn-enclosure-invariant.md) | 2026-06-15 | | [Filesystem capability seam — ctx.fs, local backend, and model-facing filesystem tools](implemented/architecture/2026-06-17-filesystem-capability-seam.md) | 2026-06-17 | | [Agent lifecycle and ownership seams](implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md) | 2026-06-18 | -| [Session surface — a linked list over the event log for LLM message derivation](implemented/architecture/2026-06-18-session-surface.md) | 2026-06-18 | +| [Session surface — an ordered projection over the event log](implemented/architecture/2026-06-18-session-surface.md) | 2026-06-18 | | [Shared persistence write coordinator](implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md) | 2026-06-18 | | [Branded IDs everywhere they belong](implemented/architecture/2026-06-20-branded-ids.md) | 2026-06-20 | | [Extract example apps into packages](implemented/architecture/2026-06-20-extract-example-app-packages.md) | 2026-06-20 | diff --git a/docs/rfc/implemented/architecture/2026-06-18-session-surface.md b/docs/rfc/implemented/architecture/2026-06-18-session-surface.md index d7a15a22af..61e292aaeb 100644 --- a/docs/rfc/implemented/architecture/2026-06-18-session-surface.md +++ b/docs/rfc/implemented/architecture/2026-06-18-session-surface.md @@ -1,4 +1,4 @@ -# RFC: Session surface — a linked list over the event log for LLM message derivation +# RFC: Session surface — an ordered projection over the event log Status: implemented @@ -8,7 +8,7 @@ The `Session` event log is the single source of truth ([event-sourced sessions]( ## Decision -Add a **surface** — a derived, cached linked list of "surface nodes" (the subset of events that produce LLM messages) — maintained by `surfaceOp` markers in the event log. +Add a **surface** — a derived, cached order of event sequences (the subset of events that produce LLM messages) — maintained by `surfaceOp` markers in the event log. ### Two new top-level fields on `SessionEvent` @@ -25,13 +25,13 @@ export type SurfaceOp = | { op: 'replace'; start: number; end: number } // shadow [start, end] inclusive ``` -1. **Append** — add a new node to the tail. Used by `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`. The loop passes `surfaceOp: 'append'` on all such appends, and `sourceEventSeqs` where applicable (e.g., `assistant/message` records its `assistant/chunk` sources; `tool/result` records its `tool/call` source). +1. **Append** — add the new event seq to the tail. Used by `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`. The loop passes `surfaceOp: 'append'` on all such appends, and `sourceEventSeqs` where applicable (e.g., `assistant/message` records its `assistant/chunk` sources; `tool/result` records its `tool/call` source). -2. **Replace** — remove nodes from `start` through `end` (both inclusive) and insert a new node in their place. Both `start` and `end` must be valid surface node seqs in the current surface; `start === end` replaces a single node. The node's `sourceEventSeqs` must contain every shadowed surface node. The shadowed events remain in the log but are no longer on the surface. +2. **Replace** — remove entries from `start` through `end` (both inclusive) and insert the new event seq in their place. Both `start` and `end` must be present in the current surface; `start === end` replaces one entry. The event's `sourceEventSeqs` must contain every shadowed surface seq. The shadowed events remain in the log but are no longer on the surface. ### SurfaceManager: delta-based, not full rebuild -A `SurfaceManager` class (private to `Session`) maintains the cached linked list. It tracks `_lastProcessedSeq` and processes only the **delta** (new events since the last access) rather than rescanning the entire log. Because the log is append-only, prior events never change; a seeded log is simply the initial delta folded on first access. +A `SurfaceManager` class (private to `Session`) maintains one ordered `number[]` of event seqs. It tracks `_lastProcessedSeq` and processes only the new events since the last access rather than rescanning the entire log. Because the log is append-only, prior events never change; a seeded log is simply the initial suffix folded on first access. Replace locates its inclusive endpoints by array position and splices the replacement seq into that range; no link objects or seq-to-node map duplicate the order. Delta processing is O(1) when no new events and O(new events) when new events arrive. @@ -54,16 +54,17 @@ Because the surface is the SOLE derivation path, a surface-eligible event that c ## Alternatives considered - **Per-plugin `agent/request` wrapping** (the pre-surface pattern for history manipulation) — listener-ordering fragility, no durable record of what was changed, and every new manipulation forces another change to core `deriveMessages()`. -- **Half-open `[start, endExclusive)` replace ranges** — rejected: the surface is a doubly-linked list whose ends are naturally named by node seqs, and single-node replacement (`start === end`) reads naturally with inclusive semantics. +- **Half-open `[start, endExclusive)` replace ranges** — rejected: endpoints are named by surface event seqs, and single-entry replacement (`start === end`) reads naturally with inclusive semantics. +- **Linked node objects plus a seq map** — rejected: production did not read predecessor links, the only successor use was the next array position, and replacement already required linear `indexOf` lookup. A single seq array preserves the same asymptotic behavior with one representation to validate. - **Full rebuild behind a dirty flag** instead of delta processing — O(N²) over a session's lifetime: every single-event append would rescan all prior events. ## Consequences -- **`packages/core/session`**: New `surface.ts` (`SurfaceManager`), new types (`SurfaceOp`, `SurfaceIntent`), new fields on `SessionEvent`, modified `append()` (third required `SurfaceIntent` param), refactored `deriveMessages()` (walks the surface as the sole derivation path), surface-aware `repair.ts`. The seed constructor rejects a surface-eligible seed event missing its `surfaceOp` marker (see § Invariants). +- **`packages/core/session`**: `surface.ts` (`SurfaceManager`) maintains one ordered seq array; `SurfaceOp`/`SurfaceIntent` and the top-level session-event fields record how entries join it. `append()` requires a `SurfaceIntent` for surface events, `deriveMessages()` walks the surface as the sole derivation path, and `repair.ts` emits surface-aware closers. The seed constructor rejects a surface-eligible seed event missing its `surfaceOp` marker (see § Invariants). - **`packages/core/agent-loop`**: All surface-capable appends pass surface opts. Chunk seqs are collected for `assistant/message` provenance; `tool/call` seqs are captured for `tool/result` provenance. - **`packages/session-persistence/session-persistence-sqlite`**: Two new nullable TEXT columns (`source_event_seqs`, `surface_op`) on the `events` table; `SCHEMA_VERSION` bumped (bump-and-reject, no migration). - **`packages/support/invariants`**: Surface-related validation rules. - **`packages/session-persistence/session-persistence-jsonl`**: No changes required. - **`packages/session-persistence/session-persistence`**: Abstract interface unchanged. -The surface is the foundation for future history manipulation. A compaction or tool-result-prune plugin appends one of the existing message-producing event types (a `user/message` carrying the summary, say) with `surfaceOp: { op: 'replace', start, end }` and `sourceEventSeqs` covering the shadowed nodes — the new node takes the range's place on the surface while the plugin's own trace events (e.g. `compaction/start`, `compaction/end`) stay off it. Replay preserves the decision deterministically. +The surface is the foundation for future history manipulation. A compaction or tool-result-prune plugin appends one of the existing message-producing event types (a `user/message` carrying the summary, say) with `surfaceOp: { op: 'replace', start, end }` and `sourceEventSeqs` covering the shadowed entries — the new event takes the range's place on the surface while the plugin's own trace events (e.g. `compaction/start`, `compaction/end`) stay off it. Replay preserves the decision deterministically. diff --git a/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md b/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md index 0b82e52581..38f5a690c6 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md +++ b/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md @@ -18,13 +18,13 @@ Prefix-cache stability is corollary #1, not the headline: an append-only log pro ### The mechanism -**Messages.** `Session.deriveMessages()` is cached: each surface node is projected exactly once, when first seen, through the public per-node function `deriveEventMessage(event)`; a surface rewrite (a compaction `replace` — `SurfaceManager.replaceGeneration`) rebuilds. Callers get a fresh array per call over shared, deep-frozen messages: mutating logged history through a projection is unrepresentable (it throws), replacing the old clone-per-call isolation. External reconstructors fold the same public function over a log prefix, so no two paths can disagree. +**Messages.** `Session.deriveMessages()` is cached: each surface entry is projected exactly once, when first seen, through the public per-event function `deriveEventMessage(event)`; a surface rewrite (a compaction `replace` — `SurfaceManager.replaceGeneration`) rebuilds. Callers get a fresh array per call over shared, deep-frozen messages: mutating logged history through a projection is unrepresentable (it throws), replacing the old clone-per-call isolation. External reconstructors fold the same public function over a log prefix, so no two paths can disagree. -**The header.** The request's non-history half — `EpochHeader`: call config (`LlmCallConfig`: model + sampling scalars), rendered system prompt, assembled tool schemas, and the session prefix (`messagePrefix`, below) — is logged session state, in canonical form (empty system/tools/prefix ≡ absent). Two log-only, turn-enclosed events in dsh-session carry it: `request/header`, a full snapshot with reason `'initial' | 'resume' | 'fallback'`, and `request/header-delta`, an amendment (`SystemDelta`: a common-prefix/suffix line trim; `ToolsDelta`: name-keyed added/removed/changed; `config`: replaced whole; `messagePrefix`: replaced whole, an empty array encoding the transition to absence — an arm the loop never exercises in practice, kept for codec totality). The pure trio `foldRequestHeader` / `diffHeader` / `applyHeaderDelta` reconstructs; the live session tracks the fold with the same lazy cursor as the message cache. Snapshots anchor the fold where a fold needs anchors — conversation birth and process boundaries — and each loop instance appends one on its first request (`'initial'` when the log has none, `'resume'` otherwise, even when nothing changed: the boundary itself is a recorded fact, and cross-restart drift becomes attributable while an unchanged header resumes byte-identical). Deltas are an encoding optimization with a safety valve, never a correctness dependency: the writer verifies `applyHeaderDelta(prev, delta)` reproduces the new header exactly and records a `'fallback'` snapshot when the encoding cannot express a change (a pure tool reordering), so a well-formed log always folds. +**The header.** The request's non-history half — `EpochHeader`: call config (`LlmCallConfig`: model + sampling scalars), rendered system prompt, assembled tool schemas, and the session prefix (`messagePrefix`, below) — is logged session state in canonical form (empty system/tools/prefix ≡ absent). One log-only, turn-enclosed event carries it: `request/header`, always a full snapshot. Each loop instance appends one on its first request (`'initial'` when the log has none, `'resume'` otherwise, even when nothing changed: the boundary itself is a recorded fact and cross-restart drift becomes attributable); a later request whose canonical header differs appends another with reason `'change'`. `foldRequestHeader` reconstructs by selecting the latest snapshot, and the live session tracks that fold with the same lazy cursor as the message cache. Legacy v0 logs containing the removed delta representation are rejected at seed and persistence-load boundaries rather than partially replayed. **The loop, transmission-stateless.** Per step: render assembly (every step — value comparison needs no change-signal discipline, and a section that varies per step surfaces as a *logged* header event per step instead of a silent bust) → on the instance's FIRST step only, the `agent/session-prefix` waterfall — request-ONLY messages fronting the entire derived history (a frozen empty seed, contributions returned as an extension of `next()`; the home for session-stable openers that must NOT become history — a skills catalog, an AGENTS.md digest), deep-frozen and cached on the instance so reuse is structural and the prefix cannot drift mid-session — → `agent/pre-step`, carrying the composed prefix (compaction's surface mutations land before derivation, and its pressure gate counts the prefix this instance will actually send — never a previous instance's logged one, which could under-gate a resumed/forked instance whose contributor grew) → **messages snapshot, then `step/start` appended as the next operation in the same synchronous frame** → seed the call config (first request of the instance: from `AgentOptions`, so explicit options always beat the logged baseline — fork model-overrides and resume reconfiguration stay correct; afterwards: from the folded header) → the `agent/request` waterfall, re-typed `(agent, turn, step, config: LlmCallConfig, next) → LlmCallConfig` — a frozen seed and a returned replacement are ALL a listener shapes; durable content flows through the log channels (`inject()`, steering, prompt-submit `additionalContext`, sections via `system-prompt/assemble`) — → the header event the request owes the log, carrying the prefix as `messagePrefix` (no session event carries it, so the header is its only durable record; resume = a new instance = a recompose, anchored by its `'resume'` snapshot) → build `GenerateOptions` from `messagePrefix + snapshot` + header, deep-freeze (`deepFreeze` exempts the `AbortSignal`, the one live control channel — freezing one breaks `AbortController.abort()`), dispatch. The loop's per-instance bookkeeping is one boolean plus the cached prefix: whether this instance has logged its anchoring snapshot, and what it composed. -**The reconstruction boundary is `step/start`, unconditionally.** A step's messages are the derivation over `events[0..stepStartSeq)`. Because the snapshot precedes the `step/start` append in the same synchronous frame, an `agent.inject()` from an `agent/request` listener or any concurrent task lands after the boundary and joins the NEXT request. `session/event` is observe-only during publication: a reentrant append is rejected until the current callback list drains, preventing nested event delivery from overtaking the event being observed. `agent/pre-step` is the sanctioned seam for content that must affect the CURRENT request. A step's header for reconstruction is the fold after its own `request/header*` event (which sits between its `step/start` and first response event) or the fold carried forward. +**The reconstruction boundary is `step/start`, unconditionally.** A step's messages are the derivation over `events[0..stepStartSeq)`. Because the snapshot precedes the `step/start` append in the same synchronous frame, an `agent.inject()` from an `agent/request` listener or any concurrent task lands after the boundary and joins the NEXT request. `session/event` is observe-only during publication: a reentrant append is rejected until the current callback list drains, preventing nested event delivery from overtaking the event being observed. `agent/pre-step` is the sanctioned seam for content that must affect the CURRENT request. A step's header for reconstruction is the latest `request/header` at or after its `step/start` (before the first response event), or the fold carried forward when the request header is unchanged. **Enforcement.** Dev-mode ([dsh-invariants](../../../../packages/support/invariants/src/index.ts)), on `llm/stream`: a frozen request with a live `sessionId` — the loop-built marker; hand-built one-shots are unfrozen and skipped — must carry messages deep-equal to the folded header's `messagePrefix` followed by the boundary derivation — the derivation rebuilt through a FRESH `Session` over `events[0..stepStartSeq)` so the live cache cannot vouch for itself — and header fields equal to `foldRequestHeader` over the log. There is no divergence allowance and nothing to allow: no seam can put unlogged content into a request — the `agent/session-prefix` seam's product enters only because the header event records it first. `prepend: true` only defends against the replay adapter's short-circuit (an append-registered listener); two prepended listeners have no defined mutual order in cordis, so correctness rests on the seq-bounded fold, never on listener timing. Measurement stays lean: the with-key e2e ([request-cache.e2e.ts](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts)) proves `usage.cacheReadTokens > 0` on every request after the first against the live API, and per-step usage in the log is the production observable — a header event or compaction shows up as a cache-read collapse on the next step. @@ -39,15 +39,16 @@ What survives from `LLMClient`: the conversation is maintained, not rebuilt — - **Per-call request scalars** (a freely mutable config handed to each `agent/request` dispatch): a listener flips the model per call with zero accounting, silently abandoning the provider cache this design exists to protect. Config is per-conversation logged state; the waterfall proposes, the log records. - **Detect-and-report** (compare consecutive requests, warn on divergence): catches violations after the fact; a violating request is still constructible and ships. Rejected for interface-level unrepresentability. - **Event-driven assembly** (re-render only on change signals): a missed-signal bug class — a tool registered mid-session emits `tools/change`, not `system-prompt/change`, and a third-party provider may emit nothing. Per-step render + value compare is robust with zero signal discipline. -- **Narrative fields on the header events** (a `reason`/`changed` list on deltas): derivable by diffing consecutive events — one home per fact; snapshots carry a reason because an anchor's cause is NOT derivable from the data. +- **A custom header-delta codec** (system line edits, name-keyed tool edits, whole config/prefix replacements): it reduced repeated header bytes but duplicated state across codec types, diff/apply machinery, and fallback handling. Full changed snapshots preserve reconstructability with one representation; compression remains available if measured logs justify it. +- **Narrative changed-field lists on header snapshots**: derivable by diffing consecutive snapshots — one home per fact. Snapshots keep a reason because an instance boundary versus an in-instance change is not derivable from data alone. ## Consequences - A request that is not explained by the log cannot be constructed by accident — not by the loop, not by a listener; mutating a built request throws; every header change is a durable, diffable log event. - Choosing between the advisory channels is a change-frequency decision, and the design makes the stable one structural: an `agent/session-prefix` contribution is composed once per loop instance and reused verbatim, so it extends the cacheable prefix at zero marginal cost and CANNOT bust the provider cache mid-session; content that changes mid-session flows through the append-only history channels — `agent.inject()`, a `tools/post-execute` decision's `additionalContext`, prompt-submit `additionalContext` — each a durable `context/message` paid once and prefix-cached thereafter, at the price of accumulating in history and the log. Route session-frozen openers to the prefix and change notices to the history channels; a per-step request-only tail slot was deliberately dropped (no consumer, and a durable append covers every current update pattern). -- What still costs full price at the provider is inherent and logged: compaction (its `compact/*` events and replace node), a real prompt/tool change (`request/header-delta`), a config switch (ditto), a process boundary with drift (`'resume'` snapshot differing from its predecessor). The provider's own reasoning-content exclusion is managed server-side. +- What still costs full price at the provider is inherent and logged: compaction (its `compact/*` events and surface replacement), a real prompt/tool/config change (`request/header` with reason `'change'`), or a process boundary with drift (`'resume'` snapshot differing from its predecessor). The provider's own reasoning-content exclusion is managed server-side. - The `step/start`-listener behavior change (above) is the one observable semantics change for plugins; `agent/pre-step` is the current-request seam. -- Tool-result trimming (planned) needs no new mechanism: a logged single-node surface replace (`start === end`) carrying a trimmed `tool/result` under the same `callId` — compaction-family, replay-correct, cache-bust batched by the same pressure logic. -- Session logs grow one `request/header` snapshot per conversation (system + tool schemas: the dominant term), plus deltas on real changes — small next to `assistant/chunk` volume; `SESSION_FORMAT_VERSION` stays `0` (pre-release churn is absorbed, backends reject-not-migrate). +- Tool-result trimming (planned) needs no new mechanism: a logged single-entry surface replace (`start === end`) carrying a trimmed `tool/result` under the same `callId` — compaction-family, replay-correct, cache-bust batched by the same pressure logic. +- Session logs grow one `request/header` snapshot per loop instance plus full snapshots on real changes. This spends more bytes than a custom delta codec but stays small beside chunk-heavy logs and leaves one replay representation. `SESSION_FORMAT_VERSION` stays `0`; a legacy v0 delta event is rejected rather than migrated. - Snapshot goldens changed once (every transcript gains its header events); the fs-writing fixtures are stored in the normalized authored form with cwd-relative tool arguments, because replay only round-trips cwd-independent argument paths. - FIXME(call-config-shape): revisit `LlmCallConfig`'s exact field set — which fields are genuinely epoch-level for cache purposes (`model` certainly; the sampling scalars sit there out of caution), and where provider-specific extras (reasoning options, extra body params) belong when an adapter needs them. diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index bba12727f7..e0835dcaa6 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -6,7 +6,7 @@ Status: implemented A long-running agent conversation grows without bound. As the event log accumulates turns, the derived message history eventually approaches the model's context window — the model then truncates mid-response (`max-tokens`) or degrades. **Compaction** is the mitigation: replace a run of older history with a concise summary, keeping recent context intact. -The [session surface](../../implemented/architecture/2026-06-18-session-surface.md) was built as the foundation for exactly this — a linked list over the event log with a `surfaceOp: { op: 'replace', start, end }` operation purpose-built to shadow a range of nodes and insert a replacement, with `sourceEventSeqs` recording provenance so the decision replays deterministically. What remained was the plugin that *decides what to compact and produces the summary*. +The [session surface](../../implemented/architecture/2026-06-18-session-surface.md) was built as the foundation for exactly this — an ordered projection over the event log with a `surfaceOp: { op: 'replace', start, end }` operation purpose-built to shadow a range of entries and insert a replacement, with `sourceEventSeqs` recording provenance so the decision replays deterministically. What remained was the plugin that *decides what to compact and produces the summary*. Two forces shape the design. First, compaction is **swappable**: token counting can be a char/4 heuristic or a real tokenizer, and summarization can be a model call, a template, or a remote service — these vary independently of *when* and *which range* to compact. Second, `SurfaceEventType` is closed to five event types (`user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`); only those may carry `surfaceOp`. A bespoke `compaction/*` event therefore **cannot** itself appear on the surface — the compiler rejects `surfaceOp` on it and the invariants plugin rejects it at runtime. @@ -54,7 +54,7 @@ This **amends** the original RFC's claim of "NO changes to `dsh-agent-loop`; com Auto-compaction fires before **every** step, not once per turn. This is **load-bearing for runaway-turn survival**: a tool-heavy ReAct turn appends an `assistant/message` + a `tool/result` per step, so the surface grows *within* a turn. A single turn can grow past the window on its own (a "runaway turn") — and the only moment to rescue it before the next model call overflows is the next step's `pre-step` checkpoint. Gating compaction to a turn's first step (or, worse, retaining the whole in-flight turn verbatim) re-opens exactly the hole compaction exists to close: the harness would die when compaction is most needed. -So retention does **not** protect the in-flight turn, and turn boundaries play no role in it. `compactIfNeeded` walks the surface nodes tail→head, summing per-node token estimates, and retains the smallest tail-run of **whole units** whose total reaches `retainTokens`; everything older is compacted (head-anchored — see below). A *unit* is either a whole closed step (its `assistant/message` plus its `tool/result`s) or a single no-step node (a pre-step `user/message`, inter-step `steering/message`, or injection `context/message`). The walk rounds toward retaining *more*: when the raw token cutoff lands mid-step, it extends the retained side head-ward until the cut before the retained node is **tool-pairing balanced**. The single structural guard is therefore **tool-pairing balance** — a region's edges are balanced cuts on the *surface* (no unanswered `tool-call` crosses either edge), so a compacted region never splits a step's tool-calls from their `tool/result`s (which would produce a transcript every provider rejects). The check is decided over the surface linked list, **not** the log's `step/*` markers: a compaction lands a replacement node at a high log seq whose surface position is the head, so a log-position scan mis-reads its neighbours — `dsh-session` exports `isToolPairingBalanced(nodes, events, beforeSeq)` for the surface-anchored check. `compactRegion` enforces it strictly, throwing on a boundary that would split a step. +So retention does **not** protect the in-flight turn, and turn boundaries play no role in it. `compactIfNeeded` walks the surface entries tail→head, summing per-entry token estimates, and retains the smallest tail-run of **whole units** whose total reaches `retainTokens`; everything older is compacted (head-anchored — see below). A *unit* is either a whole closed step (its `assistant/message` plus its `tool/result`s) or a single no-step entry (a pre-step `user/message`, inter-step `steering/message`, or injection `context/message`). The walk rounds toward retaining *more*: when the raw token cutoff lands mid-step, it extends the retained side head-ward until the cut before the retained entry is **tool-pairing balanced**. The single structural guard is therefore **tool-pairing balance** — a region's edges are balanced cuts on the *surface* (no unanswered `tool-call` crosses either edge), so a compacted region never splits a step's tool-calls from their `tool/result`s (which would produce a transcript every provider rejects). The check is decided over surface order, **not** the log's `step/*` markers: a compaction lands a replacement at a high log seq whose surface position is the head, so a log-position scan misreads its neighbours — `dsh-session` exports `isToolPairingBalanced(nodes, events, beforeSeq)` for the surface-anchored check. `compactRegion` enforces it strictly, throwing on a boundary that would split a step. A runaway turn thus compacts exactly like any other history: its early *closed* steps get summarized while its recent steps stay verbatim. When the only compactable content left is an un-splittable open tail step (its tool-calls have no results yet), compaction declines (`null`) and retries once that step closes. diff --git a/docs/rfc/implemented/feature/2026-06-29-todo-write-tool.md b/docs/rfc/implemented/feature/2026-06-29-todo-write-tool.md index 90bd274eb3..a708225482 100644 --- a/docs/rfc/implemented/feature/2026-06-29-todo-write-tool.md +++ b/docs/rfc/implemented/feature/2026-06-29-todo-write-tool.md @@ -20,7 +20,7 @@ The list is appended as a `todo/write` event carrying the full `{ todos }` snaps ### NOT a surface event -`todo/write` is deliberately excluded from `SurfaceEventType`. The surface is the projection that produces the LLM message history (`deriveMessages()`); a todo write produces no conversation message. So it carries no `surfaceOp`, never joins the surface linked list, and never reaches `deriveMessages()` — it is durable, replayable *UI* state that travels alongside the conversation without being part of it. (The dev-mode invariants still require it to sit inside an open turn, which it always does: it is appended mid-step during a tool call.) +`todo/write` is deliberately excluded from `SurfaceEventType`. The surface is the projection that produces the LLM message history (`deriveMessages()`); a todo write produces no conversation message. So it carries no `surfaceOp`, never joins the ordered surface, and never reaches `deriveMessages()` — it is durable, replayable *UI* state that travels alongside the conversation without being part of it. (The dev-mode invariants still require it to sit inside an open turn, which it always does: it is appended mid-step during a tool call.) ### Priority synthesized only at the ACP boundary diff --git a/docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md b/docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md index 39345c2b53..048c359948 100644 --- a/docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md +++ b/docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md @@ -39,7 +39,7 @@ Config plumbing follows the `persona` precedent, and `toolOrder` sits beside it: - Every registry-built assembly starts with a deterministic tool order on every host; absent an expert listener that deliberately changes it, every `request/header` event and model request inherits that order. The CI-vs-local registration-order flip is structurally gone, and the default is lexicographic. - The initial `PromptAssembly.tools` is canonical, so waterfall listeners start from the model-facing order; provider registration order is observable nowhere before that cooperative seam. - The snapshot suite's single pinned request-header fixture (`text-turn`) carries the new canonical tool order; every other ACP snapshot keeps the header bulk scrubbed as `{{system}}`/`{{tools}}`, per the pinned-header design. -- A pure tool reordering between steps is representable only as a `request/header` `'fallback'` snapshot (the name-keyed `ToolsDelta` cannot express it); with a stable canonical order such reorders no longer occur in practice, so the fallback path stays a safety valve. +- A pure tool reordering between steps is logged like any other header change: a full `request/header` snapshot with reason `'change'`. Stable canonical order prevents registration timing from creating such changes in the ordinary path. - The `toolOrder` key rides the app → `agent-core` → `SystemPrompt` forwarding chain, so deployments set it next to `persona` in the app config; `dsh-llm` and the agent loop are untouched. - A misspelled or unloaded tool name in `toolOrder` fails the turn at prompt assembly, not the boot: the loop assembles inside the turn (after `turn/start`, before `step/start`), so the rejection reaches the turn's outer catch — the turn closes balanced with an `error` reason carrying the message, `agent/error` mirrors it, no step opens, no `request/header` is logged, no request reaches the adapter, and the agent returns to idle. Every turn fails identically until the config is fixed; the process itself stays up (matching the repo rule that explicit config references must not be silently ignored — the enforcement point is the assembly because no earlier universal moment exists). - A tool provider that returns the reserved rest-entry name has the same prompt-assembly failure shape as an unknown listed name. This keeps the sentinel from becoming an ambiguous real tool and preserves the "never drops a tool" ordering contract. diff --git a/docs/rfc/implemented/feature/2026-07-06-sandbox.md b/docs/rfc/implemented/feature/2026-07-06-sandbox.md index e3e740b31c..cbfe4feee3 100644 --- a/docs/rfc/implemented/feature/2026-07-06-sandbox.md +++ b/docs/rfc/implemented/feature/2026-07-06-sandbox.md @@ -118,7 +118,7 @@ interface SessionEventMap { Each owner exports the same three-piece kit: the event declaration, a pure fold (`effectiveSandboxMode(events)` / `effectiveApprovalPolicy(events)` — a `findLast`, typed to the domain's closed union), and THE write path (`setSandboxMode(session, mode)` / `setApprovalPolicy(session, policy)` — a switch IS its event; nothing mutates state out of band). No shared owner service, no generic facts map, no registry: a third knob copies the ~40-line pattern into its own package. Execution follows the fold on both sides — the bash tool's per-call stamp reads it as the middle rung of the § Escalation precedence chain, and the approval seam's `'never'` gate is [the approval RFC](2026-07-06-approval-seam.md)'s side of the same pattern. -**Visibility is deliberately asymmetric between the knobs.** The SANDBOX mode is stated nowhere and its switches are not narrated: a standing "you are read-only" declaration teaches the model to refuse preemptively (observed live: sessions where the model would not even attempt a write it could have escalated), while the denial marker already names the mode the command ran under at exactly the moment the boundary matters — behavior, not belief, carries the state, and a switch simply changes what the next command does. The APPROVAL policy keeps both layers, because its failure mode is the opposite: an auto-rejected ask under `'never'` returns "the user rejected …" wording no behavior can disambiguate, so the prompt states `'never'` (and ONLY `'never'` — an `'ask'` promise is unknowable without asking, and absence under a logged header is how the narrator reads `'ask'` back), and an `agent/pre-step` narrator injects at most one coalesced notice per policy switch: idle flip-flops collapse to one notice at the next turn's first step, a net-zero round trip to none, and a mid-turn change is narrated no later than the next step. Its "last told" is in-memory with a log-derived fallback (the folded header's system text parsed against the closed candidate sentence; LAST occurrence wins, so a persona quoting it cannot shadow the real section), so restarts lose nothing; attribution is positional (a knob event after the log's last `request/header*` reads `changed by the user`, a drift with no such event reads `changed by the operator/config`). +**Visibility is deliberately asymmetric between the knobs.** The SANDBOX mode is stated nowhere and its switches are not narrated: a standing "you are read-only" declaration teaches the model to refuse preemptively (observed live: sessions where the model would not even attempt a write it could have escalated), while the denial marker already names the mode the command ran under at exactly the moment the boundary matters — behavior, not belief, carries the state, and a switch simply changes what the next command does. The APPROVAL policy keeps both layers, because its failure mode is the opposite: an auto-rejected ask under `'never'` returns "the user rejected …" wording no behavior can disambiguate, so the prompt states `'never'` (and ONLY `'never'` — an `'ask'` promise is unknowable without asking, and absence under a logged header is how the narrator reads `'ask'` back), and an `agent/pre-step` narrator injects at most one coalesced notice per policy switch: idle flip-flops collapse to one notice at the next turn's first step, a net-zero round trip to none, and a mid-turn change is narrated no later than the next step. Its "last told" is in-memory with a log-derived fallback (the folded header's system text parsed against the closed candidate sentence; LAST occurrence wins, so a persona quoting it cannot shadow the real section), so restarts lose nothing; attribution is positional (a knob event after the log's last `request/header` reads `changed by the user`, a drift with no such event reads `changed by the operator/config`). **The editor surface** is protocol-native [Session Config Options](https://agentclientprotocol.com/protocol/session-config-options) — the spec's replacement for session modes (slated for removal in ACP v2), already SDK-typed. The bridge advertises one independent `select` per composable knob — `sandbox-mode` (category `mode`) iff the mounted executor confines, `approval-policy` iff the approval seam is composed — with `currentValue` folded from each session's own log, in `session/new` and `session/load` responses. `session/set_config_option` validates against the same closed lists, routes to the domain setter, and returns the complete refreshed state (the spec contract). @@ -135,7 +135,7 @@ FIXME: Revisit this tool-local boundary. The follow-up design needs to determine - Unit tier (no real runner anywhere): profile dialects, per-platform chain selection (sole candidate unprobed, no chain fails closed, multi-candidate probe order), verdict caching, the fail-closed end, probe-report parsing, and the launcher/`sandbox-exec` CLI contracts via fake runner scripts in `dsh-sandbox-local`; wrapping, policy hand-off, fact stamping, and runner-failure-outranks-denial classification (foreground throw, background `runnerFailed` fact) against a fake provider in `dsh-bash-sandbox`; the error's structured identity in `dsh-sandbox`. The escalation matrix spans the three bash packages: verbatim carry-through in `dsh-bash-local`, stamp/branch/per-task-facts in `dsh-bash-sandbox`, and the capability gate, `justification` pairing, fail-closed texts (pinned verbatim), and grant stamping in `dsh-tool-bash`. The switching surface pins the folds, the stamping precedence, the `'never'` gate, per-session section rendering, the full narrator matrix (cold start, coalescing, net-zero, resume drift with operator wording, positional attribution, persona-shadow hardening), and the bridge's advertisement gating, validation rejections, idle-vs-mid-turn anchoring (dev invariants mounted), and `session/load` reporting over a real two-process JSONL round trip. - Keyless real-runner e2e, split along the seam and per rung: CI's `sandbox-e2e` matrix runs bwrap and Landlock on Linux (the Landlock leg once per architecture, each confining through the registry-installed launcher) and Seatbelt on macOS against real kernels, failing on a silent all-skip. World-proofs live in `dsh-sandbox-local` (denied writes absent on disk, workspace writes landing, temp-area grants pinned, kernel denial text matching the advertised dialect) and `dsh-bash-sandbox` (the through-`ctx.bash` consumer proofs, including denied-then-overridden-write-lands). This package's own publish path is rehearsed without publishing (`packed-install.e2e.ts`): `pnpm pack`, tarballs installed into a throwaway consumer with the launcher family resolving from the registry, plain `node` confining through the INSTALLED launcher — asserted executable apart, so a mode-stripped binary can never masquerade as a non-enforcing kernel. The switching surface has its own keyless e2e (`examples/sandbox-acp-agent`): the real `cordis.yml` tree advertises both options, honors switches end to end, and rejects out-of-vocabulary values. - With-key e2e (`examples/sandbox-acp-agent/tests/escalation.e2e.ts`): real model + real runner + the REAL bridge answerer, world-verified — denied under `read-only`, escalates with justification, the scripted editor grants and the retried write lands on disk, while a rejected escalation leaves no write. Self-skips without `DEEPSEEK_API_KEY` or a usable runner (e2e.yml installs bubblewrap so it actually executes in CI). -- Snapshot tier (`examples/sandbox-acp-agent/tests/acp.snapshot.ts`): the keyless config-option wire; the recorded mode-switching arc as the suite's pinned header — necessarily, since mid-session switches emit the `request/header-delta`s the uniformity guard licenses only in the pin — committing both switches, the prompt-section delta and one "changed by the user" notice per knob, and a confined write landing under the switched mode; and both recorded escalation branches over scripted `permissionAnswers` (grant runs confined under `workspace-write`; rejection executes nothing and pins the fail-closed text). Replay re-executes every fixture's bash calls under the host's real runner (ci.yml's snapshot lane installs bubblewrap). Deliberately absent: a fixture carrying a real DENIAL — denial stderr is the backend's dialect and would pin a fixture to its recording platform; the escalation prompts assert the prior denial instead, and the denial→marker path stays on the tiers above. +- Snapshot tier (`examples/sandbox-acp-agent/tests/acp.snapshot.ts`): the keyless config-option wire; the recorded mode-switching arc as the suite's pinned header — necessarily, since its mid-session switch emits the changed `request/header` the uniformity guard licenses only in the pin — committing both switches, the full changed prompt and one "changed by the user" notice per knob, and a confined write landing under the switched mode; and both recorded escalation branches over scripted `permissionAnswers` (grant runs confined under `workspace-write`; rejection executes nothing and pins the fail-closed text). Replay re-executes every fixture's bash calls under the host's real runner (ci.yml's snapshot lane installs bubblewrap). Deliberately absent: a fixture carrying a real DENIAL — denial stderr is the backend's dialect and would pin a fixture to its recording platform; the escalation prompts assert the prior denial instead, and the denial→marker path stays on the tiers above. ## Deferred phases @@ -168,7 +168,7 @@ Each phase gets its full design when picked up, validated against the code at th - **A generic `env/state` facts map with an owner service** — rejected: approval and sandbox compose independently, so neither's state may drag in a third package; single-key folds are one `findLast` each, dissolving the owner service; no invariant spans the knobs, so atomic multi-key patches bought nothing. - **Narrate via `agent/user-message` + a bus event** — rejected: it presupposes a turn-entry seam that does not exist (the real seam is `agent/prompt-submit`), and pre-step's position serves both the coalesced turn-entry notice and the mid-turn immediacy bound with one listener. - **A standing prompt statement of the sandbox mode (+ a switch narrator)** — shipped first, then removed on live evidence: with `Bash commands run under the "read-only" file sandbox.` in every request, the model refused to ATTEMPT denied-then-escalatable work (five of twelve turns in the first manual session ended with zero tool calls), turning the sandbox into a soft lockout. The denial marker names the mode at the moment it matters and the escalation fields carry the recovery; the approval knob keeps its statement because an auto-rejection is behaviorally indistinguishable from a human "no". -- **Track "last told" with its own bookkeeping events** — rejected: the `request/header*` fold already records the exact prompt the model saw; parsing the closed candidate sentences back replaces a second bookkeeping stream — events are needed only where they ARE the store. +- **Track "last told" with its own bookkeeping events** — rejected: the latest `request/header` already records the exact prompt the model saw; parsing the closed candidate sentences back replaces a second bookkeeping stream — events are needed only where they ARE the store. - **ACP session modes instead of config options** — rejected: one mode list cannot carry two orthogonal knobs; config options are the spec's designed surface and modes are slated for removal in ACP v2. ## Consequences diff --git a/docs/rfc/implemented/feature/2026-07-07-session-prefix.md b/docs/rfc/implemented/feature/2026-07-07-session-prefix.md index 6f81d12407..153a93f873 100644 --- a/docs/rfc/implemented/feature/2026-07-07-session-prefix.md +++ b/docs/rfc/implemented/feature/2026-07-07-session-prefix.md @@ -22,21 +22,20 @@ Because composition runs before the boundary snapshot, a composing listener's se ## Testing -**Unit** — [interception.spec.ts](../../../../packages/core/agent-loop/tests/interception.spec.ts) pins compose-once across turns and steps (one composition, zero `request/header-delta`s), canonical prepend ordering, empty-prefix omission from the header, the frozen seed (in-place push throws), held-reference mutation immunity, and composition-precedes-pre-step with the seam receiving the composed value; [cancel.spec.ts](../../../../packages/core/agent-loop/tests/cancel.spec.ts) pins cancel/dispose landing inside the composition window and the discard-and-recompose stale-cache guard; dsh-session codec tests cover the `messagePrefix` fold/diff/apply arms (empty ≡ absent); dsh-invariants tests pin the `messagePrefix + derivation` equation; dsh-compact-basic tests pin that the pressure estimate counts the handed prefix. **Snapshot** — the acp-snapshot normalizer scrubs header prefixes to count-preserving `{{messagePrefix}}` tokens (unit-covered in dsh-acp-snapshot); header content itself is pinned per [the pinned-header scenario RFC](../testing/2026-07-06-pin-request-header-content-in-one-scenario.md), and the example tree loads no prefix contributor, so live goldens stay prefix-free. **e2e** — none prefix-specific: the seam is provider-independent and deterministic; the with-key cache measurement in [request-cache.e2e.ts](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts) already proves the cacheable-prefix economics the design rests on. +**Unit** — [interception.spec.ts](../../../../packages/core/agent-loop/tests/interception.spec.ts) pins compose-once across turns and steps (one composition and no changed headers), canonical prepend ordering, empty-prefix omission from the header, the frozen seed (in-place push throws), held-reference mutation immunity, and composition-precedes-pre-step with the seam receiving the composed value; [cancel.spec.ts](../../../../packages/core/agent-loop/tests/cancel.spec.ts) pins cancel/dispose landing inside the composition window and the discard-and-recompose stale-cache guard; dsh-session header tests cover canonical prefix snapshots and latest-snapshot folding; dsh-invariants tests pin the `messagePrefix + derivation` equation; dsh-compact-basic tests pin that the pressure estimate counts the handed prefix. **Snapshot** — the acp-snapshot normalizer scrubs header prefixes to count-preserving `{{messagePrefix}}` tokens (unit-covered in dsh-acp-snapshot); header content itself is pinned per [the pinned-header scenario RFC](../testing/2026-07-06-pin-request-header-content-in-one-scenario.md), and the example tree loads no prefix contributor, so live goldens stay prefix-free. **e2e** — none prefix-specific: the seam is provider-independent and deterministic; the with-key cache measurement in [request-cache.e2e.ts](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts) already proves the cacheable-prefix economics the design rests on. ## Alternatives considered -- **Per-request `before`/`after` slots recomputed every step** (the shape first proposed: a waterfall firing on every request, contributing frozen `before` messages ahead of the history and fresh `after` messages behind it) — rejected. A per-step `before` recompose invites silent drift — nothing anchors it to the log short of logging a header delta per step — and an `after` slot sits behind the growing history, so its tokens re-pay on every request and everything after it is uncacheable. Measured against the alternatives, every current update pattern is served cheaper by a durable append (paid once, cache-read thereafter), and the only content with no home was the session-stable opener — which wants freezing, not recomputation. -- **A system-prompt section** (`system-prompt/assemble`) — rejected for this content: the assembly renders to the single `system` string, so message-shaped openers do not fit, and the system prompt is deliberately re-assembled per step (with header deltas when it changes) while the opener wants instance-frozen semantics. +- **Per-request `before`/`after` slots recomputed every step** (the shape first proposed: a waterfall firing on every request, contributing frozen `before` messages ahead of the history and fresh `after` messages behind it) — rejected. A per-step `before` recompose invites drift that must be logged as a full changed header, and an `after` slot sits behind the growing history, so its tokens re-pay on every request and everything after it is uncacheable. Measured against the alternatives, every current update pattern is served cheaper by a durable append (paid once, cache-read thereafter), and the only content with no home was the session-stable opener — which wants freezing, not recomputation. +- **A system-prompt section** (`system-prompt/assemble`) — rejected for this content: the assembly renders to the single `system` string, so message-shaped openers do not fit, and the system prompt is deliberately re-assembled per step (with a full changed header when it changes) while the opener wants instance-frozen semantics. - **A durable history opener** (`inject()` at session start) — rejected: permanent history is the failure mode in the problem statement — replayed everywhere, compactable, stale across resumes. -- **Compose per turn instead of per instance** — rejected: a turn-boundary recompose either desyncs silently from the log or forces a header delta per change, and it busts the provider cache exactly as often as it fires; the legitimate refresh point is the instance boundary, where the `'resume'` snapshot already records drift attributably. +- **Compose per turn instead of per instance** — rejected: a turn-boundary recompose either desyncs silently from the log or forces a full changed header, and it busts the provider cache exactly as often as it fires; the legitimate refresh point is the instance boundary, where the `'resume'` snapshot already records drift attributably. - **Compose lazily at the first request and let compaction read the folded header** (the shape as first merged) — superseded in review: the fold matches the live prefix only from the instance's second request on, so on a resumed/forked instance's first step the pressure gate read the PREVIOUS instance's prefix and could under-gate. Composing before the first pre-step and handing the live value through the seam makes the estimate exact at every step. -- **A dedicated session event carrying the prefix** — rejected: the header events are the request's non-history record by design; a second event would be a second home for the same fact and another codec to keep total. +- **A dedicated session event carrying the prefix** — rejected: request headers are the request's non-history record by design; a second event would be a second home for the same fact. ## Consequences - `agent/pre-step` and `CompactService.compactIfNeeded` carry a `sessionPrefix` parameter: every pre-step listener and compaction backend sees the real per-instance value (all in-repo implementations updated in the same change, per the pre-release stance). - A contributor whose content changes mid-session is not re-read until the next instance — by design. A deployment needing mid-session catalog updates routes the change notice through the append-only history channels and pays one durable `context/message`. - The dropped `after` slot leaves no request-only channel near the request tail; nothing in the repo needs one, and adding it back would re-open the every-step re-pay cost the design exists to avoid. -- The `request/header-delta` `messagePrefix` arm (whole-array replacement, empty array encoding transition to absence) exists for codec totality; the loop never exercises it, because the cached prefix cannot change within an instance. - An empty composition is canonical absence: no-contributor deployments log no extra header bytes and their requests are the bare derivation. diff --git a/docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md b/docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md index 3ec6c75cbc..0899065b71 100644 --- a/docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md +++ b/docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md @@ -52,7 +52,7 @@ Freshness is gated like every generated artifact: `pnpm run verify-cordis-api` ( The plugin exposes one config field, validated by schemastery and documented in [the config catalog](../../../config-catalog.md): `vmTimeoutMs` (default 5000), the millisecond bound on the synchronous portion of mount-code evaluation. Tool names, the `cordis-dynamic` group name, and the `dyn-` id prefix are structural vocabulary and stay fixed. All three tools render as `generic` cards per [the tool cookbook](../../../cookbook/adding-a-tool.md) (`cordis_inspect` a `read`, `cordis_mount` an `execute` carrying the code as `rawInput`, `cordis_unmount` a `delete`), with no `presentResult` overrides. -Model-visible ⟺ logged holds with no new session event type: a mount or unmount is visible only through its own `tool/call` / `tool/result` pair, which the loop logs, and the changed tool set a mount induces is logged by the request-header delta the loop already emits when schemas change between steps. There is deliberately no `cordis/mount` provenance event — it would duplicate what the tool-call pair records. Dynamic mounts are process-lifetime, not session state: resuming a persisted session rehydrates the conversation but does not re-mount plugins. +Model-visible ⟺ logged holds with no new session event type: a mount or unmount is visible only through its own `tool/call` / `tool/result` pair, which the loop logs, and the changed tool set a mount induces is logged by the full changed request header the loop emits when schemas change between steps. There is deliberately no `cordis/mount` provenance event — it would duplicate what the tool-call pair records. Dynamic mounts are process-lifetime, not session state: resuming a persisted session rehydrates the conversation but does not re-mount plugins. ## Alternatives considered @@ -71,7 +71,7 @@ The correctness investment therefore goes where it pays for every capability at **A hand-maintained service/event reference in the tool.** The first cut of the inspect tool carried a hand-written table of service method signatures. It was replaced by the generated `api-catalog.ts` because a hand table drifts from the JSDoc the moment a signature changes and nothing gates the drift, whereas the generated artifact is freshness-checked against the same AST the docs use. -**A new `cordis/mount` session event.** A durable provenance event recording each mount (source, name) has clear precedent (`hook/invoked`, `compact/start`). It was declined for v1: mount and unmount are already visible as `tool/call` / `tool/result` pairs and the tool-set change is already logged as a request-header delta, so a dedicated event would only duplicate the record. It remains addable if an audit use case needs mount provenance separable from the tool call. +**A new `cordis/mount` session event.** A durable provenance event recording each mount (source, name) has clear precedent (`hook/invoked`, `compact/start`). It was declined for v1: mount and unmount are already visible as `tool/call` / `tool/result` pairs and the tool-set change is already logged as a full changed request header, so a dedicated event would only duplicate the record. It remains addable if an audit use case needs mount provenance separable from the tool call. **A hardened / capability-restricted sandbox.** Trapping Node built-ins and handing mount code a whitelist façade rather than the raw context might suggest an intent to sandbox for safety. It is explicitly not that: the traps and the façade narrow the *surface* mount code sees — steering it onto cordis services and away from leak-prone Node built-ins and framework internals — for correctness and to close the unguarded-context escape, but the capabilities the façade exposes (`ctx.bash`, `ctx.fs`, `ctx.web`) reach the real runtime, so it is not a security boundary. A real one (separate process, permission prompts) was out of scope for a dev/opt-in toolset and would fight the entire point — handing the model the live runtime. diff --git a/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md b/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md new file mode 100644 index 0000000000..dae2ecbec3 --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md @@ -0,0 +1,33 @@ +# RFC: Simplify session-log representation + +Status: implemented + +## Problem + +The session log maintains two representations that cost more machinery than their consumers require: a pseudo-linked surface and custom request-header deltas. + +`SurfaceManager` stores the same order in an array, a seq map, and mutable `prev`/`next` links. Production never reads `prev`; compact's sole `next` read is the successor of an array position. Replacement already uses `indexOf`, so the links do not make its dominant operation constant-time. A seq array with linear replacement lookup has the same asymptotic replacement cost and one representation to validate. + +The request-header subsystem implements a custom system/tool delta codec and transmission-decision layer even though its contract says deltas are an encoding optimization, not a reconstructability requirement. Retaining the initial/resume full snapshot at each loop-instance boundary, then writing a canonical full `request/header` whenever that instance's assembled header changes, preserves replay while deleting `SystemDelta`, `ToolsDelta`, round-trip fallback, and the durable `request/header-delta` variant. Codec-only vocabulary disappears with the codec, not because its individual arms were invalid. + +This proposal deliberately retains append and replacement `sourceEventSeqs`, crash-repair provenance, and all `SessionStartSource` variants: implemented RFCs give those fields an audit/interception role that zero current readers does not overturn. + +## Decision + +`SurfaceManager.nodes` is a `readonly number[]` of event sequences; the public `SurfaceNode` shape, node links, and seq-to-node map are removed. The internal replace-generation signal remains. Tool-pairing balance and compaction use array values and indices for successor and replacement ranges. + +Request headers use canonical full snapshots only. Initial and resume anchors remain full snapshots even when unchanged; an in-instance change appends another full `request/header` with reason `change`. The delta event, codec types, diff/apply helpers, and codec-only `fallback` reason are removed. Request reconstruction selects the latest snapshot. + +`SESSION_FORMAT_VERSION` remains pinned at `0`, so seed and persistence-load validation explicitly reject an old v0 log containing `request/header-delta`. There is no compatibility fold or migration. JSONL and SQLite tests pin this fail-loud boundary, and the ACP snapshot harness represents legitimate mid-session changes as full pinned headers and full readable prompts. + +## Alternatives considered + +**Keep linked nodes and compact deltas for possible scale.** Links could help a future cursor API, and deltas can reduce logs when large tool schemas change by a small amount. No shipped cursor uses the links, while full snapshots trade disk size for substantially simpler correctness. If header volume proves material, compression or a measured canonical-delta scheme can be designed around real traces. + +## Verification + +Unit coverage pins ordered-surface append/replace behavior, tool pairing, compaction, full-header folding/logging, request reconstruction, and dev invariants. Seed validation plus JSONL and SQLite load tests reject the legacy event before replay. The keyless ACP suite exercises record, refresh, replay, changed-header pinning, and the sandbox mode-switch fixture in the new shape. + +## Consequences + +Full headers increase log volume, and linear replacement lookup could be slower on very large surfaces. Replacements were already linear because the prior implementation called `indexOf`; benchmarks are deferred until real traces show the simpler array is a bottleneck. The format version remains `0`, so explicit legacy-event rejection is a permanent part of the pre-release format boundary. In return, surface order and request-header state each have one representation, deleting link maintenance, maps, codec arms, round-trip fallback, and delta-aware snapshot normalization. diff --git a/docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md b/docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md index 00a60ad4bc..cdb316b053 100644 --- a/docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md +++ b/docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md @@ -10,9 +10,9 @@ An ACP snapshot suite needs to prove the exact composed system prompt and tool-s Exactly one scenario per header-composition class is flagged `pinsHeader`. Its directory splits the pin by review format: `system-prompt.golden.md` contains the normalized composed prompt as ordinary Markdown, while `session.jsonl` keeps the full tool-schema list, config, and reason but stores `header.system` as `"{{system}}"`. Every other JSONL stores both the system prompt and tool list as `"{{system}}"` / `"{{tools}}"`. The pin mechanics live in [`dsh-acp-snapshot`](../../../../packages/support/acp-snapshot/README.md), whose suite factory enforces one pin per class. -The pure `scrubSystemPrompts` normalizer applies to every stored session fixture and tokenizes both an initial header's prompt and a header delta's inserted prompt lines. `scrubRequestHeaders` additionally tokenizes tool schemas and session-prefix content for non-pinning scenarios while retaining structural facts: system-delta positions and arity, added/removed/changed tool names, prefix message count, field presence, config, and reason. Record and refresh write-back apply the appropriate scrub before writing JSONL and regenerate the Markdown prompt from the normalized live header, so neither path can reintroduce prompt text into JSONL or leave the readable snapshot stale. +The pure `scrubSystemPrompts` normalizer applies to every stored session fixture and tokenizes every full header's prompt. `scrubRequestHeaders` additionally tokenizes tool schemas and session-prefix content for non-pinning scenarios while retaining prefix message count, field presence, config, and reason. Record and refresh write-back apply the appropriate scrub before writing JSONL and regenerate the Markdown prompt from the normalized live headers, so neither path can reintroduce prompt text into JSONL or leave the readable snapshot stale. A pinning scenario with a legitimate changed header declares its count; the Markdown artifact records each later full prompt under a `request/header change` marker. -Guards make the split self-enforcing. On disk, every `session*.jsonl` is a fixed point of `scrubSystemPrompts`, only non-pinning fixtures are fixed points of the full header scrub, `system-prompt.golden.md` exists exactly beside pinning fixtures, and each class has one pin. Live, every `request/header` produced by a parent, spawn child, fork child, initial request, or resume must match both halves of its class's pin after volatile-value normalization. A header without a string prompt or any `request/header-delta` fails loud because the two static pin artifacts cannot represent it. +Guards make the split self-enforcing. On disk, every `session*.jsonl` is a fixed point of `scrubSystemPrompts`, only non-pinning fixtures are fixed points of the full header scrub, `system-prompt.golden.md` exists exactly beside pinning fixtures, and each class has one pin. Live, every `request/header` produced by a parent, spawn child, fork child, initial request, or resume must match the corresponding class pin after volatile-value normalization. A header without a string prompt or an undeclared changed-header count fails loud because the static pin artifacts cannot represent it. One pin covers the whole suite because every session — parent, spawn child, fork child — composes the identical tool list and the identical prompt modulo cwd, and the uniformity guard fails the suite the moment that stops holding. If header composition ever becomes session-dependent by design (a restricted subagent toolset, say), the divergent shape gets its own pinning scenario. @@ -26,7 +26,7 @@ One pin covers the whole suite because every session — parent, spawn child, fo ## Verification -The suite replays every scenario against the split pins. Unit coverage exercises both scrub levels, Markdown formatting, record/refresh regeneration, normalized prompt extraction, fixed-point enforcement, required-file symmetry, header uniformity, and delta rejection. +The suite replays every scenario against the split pins. Unit coverage exercises both scrub levels, multi-header Markdown formatting, record/refresh regeneration, normalized prompt extraction, fixed-point enforcement, required-file symmetry, header uniformity, and changed-header count rejection. ## Consequences diff --git a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md b/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md index 2f631a5d8a..c622a7f1be 100644 --- a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md +++ b/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md @@ -16,7 +16,7 @@ The machinery lives in [`packages/support/acp-snapshot`](../../../../packages/su **`src/normalize.ts`** — the pure normalizers, hook-free by policy: when a future event carries a new volatile field (an approval duration, say), the shared normalizer learns it in the same change, keeping one home for what "normalized" means rather than per-suite scrub extensions. -**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record/refresh fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL a `scrubSystemPrompts` fixed point, non-pinning fixtures also `scrubRequestHeaders` fixed points). The pinned-header contract ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each header class flags exactly one `pinsHeader` scenario, whose `system-prompt.golden.md` and JSONL tool list split the composed header into reviewable artifacts; the uniformity guard compares both against every live header in that class. The pure helpers (`childFixturePaths`, `fixtureContext`, `normalizedHeaders`, `normalizedSystemPrompts`, `formatSystemPromptSnapshot`, `headerDeltaCount`) are exported from the module for direct unit coverage. +**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record/refresh fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL a `scrubSystemPrompts` fixed point, non-pinning fixtures also `scrubRequestHeaders` fixed points). The pinned-header contract ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each header class flags exactly one `pinsHeader` scenario, whose `system-prompt.golden.md` and JSONL tool list split the composed header into reviewable artifacts; the uniformity guard compares both against every live header in that class. A pinning scenario declares any legitimate changed-header count, and its Markdown artifact records every full changed prompt. The pure helpers (`childFixturePaths`, `fixtureContext`, `normalizedHeaders`, `normalizedSystemPrompts`, `formatSystemPromptSnapshot`, `headerChangeCount`) are exported from the module for direct unit coverage. ## Alternatives considered diff --git a/docs/rfc/proposed/simplification/2026-07-12-simplify-session-log-representation.md b/docs/rfc/proposed/simplification/2026-07-12-simplify-session-log-representation.md deleted file mode 100644 index f335afafe1..0000000000 --- a/docs/rfc/proposed/simplification/2026-07-12-simplify-session-log-representation.md +++ /dev/null @@ -1,36 +0,0 @@ -# RFC: Simplify session-log representation - -Status: proposed - -## Problem - -The session log maintains two representations that cost more machinery than their consumers require: a pseudo-linked surface and custom request-header deltas. - -`SurfaceManager` stores the same order in an array, a seq map, and mutable `prev`/`next` links. Production never reads `prev`; compact's sole `next` read is the successor of an array position. Replacement already uses `indexOf`, so the links do not make its dominant operation constant-time. A seq array with linear replacement lookup has the same asymptotic replacement cost and one representation to validate. - -The request-header subsystem implements a custom system/tool delta codec and transmission-decision layer even though its contract says deltas are an encoding optimization, not a reconstructability requirement. Retaining the initial/resume full snapshot at each loop-instance boundary, then writing a canonical full `request/header` whenever that instance's assembled header changes, preserves replay while deleting `SystemDelta`, `ToolsDelta`, round-trip fallback, and the durable `request/header-delta` variant. Codec-only vocabulary disappears with the codec, not because its individual arms were invalid. - -This proposal deliberately retains append and replacement `sourceEventSeqs`, crash-repair provenance, and all `SessionStartSource` variants: implemented RFCs give those fields an audit/interception role that zero current readers does not overturn. - -## Proposal - -Make `SurfaceManager.nodes` a `readonly number[]` of event sequences and remove the public `SurfaceNode` shape. Keep the internal replace-generation signal; update tool-pairing balance and compaction callers to use array values/indices for predecessor, successor, and replacement ranges, removing node links and the seq-to-node map. Replace post-anchor header deltas with canonical full changed-header snapshots and remove the delta codec/event/tests; initial and resume anchors remain full snapshots even when the folded header is unchanged. - -Amend the session-surface and reconstructable-request RFCs where they describe the removed encoding. Update event types/invariants, request logging/replay, persistence fixtures, generated catalogs, package docs, and snapshots. Replace the codec-only `fallback` reason with an explicit `change` reason for post-anchor full snapshots, distinguishing them from the retained `initial` and `resume` anchors. - -`SESSION_FORMAT_VERSION` is deliberately pinned at `0`, so an old v0 log containing `request/header-delta` would otherwise pass the version check and silently lose header changes after the delta fold is deleted. Seed/load validation must reject that legacy event fail-loud at the format boundary; no compatibility fold or migration is added. - -## Alternatives considered - -**Keep linked nodes and compact deltas for possible scale.** Links could help a future cursor API, and deltas can reduce logs when large tool schemas change by a small amount. No shipped cursor uses the links, while full snapshots trade disk size for substantially simpler correctness. If header volume proves material, compression or a measured canonical-delta scheme can be designed around real traces. - -## Acceptance criteria - -- `SurfaceManager.nodes` is one ordered seq array with no `SurfaceNode`, link fields, or seq-to-node map; incremental append processing and the internal replace-generation signal remain, while the separate public `invalidate()` deletion stays owned by the dead-surface RFC. -- Replaying full changed-header snapshots reconstructs exactly the same requests; no header-delta event/type/codec remains. -- A v0 seed or persisted log containing legacy `request/header-delta` is rejected before replay, with coverage for JSONL and SQLite load paths. -- New-shape v0 JSONL/SQLite replay, provenance, crash repair, compaction, snapshots, invariants, typecheck, coverage, doc-sync, build, and hygiene pass. - -## Risks - -Full headers increase log volume, and linear replacement lookup could be slower on very large surfaces. Replacements are already linear because the implementation calls `indexOf`; benchmarks should be added only if real traces show the simpler array is a bottleneck. Because the format version remains `0`, forgetting the explicit legacy-event rejection would be silent data corruption rather than a type error; the fail-loud load test is therefore part of the proposal, not optional cleanup. diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 9ea71d3005..ccd3cef9fd 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -18,7 +18,7 @@ This table connects model-visible tool names to the plugin package and service s | `@deepseek-ai/dsh-tool-ask-user` | `ask_user_question` | `ctx.tools`, `ctx.userInteraction` | `tool/call`, `tool/result after a UI/provider answers the question` | - | ask_user_question pauses the tool call until the active UI provider returns a human answer. | | `@deepseek-ai/dsh-tools` | `run_code` | `ctx.tools`, `ctx.codeRuntime (execution time)`, `ctx.systemPrompt` | `tool/call`, `one tool/code-dispatch per bridged sub-call`, `tool/result` | - | Owned by the tool registry as a reserved transport outside filterable capability layers under `mode: code` / `mode: both` (see the Code Mode RFC). Under `code` it is the registry's only wire contribution; the other visible capabilities are declared in a generated TypeScript SDK section, and a program calls them through serialized bindings that re-enter the complete guarded tool pipeline and link each nested execution to this outer result. | | `@deepseek-ai/dsh-tool-bash` | `bash`, `bash_kill`, `bash_output` | `ctx.tools`, `ctx.bash` | `tool/call`, `tool/result`, `context/message via agent.inject() for background completion notices` | - | The bash/bash_output/bash_kill tools are model-facing consumers of the bash executor seam. | -| `@deepseek-ai/dsh-tool-cordis` | `cordis_inspect`, `cordis_mount`, `cordis_unmount` | `ctx.tools` | `tool/call`, `tool/result`, `live plugin-tree mutations (mount/unmount)` | - | Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; the request-header ToolsDelta logs those tool-set changes. | +| `@deepseek-ai/dsh-tool-cordis` | `cordis_inspect`, `cordis_mount`, `cordis_unmount` | `ctx.tools` | `tool/call`, `tool/result`, `live plugin-tree mutations (mount/unmount)` | - | Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; a full changed request header logs those tool-set changes. | | `@deepseek-ai/dsh-tool-fs` | `edit`, `read`, `write` | `ctx.tools`, `ctx.fs`, `ctx.systemPrompt` | `tool/call`, `fs/write-intent or fs/edit-intent for mutations`, `fs/observed after successful file operations`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin. | | `@deepseek-ai/dsh-tool-skill` | `skill` | `ctx.tools`, `ctx.skills` | `tool/call`, `tool/result` | - | - | | `@deepseek-ai/dsh-tool-subagent` | `subagent` | `ctx.tools`, `ctx.subagents` | `tool/call`, `tool/result`, `child session events through the chosen provider` | `subagent`, `subagent_fork` | The registered tool name is the load-time `toolName` config (default `subagent`); the schema above is that default. The shipped example agents load this package once per subagent backend, so the model additionally sees `subagent_fork` (bound to the fork backend) with an identical schema — see `examples/coding-agent/cordis.yml` and `examples/acp-agent/cordis.yml`. | @@ -275,7 +275,7 @@ Dispose a plugin previously mounted with cordis_mount, by id. All its registrati Source: [`packages/cordis/tool-cordis/src/index.ts`](../packages/cordis/tool-cordis/src/index.ts) -Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; the request-header ToolsDelta logs those tool-set changes. +Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; a full changed request header logs those tool-set changes. ## `@deepseek-ai/dsh-tool-fs` diff --git a/examples/sandbox-acp-agent/tests/acp.snapshot.ts b/examples/sandbox-acp-agent/tests/acp.snapshot.ts index 418b8068d3..95667d5b6b 100644 --- a/examples/sandbox-acp-agent/tests/acp.snapshot.ts +++ b/examples/sandbox-acp-agent/tests/acp.snapshot.ts @@ -35,7 +35,7 @@ const SCENARIOS: Scenario[] = [ { name: 'config-options', hasModelTurn: false, recorded: false }, // The runtime mode-switching arc, and NECESSARILY the pinned-header // scenario: an approval-policy switch rewrites its prompt section, and the - // resulting request/header-delta is legal only in the pinning scenario + // resulting changed request/header is legal only in the pinning scenario // (the factory's uniformity guard). The pin commits this composition's // full header — persona, tool schemas WITH the escalation fields — plus // the approval delta and its "changed by the user" notice verbatim. The @@ -43,9 +43,9 @@ const SCENARIOS: Scenario[] = [ // sandbox RFC's visibility asymmetry): the recorded arc proves it by // BEHAVIOR, a confined write landing under the switched mode with no // header change. - { name: 'mode-switching', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderDeltas: 1 }, + { name: 'mode-switching', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderChanges: 1 }, // The approval wire end-to-end, under the DEFAULT read-only/ask (a switch - // would emit a header-delta the uniformity guard forbids here): the + // would emit a changed header the uniformity guard forbids here): the // escalating bash call streams, session/request_permission attaches to it // (allow-once / reject-once), and the scripted answer drives each branch — // an approved run executes CONFINED under the granted workspace-write; a diff --git a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl b/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl index ef287390aa..e63e644459 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl +++ b/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl @@ -174,7 +174,7 @@ {"type":"user/message","seq":172,"time":1783613229056,"data":{"content":[{"type":"text","text":"Without using any tools, state your current approval policy in one short sentence and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"context/message","seq":173,"time":1783613229057,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"user-approval"}},"surfaceOp":"append"} {"type":"step/start","seq":174,"time":1783613229057,"data":{"turn":3,"step":1}} -{"type":"request/header-delta","seq":175,"time":1783613229057,"data":{"system":{"keepStart":9,"keepEnd":0,"insert":["{{system}}","{{system}}"]}}} +{"type":"request/header","seq":175,"time":1783613229057,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}}]},"reason":"change"}} {"type":"assistant/chunk","seq":176,"time":1783613230100,"data":{"turn":3,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":177,"time":1783613230100,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":178,"time":1783613230192,"data":{"turn":3,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/system-prompt.golden.md b/examples/sandbox-acp-agent/tests/snapshots/mode-switching/system-prompt.golden.md index 2da5f39805..1e6e8a5ee0 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/system-prompt.golden.md +++ b/examples/sandbox-acp-agent/tests/snapshots/mode-switching/system-prompt.golden.md @@ -9,7 +9,16 @@ Check the [exit code: N] marker on every bash result; investigate failures befor - + + +You are an AI agent powered by the DeepSeek Harness SDK. + +You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. + +Verify your work by running the code or tests. Keep answers brief and factual. + + +Check the [exit code: N] marker on every bash result; investigate failures before moving on. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/packages/bash/bash/src/session-mode.ts b/packages/bash/bash/src/session-mode.ts index 03ad6e3d7c..a1a16369f6 100644 --- a/packages/bash/bash/src/session-mode.ts +++ b/packages/bash/bash/src/session-mode.ts @@ -25,7 +25,7 @@ declare module '@deepseek-ai/dsh-session' { * NOT a surface event, carries no `surfaceOp`): durable and replayable, * never in the model transcript. The LAST such event is the session's * override ({@link effectiveSandboxMode}); who asked for it is derivable - * from position (an event after the log's last `request/header*` was a + * from position (an event after the log's last `request/header` was a * runtime switch by the user; see the tool layer's narrator). */ 'bash/sandbox-mode': { mode: SandboxMode } diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index c0d4ff483a..0b0300472c 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -455,11 +455,11 @@ export class BasicCompactService extends CompactService { // position, so the surface order (head→tail) no longer tracks seq order — // `[newSummarySeq, olderRetainedSeq, …]` is normal. Indexing into the // ordered node list and slicing it is the only correct way to read a range; - // a `node.seq >= start && node.seq <= end` interval test would mis-collect + // a `seq >= start && seq <= end` interval test would mis-collect // nodes (and `start > end` would falsely reject) once that happens. const nodes = session.surface.nodes - const startIdx = nodes.findIndex(n => n.seq === start) - const endIdx = nodes.findIndex(n => n.seq === end) + const startIdx = nodes.indexOf(start) + const endIdx = nodes.indexOf(end) if (startIdx === -1) throw new Error(`compactRegion: start seq ${start} not found in surface`) if (endIdx === -1) throw new Error(`compactRegion: end seq ${end} not found in surface`) if (startIdx > endIdx) { @@ -480,8 +480,7 @@ export class BasicCompactService extends CompactService { } // The cut after `end` is named by `end`'s surface successor, or `null` when // `end` is the tail. - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const afterEnd: number | null = nodes[endIdx]!.next + const afterEnd = nodes[endIdx + 1] ?? null if (!isToolPairingBalanced(nodes, events, afterEnd)) { throw new Error(`compactRegion: end seq ${end} is not a balanced boundary (would split a step, or the step is still open)`) } @@ -503,7 +502,7 @@ export class BasicCompactService extends CompactService { } // Slice the ordered surface nodes [startIdx, endIdx] inclusive — the // shadowed range is positional, so this is the set the replace op covers. - const shadowedSeqs = nodes.slice(startIdx, endIdx + 1).map(n => n.seq) + const shadowedSeqs = nodes.slice(startIdx, endIdx + 1) // --- Acquire lock --- const startEvent = session.append('compact/start', { turn: openTurn }) @@ -639,9 +638,9 @@ export class BasicCompactService extends CompactService { let keepFromIdx = nodes.length // nothing retained yet for (let i = nodes.length - 1; i >= 0; i--) { // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const node = nodes[i]! - const event = events[node.seq] - /* v8 ignore next -- node.seq is a surface-node seq, always a valid log index by construction */ + const seq = nodes[i]! + const event = events[seq] + /* v8 ignore next -- seq is a surface event sequence, always a valid log index by construction */ if (event) accumulated += this.estimateEventTokens(event) keepFromIdx = i if (accumulated >= retainBudget) break @@ -660,16 +659,16 @@ export class BasicCompactService extends CompactService { // step — retry once it closes). while (keepFromIdx > 0) { // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - if (isToolPairingBalanced(nodes, events, nodes[keepFromIdx]!.seq)) break + if (isToolPairingBalanced(nodes, events, nodes[keepFromIdx]!)) break keepFromIdx -= 1 } if (keepFromIdx === 0) return null // The compacted range is [head … keepFromIdx - 1], anchored at the head. // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const firstSeq = nodes[0]!.seq + const firstSeq = nodes[0]! // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const cutoffSeq = nodes[keepFromIdx - 1]!.seq + const cutoffSeq = nodes[keepFromIdx - 1]! return { start: firstSeq, end: cutoffSeq } } diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index e47ca434e3..1a30cc9fc9 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -259,8 +259,8 @@ describe('BasicCompactService step-alignment (never split a tool-call/result pai const svc = createTestService() const session = toolTurnSession(1) const nodes = session.surface.nodes // [user, asst(tool-call), result] - const userSeq = nodes[0]!.seq - const resultSeq = nodes[2]!.seq + const userSeq = nodes[0]! + const resultSeq = nodes[2]! // start = the tool/result: its issuing assistant precedes it IN THE SAME STEP, // so starting here would orphan that assistant's tool-call. end is fine (user). await expect(compactRegion(svc, session, resultSeq, resultSeq, 'm')) @@ -272,8 +272,8 @@ describe('BasicCompactService step-alignment (never split a tool-call/result pai const svc = createTestService() const session = toolTurnSession(1) const nodes = session.surface.nodes - const userSeq = nodes[0]!.seq - const asstSeq = nodes[1]!.seq + const userSeq = nodes[0]! + const asstSeq = nodes[1]! // end = the assistant/message: its tool/result follows IN THE SAME STEP, so // ending here would strand that result. start is fine (the pre-step user). await expect(compactRegion(svc, session, userSeq, asstSeq, 'm')) @@ -291,8 +291,8 @@ describe('BasicCompactService step-alignment (never split a tool-call/result pai content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], }, { surfaceOp: 'append' }) const nodes = s.surface.nodes // [user, asst] - const userSeq = nodes[0]!.seq - const asstSeq = nodes[1]!.seq + const userSeq = nodes[0]! + const asstSeq = nodes[1]! await expect(compactRegion(svc, s, userSeq, asstSeq, 'm')) .rejects.toThrow(/end seq .* is not a balanced boundary/) }) @@ -301,8 +301,8 @@ describe('BasicCompactService step-alignment (never split a tool-call/result pai const svc = createTestService() const session = toolTurnSession(2) const nodes = session.surface.nodes // [user1, asst1, res1, user2, asst2, res2] - const startSeq = nodes[0]!.seq // pre-step user1 (free boundary) - const endSeq = nodes[2]!.seq // res1 = last node of turn 1's closed step + const startSeq = nodes[0]! // pre-step user1 (free boundary) + const endSeq = nodes[2]! // res1 = last node of turn 1's closed step const result = await compactRegion(svc, session, startSeq, endSeq, 'm') expect(result.shadowedRange).toEqual({ start: startSeq, end: endSeq }) expectNoOrphanToolResults(session.deriveMessages()) @@ -312,7 +312,7 @@ describe('BasicCompactService step-alignment (never split a tool-call/result pai const svc = createTestService() const session = toolTurnSession(1) const nodes = session.surface.nodes - const userSeq = nodes[0]!.seq // pre-step user: free boundary both ways + const userSeq = nodes[0]! // pre-step user: free boundary both ways const result = await compactRegion(svc, session, userSeq, userSeq, 'm') expect(result.shadowedRange).toEqual({ start: userSeq, end: userSeq }) }) @@ -327,7 +327,7 @@ describe('BasicCompactService step-alignment (never split a tool-call/result pai s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) const nodes = s.surface.nodes - const ctxSeq = nodes[0]!.seq + const ctxSeq = nodes[0]! const result = await compactRegion(svc, s, ctxSeq, ctxSeq, 'm') expect(result.shadowedRange).toEqual({ start: ctxSeq, end: ctxSeq }) }) @@ -386,8 +386,8 @@ describe('BasicCompactService.compactRegion', () => { const nodes = session.surface.nodes expect(nodes.length).toBe(6) - const firstSeq = nodes[0]!.seq - const secondSeq = nodes[1]!.seq + const firstSeq = nodes[0]! + const secondSeq = nodes[1]! const result = await compactRegion(svc, session, firstSeq, secondSeq, 'test-model') expect(result.shadowedSeqs).toEqual([firstSeq, secondSeq]) @@ -427,7 +427,7 @@ describe('BasicCompactService.compactRegion', () => { // Surface now has: summary user/message + retained 4 nodes = 5 nodes. const newNodes = session.surface.nodes expect(newNodes.length).toBe(5) - expect(newNodes[0]!.seq).toBe(userMsg.seq) + expect(newNodes[0]!).toBe(userMsg.seq) // deriveMessages() produces the framed summary as a user-role message: // a checkpoint preamble + tag-wrapped summary blocks. @@ -452,7 +452,7 @@ describe('BasicCompactService.compactRegion', () => { const svc = createTestService() const session = multiTurnSession(2, 1) const nodes = session.surface.nodes - await expect(compactRegion(svc, session, nodes[1]!.seq, nodes[0]!.seq, 'm')) + await expect(compactRegion(svc, session, nodes[1]!, nodes[0]!, 'm')) .rejects.toThrow(/is after end seq .* on the surface/) }) @@ -461,7 +461,7 @@ describe('BasicCompactService.compactRegion', () => { const session = multiTurnSession(2, 1) const nodes = session.surface.nodes session.append('compact/start', { turn: 2 }) - await expect(compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm')) + await expect(compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm')) .rejects.toThrow(/compaction already in progress/) }) @@ -471,7 +471,7 @@ describe('BasicCompactService.compactRegion', () => { const session = multiTurnSession(2, 1) const nodes = session.surface.nodes - await expect(compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm')) + await expect(compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm')) .rejects.toThrow('model unavailable') const endEvent = session.events.findLast(e => e.type === 'compact/end') @@ -494,7 +494,7 @@ describe('BasicCompactService.compactRegion', () => { const session = multiTurnSession(1, 2) const nodes = session.surface.nodes - await compactRegion(svc, session, nodes[0]!.seq, nodes[nodes.length - 1]!.seq, 'm') + await compactRegion(svc, session, nodes[0]!, nodes[nodes.length - 1]!, 'm') expect(svc.summarizeCalls.length).toBe(1) const { text, model } = svc.summarizeCalls[0]! @@ -509,7 +509,7 @@ describe('BasicCompactService.compactRegion', () => { const session = multiTurnSession(3, 1) const nodes = session.surface.nodes - const result = await compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm') + const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm') // Provenance (compact/summary) carries the RAW, unframed summary. expect(result.summary).toEqual([{ type: 'text', text: 'STRUCTURED SUMMARY' }]) @@ -529,8 +529,8 @@ describe('BasicCompactService.compactRegion', () => { const session = sessionWithTools() const nodes = session.surface.nodes - const firstSeq = nodes[0]!.seq - const lastSeq = nodes[nodes.length - 1]!.seq + const firstSeq = nodes[0]! + const lastSeq = nodes[nodes.length - 1]! await compactRegion(svc, session, firstSeq, lastSeq, 'm') expect(svc.summarizeCalls.length).toBe(1) @@ -601,7 +601,7 @@ describe('BasicCompactService.compactIfNeeded', () => { expect(result).not.toBeNull() const nodes = session.surface.nodes expect(result!.shadowedSeqs.length).toBeGreaterThan(0) - expect(result!.shadowedSeqs).not.toContain(nodes[nodes.length - 1]!.seq) + expect(result!.shadowedSeqs).not.toContain(nodes[nodes.length - 1]!) }) it('returns null when the whole surface fits the retain budget (over threshold by role/system overhead)', async () => { @@ -653,7 +653,7 @@ describe('BasicCompactService.compactIfNeeded', () => { // The most-recent step's tool result is retained verbatim (still on surface). const lastResultSeq = s.events.findLast(e => e.type === 'tool/result')!.seq expect(result!.shadowedSeqs).not.toContain(lastResultSeq) - expect(s.surface.nodes.some(n => n.seq === lastResultSeq)).toBe(true) + expect(s.surface.nodes).toContain(lastResultSeq) // No orphaned tool-result survives (whole-step boundaries respected). expectNoOrphanToolResults(s.deriveMessages()) }) @@ -677,7 +677,7 @@ describe('BasicCompactService.compactIfNeeded', () => { const first = await compactIfNeeded(svc, s, '', 'm', SIGNAL) expect(first).not.toBeNull() // The summary node now heads the surface with a fresh high seq. - const summaryHeadSeq = s.surface.nodes[0]!.seq + const summaryHeadSeq = s.surface.nodes[0]! const turn5StartSeq = s.events.filter(e => e.type === 'turn/start').at(-1)!.seq expect(summaryHeadSeq).toBeGreaterThan(turn5StartSeq) @@ -745,7 +745,7 @@ describe('BasicCompactService replay equivalence', () => { const session = multiTurnSession(3, 1) const nodes = session.surface.nodes - await compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm') + await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm') const derived = session.deriveMessages() const replayed = new Session(SessionId('replay'), [...session.events]) @@ -761,7 +761,7 @@ describe('BasicCompactService blocking (compaction in progress)', () => { const nodes = session.surface.nodes // Whole step (user → assistant) is a step-aligned region, so the call reaches // the in-progress check rather than being rejected for splitting a step. - await expect(compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm')) + await expect(compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm')) .rejects.toThrow(/compaction already in progress/) }) @@ -771,7 +771,7 @@ describe('BasicCompactService blocking (compaction in progress)', () => { const nodes = session.surface.nodes session.append('compact/start', { turn: 1 }) session.append('compact/end', { turn: 1 }) - const result = await compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm') + const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm') expect(result).toBeDefined() }) @@ -794,7 +794,7 @@ describe('BasicCompactService blocking (compaction in progress)', () => { const nodes = s.surface.nodes // The stale start is before the turn/end, so it is NOT seen as in-progress. - const result = await compactRegion(svc, s, nodes[0]!.seq, nodes[1]!.seq, 'm') + const result = await compactRegion(svc, s, nodes[0]!, nodes[1]!, 'm') expect(result).toBeDefined() }) }) @@ -1112,7 +1112,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { const before = [...session.surface.nodes] const nodes = session.surface.nodes - await expect(compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'test-model')) + await expect(compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model')) .rejects.toMatchObject({ code: 'MAX_TOKENS' }) // No replacement landed — the surface is byte-identical, and the lock was @@ -1129,7 +1129,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { const session = multiTurnSession(2, 1) const nodes = session.surface.nodes - const result = await compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'test-model') + const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') expect(result.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) // The raw summary is wrapped in the checkpoint framing on the surface. expect(session.deriveMessages()[0]!.content).toContainEqual({ type: 'text', text: 'CONDENSED' }) @@ -1141,7 +1141,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { const nodes = session.surface.nodes svc.mockSummary = Array.from({ length: 20 }, (_, index) => ({ type: 'text', text: `large ${index}` })) - await expect(compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm')) + await expect(compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm')) .rejects.toThrow(/summary is not smaller than the shadowed content/) expect(session.events.some(e => e.type === 'compact/summary')).toBe(false) }) @@ -1160,7 +1160,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { const before = [...session.surface.nodes] const nodes = session.surface.nodes - await expect(compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm')) + await expect(compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm')) .rejects.toThrow(/summary is not smaller than the shadowed content/) expect(session.events.some(e => e.type === 'compact/summary')).toBe(false) expect(session.surface.nodes).toEqual(before) @@ -1321,7 +1321,7 @@ describe('BasicCompactService transcript rendering (delegated to dsh-compact)', s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) const nodes = s.surface.nodes - await compactRegion(svc, s, nodes[0]!.seq, nodes[nodes.length - 1]!.seq, 'm') + await compactRegion(svc, s, nodes[0]!, nodes[nodes.length - 1]!, 'm') const { text } = svc.summarizeCalls[0]! expect(text).toContain('[Context: project context here]') @@ -1350,7 +1350,7 @@ describe('BasicCompactService transcript rendering (delegated to dsh-compact)', s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) const nodes = s.surface.nodes - await compactRegion(svc, s, nodes[0]!.seq, nodes[nodes.length - 1]!.seq, 'm') + await compactRegion(svc, s, nodes[0]!, nodes[nodes.length - 1]!, 'm') expect(svc.summarizeCalls[0]!.text).toContain('Tool error (call c9): boom failure') }) }) @@ -1384,7 +1384,7 @@ describe('BasicCompactService edge cases', () => { s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) const nodes = s.surface.nodes - await compactRegion(svc, s, nodes[0]!.seq, nodes[nodes.length - 1]!.seq, 'm') + await compactRegion(svc, s, nodes[0]!, nodes[nodes.length - 1]!, 'm') const { text } = svc.summarizeCalls[0]! expect(text).toContain('[tool-result: [chart]]') // nested tool-result with content expect(text).toContain('[custom-widget]') // unknown block placeholder @@ -1432,7 +1432,7 @@ describe('BasicCompactService edge cases', () => { s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) const nodes = s.surface.nodes - await expect(compactRegion(svc, s, nodes[0]!.seq, nodes[1]!.seq, 'm')) + await expect(compactRegion(svc, s, nodes[0]!, nodes[1]!, 'm')) .rejects.toThrow(/no open turn/) // The lock was never acquired — no compact/start landed. expect(s.events.some(e => e.type === 'compact/start')).toBe(false) @@ -1447,7 +1447,7 @@ describe('BasicCompactService edge cases', () => { s.append('user/message', { content: [{ type: 'text', text: 'orphan' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) const nodes = s.surface.nodes - await expect(compactRegion(svc, s, nodes[0]!.seq, nodes[0]!.seq, 'm')) + await expect(compactRegion(svc, s, nodes[0]!, nodes[0]!, 'm')) .rejects.toThrow(/no open turn/) expect(s.events.some(e => e.type === 'compact/start')).toBe(false) }) @@ -1464,7 +1464,7 @@ describe('BasicCompactService edge cases', () => { const svc = createTestService() const session = multiTurnSession(1, 1) const nodes = session.surface.nodes - await expect(compactRegion(svc, session, nodes[0]!.seq, 9999, 'm')) + await expect(compactRegion(svc, session, nodes[0]!, 9999, 'm')) .rejects.toThrow(/end seq 9999 not found in surface/) }) @@ -1476,7 +1476,7 @@ describe('BasicCompactService edge cases', () => { const nodes = session.surface.nodes // Whole step (user → assistant): a step-aligned region that reaches summarize. - await expect(compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm')).rejects.toBe('plain string failure') + await expect(compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm')).rejects.toBe('plain string failure') const endEvent = session.events.findLast(e => e.type === 'compact/end')! expect(endEvent.data).toMatchObject({ error: 'plain string failure' }) }) @@ -1542,7 +1542,7 @@ describe('BasicCompactService edge cases', () => { s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) const nodes = s.surface.nodes - await compactRegion(svc, s, nodes[0]!.seq, nodes[nodes.length - 1]!.seq, 'm') + await compactRegion(svc, s, nodes[0]!, nodes[nodes.length - 1]!, 'm') // Every empty-content message (user text, empty reasoning, empty-content // tool/result, empty context, empty steering) extracted to nothing and was // skipped — the only surviving line is the assistant's tool-call (which a @@ -1580,7 +1580,7 @@ describe('BasicCompactService edge cases', () => { s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) const nodes = s.surface.nodes - await compactRegion(svc, s, nodes[0]!.seq, nodes[nodes.length - 1]!.seq, 'm') + await compactRegion(svc, s, nodes[0]!, nodes[nodes.length - 1]!, 'm') const { text } = svc.summarizeCalls[0]! // Every non-text block surfaces as a placeholder rather than being dropped. expect(text).toContain('User: [chart]') @@ -1604,32 +1604,32 @@ describe('BasicCompactService positional range (surface seqs are not monotonic a // First compaction: shadow the two oldest surface nodes. const nodes0 = session.surface.nodes - const first = await compactRegion(svc, session, nodes0[0]!.seq, nodes0[1]!.seq, 'm') + const first = await compactRegion(svc, session, nodes0[0]!, nodes0[1]!, 'm') // The summary node now sits at the head with a seq HIGHER than the // retained older nodes that follow it — the non-monotonic surface. (The // head is the user/message replace node, appended after the compact/summary // provenance event, so its seq is at least first.summarySeq.) const nodes1 = session.surface.nodes - expect(nodes1[0]!.seq).toBeGreaterThanOrEqual(first.summarySeq) - expect(nodes1[0]!.seq).toBeGreaterThan(nodes1[1]!.seq) + expect(nodes1[0]!).toBeGreaterThanOrEqual(first.summarySeq) + expect(nodes1[0]!).toBeGreaterThan(nodes1[1]!) // Second compaction: shadow [summary(head) … turn-2's step end]. The start // seq (the head summary node) is GREATER than the end seq (an older retained // node), so the range is a SURFACE-POSITION span, not a numeric seq interval. // The end must land on a step boundary (turn-2's assistant message closes // its step). - const startSeq = nodes1[0]!.seq - const endSeq = nodes1[2]!.seq + const startSeq = nodes1[0]! + const endSeq = nodes1[2]! expect(startSeq).toBeGreaterThan(endSeq) const second = await compactRegion(svc, session, startSeq, endSeq, 'm') // Exactly the three nodes at surface positions [0..2] are shadowed, in // surface order — the positional slice, regardless of their seq values. - expect(second.shadowedSeqs).toEqual([nodes1[0]!.seq, nodes1[1]!.seq, nodes1[2]!.seq]) + expect(second.shadowedSeqs).toEqual([nodes1[0]!, nodes1[1]!, nodes1[2]!]) // The surface still derives cleanly: a new head replace node + the rest. const finalNodes = session.surface.nodes - expect(finalNodes[0]!.seq).toBeGreaterThanOrEqual(second.summarySeq) + expect(finalNodes[0]!).toBeGreaterThanOrEqual(second.summarySeq) expect(session.deriveMessages().length).toBe(finalNodes.length) }) @@ -1640,14 +1640,14 @@ describe('BasicCompactService positional range (surface seqs are not monotonic a // First compaction shadows the oldest two surface nodes, landing a high-seq // summary node at the head. const n0 = session.surface.nodes - await compactRegion(svc, session, n0[0]!.seq, n0[1]!.seq, 'm') + await compactRegion(svc, session, n0[0]!, n0[1]!, 'm') // Second compaction spans [head summary … turn-2's step end]. The head's seq // is higher than the older retained nodes' seqs, so a log-seq-order walk // would emit the older messages BEFORE the checkpoint. const n1 = session.surface.nodes svc.summarizeCalls = [] - await compactRegion(svc, session, n1[0]!.seq, n1[2]!.seq, 'm') + await compactRegion(svc, session, n1[0]!, n1[2]!, 'm') // The extracted transcript follows surface order: the checkpoint (head) // first, then the older retained messages — matching deriveMessages(). @@ -1679,7 +1679,7 @@ describe('BasicCompactService llm inject (real plugin-load path)', () => { const svc = ctx.compact as BasicCompactService const session = multiTurnSession(2, 1) const nodes = session.surface.nodes - const result = await compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'test-model') + const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') expect(result.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) // Tear the fiber down so this test owns no leaked registration; the @@ -1727,9 +1727,9 @@ describe('BasicCompactService under the real invariants plugin', () => { const nodes = session.surface.nodes // No invariant throws here: compact/* + the replacement are all in turn 3. - const result = await compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'test-model') + const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') expect(result.shadowedSeqs.length).toBe(2) - expect(session.surface.nodes[0]!.seq).toBeGreaterThan(session.surface.nodes[1]!.seq) + expect(session.surface.nodes[0]!).toBeGreaterThan(session.surface.nodes[1]!) }) it('accepts a second compaction over the non-monotonic surface left by the first', async () => { @@ -1740,14 +1740,14 @@ describe('BasicCompactService under the real invariants plugin', () => { session.append('turn/start', { turn: 4, trigger: { kind: 'message', source: { kind: 'user' } } }) const n0 = session.surface.nodes - await compactRegion(svc, session, n0[0]!.seq, n0[1]!.seq, 'test-model') + await compactRegion(svc, session, n0[0]!, n0[1]!, 'test-model') // Surface head now carries a higher seq than the older retained nodes. A // second compaction spanning [head … a later closed-step end] must pass the // invariants' positional replace check even though startSeq > endSeq. const n1 = session.surface.nodes - expect(n1[0]!.seq).toBeGreaterThan(n1[2]!.seq) - const second = await compactRegion(svc, session, n1[0]!.seq, n1[2]!.seq, 'test-model') - expect(second.shadowedSeqs).toEqual([n1[0]!.seq, n1[1]!.seq, n1[2]!.seq]) + expect(n1[0]!).toBeGreaterThan(n1[2]!) + const second = await compactRegion(svc, session, n1[0]!, n1[2]!, 'test-model') + expect(second.shadowedSeqs).toEqual([n1[0]!, n1[1]!, n1[2]!]) }) }) diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index 1efb417b48..bb77e44a9c 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -142,12 +142,12 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () // scan reached the neighbouring step's assistant/message. const nodes = agent.session.surface.nodes for (const cp of checkpoints) { - const node = nodes.find(n => n.seq === cp.seq) - if (!node) continue // shadowed by a later checkpoint — no longer an edge. - expect(isToolPairingBalanced(nodes, events, node.seq), - `checkpoint seq ${node.seq} must be a balanced region START`).toBe(true) - expect(isToolPairingBalanced(nodes, events, node.next), - `checkpoint seq ${node.seq} must be a balanced region END`).toBe(true) + const index = nodes.indexOf(cp.seq) + if (index === -1) continue // shadowed by a later checkpoint — no longer an edge. + expect(isToolPairingBalanced(nodes, events, cp.seq), + `checkpoint seq ${cp.seq} must be a balanced region START`).toBe(true) + expect(isToolPairingBalanced(nodes, events, nodes[index + 1] ?? null), + `checkpoint seq ${cp.seq} must be a balanced region END`).toBe(true) } } finally { await ctx.fiber.dispose() diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 7a7ca2e28c..711e6fab69 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -170,8 +170,8 @@ export interface LoopHandle { * boundary = session.deriveMessages() ⟵ the reconstruction boundary: snapshot in the * session('step/start') same sync frame, strictly before step/start * config = waterfall agent/request(config) ⟵ frozen seed; a returned replacement switches - * session('request/header'|'request/header-delta') ⟵ the header event this request owes the - * log (initial/resume anchor, delta, fallback) + * session('request/header') ⟵ the header event this request owes the + * log (initial/resume anchor or changed snapshot) * req = freeze({header..., messages: prefix+boundary, sessionId, signal}) * stream ctx.llm.stream(req) ⟵ waterfall llm/stream (raw chunks, frozen req) * session('assistant/chunk') @@ -774,7 +774,7 @@ async function runStep( // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- runTurn composes the prefix before every runStep call const sessionPrefix = transmission.sessionPrefix! - // The request header (the log's request/header* vocabulary): canonical form, + // The request header (the log's request/header snapshots): canonical form, // recorded before dispatch so the log always explains the request — // including the session prefix, which no other event carries. const header = canonicalHeader({ diff --git a/packages/core/agent-loop/src/request-log.ts b/packages/core/agent-loop/src/request-log.ts index d2763f5c2a..94e121d0f6 100644 --- a/packages/core/agent-loop/src/request-log.ts +++ b/packages/core/agent-loop/src/request-log.ts @@ -5,12 +5,12 @@ * otherwise transmission-stateless — the comparison baseline is the log's own * folded header (`Session.requestHeader()`), so resume and fork need no * special path: a fresh loop instance simply logs a `'resume'` snapshot on - * its first request and deltas from there. + * its first request and full changed-header snapshots from there. * * @module dsh-agent-loop/request-log */ -import { diffHeader, headerEquals, applyHeaderDelta } from '@deepseek-ai/dsh-session' +import { headerEquals } from '@deepseek-ai/dsh-session' import type { EpochHeader, Session } from '@deepseek-ai/dsh-session' import type { Message } from '@deepseek-ai/dsh-llm' @@ -38,7 +38,7 @@ export function createTransmissionLog(): TransmissionLog { /** * Append whatever header event this request owes the log, so folding the log - * reproduces the header the request was built under. Exactly one of four + * reproduces the header the request was built under. Exactly one of three * things happens: * * 1. This loop instance has not logged a header yet → a full `request/header` @@ -48,11 +48,7 @@ export function createTransmissionLog(): TransmissionLog { * snapshot is appended even when nothing changed). * 2. The header equals the folded baseline → nothing; the log already * explains this request. - * 3. It differs and the delta round-trips (`applyHeaderDelta` on the baseline - * reproduces the header exactly) → a `request/header-delta`. - * 4. It differs and the delta encoding cannot express the change (a pure tool - * reordering) → a full snapshot with reason `'fallback'`; deltas are an - * encoding optimization, never a correctness dependency. + * 3. It differs → a full snapshot with reason `'change'`. * * @param session - the session whose log explains the request. * @param state - this loop instance's bookkeeping (mutated on first log). @@ -69,12 +65,5 @@ export function recordRequestHeader(session: Session, state: TransmissionLog, he // eslint-disable-next-line @typescript-eslint/no-non-null-assertion const baseline = session.requestHeader()! if (headerEquals(baseline, header)) return - const delta = diffHeader(baseline, header) - /* v8 ignore next -- headerEquals false ⟹ diffHeader defined: both compare the same four parts */ - if (delta === undefined) return - if (headerEquals(applyHeaderDelta(baseline, delta), header)) { - session.append('request/header-delta', delta) - } else { - session.append('request/header', { header, reason: 'fallback' }) - } + session.append('request/header', { header, reason: 'change' }) } diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index d4ec6312ba..1ec48e553f 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -374,8 +374,8 @@ describe('agent/session-prefix', () => { expect(request.messages[0]).toEqual(reminder) } // The anchoring snapshot is the prefix's durable record — and the ONLY - // header event: reuse means no request/header-delta ever. - const headerEvents = events(agent).filter(e => e.type === 'request/header' || e.type === 'request/header-delta') + // header event: reuse means no changed snapshot ever. + const headerEvents = events(agent).filter(e => e.type === 'request/header') expect(headerEvents).toHaveLength(1) expect(headerEvents[0]?.type === 'request/header' && headerEvents[0].data.header.messagePrefix).toEqual([reminder]) // Never session history: the derivation starts at the real user prompt. @@ -491,7 +491,7 @@ describe('agent/session-prefix', () => { // cached prefix is a deep-frozen clone, so step 2's request is unchanged. held.content = [{ type: 'text', text: 'v2' }] expect(adapter.requests[1]!.messages[0]).toEqual({ role: 'user', content: [{ type: 'text', text: 'v1' }] }) - expect(events(agent).filter(e => e.type === 'request/header-delta')).toHaveLength(0) + expect(events(agent).filter(e => e.type === 'request/header')).toHaveLength(1) }) }) diff --git a/packages/core/agent-loop/tests/request-log.spec.ts b/packages/core/agent-loop/tests/request-log.spec.ts index a6befde84e..f281f1e9db 100644 --- a/packages/core/agent-loop/tests/request-log.spec.ts +++ b/packages/core/agent-loop/tests/request-log.spec.ts @@ -1,9 +1,8 @@ /** - * recordRequestHeader unit tests: exactly one of four things per request — + * recordRequestHeader unit tests: exactly one of three things per request — * an 'initial' snapshot (log has no header yet), a 'resume' snapshot (fresh - * loop instance over a log that has one), nothing (header unchanged), a - * round-tripping delta, or a 'fallback' snapshot when the delta encoding - * cannot express the change (pure tool reordering). + * loop instance over a log that has one), nothing (header unchanged), or a + * full 'change' snapshot. */ import { describe, expect, it } from 'vitest' @@ -23,7 +22,7 @@ function openSession(id: string): Session { } function headerEvents(session: Session): SessionEvent[] { - return session.events.filter(e => e.type === 'request/header' || e.type === 'request/header-delta') + return session.events.filter(e => e.type === 'request/header') } describe('recordRequestHeader', () => { @@ -53,8 +52,8 @@ describe('recordRequestHeader', () => { expect(events[1]?.type === 'request/header' && events[1].data.reason).toBe('resume') }) - it('logs a round-tripping delta for a mid-run change, and the fold reproduces the header', () => { - const session = openSession('rl-delta') + it("logs a full 'change' snapshot for a mid-run change, and the fold reproduces the header", () => { + const session = openSession('rl-change') const state = createTransmissionLog() const first = canonicalHeader({ config: { model: 'm' }, system: 'a\nb', tools: [tool('t')] }) recordRequestHeader(session, state, first) @@ -63,12 +62,12 @@ describe('recordRequestHeader', () => { recordRequestHeader(session, state, second) const events = headerEvents(session) expect(events).toHaveLength(2) - expect(events[1]?.type).toBe('request/header-delta') + expect(events[1]?.type === 'request/header' && events[1].data.reason).toBe('change') expect(session.requestHeader()).toEqual(second) }) - it("records a change the delta cannot express (pure reordering) as a 'fallback' snapshot", () => { - const session = openSession('rl-fallback') + it("records a pure tool reordering as a 'change' snapshot", () => { + const session = openSession('rl-reorder') const state = createTransmissionLog() const first = canonicalHeader({ config: { model: 'm' }, tools: [tool('a'), tool('b')] }) recordRequestHeader(session, state, first) @@ -77,9 +76,7 @@ describe('recordRequestHeader', () => { recordRequestHeader(session, state, reordered) const events = headerEvents(session) expect(events).toHaveLength(2) - expect(events[1]?.type === 'request/header' && events[1].data.reason).toBe('fallback') - // The fold still lands on the exact header — deltas are an encoding - // optimization, never a correctness dependency. + expect(events[1]?.type === 'request/header' && events[1].data.reason).toBe('change') expect(session.requestHeader()).toEqual(reordered) }) }) diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index bb6d613954..7054b683cb 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -1,7 +1,7 @@ /** * Loop-level reconstructability: every request the loop sends is a pure * function of the session log — messages are the derivation at the step/start - * boundary, the header is the fold of request/header* events — and every + * boundary, the header is the latest request/header snapshot — and every * request is an append-extension of its predecessor unless a logged event * (compaction replace, header change) explains the difference. The requests * recorded by the mock adapter are the observable; the offline-rebuild test @@ -87,7 +87,7 @@ describe('request stability across the loop', () => { expect(Object.isFrozen(request.messages)).toBe(true) } // One anchoring header snapshot; no further header events (nothing changed). - const headerEvents = agent.session.events.filter(e => e.type === 'request/header' || e.type === 'request/header-delta') + const headerEvents = agent.session.events.filter(e => e.type === 'request/header') expect(headerEvents).toHaveLength(1) expect(headerEvents[0]?.type === 'request/header' && headerEvents[0].data.reason).toBe('initial') }) @@ -124,8 +124,8 @@ describe('request stability across the loop', () => { content: [{ type: 'text', text: '[summary of turn 1]' }], source: { kind: 'plugin', plugin: 'test-compact' }, }, { - surfaceOp: { op: 'replace', start: nodes[0]!.seq, end: nodes[1]!.seq }, - sourceEventSeqs: [nodes[0]!.seq, nodes[1]!.seq], + surfaceOp: { op: 'replace', start: nodes[0]!, end: nodes[1]! }, + sourceEventSeqs: [nodes[0]!, nodes[1]!], }) }) @@ -139,7 +139,7 @@ describe('request stability across the loop', () => { expect(agent.session.events.filter(e => e.type === 'request/header')).toHaveLength(1) }) - it('a real system-prompt change is a logged header delta; a stable prompt logs nothing', async () => { + it('a real system-prompt change is a full changed-header snapshot; a stable prompt logs nothing', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two'), textResponse('three')]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) @@ -149,14 +149,15 @@ describe('request stability across the loop', () => { send(agent, 'second') await waitForIdle(ctx, agent) // Identical assembly re-rendered per step is NOT a change. - expect(agent.session.events.filter(e => e.type === 'request/header-delta')).toHaveLength(0) + expect(agent.session.events.filter(e => e.type === 'request/header')).toHaveLength(1) ctx.systemPrompt.section({ name: 'extra', order: 2, text: 'new guidance' }) send(agent, 'third') await waitForIdle(ctx, agent) - const deltas = agent.session.events.filter(e => e.type === 'request/header-delta') - expect(deltas).toHaveLength(1) + const snapshots = agent.session.events.filter(e => e.type === 'request/header') + expect(snapshots).toHaveLength(2) + expect(snapshots[1]?.data.reason).toBe('change') expect(adapter.requests[2]!.system).toContain('new guidance') // History is preserved across the change — only the header moved. expect(adapter.requests[2]!.messages.length).toBeGreaterThan(adapter.requests[1]!.messages.length) @@ -262,9 +263,9 @@ describe('request stability across the loop', () => { send(agent, 'second') await waitForIdle(ctx, agent) - // No delta was logged (nothing really changed), and the session's own + // No changed snapshot was logged (nothing really changed), and the session's own // fold is immutable state. - expect(agent.session.events.filter(e => e.type === 'request/header-delta')).toHaveLength(0) + expect(agent.session.events.filter(e => e.type === 'request/header')).toHaveLength(1) expect(Object.isFrozen(agent.session.requestHeader())).toBe(true) expect(adapter.requests[1]!.temperature).toBeUndefined() }) @@ -298,7 +299,7 @@ describe('request stability across the loop', () => { const rebuilt = new Session(SessionId(`rebuild-${index}`), structuredClone(events.slice(0, stepStart.seq))) expect(structuredClone(request.messages)).toEqual(rebuilt.deriveMessages()) - // Header: the fold of request/header* events up to this step's dispatch + // Header: the latest request/header snapshot up to this step's dispatch // (its header event sits between step/start and the first chunk). const firstChunk = events.find(e => e.type === 'assistant/chunk' && e.seq > stepStart.seq)! const header = foldRequestHeader(events.slice(0, firstChunk.seq))! diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index 7a046dcc82..a990f0d67d 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -464,7 +464,7 @@ declare module 'cordis' { * `additionalContext`, prompt sections via `system-prompt/assemble`, or * the header-logged session prefix via {@link agent/session-prefix} * — never through request mutation, and the loop records whatever config - * the request actually uses as a `request/header*` event before dispatch. + * the request actually uses as a `request/header` event before dispatch. * The step's messages are already snapshotted when this fires (the * `step/start` boundary): an `inject()` from a listener here lands in the * log but joins the NEXT request. For surface mutation that must precede diff --git a/packages/core/session/README.md b/packages/core/session/README.md index 25d6b40be6..39582ad555 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -1,6 +1,6 @@ # dsh-session -Event-sourced session log and in-memory store. A `Session` is the append-only source of truth for an agent's whole interaction history — the LLM message history is *derived* from it. A **surface** layer (a linked list of message-producing events) is maintained on top of the raw log for efficient derivation and compaction. +Event-sourced session log and in-memory store. A `Session` is the append-only source of truth for an agent's whole interaction history — the LLM message history is *derived* from it. A **surface** layer (an ordered sequence of message-producing event seqs) is maintained on top of the raw log for efficient derivation and compaction. ## Service: `SessionStore` (ctx key: `sessions`) @@ -33,7 +33,7 @@ The store pairs announced creation with disposal, publishes each append, and pro Plain class (not a Cordis Service). Create via `ctx.sessions.create()`. - `session.append(type, data, opts?): SessionEvent` — synchronous, never blocks on I/O. At this durable boundary, data and surface metadata are lossless-JSON snapshotted and deep-frozen. For an attached session, a reentrant append during dispatch/observer publication rejects, and detach waits for that publication to unwind. Callbacks resolve before the log push; the push is the commit point, after which each observer failure is contained independently. Runtime surface validation covers widened unions and raw seed/load logs. -- `session.deriveMessages(): Message[]` — the LLM message history, CACHED: each surface node is projected exactly once, when first seen (O(new nodes) per call; a surface rewrite rebuilds via `surface.replaceGeneration`). Returns a fresh array per call over shared, deep-frozen `Message` objects. Each projection reuses the already deep-frozen content in its durable log event, so no second deep clone is needed and a consumer still cannot mutate logged data. The surface is the single source of derived history — there is no raw-log fallback. +- `session.deriveMessages(): Message[]` — the LLM message history, CACHED: each surface entry is projected exactly once, when first seen (O(new entries) per call; a surface rewrite rebuilds via `surface.replaceGeneration`). Returns a fresh array per call over shared, deep-frozen `Message` objects. Each projection reuses the already deep-frozen content in its durable log event, so no second deep clone is needed and a consumer still cannot mutate logged data. The surface is the single source of derived history — there is no raw-log fallback. - `session.deriveEventMessage(event): Message | null` — the per-event projection `deriveMessages()` folds: a fresh message wrapper that reuses the event's already frozen content, or `null` when the event produces none (a non-surface event, or an empty-content `assistant/message` hosting only usage). External reconstructors and the dev invariant fold the same function over a log prefix's surface, so no two paths can disagree about what a request's messages were (the reconstructability RFC). - `session.surface: SurfaceManager` — the derived surface, lazily folded from `surfaceOp` markers in the log. Processes only new events (delta) on each access — the log is append-only, so prior events never change. `surface.replaceGeneration` is the rewrite signal: bumped by every folded `replace` and never reset, so an incremental consumer comparing generations cannot be fooled. - `session.events` — a cached, frozen array snapshot over deep-frozen events. Repeated reads without an append return the same array; an append invalidates the cache and the next read returns a new snapshot, while earlier snapshots stay unchanged. Neither a cast nor a retained reference can push into the live log or rewrite an accepted event. @@ -46,14 +46,13 @@ Durable values need one accepted representation, not a check followed by a secon ### Surface types -- `SurfaceOp` — how a surface node entered the linked list: `'append'` (normal tail append) or `{ op: 'replace', start, end }` (replace nodes from `start` through `end` inclusive — both must be valid surface node seqs; `start === end` replaces a single node). Used by compaction to shadow old nodes without deleting them. +- `SurfaceOp` — how an event entered the ordered surface: `'append'` (normal tail append) or `{ op: 'replace', start, end }` (replace entries from `start` through `end` inclusive — both must be valid surface seqs; `start === end` replaces one entry). Used by compaction to shadow old events without deleting them. - `SurfaceIntent` — `{ surfaceOp: SurfaceOp; sourceEventSeqs?: number[] }`, the required third parameter to `session.append()` for surface-eligible types. -- `SurfaceNode` — `{ seq: number; prev: number | null; next: number | null }`, one node in the surface linked list. -- `isSurfaceEvent(event)` / `isSurfaceEligibleType(type)` — the first narrows a `SessionEvent` to a fully-formed surface node (type is surface-eligible AND `surfaceOp` present); the second is the type-only check (is this one of the five `SurfaceEventType` values?), used to detect a surface-eligible event MISSING its marker — e.g. when validating a seed/load log. +- `isSurfaceEvent(event)` / `isSurfaceEligibleType(type)` — the first narrows a `SessionEvent` to a fully formed surface event (type is surface-eligible AND `surfaceOp` present); the second is the type-only check (is this one of the five `SurfaceEventType` values?), used to detect a surface-eligible event MISSING its marker — e.g. when validating a seed/load log. ### Request-header reconstruction (`request-header.ts`) -The `request/header` (full `EpochHeader` snapshot with a `RequestHeaderReason`) and `request/header-delta` (system line-trim / name-keyed tools delta / whole config / whole session prefix) events make the request envelope logged session state, so every conversation request is a pure function of the log. The pure trio reconstructs it: `foldRequestHeader(events)` folds a log (or any prefix) into the header in force; `diffHeader(prev, next)` encodes a change (undefined when equal); `applyHeaderDelta(prev, delta)` replays one. Writer contract: every logged delta is round-trip-verified (`apply(prev, delta)` deep-equals the new header) with a `'fallback'` snapshot when the encoding cannot express the change (a pure tool reordering), so folding never needs error recovery on a well-formed log. `canonicalHeader` pins the one representation of absence (empty system/tools/messagePrefix ≡ absent fields; a delta's EMPTY prefix array encodes the transition back to absence). `EpochHeader.messagePrefix` is the durable record of the `agent/session-prefix` waterfall's product — composed once per loop instance, the request is `messagePrefix + derived history`, and `deriveMessages()` never returns it. +The `request/header` event records a full canonical `EpochHeader` snapshot with reason `initial`, `resume`, or `change`, making the request envelope logged session state and every conversation request a pure function of the log. `foldRequestHeader(events)` selects the latest snapshot from a log or prefix; `canonicalHeader` pins the one representation of absence (empty system/tools/messagePrefix ≡ absent fields), and `headerEquals` compares canonical headers. `EpochHeader.messagePrefix` is the durable record of the `agent/session-prefix` waterfall's product — composed once per loop instance, the request is `messagePrefix + derived history`, and `deriveMessages()` never returns it. Legacy v0 seeds containing the removed `request/header-delta` format are rejected rather than partially replayed. ### Session event vocabulary (`types.ts`) diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index a6dff5cd27..06669ca85c 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -22,10 +22,9 @@ export * from './types.ts' export { isJsonValue, snapshotJsonValue } from './json.ts' export type { JsonValue } from './json.ts' export { interruptedTurnClosers } from './repair.ts' -export type { SurfaceNode } from './surface.ts' export { isSurfaceEvent, isSurfaceEligibleType } from './surface.ts' export { isToolPairingBalanced } from './tool-pairing.ts' -export { applyHeaderDelta, canonicalHeader, diffHeader, foldRequestHeader, headerEquals } from './request-header.ts' +export { canonicalHeader, foldRequestHeader, headerEquals } from './request-header.ts' declare module 'cordis' { interface Context { @@ -197,6 +196,9 @@ function assertSurfaceMetadataShape( /** Validate the fixed event envelope after one-pass JSON materialization. */ function assertSessionEventEnvelope(value: Record, index: number): asserts value is SessionEvent { const event = value + if (event['type'] === 'request/header-delta') { + throw new Error(`seed event at index ${index} uses unsupported legacy request/header-delta format`) + } const allowed = new Set(['type', 'seq', 'time', 'data', 'surfaceOp', 'sourceEventSeqs']) if (Object.keys(event).some(key => !allowed.has(key)) || !Object.hasOwn(event, 'type') || typeof event['type'] !== 'string' @@ -262,7 +264,7 @@ export class Session { private log: SessionEvent[] = [] /** - * Derived surface — a cached linked list of message-producing events. + * Derived surface — a cached order of message-producing event sequences. * Lazily rebuilt from `surfaceOp` markers in the log; processes only new * events (delta) on each access — the log is append-only, so prior events * never change. @@ -270,7 +272,7 @@ export class Session { */ private _surface: SurfaceManager | undefined - /** The surface linked list over this session's event log. */ + /** The ordered surface over this session's event log. */ get surface(): SurfaceManager { if (!this._surface) this._surface = new SurfaceManager(this.log) return this._surface @@ -354,7 +356,7 @@ export class Session { * @param type - The event type (key of {@link SessionEventMap}). * @param data - The event payload; must be JSON-serializable. * @param opts - Surface metadata: `surfaceOp` controls how the event enters - * the surface linked list; `sourceEventSeqs` records provenance (the seq + * the ordered surface; `sourceEventSeqs` records provenance (the seq * numbers of events this one derives from). REQUIRED for * {@link SurfaceEventType} events (every message-producing event must * declare how it joins the surface, the sole source of derived history) and @@ -463,8 +465,8 @@ export class Session { private derivedGeneration = 0 /** - * Derive the LLM message history by walking the session surface — the linked - * list of message-producing events maintained by `surfaceOp` markers. The + * Derive the LLM message history by walking the ordered sequences of + * message-producing events maintained by `surfaceOp` markers. The * surface is the single source of derived history: every message-producing * append records its `surfaceOp`, so a raw event with no marker (a chunk, a * turn boundary) is correctly absent, and a compaction `replace` deletes the @@ -488,11 +490,11 @@ export class Session { this.derivedNodes = 0 this.derivedGeneration = generation } - for (const node of nodes.slice(this.derivedNodes)) { - // Surface nodes are built from this.log — node.seq is always a valid + for (const seq of nodes.slice(this.derivedNodes)) { + // Surface sequences are built from this.log — seq is always a valid // index by construction. The non-null assertion expresses that invariant. // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const msg = this.deriveEventMessage(this.log[node.seq]!) + const msg = this.deriveEventMessage(this.log[seq]!) // A surface node is one of the five message-producing types, but an // empty-content assistant/message (a max-tokens step that hosts only // usage) derives to null and must not enter the transcript. diff --git a/packages/core/session/src/request-header.ts b/packages/core/session/src/request-header.ts index eeb2fe40ed..8dd61ee884 100644 --- a/packages/core/session/src/request-header.ts +++ b/packages/core/session/src/request-header.ts @@ -1,35 +1,20 @@ /** - * Request-header reconstruction utilities: the pure fold/diff/apply trio over - * the `request/header` / `request/header-delta` session events. Anyone - * holding a session log reconstructs the {@link EpochHeader} any request was - * built under by folding these events in log order; the loop uses the same - * functions to decide whether a step's header changed and to encode the - * change. Deltas are an encoding optimization with a safety valve — the - * writer round-trip-verifies every delta before appending and falls back to - * a full snapshot when the encoding cannot express the change — so folding - * never needs error recovery on a well-formed log. + * Request-header reconstruction utilities over full `request/header` session + * events. Anyone holding a session log reconstructs the {@link EpochHeader} + * any request was built under by taking the latest canonical snapshot; the + * loop uses the same equality helper to avoid logging unchanged headers. * * @module dsh-session/request-header */ import { callConfigEquals } from '@deepseek-ai/dsh-llm' -import type { LlmCallConfig, Message, ToolSchema } from '@deepseek-ai/dsh-llm' -import type { EpochHeader, SessionEvent, SystemDelta, ToolsDelta } from './types.ts' - -/** The `request/header-delta` payload shape: each present field amends the folded header. */ -type HeaderDelta = { - system?: SystemDelta - tools?: ToolsDelta - config?: LlmCallConfig - messagePrefix?: Message[] -} +import type { Message, ToolSchema } from '@deepseek-ai/dsh-llm' +import type { EpochHeader, SessionEvent } from './types.ts' /** - * Normalize a header to canonical form: an empty system prompt, an empty - * tool list, and an empty session prefix become ABSENT fields, matching how - * requests are built (the request-build spreads skip empty values). Diff, - * fold, and comparison all operate on canonical headers, so "no system - * prompt" (and "no session prefix") has exactly one representation. + * Normalize a header to canonical form: an empty system prompt, an empty tool + * list, and an empty session prefix become absent fields, matching how requests + * are built. Logging, folding, and comparison use this one representation. * @param header - the header to normalize (not mutated). * @returns the canonical header. */ @@ -42,88 +27,22 @@ export function canonicalHeader(header: EpochHeader): EpochHeader { } } -/** Split a canonical (possibly absent) system prompt into lines; absence is zero lines. */ -function systemLines(system: string | undefined): string[] { - return system === undefined ? [] : system.split('\n') -} - -/** Join lines back into a canonical system value; zero lines is absence. */ -function joinSystem(lines: string[]): string | undefined { - return lines.length === 0 ? undefined : lines.join('\n') -} - -/** - * Compute the line-level {@link SystemDelta} between two canonical system - * prompts: trim the common prefix and (non-overlapping) common suffix, and - * carry the replacement lines between them. Deterministic and library-free; - * with nothing shared it degenerates to a full replacement. - */ -function diffSystem(prev: string | undefined, next: string | undefined): SystemDelta { - const a = systemLines(prev) - const b = systemLines(next) - let keepStart = 0 - while (keepStart < a.length && keepStart < b.length && a[keepStart] === b[keepStart]) keepStart += 1 - let keepEnd = 0 - while ( - keepEnd < a.length - keepStart && - keepEnd < b.length - keepStart && - a[a.length - 1 - keepEnd] === b[b.length - 1 - keepEnd] - ) keepEnd += 1 - return { keepStart, keepEnd, insert: b.slice(keepStart, b.length - keepEnd) } -} - -/** Apply a {@link SystemDelta} to a canonical system prompt. */ -function applySystem(prev: string | undefined, delta: SystemDelta): string | undefined { - const a = systemLines(prev) - return joinSystem([...a.slice(0, delta.keepStart), ...delta.insert, ...a.slice(a.length - delta.keepEnd)]) -} - -/** Canonical JSON equality for tool schemas — sound because schemas are - * JSON-serializable by construction and both sides come from the same - * assembly path, so key insertion order matches when the values do. */ +/** Canonical JSON equality for tool schemas assembled through the same path. */ function sameSchema(a: ToolSchema, b: ToolSchema): boolean { return JSON.stringify(a) === JSON.stringify(b) } -/** - * Compute the name-keyed {@link ToolsDelta} between two canonical tool lists. - * A pure reordering produces an empty delta — the writer's round-trip guard - * catches that case and records a snapshot instead. - */ -function diffTools(prev: readonly ToolSchema[], next: readonly ToolSchema[]): ToolsDelta { - const prevByName = new Map(prev.map(tool => [tool.name, tool])) - const nextNames = new Set(next.map(tool => tool.name)) - return { - added: next.filter(tool => !prevByName.has(tool.name)), - removed: prev.filter(tool => !nextNames.has(tool.name)).map(tool => tool.name), - changed: next.filter((tool) => { - const before = prevByName.get(tool.name) - return before !== undefined && !sameSchema(before, tool) - }), - } -} - -/** Apply a {@link ToolsDelta} to a canonical tool list: drop removed, replace changed in place, append added. */ -function applyTools(prev: readonly ToolSchema[], delta: ToolsDelta): ToolSchema[] { - const removed = new Set(delta.removed) - const changedByName = new Map(delta.changed.map(tool => [tool.name, tool])) - const kept = prev - .filter(tool => !removed.has(tool.name)) - .map(tool => changedByName.get(tool.name) ?? tool) - return [...kept, ...delta.added] +/** Canonical JSON equality over session-prefix arrays; absence equals empty. */ +function sameMessages(a: readonly Message[] | undefined, b: readonly Message[] | undefined): boolean { + return JSON.stringify(a ?? []) === JSON.stringify(b ?? []) } /** - * Field-wise equality over canonical headers — the cheap comparison the - * writer's round-trip guard runs (`applyHeaderDelta(prev, delta)` must equal - * the intended header) and the loop runs to skip logging an unchanged header. - * Tools compare per-schema IN ORDER (canonical JSON), so a pure reordering is - * correctly unequal; the session prefix compares as canonical JSON (both - * sides come from the same build path, so key order matches when the values - * do). + * Field-wise equality over canonical headers. Tool schemas compare in order; + * the session prefix compares as canonical JSON. * @param a - one canonical header. * @param b - the other. - * @returns whether config, system, tools (in order), and the session prefix all match. + * @returns whether config, system, tools, and session prefix all match. */ export function headerEquals(a: EpochHeader, b: EpochHeader): boolean { if (!callConfigEquals(a.config, b.config) || a.system !== b.system) return false @@ -133,77 +52,19 @@ export function headerEquals(a: EpochHeader, b: EpochHeader): boolean { return at.length === bt.length && at.every((tool, i) => sameSchema(tool, bt[i] as ToolSchema)) } -/** Canonical JSON equality over session-prefix arrays; absence equals the empty array. */ -function sameMessages(a: readonly Message[] | undefined, b: readonly Message[] | undefined): boolean { - return JSON.stringify(a ?? []) === JSON.stringify(b ?? []) -} - /** - * Compute the `request/header-delta` payload between two canonical headers, - * or undefined when they are equal. The caller MUST round-trip the result - * ({@link applyHeaderDelta} on `prev` deep-equals `next`) before logging it — - * the encoding cannot express every change (a pure tool reordering) — and - * fall back to a full `request/header` snapshot when the check fails. - * The session prefix is replaced whole (small advisory content, not worth - * diffing); an empty replacement array encodes the transition to "none". - * @param prev - the folded header the log currently implies. - * @param next - the header the next request will actually use. - * @returns the delta payload, or undefined when nothing changed. - */ -export function diffHeader(prev: EpochHeader, next: EpochHeader): HeaderDelta | undefined { - const delta: HeaderDelta = {} - if (prev.system !== next.system) delta.system = diffSystem(prev.system, next.system) - const prevTools = prev.tools ?? [] - const nextTools = next.tools ?? [] - if (JSON.stringify(prevTools) !== JSON.stringify(nextTools)) delta.tools = diffTools(prevTools, nextTools) - if (!callConfigEquals(prev.config, next.config)) delta.config = next.config - if (!sameMessages(prev.messagePrefix, next.messagePrefix)) delta.messagePrefix = next.messagePrefix ?? [] - return Object.keys(delta).length > 0 ? delta : undefined -} - -/** - * Apply a `request/header-delta` payload to a canonical header, producing the - * canonical header it encodes. Total for well-formed logs (the writer only - * appends round-trip-verified deltas). - * @param prev - the folded header before the delta. - * @param delta - the logged delta payload. - * @returns the canonical header after the delta. - */ -export function applyHeaderDelta(prev: EpochHeader, delta: HeaderDelta): EpochHeader { - const system = delta.system !== undefined ? applySystem(prev.system, delta.system) : prev.system - const tools = delta.tools !== undefined ? applyTools(prev.tools ?? [], delta.tools) : prev.tools - const messagePrefix = delta.messagePrefix ?? prev.messagePrefix - return canonicalHeader({ - config: delta.config ?? prev.config, - ...system !== undefined ? { system } : {}, - ...tools !== undefined ? { tools } : {}, - ...messagePrefix !== undefined ? { messagePrefix } : {}, - }) -} - -/** - * Fold the header events of a log (or any prefix of one) into the - * {@link EpochHeader} in force after the last of them: each - * `request/header` snapshot replaces the state, each `request/header-delta` - * amends it. The pure, offline form of reconstruction — external tooling and - * the dev invariant both use it; the live session tracks the same fold - * incrementally. - * @param events - session events in log order (non-header events are skipped). - * @param from - a previously folded state to continue from (the live session's - * incremental cursor); omit to fold from nothing. - * @returns the folded header, or undefined when no header event exists yet. + * Fold the header events of a log (or any prefix) into the + * {@link EpochHeader} in force after the last snapshot. Non-header events are + * skipped. This is the pure offline reconstruction path; the live session + * tracks the same fold incrementally. + * @param events - session events in log order. + * @param from - a previously folded state to continue from. + * @returns the latest canonical header, or undefined when none exists yet. */ export function foldRequestHeader(events: readonly SessionEvent[], from?: EpochHeader): EpochHeader | undefined { - let state: EpochHeader | undefined = from + let state = from for (const event of events) { - if (event.type === 'request/header') { - state = canonicalHeader(event.data.header) - } else if (event.type === 'request/header-delta') { - if (state === undefined) { - throw new Error(`request/header-delta at seq ${event.seq} before any request/header snapshot: corrupt log`) - } - state = applyHeaderDelta(state, event.data) - } + if (event.type === 'request/header') state = canonicalHeader(event.data.header) } return state } diff --git a/packages/core/session/src/surface.ts b/packages/core/session/src/surface.ts index d6322c72e7..18721281db 100644 --- a/packages/core/session/src/surface.ts +++ b/packages/core/session/src/surface.ts @@ -1,6 +1,6 @@ /** - * Surface layer on top of the session event log: a derived, cached linked list - * of events that produce LLM messages. Rebuilt deterministically from + * Surface layer on top of the session event log: a derived, cached sequence + * list of events that produce LLM messages. Folded deterministically from * `surfaceOp` markers in the log — the log is the source of truth; the surface * is a view. * @@ -10,7 +10,7 @@ import type { SessionEvent, SurfaceEvent, SurfaceEventType, SurfaceOp } from './types.ts' /** - * The set of event type strings that are eligible for the surface linked list. + * The set of event type strings that are eligible for the surface sequence. * Mirrors the {@link SurfaceEventType} union; kept as a runtime set so the * type guard can check membership without a chain of string comparisons. */ @@ -51,28 +51,16 @@ export function isSurfaceEvent(event: SessionEvent): event is SurfaceEvent { return true } -/** One node in the surface linked list. */ -export interface SurfaceNode { - /** The event seq of this surface node. */ - seq: number - /** The previous surface node's seq, or null if this is the head. */ - prev: number | null - /** The next surface node's seq, or null if this is the tail. */ - next: number | null -} - /** - * Maintains a cached linked list of surface nodes, rebuilt lazily from + * Maintains a cached ordered list of surface event sequences, folded lazily from * `surfaceOp` markers in the event log. Because the log is append-only, it * processes only the delta since the last rebuild — new events are folded * into the existing surface in O(new events) rather than rescanning the * whole log. */ export class SurfaceManager { - /** Surface nodes in linked-list order (head to tail). Empty until first access. */ - private _nodes: SurfaceNode[] = [] - /** Map from event seq → node. */ - private _nodeBySeq = new Map() + /** Surface event sequences in head-to-tail order. Empty until first access. */ + private _nodes: number[] = [] /** The last processed seq. -1 folds the seeded log on first access. */ private _lastProcessedSeq = -1 @@ -95,15 +83,15 @@ export class SurfaceManager { return this._replaceGeneration } - /** The surface nodes in linked-list order (head to tail). */ - get nodes(): readonly SurfaceNode[] { + /** Surface event sequences in head-to-tail order. */ + get nodes(): readonly number[] { if (this._lastProcessedSeq < this.log.length - 1) this._processDelta() return this._nodes } /** * Process events from `_lastProcessedSeq + 1` through the end of the log, - * folding new surface markers into the existing linked list. + * folding new surface markers into the existing sequence list. */ private _processDelta(): void { for (let i = this._lastProcessedSeq + 1; i < this.log.length; i++) { @@ -116,11 +104,7 @@ export class SurfaceManager { if (!isSurfaceEvent(event)) continue if (event.surfaceOp === 'append') { - const tail = this._nodes.length > 0 ? this._nodes[this._nodes.length - 1] : undefined - const node: SurfaceNode = { seq: event.seq, prev: tail?.seq ?? null, next: null } - if (tail) tail.next = event.seq - this._nodes.push(node) - this._nodeBySeq.set(event.seq, node) + this._nodes.push(event.seq) } else { this._replace(event.seq, event.surfaceOp) } @@ -133,38 +117,21 @@ export class SurfaceManager { newSeq: number, op: Extract, ): void { - const startNode = this._nodeBySeq.get(op.start) - if (!startNode) { + const startIdx = this._nodes.indexOf(op.start) + if (startIdx === -1) { throw new Error(`surface replace: start seq ${op.start} not found in surface`) } - const endNode = this._nodeBySeq.get(op.end) - if (!endNode) { + const endIdx = this._nodes.indexOf(op.end) + if (endIdx === -1) { throw new Error(`surface replace: end seq ${op.end} not found in surface`) } - const startIdx = this._nodes.indexOf(startNode) - const endIdx = this._nodes.indexOf(endNode) if (startIdx > endIdx) { throw new Error(`surface replace: start seq ${op.start} (index ${startIdx}) is after end seq ${op.end} (index ${endIdx})`) } // Remove shadowed nodes from `[startIdx, endIdx]` inclusive. const count = endIdx - startIdx + 1 - const removed = this._nodes.splice(startIdx, count) - for (const r of removed) this._nodeBySeq.delete(r.seq) - - // Insert the new node where the removed range was. - const prevNode = startIdx > 0 ? this._nodes[startIdx - 1] : undefined - const nextNode = startIdx < this._nodes.length ? this._nodes[startIdx] : undefined - - const newNode: SurfaceNode = { - seq: newSeq, - prev: prevNode?.seq ?? null, - next: nextNode?.seq ?? null, - } - if (prevNode) prevNode.next = newSeq - if (nextNode) nextNode.prev = newSeq - this._nodes.splice(startIdx, 0, newNode) - this._nodeBySeq.set(newSeq, newNode) + this._nodes.splice(startIdx, count, newSeq) this._replaceGeneration += 1 } } diff --git a/packages/core/session/src/tool-pairing.ts b/packages/core/session/src/tool-pairing.ts index 6ea3042bd7..8f1b35708f 100644 --- a/packages/core/session/src/tool-pairing.ts +++ b/packages/core/session/src/tool-pairing.ts @@ -35,7 +35,6 @@ */ import type { SessionEvent } from './types.ts' -import type { SurfaceNode } from './surface.ts' /** * The tool-pairing delta of a surface node: how it shifts the count of @@ -62,20 +61,20 @@ function nodeDelta(event: SessionEvent): number { * cut has its answering `tool/result` before the cut too, so the cut is a safe * edge for a collapsed region (it cannot split an assistant↔result pair). * - * `nodes` is the surface linked list in head→tail order (e.g. + * `nodes` is the surface sequence list in head→tail order (e.g. * `session.surface.nodes`); `events` is the session log, used to look each - * node's event up by `seq`. `beforeSeq` names the cut by the surface node it + * event up by sequence. `beforeSeq` names the cut by the surface event it * sits immediately before; the after-tail cut (the whole surface) is `null`, * as is any `beforeSeq` not present on the surface. * * A region `[start..end]` is collapsible iff both edges are balanced cuts: call * `isToolPairingBalanced(nodes, events, start)` for the cut before `start`, and * `isToolPairingBalanced(nodes, events, after)` — where `after` is `end`'s - * surface successor (`SurfaceNode.next`), or `null` when `end` is the tail — + * surface successor (`nodes[index + 1]`), or `null` when `end` is the tail — * for the cut after `end`. * - * @param nodes - the surface linked list in head→tail order. - * @param events - the session log each node's `seq` indexes into. + * @param nodes - surface event sequences in head→tail order. + * @param events - the session log each sequence indexes into. * @param beforeSeq - names the cut (the node it sits immediately before); * `null` — or any seq not on the surface — means the after-tail cut. * @returns true when every `tool-call` before the cut is answered before it @@ -86,18 +85,18 @@ function nodeDelta(event: SessionEvent): number { * rather than silently mis-classifying a boundary. */ export function isToolPairingBalanced( - nodes: readonly SurfaceNode[], + nodes: readonly number[], events: readonly SessionEvent[], beforeSeq: number | null, ): boolean { let depth = 0 - for (const node of nodes) { - if (node.seq === beforeSeq) return depth === 0 - // node.seq is a surface-node seq, always a valid log index by construction. + for (const seq of nodes) { + if (seq === beforeSeq) return depth === 0 + // seq is a surface event sequence, always a valid log index by construction. // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - depth += nodeDelta(events[node.seq]!) + depth += nodeDelta(events[seq]!) if (depth < 0) { - throw new Error(`tool-pairing balance: tool/result at surface seq ${node.seq} has no matching tool-call (corrupt surface)`) + throw new Error(`tool-pairing balance: tool/result at surface seq ${seq} has no matching tool-call (corrupt surface)`) } } // Reached the after-tail cut (beforeSeq === null, or a seq not on the diff --git a/packages/core/session/src/types.ts b/packages/core/session/src/types.ts index c4838808c1..c2997c0b47 100644 --- a/packages/core/session/src/types.ts +++ b/packages/core/session/src/types.ts @@ -195,10 +195,9 @@ export interface TodoItem { * The request header: everything about an LLM request besides its derived * message history — the call configuration plus the rendered system prompt, * tool schemas, and the session prefix. Logged session state (the - * reconstructability RFC): a - * {@link SessionEventMap} `request/header` snapshot installs one, a - * `request/header-delta` amends it, and folding those events over the log - * (`foldRequestHeader`) reconstructs the header any request was built under. + * reconstructability RFC): each changed header is logged as a full + * {@link SessionEventMap} `request/header` snapshot, and taking the latest + * snapshot (`foldRequestHeader`) reconstructs the header any request used. * Canonical form: an empty system prompt, an empty tool list, and an empty * prefix are ABSENT fields, matching how requests are built. */ @@ -223,43 +222,9 @@ export interface EpochHeader { * Why a `request/header` snapshot was appended: `'initial'` — the log's first * header (a new conversation); `'resume'` — a loop instance's first request * over a log that already has header events (process restart, fork seed); - * `'fallback'` — a mid-run change the delta encoding could not round-trip - * (e.g. a pure tool reordering), recorded whole instead. + * `'change'` — a later request used a different header. */ -export type RequestHeaderReason = 'initial' | 'resume' | 'fallback' - -/** - * Line-level edit of the system prompt: keep the first `keepStart` and last - * `keepEnd` lines of the previous text, with `insert` replacing everything - * between. Computed as a common-prefix/common-suffix trim — deterministic, - * library-free, degenerating to a full replacement when nothing is shared. - * Absence is encoded as zero lines (the canonical form has no empty-string - * system), so a transition to or from "no system prompt" round-trips. - */ -export interface SystemDelta { - /** Lines kept from the start of the previous system prompt. */ - keepStart: number - /** Lines kept from the end of the previous system prompt. */ - keepEnd: number - /** Lines replacing everything between the kept edges. */ - insert: string[] -} - -/** - * Tool-set edit keyed by tool name (names are unique — the registry rejects - * duplicates): `removed` names drop, `changed` schemas replace their - * predecessor in place, `added` schemas append at the end. A change this - * encoding cannot express (a pure reordering) fails the writer's round-trip - * guard and is recorded as a `'fallback'` snapshot instead. - */ -export interface ToolsDelta { - /** Schemas appended to the end of the tool list. */ - added: ToolSchema[] - /** Names of schemas dropped from the tool list. */ - removed: string[] - /** Schemas replacing the same-named predecessor in place. */ - changed: ToolSchema[] -} +export type RequestHeaderReason = 'initial' | 'resume' | 'change' /** * The session event vocabulary — the append-only source of truth for an @@ -363,32 +328,14 @@ export interface SessionEventMap { * Full snapshot of the {@link EpochHeader} the NEXT request is built under, * with the {@link RequestHeaderReason} it was recorded whole. Appended by * the loop inside the step, before dispatch, on a loop instance's first - * request-building step (`'initial'`/`'resume'`) or when a delta failed its - * round-trip guard (`'fallback'`); always records what the request actually - * used, post-`agent/request`. Anchors the header fold: reconstruction reads - * the latest snapshot and applies the deltas after it. NOT a + * request-building step (`'initial'`/`'resume'`) or when a later request's + * header changes (`'change'`); always records what the request actually used, + * post-`agent/request`. Reconstruction reads the latest snapshot. NOT a * {@link SurfaceEventType}: it produces no LLM message — it is the request * envelope, logged so every request is a pure function of the session log * (the reconstructability RFC). */ 'request/header': { header: EpochHeader; reason: RequestHeaderReason } - /** - * Amendment to the folded {@link EpochHeader}: at least one of a - * {@link SystemDelta}, a {@link ToolsDelta}, a whole replacement - * {@link LlmCallConfig} (four scalars — not worth diffing), or a whole - * replacement session prefix (`messagePrefix` — small advisory content, - * replaced whole; an EMPTY array encodes the transition to "none", - * mirroring the canonical form's absent field — the loop never produces - * one in practice: the prefix is composed once per instance and anchored - * by that instance's snapshot, so this arm exists for codec totality). - * Appended by the - * loop inside the step, before dispatch, when the header for this request - * differs from the fold of the log so far; the writer verifies - * `applyHeaderDelta(previous, delta)` reproduces the new header exactly and - * falls back to a `'fallback'` `request/header` snapshot when it cannot, so - * a logged delta ALWAYS round-trips. NOT a {@link SurfaceEventType}. - */ - 'request/header-delta': { system?: SystemDelta; tools?: ToolsDelta; config?: LlmCallConfig; messagePrefix?: Message[] } } /** The appendable event-type keys of {@link SessionEventMap}, plugin-merged extensions included. */ @@ -396,7 +343,7 @@ export type SessionEventType = keyof SessionEventMap /** * The subset of {@link SessionEventType} values whose events produce LLM - * messages and are eligible to appear on the surface linked list. Only these + * messages and are eligible to appear on the ordered surface. Only these * event types may carry {@link SurfaceOp} and {@link SessionEvent.sourceEventSeqs}. */ export type SurfaceEventType = @@ -407,7 +354,7 @@ export type SurfaceEventType = | 'steering/message' /** - * A {@link SessionEvent} that is **on** the surface linked list — its + * A {@link SessionEvent} that is **on** the ordered surface — its * `surfaceOp` is guaranteed present (mandatory), narrowed from a * surface-eligible {@link SessionEvent} by checking both `type` and * `surfaceOp` at runtime. @@ -418,7 +365,7 @@ export type SurfaceEventType = export type SurfaceEvent = SessionEvent & { surfaceOp: SurfaceOp } /** - * How a session event entered the surface linked list. Only valid on + * How a session event entered the ordered surface. Only valid on * {@link SurfaceEventType} events. * * - `'append'`: added to the tail — normal path for user/assistant/tool/context @@ -435,7 +382,7 @@ export type SurfaceOp = /** * Surface metadata passed to {@link Session.append}. - * `surfaceOp` controls how the event enters the surface linked list; + * `surfaceOp` controls how the event enters the ordered surface; * `sourceEventSeqs` records the seq numbers of events that are provenance * sources of this one (e.g. the `assistant/chunk` seqs behind an * `assistant/message`, or the shadowed nodes behind a compaction replacement). diff --git a/packages/core/session/tests/derived-cache.spec.ts b/packages/core/session/tests/derived-cache.spec.ts index 493a5a96f0..c65755ce8f 100644 --- a/packages/core/session/tests/derived-cache.spec.ts +++ b/packages/core/session/tests/derived-cache.spec.ts @@ -44,7 +44,7 @@ describe('derived-message cache', () => { const nodes = session.surface.nodes session.append('context/message', { content: [{ type: 'text', text: 'summary' }], source: { kind: 'plugin', plugin: 'compact' }, - }, { surfaceOp: { op: 'replace', start: nodes[0]!.seq, end: nodes[1]!.seq }, sourceEventSeqs: [nodes[0]!.seq, nodes[1]!.seq] }) + }, { surfaceOp: { op: 'replace', start: nodes[0]!, end: nodes[1]! }, sourceEventSeqs: [nodes[0]!, nodes[1]!] }) expect(session.deriveMessages()).toHaveLength(1) expect(session.deriveMessages()).toEqual(scratch(session)) diff --git a/packages/core/session/tests/request-header.spec.ts b/packages/core/session/tests/request-header.spec.ts index 8a5af819c3..fa2acdda28 100644 --- a/packages/core/session/tests/request-header.spec.ts +++ b/packages/core/session/tests/request-header.spec.ts @@ -1,14 +1,7 @@ -/** - * Request-header utility tests: canonical form, the system line-diff - * (prefix/suffix trim), the name-keyed tools delta, config replacement, the - * round-trip contract (including the reorder case the encoding cannot - * express), and the log fold. These pin the reconstruction algebra: for every - * logged delta, apply(prev, delta) === next, and folding a log prefix yields - * the header its next request was built under. - */ +/** Request-header canonicalization, equality, snapshot folding, and format rejection. */ import { describe, expect, it } from 'vitest' -import { Session, SessionId, applyHeaderDelta, canonicalHeader, diffHeader, foldRequestHeader, headerEquals } from '@deepseek-ai/dsh-session' +import { Session, SessionId, canonicalHeader, foldRequestHeader, headerEquals } from '@deepseek-ai/dsh-session' import type { EpochHeader, SessionEvent } from '@deepseek-ai/dsh-session' import type { Message, ToolSchema } from '@deepseek-ai/dsh-llm' @@ -22,165 +15,57 @@ function msg(text: string): Message { return { role: 'user', content: [{ type: 'text', text }] } } -/** Round-trip helper: diff must reproduce `next` from `prev` exactly. */ -function roundTrip(prev: EpochHeader, next: EpochHeader): ReturnType { - const delta = diffHeader(prev, next) - if (delta !== undefined) { - expect(applyHeaderDelta(prev, delta)).toEqual(canonicalHeader(next)) - } - return delta -} - describe('canonicalHeader', () => { - it('normalizes empty system and empty tools to absent fields', () => { - expect(canonicalHeader({ config: CONFIG, system: '', tools: [] })).toEqual({ config: CONFIG }) - const full = canonicalHeader({ config: CONFIG, system: 's', tools: [tool('a')] }) - expect(full.system).toBe('s') - expect(full.tools).toHaveLength(1) + it('normalizes empty optional fields to absence and preserves populated fields', () => { + expect(canonicalHeader({ config: CONFIG, system: '', tools: [], messagePrefix: [] })).toEqual({ config: CONFIG }) + const full = canonicalHeader({ config: CONFIG, system: 's', tools: [tool('a')], messagePrefix: [msg('p')] }) + expect(full).toEqual({ config: CONFIG, system: 's', tools: [tool('a')], messagePrefix: [msg('p')] }) }) }) -describe('diffHeader / applyHeaderDelta', () => { - it('returns undefined for equal headers', () => { - const header = canonicalHeader({ config: CONFIG, system: 'a\nb', tools: [tool('t')] }) - expect(diffHeader(header, header)).toBeUndefined() +describe('headerEquals', () => { + const base = canonicalHeader({ config: CONFIG, system: 's', tools: [tool('a')], messagePrefix: [msg('p')] }) + + it('compares every canonical field and preserves tool order', () => { + expect(headerEquals(base, structuredClone(base))).toBe(true) + expect(headerEquals(base, { ...base, config: { model: 'other' } })).toBe(false) + expect(headerEquals(base, { ...base, system: 'other' })).toBe(false) + expect(headerEquals(base, { ...base, messagePrefix: [msg('other')] })).toBe(false) + expect(headerEquals(base, { ...base, tools: [] })).toBe(false) + expect(headerEquals(base, { ...base, tools: [tool('a', 'changed')] })).toBe(false) + expect(headerEquals({ config: CONFIG, tools: [tool('a'), tool('b')] }, { config: CONFIG, tools: [tool('b'), tool('a')] })).toBe(false) }) - it('encodes a mid-prompt line change as a prefix/suffix trim', () => { - const prev = canonicalHeader({ config: CONFIG, system: 'keep1\nold\nkeep2\nkeep3' }) - const next = canonicalHeader({ config: CONFIG, system: 'keep1\nnew A\nnew B\nkeep2\nkeep3' }) - const delta = roundTrip(prev, next) - expect(delta?.system).toEqual({ keepStart: 1, keepEnd: 2, insert: ['new A', 'new B'] }) - expect(delta?.tools).toBeUndefined() - expect(delta?.config).toBeUndefined() - }) - - it('degenerates to a full replacement when nothing is shared, and round-trips absence transitions', () => { - const none = canonicalHeader({ config: CONFIG }) - const some = canonicalHeader({ config: CONFIG, system: 'x\ny' }) - const gained = roundTrip(none, some) - expect(gained?.system).toEqual({ keepStart: 0, keepEnd: 0, insert: ['x', 'y'] }) - const lost = roundTrip(some, none) - expect(lost?.system).toEqual({ keepStart: 0, keepEnd: 0, insert: [] }) - }) - - it('does not double-count overlapping prefix and suffix (repeated lines)', () => { - const prev = canonicalHeader({ config: CONFIG, system: 'a\na' }) - const next = canonicalHeader({ config: CONFIG, system: 'a\na\na' }) - roundTrip(prev, next) - }) - - it('encodes tool addition, removal, and in-place schema change by name', () => { - const prev = canonicalHeader({ config: CONFIG, tools: [tool('keep'), tool('drop'), tool('edit', 'before')] }) - const next = canonicalHeader({ config: CONFIG, tools: [tool('keep'), tool('edit', 'after'), tool('new')] }) - const delta = roundTrip(prev, next) - expect(delta?.tools?.added.map(t => t.name)).toEqual(['new']) - expect(delta?.tools?.removed).toEqual(['drop']) - expect(delta?.tools?.changed.map(t => t.name)).toEqual(['edit']) - }) - - it('round-trips a tool set gained from a tool-less header and lost back to one', () => { - const none = canonicalHeader({ config: CONFIG }) - const some = canonicalHeader({ config: CONFIG, tools: [tool('t')] }) - const gained = roundTrip(none, some) - expect(gained?.tools?.added.map(t => t.name)).toEqual(['t']) - const lost = roundTrip(some, none) - expect(lost?.tools?.removed).toEqual(['t']) - }) - - it('cannot express a pure reordering — the writer detects it via the round-trip check', () => { - const prev = canonicalHeader({ config: CONFIG, tools: [tool('a'), tool('b')] }) - const next = canonicalHeader({ config: CONFIG, tools: [tool('b'), tool('a')] }) - const delta = diffHeader(prev, next) - // A delta IS produced (the lists differ)… - expect(delta).toBeDefined() - // …but applying it cannot reproduce the new order — exactly the case the - // writer's guard turns into a 'fallback' snapshot. - expect(applyHeaderDelta(prev, delta!)).not.toEqual(next) - }) - - it('replaces the config whole and leaves untouched parts alone', () => { - const prev = canonicalHeader({ config: { model: 'm' }, system: 's', tools: [tool('t')] }) - const next = canonicalHeader({ config: { model: 'm2', temperature: 0.1 }, system: 's', tools: [tool('t')] }) - const delta = roundTrip(prev, next) - expect(delta).toEqual({ config: { model: 'm2', temperature: 0.1 } }) - }) -}) - -describe('the session prefix (messagePrefix)', () => { - it('canonicalHeader normalizes an empty prefix to an absent field', () => { - expect(canonicalHeader({ config: CONFIG, messagePrefix: [] })).toEqual({ config: CONFIG }) - const full = canonicalHeader({ config: CONFIG, messagePrefix: [msg('p')] }) - expect(full.messagePrefix).toEqual([msg('p')]) - }) - - it('headerEquals treats absence and empty as one representation, content differences as unequal', () => { - expect(headerEquals(canonicalHeader({ config: CONFIG }), { config: CONFIG, messagePrefix: [] })).toBe(true) - expect(headerEquals({ config: CONFIG, messagePrefix: [msg('a')] }, { config: CONFIG, messagePrefix: [msg('b')] })).toBe(false) - expect(headerEquals({ config: CONFIG, messagePrefix: [msg('a')] }, { config: CONFIG })).toBe(false) - }) - - it('replaces a changed prefix whole and leaves untouched parts alone', () => { - const prev = canonicalHeader({ config: CONFIG, system: 'keep', messagePrefix: [msg('old')] }) - const next = canonicalHeader({ config: CONFIG, system: 'keep', messagePrefix: [msg('new'), msg('more')] }) - const delta = roundTrip(prev, next) - expect(delta).toEqual({ messagePrefix: [msg('new'), msg('more')] }) - }) - - it('round-trips a prefix gained from a bare header and lost back to one (empty array encodes absence)', () => { - const none = canonicalHeader({ config: CONFIG }) - const some = canonicalHeader({ config: CONFIG, messagePrefix: [msg('p')] }) - const gained = roundTrip(none, some) - expect(gained).toEqual({ messagePrefix: [msg('p')] }) - const lost = roundTrip(some, none) - expect(lost).toEqual({ messagePrefix: [] }) - }) - - it('folds prefix deltas over the log like any other header amendment', () => { - const session = new Session(SessionId('fold-prefix')) - session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - const first = canonicalHeader({ config: CONFIG, messagePrefix: [msg('catalog v1')] }) - session.append('request/header', { header: first, reason: 'initial' }) - const second = canonicalHeader({ config: CONFIG, messagePrefix: [msg('catalog v2')] }) - session.append('request/header-delta', diffHeader(first, second)!) - expect(foldRequestHeader(session.events)).toEqual(second) - session.append('request/header-delta', diffHeader(second, canonicalHeader({ config: CONFIG }))!) - expect(foldRequestHeader(session.events)).toEqual({ config: CONFIG }) + it('treats absent and empty prefix/tool arrays as equivalent canonical absence', () => { + expect(headerEquals({ config: CONFIG }, { config: CONFIG, tools: [], messagePrefix: [] })).toBe(true) }) }) describe('foldRequestHeader', () => { - function headerEvents(session: Session): readonly SessionEvent[] { - return session.events - } - - it('returns undefined on a log with no header events', () => { - const session = new Session(SessionId('fold-none')) - session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - expect(foldRequestHeader(headerEvents(session))).toBeUndefined() + it('returns the supplied baseline when no snapshot follows', () => { + const from: EpochHeader = { config: CONFIG, system: 'baseline' } + const unrelated: SessionEvent[] = [ + { type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } }, + ] + expect(foldRequestHeader(unrelated)).toBeUndefined() + expect(foldRequestHeader(unrelated, from)).toBe(from) }) - it('folds snapshot then deltas into the header in force, skipping unrelated events', () => { + it('takes the latest full snapshot and skips unrelated events', () => { const session = new Session(SessionId('fold')) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - const first = canonicalHeader({ config: { model: 'm' }, system: 'a\nb', tools: [tool('t')] }) - session.append('request/header', { header: first, reason: 'initial' }) + session.append('request/header', { header: { config: CONFIG, system: 'first' }, reason: 'initial' }) session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - - const second = canonicalHeader({ config: { model: 'm' }, system: 'a\nc', tools: [tool('t')] }) - session.append('request/header-delta', diffHeader(first, second)!) - expect(foldRequestHeader(headerEvents(session))).toEqual(second) - - // A later snapshot replaces the state wholesale (the 'resume'/'fallback' anchor). - const third = canonicalHeader({ config: { model: 'other' } }) - session.append('request/header', { header: third, reason: 'resume' }) - expect(foldRequestHeader(headerEvents(session))).toEqual(third) - }) - - it('throws on a delta before any snapshot (corrupt log)', () => { - const session = new Session(SessionId('fold-corrupt')) - session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - session.append('request/header-delta', { config: { model: 'x' } }) - expect(() => foldRequestHeader(headerEvents(session))).toThrow(/before any request\/header snapshot/) + session.append('request/header', { header: { config: { model: 'other' }, tools: [] }, reason: 'change' }) + expect(foldRequestHeader(session.events)).toEqual({ config: { model: 'other' } }) + }) +}) + +describe('legacy request-header format', () => { + it('rejects a v0 seed containing request/header-delta', () => { + const legacy = [{ + type: 'request/header-delta', seq: 0, time: 1, data: { config: CONFIG }, + }] as unknown as SessionEvent[] + expect(() => new Session(SessionId('legacy'), legacy)).toThrow(/unsupported legacy request\/header-delta/) }) }) diff --git a/packages/core/session/tests/session.spec.ts b/packages/core/session/tests/session.spec.ts index 2204fc9027..20746260d5 100644 --- a/packages/core/session/tests/session.spec.ts +++ b/packages/core/session/tests/session.spec.ts @@ -1171,8 +1171,8 @@ describe('todo/write event', () => { session.append('todo/write', { todos: [{ content: 'a task', status: 'pending' }] }) // The todo event must not add a message to the derived history… expect(session.deriveMessages()).toHaveLength(before) - // …and must not appear on the surface linked list. - expect(session.surface.nodes.some(node => node.seq === session.seq - 1)).toBe(false) + // …and must not appear on the ordered surface. + expect(session.surface.nodes).not.toContain(session.seq - 1) }) it('round-trips through a seeded replay identically (durable, no surfaceOp needed)', () => { diff --git a/packages/core/session/tests/surface.spec.ts b/packages/core/session/tests/surface.spec.ts index c03a77d2c3..2a658ff82a 100644 --- a/packages/core/session/tests/surface.spec.ts +++ b/packages/core/session/tests/surface.spec.ts @@ -14,18 +14,12 @@ function surfaceSession(): Session { } describe('SurfaceManager', () => { - it('rebuilds a linked list from surfaceOp: append markers', () => { + it('folds an ordered sequence list from surfaceOp: append markers', () => { const s = surfaceSession() const nodes = s.surface.nodes // Only the user/message and assistant/message carry surfaceOp: 'append'. // The turn boundaries do not have surface markers. - expect(nodes.length).toBe(2) - expect(nodes[0]!.seq).toBe(1) // user/message (turn/start is seq 0) - expect(nodes[0]!.prev).toBeNull() - expect(nodes[0]!.next).toBe(2) // assistant/message (seq 2) - expect(nodes[1]!.seq).toBe(2) - expect(nodes[1]!.prev).toBe(1) - expect(nodes[1]!.next).toBeNull() + expect(nodes).toEqual([1, 2]) }) it('empty surface yields empty nodes', () => { @@ -46,9 +40,7 @@ describe('SurfaceManager', () => { // Append another surface node s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'ok' }], isError: false }, { surfaceOp: 'append' }) expect(s.surface.nodes.length).toBe(3) - expect(s.surface.nodes[2]!.seq).toBe(4) // seq 4: after turn/end at seq 3 - expect(s.surface.nodes[2]!.prev).toBe(2) - expect(s.surface.nodes[1]!.next).toBe(4) + expect(s.surface.nodes[2]!).toBe(4) // seq 4: after turn/end at seq 3 }) it('replays identically from a seeded log with surface markers', () => { @@ -56,7 +48,7 @@ describe('SurfaceManager', () => { original.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'ok' }], isError: false }, { surfaceOp: 'append' }) const replayed = new Session(SessionId('replay'), [...original.events]) // Surface rebuilds from the seeded log's markers. - expect(replayed.surface.nodes.map(n => n.seq)).toEqual([1, 2, 4]) + expect(replayed.surface.nodes).toEqual([1, 2, 4]) expect(replayed.deriveMessages()).toEqual(original.deriveMessages()) }) @@ -70,10 +62,7 @@ describe('SurfaceManager', () => { { surfaceOp: { op: 'replace', start: 1, end: 2 }, sourceEventSeqs: [1, 2] }, ) // Now the surface should have just the compaction node. - expect(s.surface.nodes.length).toBe(1) - expect(s.surface.nodes[0]!.seq).toBe(4) // seq of the compaction marker - expect(s.surface.nodes[0]!.prev).toBeNull() - expect(s.surface.nodes[0]!.next).toBeNull() + expect(s.surface.nodes).toEqual([4]) }) it('replace with both ends at real nodes splices only the range', () => { @@ -86,12 +75,7 @@ describe('SurfaceManager', () => { { turn: 1, step: 1, content: [{ type: 'text', text: 'summary' }] }, { surfaceOp: { op: 'replace', start: 0, end: 1 }, sourceEventSeqs: [0, 1] }, ) // seq 3 - expect(s.surface.nodes.map(n => n.seq)).toEqual([3, 2]) - // Links: 3 ↔ 2 - expect(s.surface.nodes[0]!.prev).toBeNull() - expect(s.surface.nodes[0]!.next).toBe(2) - expect(s.surface.nodes[1]!.prev).toBe(3) - expect(s.surface.nodes[1]!.next).toBeNull() + expect(s.surface.nodes).toEqual([3, 2]) }) it('single-node replacement (start === end)', () => { @@ -103,9 +87,7 @@ describe('SurfaceManager', () => { { turn: 1, step: 1, content: [{ type: 'text', text: 'x' }] }, { surfaceOp: { op: 'replace', start: 1, end: 1 }, sourceEventSeqs: [1] }, ) // seq 2 - expect(s.surface.nodes.map(n => n.seq)).toEqual([0, 2]) - expect(s.surface.nodes[0]!.next).toBe(2) - expect(s.surface.nodes[1]!.prev).toBe(0) + expect(s.surface.nodes).toEqual([0, 2]) }) it('throws when replace start is not found', () => { @@ -151,7 +133,7 @@ describe('SurfaceManager', () => { expect(logged.sourceEventSeqs).toEqual([10, 20]) }) - it('replace starting at non-head position links to previous node correctly', () => { + it('replace starting at non-head position preserves surrounding order', () => { const s = new Session(SessionId('mid-replace')) s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 0 s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 1 @@ -161,14 +143,7 @@ describe('SurfaceManager', () => { { turn: 1, step: 1, content: [{ type: 'text', text: 'x' }] }, { surfaceOp: { op: 'replace', start: 1, end: 1 }, sourceEventSeqs: [1] }, ) // seq 3 - expect(s.surface.nodes.map(n => n.seq)).toEqual([0, 3, 2]) - // Links: 0 → 3 → 2 - expect(s.surface.nodes[0]!.prev).toBeNull() - expect(s.surface.nodes[0]!.next).toBe(3) - expect(s.surface.nodes[1]!.prev).toBe(0) - expect(s.surface.nodes[1]!.next).toBe(2) - expect(s.surface.nodes[2]!.prev).toBe(3) - expect(s.surface.nodes[2]!.next).toBeNull() + expect(s.surface.nodes).toEqual([0, 3, 2]) }) it('surfaceOp replace object is snapshot so caller mutation is isolated', () => { @@ -340,7 +315,7 @@ describe('SurfaceManager.replaceGeneration', () => { const nodes = s.surface.nodes s.append('context/message', { content: [{ type: 'text', text: 'summary' }], source: { kind: 'plugin', plugin: 'compact' }, - }, { surfaceOp: { op: 'replace', start: nodes[0]!.seq, end: nodes[1]!.seq }, sourceEventSeqs: [nodes[0]!.seq, nodes[1]!.seq] }) + }, { surfaceOp: { op: 'replace', start: nodes[0]!, end: nodes[1]! }, sourceEventSeqs: [nodes[0]!, nodes[1]!] }) expect(s.surface.replaceGeneration).toBe(1) }) }) diff --git a/packages/core/session/tests/tool-pairing.spec.ts b/packages/core/session/tests/tool-pairing.spec.ts index 307b0d8658..8e7b8b4a03 100644 --- a/packages/core/session/tests/tool-pairing.spec.ts +++ b/packages/core/session/tests/tool-pairing.spec.ts @@ -1,7 +1,7 @@ import { describe, expect, it } from 'vitest' import { CallId } from '@deepseek-ai/dsh-llm' import { Session, SessionId, isToolPairingBalanced } from '../src/index.ts' -import type { SessionEvent, SurfaceNode } from '../src/index.ts' +import type { SessionEvent } from '../src/index.ts' /** * Unit coverage for the tool-pairing balance check. It decides whether a CUT in @@ -12,8 +12,8 @@ import type { SessionEvent, SurfaceNode } from '../src/index.ts' * no step (pre-step user message, inter-step steering, injection context) are * pairing-neutral, so their cuts are free boundaries. * - * The fixtures are built through a real {@link Session} so the surface linked - * list is derived exactly as production does — including the non-monotonic + * The fixtures are built through a real {@link Session} so the ordered surface + * sequence list is derived exactly as production does — including the non-monotonic * surface a `replace` op leaves (a compaction checkpoint at a high log seq * sitting at the surface head), which is the case the abandoned log-position * scan mis-classified. @@ -27,7 +27,7 @@ import type { SessionEvent, SurfaceNode } from '../src/index.ts' const SURFACE = { surfaceOp: 'append' as const } /** Surface nodes + log for a session, the two args the balance check takes. */ -function surfaceOf(session: Session): { nodes: readonly SurfaceNode[]; events: readonly SessionEvent[] } { +function surfaceOf(session: Session): { nodes: readonly number[]; events: readonly SessionEvent[] } { return { nodes: session.surface.nodes, events: session.events } } @@ -40,9 +40,9 @@ function startBalanced(session: Session, seq: number): boolean { /** The cut AFTER the surface node at `seq` is balanced (safe region end). */ function endBalanced(session: Session, seq: number): boolean { const { nodes, events } = surfaceOf(session) - const node = nodes.find(n => n.seq === seq) - if (!node) throw new Error(`seq ${seq} is not a surface node`) - return isToolPairingBalanced(nodes, events, node.next) + const index = nodes.indexOf(seq) + if (index === -1) throw new Error(`seq ${seq} is not a surface node`) + return isToolPairingBalanced(nodes, events, nodes[index + 1] ?? null) } /** Surface seq of the nth (0-based) event of a given type. */ @@ -274,20 +274,20 @@ describe('isToolPairingBalanced — CBR-001: a head checkpoint left by a replace it('the head checkpoint sits at the surface head while a later surface node follows it in the log', () => { const s = checkpointHeadedSession() const nodes = s.surface.nodes - const checkpointSeq = nodes[0]!.seq + const checkpointSeq = nodes[0]! // The checkpoint heads the surface, yet a surface node (the open step's // assistant) follows it in LOG order — the exact split between surface // position and log position that the log-position scan tripped on. const laterSurfaceInLog = s.events.find( - e => e.seq > checkpointSeq && nodes.some(n => n.seq === e.seq), + e => e.seq > checkpointSeq && nodes.includes(e.seq), ) expect(laterSurfaceInLog).toBeDefined() - expect(nodes[0]!.seq).toBe(checkpointSeq) + expect(nodes[0]!).toBe(checkpointSeq) }) it('start cut before the head checkpoint is balanced (it is the head)', () => { const s = checkpointHeadedSession() - expect(startBalanced(s, s.surface.nodes[0]!.seq)).toBe(true) + expect(startBalanced(s, s.surface.nodes[0]!)).toBe(true) }) it('end cut after the head checkpoint is balanced (it carries no tool pair)', () => { @@ -296,7 +296,7 @@ describe('isToolPairingBalanced — CBR-001: a head checkpoint left by a replace // wrongly reported mid-step. The surface balance sees a neutral node whose // following cut closes no open call. const s = checkpointHeadedSession() - expect(endBalanced(s, s.surface.nodes[0]!.seq)).toBe(true) + expect(endBalanced(s, s.surface.nodes[0]!)).toBe(true) }) }) diff --git a/packages/llm/llm/src/call-config.ts b/packages/llm/llm/src/call-config.ts index 53cb157214..19bb95bd12 100644 --- a/packages/llm/llm/src/call-config.ts +++ b/packages/llm/llm/src/call-config.ts @@ -7,7 +7,7 @@ * the same way out of caution. It is per-conversation state recorded in the * session log (the reconstructability RFC), never a silently-drifting * per-call knob: the `agent/request` waterfall proposes a replacement, and - * the loop logs a real change as a `request/header-delta` event. + * the loop logs a real change as a `request/header` snapshot. * * @module dsh-llm/call-config */ @@ -27,7 +27,7 @@ export interface LlmCallConfig { /** * Field-wise equality over {@link LlmCallConfig} — the comparison a caller * runs to decide whether a proposed configuration is a real change (worth a - * logged header delta) or the held one restated. + * logged header snapshot) or the held one restated. * @param a - one configuration. * @param b - the other. * @returns whether every field (including the `stop` list, element-wise) matches. diff --git a/packages/llm/llm/tests/call-config.spec.ts b/packages/llm/llm/tests/call-config.spec.ts index 65ff7d7d34..951a250a9f 100644 --- a/packages/llm/llm/tests/call-config.spec.ts +++ b/packages/llm/llm/tests/call-config.spec.ts @@ -1,6 +1,6 @@ /** * call-config unit tests: field-wise LlmCallConfig equality (the real-change - * detector behind logged header deltas) and the deepFreeze ownership helper + * detector behind logged changed headers) and the deepFreeze ownership helper * the loop applies to every built request. */ diff --git a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts index e5c2955ef2..b9bc0f8d9a 100644 --- a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts +++ b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts @@ -6,7 +6,7 @@ import { join } from 'node:path' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { Session, SessionEvent, SessionHeader } from '@deepseek-ai/dsh-session' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' -import { encodeSegment, logPath, scanLog, sessionDir } from '../src/format.ts' +import { encodeSegment, logPath, scanLog, sessionDir, toHeaderLine } from '../src/format.ts' import { runPersistenceContract, meta, oneTurnLog, appendLog } from '../../session-persistence/tests/contract.ts' import { runCoordinatorContract, type CoordinatorFixture } from '../../session-persistence/tests/coordinator-contract.ts' @@ -147,6 +147,21 @@ describe('SessionPersistenceJsonl: durability and crash semantics', () => { expect(loaded.events).toEqual(log) // chunks preserved, contiguous seqs }) + it('rejects a stored v0 log containing a legacy request/header-delta event', async () => { + const m = meta('legacy-header-delta', '/legacy') + const path = logPath(root, m.cwd, m.id) + await mkdir(sessionDir(root, m.cwd), { recursive: true }) + await writeFile(path, [ + JSON.stringify(toHeaderLine(m)), + JSON.stringify({ type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } }), + JSON.stringify({ type: 'request/header-delta', seq: 1, time: 2, data: { config: { model: 'legacy' } } }), + JSON.stringify({ type: 'turn/end', seq: 2, time: 3, data: { turn: 1, reason: { kind: 'completed' } } }), + '', + ].join('\n')) + + await expect(ctx.sessionPersistence.load(m.id)).rejects.toThrow(/unsupported legacy request\/header-delta event at seq 1/) + }) + it('persists a forked child seed through the existing session write path', async () => { const source = ctx.sessions.create(SessionId('persist-parent'), { meta: { cwd: '/workspace' } }) appendClosedTurn(source) diff --git a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts index a6eda72685..12857d2cd8 100644 --- a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts +++ b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts @@ -144,6 +144,23 @@ describe('scanRows', () => { }) describe('SessionPersistenceSqlite: durability and crash semantics', () => { + it('rejects a stored v0 log containing a legacy request/header-delta event', async () => { + const path = await freshDbPath() + const m = meta('legacy-header-delta', '/legacy') + const db = openDatabase(path, 'wal') + db.prepare('INSERT INTO sessions (id, version, created_at, cwd, parent_session, seed_length) VALUES (?, ?, ?, ?, NULL, NULL)') + .run(m.id, m.version, m.createdAt, m.cwd ?? null) + const insert = db.prepare('INSERT INTO events (session_id, seq, type, time, data) VALUES (?, ?, ?, ?, ?)') + insert.run(m.id, 0, 'turn/start', 1, JSON.stringify({ turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })) + insert.run(m.id, 1, 'request/header-delta', 2, JSON.stringify({ config: { model: 'legacy' } })) + insert.run(m.id, 2, 'turn/end', 3, JSON.stringify({ turn: 1, reason: { kind: 'completed' } })) + db.close() + + const mounted = await backend(path) + await expect(mounted.ctx.sessionPersistence.load(m.id)).rejects.toThrow(/unsupported legacy request\/header-delta event at seq 1/) + await mounted.dispose() + }) + it('an interrupted turn (rows after the last turn/end) is PRESERVED and closed during load', async () => { const path = await freshDbPath() const m = meta('crash') diff --git a/packages/session-persistence/session-persistence/src/coordinator.ts b/packages/session-persistence/session-persistence/src/coordinator.ts index a3bae9cf87..4c42751816 100644 --- a/packages/session-persistence/session-persistence/src/coordinator.ts +++ b/packages/session-persistence/session-persistence/src/coordinator.ts @@ -151,6 +151,15 @@ function seedCoversPrefix(seed: readonly SessionEvent[], prefix: readonly Sessio }) } +/** Reject events from an obsolete v0 vocabulary that this build cannot replay. */ +function assertSupportedEvents(events: readonly SessionEvent[], id: SessionId): void { + const legacyType: string = 'request/header-delta' + const legacy = events.find(event => event.type === legacyType) + if (legacy !== undefined) { + throw new Error(`session "${id}" contains unsupported legacy request/header-delta event at seq ${legacy.seq}`) + } +} + /** * Owns the backend-agnostic session write-path orchestration. A backend * constructs one (`new PersistenceCoordinator(ctx, this)`), implements @@ -242,6 +251,7 @@ export class PersistenceCoordinator { if (batch === undefined) { throw new TypeError('session event batch is not losslessly JSON-serializable because it contains non-JSON-serializable data') } + assertSupportedEvents(batch, id) return this.serialize(id, () => this.appendCore(id, batch)) } @@ -280,6 +290,7 @@ export class PersistenceCoordinator { if (stored === undefined) throw new Error(`session "${id}" not found`) const { meta, events, tornMarker } = stored this.assertVersion(meta) + assertSupportedEvents(events, id) // Crash-recovery: if the log ended mid-turn (real, preserved events but no // closing turn/end), close it durably DURING load so disk, the returned log, diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 501b98b793..13dd1ab247 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -35,7 +35,7 @@ defineAcpSnapshotSuite({ }) ``` -A scenario booting a differently-composed tree sets its own `configPath` (an overlay whose basename still ends in `cordis.yml`, so the bin's replay swap finds the sibling `*cordis.snapshot.yml`) and, when that composition changes the request header, its own `headerClass` with its own pinning scenario — the acp-agent example's Code Mode scenarios are the template. Each pinning directory's generated `system-prompt.golden.md` is the reviewable snapshot of the normalized composed prompt; `session.jsonl` stores `"system":"{{system}}"` while retaining the complete tool list. +A scenario booting a differently-composed tree sets its own `configPath` (an overlay whose basename still ends in `cordis.yml`, so the bin's replay swap finds the sibling `*cordis.snapshot.yml`) and, when that composition changes the request header, its own `headerClass` with its own pinning scenario — the acp-agent example's Code Mode scenarios are the template. Each pinning directory's generated `system-prompt.golden.md` is the reviewable snapshot of the normalized composed prompt; `session.jsonl` stores `"system":"{{system}}"` while retaining the complete tool list. A pin whose scenario legitimately changes its header mid-run declares `expectedHeaderChanges`; the Markdown snapshot then records each later full prompt under a `request/header change` marker. The example also ships a `cordis.snapshot.yml` replay overlay next to its `cordis.yml` (the bin swaps them under `DSH_SNAPSHOT=replay` — [single-source replay config RFC](../../../docs/rfc/implemented/testing/2026-07-04-single-source-acp-replay-config.md)); replay fixtures are served by [`dsh-llm-replay`](../llm-replay/README.md), which this package points at via the `DSH_SNAPSHOT_*` env vars it sets on the child. `pnpm run test:snapshot:record` calls the live LLM and rewrites the recorded scenarios' model fixtures; `pnpm run test:snapshot:refresh` stays keyless, runs the replay overlay, and rewrites stdout, comparable session-log goldens, and each pin's Markdown prompt snapshot from the committed model scripts. Fixture roles, record/replay/refresh semantics, and scenario-table fields are documented on `Scenario` and in the [snapshot RFC](../../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md). diff --git a/packages/support/acp-snapshot/src/normalize.ts b/packages/support/acp-snapshot/src/normalize.ts index a68fcf83d3..778353f762 100644 --- a/packages/support/acp-snapshot/src/normalize.ts +++ b/packages/support/acp-snapshot/src/normalize.ts @@ -135,8 +135,8 @@ export function normalizeSessionLog(rawLog: string, ctx: NormalizeContext): stri } /** - * Replace system-prompt content in request headers and header deltas with - * `{{system}}` tokens while retaining field presence and delta structure. + * Replace system-prompt content in request headers with `{{system}}` tokens + * while retaining field presence. * Other header content stays verbatim, so a header-pinning fixture can keep * its complete tool schemas while every JSONL fixture omits the prompt text. * Lines without a system payload pass through byte-for-byte; the transform is @@ -153,9 +153,9 @@ export function scrubSystemPrompts(rawLog: string): string { * Replace all bulky request-header content in a session JSONL with stable * tokens. This includes the system-prompt fields handled by * {@link scrubSystemPrompts}, tool schemas, and session-prefix messages. It - * keeps system-delta line positions and arity, tool-delta names, prefix - * message counts, field presence, config, and reason. Lines without content - * to scrub pass through byte-for-byte, and the transform is idempotent. + * keeps prefix message counts, field presence, config, and reason. Lines + * without content to scrub pass through byte-for-byte, and the transform is + * idempotent. * * @param rawLog The raw session `.jsonl` content. * @returns The JSONL with all header bulk tokenized, other lines byte-identical. @@ -184,33 +184,7 @@ function scrubHeaderContent(rawLog: string, scrubToolsAndPrefix: boolean): strin } return touched ? JSON.stringify(record) : line } - if (record.type === 'request/header-delta') { - let touched = false - const system = data.system as Record | null | undefined - if (system !== null && typeof system === 'object' && Array.isArray(system.insert)) { - system.insert = system.insert.map(() => SYSTEM) - touched = true - } - const tools = data.tools as Record | null | undefined - if (scrubToolsAndPrefix && tools !== null && typeof tools === 'object') { - if (Array.isArray(tools.added)) { tools.added = tools.added.map(scrubToolSchema); touched = true } - if (Array.isArray(tools.changed)) { tools.changed = tools.changed.map(scrubToolSchema); touched = true } - } - if (scrubToolsAndPrefix && Array.isArray(data.messagePrefix)) { - data.messagePrefix = data.messagePrefix.map(() => MESSAGE_PREFIX) - touched = true - } - return touched ? JSON.stringify(record) : line - } return line }) return out.join('\n') } - -/** Tokenize one tool schema's bulk (description, parameters, anything else), keeping its identifying `name`. */ -function scrubToolSchema(tool: unknown): unknown { - if (tool === null || typeof tool !== 'object' || Array.isArray(tool)) return tool - const out: Record = {} - for (const [k, v] of Object.entries(tool)) out[k] = k === 'name' ? v : TOOLS - return out -} diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts index 418470f2be..523092bf09 100644 --- a/packages/support/acp-snapshot/src/suite.ts +++ b/packages/support/acp-snapshot/src/suite.ts @@ -16,7 +16,7 @@ * scenario stores the readable prompt in `system-prompt.golden.md` and keeps its full * tool schemas in `session.jsonl`, while every other fixture also scrubs tools * to `{{tools}}`. A per-run uniformity guard compares both artifacts against - * every live header and forbids unrepresented header deltas (see the + * every live header and forbids unrepresented changed headers (see the * pinned-header RFC, * docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md). * @@ -106,14 +106,11 @@ export interface Scenario { */ pinsHeader?: boolean /** - * How many `request/header-delta` events this PINNING scenario's fixture - * legitimately carries (default 0). A recorded mid-run header change — a - * config-option switch rewriting a prompt section — is part of the pinned - * surface, with readable prompt text in Markdown; any OTHER count - * still fails, so fixture rot stays caught. Meaningless off the pin (the - * live uniformity guard keeps non-pinning scenarios delta-free). + * How many changed `request/header` snapshots this PINNING scenario's primary + * fixture legitimately carries (default 0). Their full prompt text is kept in + * the readable Markdown pin; any other count fails. Meaningless off the pin. */ - expectedHeaderDeltas?: number + expectedHeaderChanges?: number /** * Which header-composition class this scenario belongs to. Scenarios that * boot the same config compose the same header; each class has exactly one @@ -225,79 +222,46 @@ export function normalizedSystemPrompts(rawLog: string, ctx: NormalizeContext): }) } -/** One normalized system-prompt edit carried by a `request/header-delta`. */ -export interface SystemPromptDeltaSnapshot { - /** How many leading lines remain from the prior prompt. */ - keepStart: number - /** How many trailing lines remain from the prior prompt. */ - keepEnd: number - /** The normalized replacement lines inserted between the retained ranges. */ - insert: string[] -} - -/** - * Extract normalized system-prompt edits from request-header deltas in log - * order. Deltas without a well-formed system edit are omitted; their non-prompt - * structure remains pinned in JSONL. - * - * @param rawLog The session `.jsonl` content to inspect. - * @param ctx The volatile values of the run that produced it. - * @returns The normalized system-prompt edits, in event order. - */ -export function normalizedSystemPromptDeltas(rawLog: string, ctx: NormalizeContext): SystemPromptDeltaSnapshot[] { - return normalizeSessionLog(rawLog, ctx) - .split('\n') - .filter(line => line.trim().length > 0) - .map(line => JSON.parse(line) as { type?: unknown; data?: { system?: unknown } }) - .filter(record => record.type === 'request/header-delta') - .flatMap((record) => { - const system = record.data?.system - if (system === null || typeof system !== 'object') return [] - const { keepStart, keepEnd, insert } = system as { keepStart?: unknown; keepEnd?: unknown; insert?: unknown } - if (typeof keepStart !== 'number' || typeof keepEnd !== 'number' || !Array.isArray(insert)) return [] - if (!insert.every(line => typeof line === 'string')) return [] - return [{ keepStart, keepEnd, insert: insert }] - }) -} - /** * Render a normalized prompt as a repository-friendly Markdown snapshot. * Prompt text is unchanged except that a missing terminal newline is added so * the committed file follows the repository newline contract. * * @param prompt The normalized system prompt. - * @param deltas Normalized prompt edits to append as readable sections. + * @param changes Full normalized prompts from later changed-header snapshots. * @returns Markdown snapshot text ending in a newline. */ export function formatSystemPromptSnapshot( prompt: string, - deltas: readonly SystemPromptDeltaSnapshot[] = [], + changes: readonly string[] = [], ): string { let snapshot = prompt.endsWith('\n') ? prompt : `${prompt}\n` - for (const [index, delta] of deltas.entries()) { - snapshot += `\n\n\n` - const insert = delta.insert.join('\n') - snapshot += insert.endsWith('\n') ? insert : `${insert}\n` + for (const [index, change] of changes.entries()) { + snapshot += `\n\n\n` + snapshot += change.endsWith('\n') ? change : `${change}\n` } return snapshot } -/** Return the initial-prompt portion of a possibly delta-bearing snapshot. */ +/** Return the initial-prompt portion of a possibly multi-header snapshot. */ function initialSystemPromptSnapshot(snapshot: string): string { - const marker = snapshot.indexOf('\n + + +SYS PROMPT NEW PROMPT LINE diff --git a/packages/support/acp-snapshot/tests/normalize.spec.ts b/packages/support/acp-snapshot/tests/normalize.spec.ts index bdde120a76..fa06d55d14 100644 --- a/packages/support/acp-snapshot/tests/normalize.spec.ts +++ b/packages/support/acp-snapshot/tests/normalize.spec.ts @@ -180,89 +180,19 @@ describe('scrubRequestHeaders', () => { expect(scrubRequestHeaders(`${headerLine}\n${odd}\n`)).toContain('"messagePrefix":"weird"') }) - it('scrubs a header-delta prefix replacement to one token per message', () => { - const delta = JSON.stringify({ - type: 'request/header-delta', seq: 8, time: 9, - data: { messagePrefix: [{ role: 'user', content: [{ type: 'text', text: 'leaked opener' }] }] }, - }) - const out = scrubRequestHeaders(`${headerLine}\n${delta}\n`) - expect(out).toContain('"messagePrefix":["{{messagePrefix}}"]') - expect(out).not.toContain('leaked opener') - // The empty-array transition-to-absence stays a structural fact. - const toNone = JSON.stringify({ type: 'request/header-delta', seq: 9, time: 9, data: { messagePrefix: [] } }) - expect(scrubRequestHeaders(`${headerLine}\n${toNone}\n`)).toContain('"messagePrefix":[]') - }) - - it('leaves a delta with no scrubbable payload byte-identical (config-only, or non-array shapes)', () => { - const configOnly = JSON.stringify({ type: 'request/header-delta', seq: 8, time: 9, data: { config: { model: 'm2' } } }) - const oddShapes = JSON.stringify({ type: 'request/header-delta', seq: 9, time: 9, data: { system: { insert: 'not-an-array' }, tools: null } }) + it('leaves malformed headers with no scrubbable payload byte-identical', () => { const headerless = JSON.stringify({ type: 'request/header', seq: 10, time: 9, data: { reason: 'initial' } }) const nullData = JSON.stringify({ type: 'request/header', seq: 11, time: 9, data: null }) - const raw = `${headerLine}\n${configOnly}\n${oddShapes}\n${headerless}\n${nullData}\n` + const raw = `${headerLine}\n${headerless}\n${nullData}\n` expect(scrubRequestHeaders(raw)).toBe(raw) }) - it('scrubs a one-sided tools delta and passes non-object schema entries through', () => { - const addedOnly = JSON.stringify({ - type: 'request/header-delta', seq: 8, time: 9, - data: { tools: { added: [null, 'weird', { name: 'x', description: 'D' }] } }, - }) - const out = scrubRequestHeaders(`${headerLine}\n${addedOnly}\n`) - // Non-object entries survive untouched; the object entry keeps only name. - expect(out).toContain('"added":[null,"weird",{"name":"x","description":"{{tools}}"}]') - const changedOnly = JSON.stringify({ - type: 'request/header-delta', seq: 8, time: 9, - data: { tools: { changed: [{ name: 'y', parameters: {} }] } }, - }) - expect(scrubRequestHeaders(`${headerLine}\n${changedOnly}\n`)) - .toContain('"changed":[{"name":"y","parameters":"{{tools}}"}]') - }) - - it('scrubs a header-delta system payload but keeps its line positions and arity', () => { - const delta = JSON.stringify({ - type: 'request/header-delta', seq: 8, time: 9, - data: { system: { keepStart: 1, keepEnd: 4, insert: ['leaked prompt line', 'second line'] }, config: { model: 'm2' } }, - }) - const out = scrubRequestHeaders(`${headerLine}\n${delta}\n`) - // One token PER inserted line: the edit's position AND extent survive. - expect(out).toContain('"insert":["{{system}}","{{system}}"]') - expect(out).toContain('"keepStart":1') - expect(out).toContain('"keepEnd":4') - expect(out).toContain('"config":{"model":"m2"}') - expect(out).not.toContain('leaked prompt line') - expect(out).not.toContain('{{tools}}') // no tools delta → none invented - }) - - it('scrubs a header-delta tools payload but keeps the added/removed/changed names', () => { - const delta = JSON.stringify({ - type: 'request/header-delta', seq: 8, time: 9, - data: { - tools: { - added: [{ name: 'grep', description: 'Search files.', parameters: { type: 'object' } }], - removed: ['bash_kill'], - changed: [{ name: 'read', description: 'Read v2.', parameters: { type: 'object' } }], - }, - }, - }) - const out = scrubRequestHeaders(`${headerLine}\n${delta}\n`) - // WHICH tools changed is behavior and survives; their bulk does not. - expect(out).toContain('"added":[{"name":"grep","description":"{{tools}}","parameters":"{{tools}}"}]') - expect(out).toContain('"removed":["bash_kill"]') - expect(out).toContain('"changed":[{"name":"read","description":"{{tools}}","parameters":"{{tools}}"}]') - expect(out).not.toContain('Search files') - expect(out).not.toContain('Read v2') - }) - it('passes every other line through byte-for-byte and is idempotent', () => { const other = JSON.stringify({ type: 'assistant/chunk', seq: 4, time: 9, data: { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'hi' } } }) - const delta = JSON.stringify({ - type: 'request/header-delta', seq: 8, time: 9, - data: { system: { keepStart: 0, keepEnd: 0, insert: ['x'] }, tools: { added: [{ name: 't', description: 'd', parameters: {} }], removed: [], changed: [] } }, - }) - const raw = `${headerLine}\n${headerEvent({ config: { model: 'm' }, system: 's', tools: [] })}\n${delta}\n${other}\n` + const raw = `${headerLine}\n${headerEvent({ config: { model: 'm' }, system: 's', tools: [] })}\n${other}\n` const once = scrubRequestHeaders(raw) expect(once.split('\n')[0]).toBe(headerLine) - expect(once.split('\n')[3]).toBe(other) + expect(once.split('\n')[2]).toBe(other) expect(scrubRequestHeaders(once)).toBe(once) }) }) @@ -280,12 +210,15 @@ describe('scrubSystemPrompts', () => { reason: 'initial', }, }) - const delta = JSON.stringify({ - type: 'request/header-delta', seq: 2, time: 3, + const changed = JSON.stringify({ + type: 'request/header', seq: 2, time: 3, data: { - system: { keepStart: 1, keepEnd: 2, insert: ['new prompt line'] }, - tools: { changed: [{ name: 'read', description: 'changed schema' }] }, - messagePrefix: [{ role: 'user', content: [{ type: 'text', text: 'changed prefix' }] }], + header: { + system: 'new prompt', + tools: [{ name: 'read', description: 'changed schema' }], + messagePrefix: [{ role: 'user', content: [{ type: 'text', text: 'changed prefix' }] }], + }, + reason: 'change', }, }) const toolsOnly = JSON.stringify({ @@ -293,11 +226,10 @@ describe('scrubSystemPrompts', () => { data: { header: { tools: [{ name: 'read', description: 'schema only' }] }, reason: 'resume' }, }) - const out = scrubSystemPrompts(`${header}\n${delta}\n${toolsOnly}\n`) + const out = scrubSystemPrompts(`${header}\n${changed}\n${toolsOnly}\n`) expect(out).toContain('"system":"{{system}}"') - expect(out).toContain('"insert":["{{system}}"]') expect(out).not.toContain('full prompt') - expect(out).not.toContain('new prompt line') + expect(out).not.toContain('new prompt') expect(out).toContain('full schema') expect(out).toContain('full prefix') expect(out).toContain('changed schema') diff --git a/packages/support/acp-snapshot/tests/suite.spec.ts b/packages/support/acp-snapshot/tests/suite.spec.ts index d6e3e2b912..4ca9c8573d 100644 --- a/packages/support/acp-snapshot/tests/suite.spec.ts +++ b/packages/support/acp-snapshot/tests/suite.spec.ts @@ -9,9 +9,8 @@ import { childFixturePaths, fixtureContext, formatSystemPromptSnapshot, - headerDeltaCount, + headerChangeCount, normalizedHeaders, - normalizedSystemPromptDeltas, normalizedSystemPrompts, refreshFixtureReplacements, stabilizeRefreshLog, @@ -51,7 +50,7 @@ const RECORD_SRC = fileURLToPath(new URL('./fixtures/record-suite', import.meta. // is what this suite can exercise; the real overlay boot is the acp-agent // example's code-mode scenarios). const REPLAY_SCENARIOS: Scenario[] = [ - { name: 'pin-turn', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderDeltas: 1, headerClass: 'main' }, + { name: 'pin-turn', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderChanges: 1, headerClass: 'main' }, { name: 'plain-turn', hasModelTurn: true, recorded: true, childSessions: 1, headerClass: 'main', configPath: AGENT.configPath }, { name: 'no-model', hasModelTurn: false, recorded: false, headerClass: 'main' }, { name: 'blocked-log', hasModelTurn: false, comparesLog: true, recorded: false, headerClass: 'main' }, @@ -132,7 +131,9 @@ describe('defineAcpSnapshotSuite: refresh write-back', () => { expect(readFileSync(join(refreshDir, 'pin-turn', 'system-prompt.golden.md'), 'utf8')).toBe([ 'SYS PROMPT', '', - '', + '', + '', + 'SYS PROMPT', '', 'NEW PROMPT LINE', '', @@ -247,46 +248,30 @@ describe('normalizedSystemPrompts', () => { }) }) -describe('normalizedSystemPromptDeltas', () => { - it('extracts and normalizes well-formed system edits', () => { - const log = [ - '{"type":"request/header-delta","data":{"system":{"keepStart":1,"keepEnd":0,"insert":["work in /w"]}}}', - '{"type":"request/header-delta","data":{"tools":{"replace":[]}}}', - '{"type":"request/header-delta","data":{"system":{"keepStart":"1","keepEnd":0,"insert":[]}}}', - '{"type":"request/header-delta","data":{"system":{"keepStart":1,"keepEnd":0,"insert":[null]}}}', - '', - ].join('\n') - expect(normalizedSystemPromptDeltas(log, { sessionIds: [], cwd: '/w' })).toEqual([ - { keepStart: 1, keepEnd: 0, insert: ['work in {{cwd}}'] }, - ]) - }) -}) - describe('formatSystemPromptSnapshot', () => { it('adds a missing terminal newline without changing an existing one', () => { expect(formatSystemPromptSnapshot('prompt')).toBe('prompt\n') expect(formatSystemPromptSnapshot('prompt\n')).toBe('prompt\n') }) - it('renders readable system-prompt delta sections', () => { - expect(formatSystemPromptSnapshot('prompt', [ - { keepStart: 1, keepEnd: 0, insert: ['new', 'lines'] }, - ])).toBe('prompt\n\n\n\nnew\nlines\n') + it('renders readable changed-prompt sections', () => { + expect(formatSystemPromptSnapshot('prompt', ['new\nlines'])) + .toBe('prompt\n\n\n\nnew\nlines\n') }) - it('does not double the newline of a delta insert with a trailing blank line', () => { - expect(formatSystemPromptSnapshot('prompt\n', [ - { keepStart: 2, keepEnd: 1, insert: ['tail', ''] }, - ])).toBe('prompt\n\n\n\ntail\n') + it('does not double the newline of a changed prompt', () => { + expect(formatSystemPromptSnapshot('prompt\n', ['changed\n'])) + .toBe('prompt\n\n\n\nchanged\n') }) }) -describe('headerDeltaCount', () => { - it('counts request/header-delta events, ignoring blanks and other lines', () => { - const delta = JSON.stringify({ type: 'request/header-delta', seq: 2, time: 9, data: {} }) - const other = JSON.stringify({ type: 'request/header', seq: 0, time: 9, data: {} }) - expect(headerDeltaCount(`${other}\n\n${delta}\n${delta}\n`)).toBe(2) - expect(headerDeltaCount(`${other}\n`)).toBe(0) +describe('headerChangeCount', () => { + it('counts changed request headers, ignoring anchors, blanks, and other lines', () => { + const change = JSON.stringify({ type: 'request/header', seq: 2, time: 9, data: { reason: 'change' } }) + const anchor = JSON.stringify({ type: 'request/header', seq: 0, time: 9, data: { reason: 'initial' } }) + const other = JSON.stringify({ type: 'turn/start', seq: 1, time: 9, data: {} }) + expect(headerChangeCount(`${anchor}\n${other}\n\n${change}\n${change}\n`)).toBe(2) + expect(headerChangeCount(`${anchor}\n`)).toBe(0) }) }) diff --git a/packages/support/invariants/README.md b/packages/support/invariants/README.md index c4b909773d..849a741274 100644 --- a/packages/support/invariants/README.md +++ b/packages/support/invariants/README.md @@ -39,7 +39,7 @@ Agent status (per agent): Model requests (on `llm/stream`): -- **a loop-built request is exactly what the log reconstructs** — a frozen request with a live `sessionId` (the loop-built marker; hand-built one-shots like compaction's summarize are unfrozen and skipped) must carry frozen `messages` deep-equal to the derivation over the log prefix strictly before the in-flight step's `step/start` (rebuilt through a FRESH `Session`, so the live cache cannot vouch for itself — and boundary-correct: content logged after `step/start` legitimately belongs to the next request), and every non-content field must equal the fold of the log's `request/header*` events (see [the reconstructability RFC](../../../docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md)). Registered with `prepend: true` so a short-circuiting `llm/stream` listener (the replay adapter) cannot silence it; prepend orders it against append-registered listeners only — correctness rests on the seq-bounded rebuild, never listener timing. +- **a loop-built request is exactly what the log reconstructs** — a frozen request with a live `sessionId` (the loop-built marker; hand-built one-shots like compaction's summarize are unfrozen and skipped) must carry frozen `messages` deep-equal to the derivation over the log prefix strictly before the in-flight step's `step/start` (rebuilt through a FRESH `Session`, so the live cache cannot vouch for itself — and boundary-correct: content logged after `step/start` legitimately belongs to the next request), and every non-content field must equal the latest logged `request/header` (see [the reconstructability RFC](../../../docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md)). Registered with `prepend: true` so a short-circuiting `llm/stream` listener (the replay adapter) cannot silence it; prepend orders it against append-registered listeners only — correctness rests on the seq-bounded rebuild, never listener timing. On any violation it throws `InvariantError` (`code: 'INVARIANT'`). diff --git a/packages/support/invariants/src/index.ts b/packages/support/invariants/src/index.ts index f5ef6d2b4a..8dcf901d32 100644 --- a/packages/support/invariants/src/index.ts +++ b/packages/support/invariants/src/index.ts @@ -60,8 +60,8 @@ interface SessionTrace { /** Every seq seen so far — validates `sourceEventSeqs` references. */ knownSeqs: Set /** - * The seqs currently on the surface linked list, in linked-list order - * (head to tail). A replace reorders this relative to seq order (the new + * The seqs currently on the surface, in derived-message order. A replace + * reorders this relative to seq order (the new * node takes the replaced range's position), so range validation is * positional, not by seq comparison. */ @@ -154,7 +154,7 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr } } } - // Fold this event into the tracked surface linked list, validating the + // Fold this event into the tracked surface order, validating the // replace contract as we go. `append` adds a tail node; `replace` shadows a // positional range — every shadowed node must appear in sourceEventSeqs. if (se.surfaceOp !== undefined) { @@ -497,7 +497,7 @@ export function apply(ctx: Context): void { // the boundary (an `agent/request`-window inject) is legitimately absent // from this request, and a current-surface comparison would false-fire. // - header: every non-content field must equal the fold of the log's - // `request/header*` events — the loop logs the header event BEFORE + // `request/header` events — the loop logs the header event BEFORE // dispatch, so the fold already covers this request. // // Registered with `prepend: true` so a short-circuiting llm/stream listener diff --git a/packages/support/invariants/tests/invariants.spec.ts b/packages/support/invariants/tests/invariants.spec.ts index 5c26b1f4d7..365a59fed7 100644 --- a/packages/support/invariants/tests/invariants.spec.ts +++ b/packages/support/invariants/tests/invariants.spec.ts @@ -635,7 +635,7 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2 session.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 3 // Replace node 2 (position 0) with seq 4 — surface is now [4, 3], so seq 4 - // precedes seq 3 in linked-list order even though 4 > 3 numerically. + // precedes seq 3 in surface order even though 4 > 3 numerically. session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [2] }) // seq 4 // A replace with start=3, end=4 passes the seq check (3 <= 4) but is // reversed positionally (3 is at pos 1, 4 is at pos 0). @@ -745,7 +745,7 @@ describe('request-reconstruction cross-check (llm/stream)', () => { it('expects the folded header\'s session prefix ahead of the derivation (prefix + derived)', async () => { const { ctx, session, boundary } = await requestSetup() const prefix = { role: 'user' as const, content: [{ type: 'text' as const, text: 'catalog' }] } - session.append('request/header-delta', { messagePrefix: [prefix] }) + session.append('request/header', { header: { config: { model: 'm' }, messagePrefix: [prefix] }, reason: 'change' }) // The prefixed request matches the fold… const prefixed = Object.freeze({ model: 'm', messages: Object.freeze([prefix, ...boundary]), sessionId: session.id }) expect(() => { dispatch(ctx, prefixed) }).not.toThrow() diff --git a/packages/ui/user-approval/README.md b/packages/ui/user-approval/README.md index a50bffad0b..32d7f31ab5 100644 --- a/packages/ui/user-approval/README.md +++ b/packages/ui/user-approval/README.md @@ -6,7 +6,7 @@ The contract in one line: `ctx.approval.request(req)` puts exactly one question The service is the mechanism, answerers are the policy. Answerers are `approval/request` waterfall listeners occupying a single decision slot: answer for an agent you own by returning an outcome without calling `next()`, or delegate an agent you don't recognize by calling `next()` — the chain's built-in default is `unavailable`, so a deployment with no answerer (headless, CI) fails closed with zero configuration. Dispatch is keyed by `req.agent`: a listener registered through `agent.ctx` receives only that agent's questions, while a plain-context listener receives every agent's. Registration order across sibling plugins is not load-order deterministic; compose one terminal answerer per deployment and use `prepend` listeners only for decide-or-delegate gates. -The seam also owns the per-session POLICY tier ([the sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)): `ApprovalPolicy` is `'ask'` (delegate to the answerers) or `'never'` (deterministically reject without prompting anyone; the strict CI/unattended stance), with `effective = fold(the session's 'approval/policy' events, last one wins) ?? Config.policy` — the session log is the store, written only through `setApprovalPolicy(session, policy)`, which rejects any value outside that closed vocabulary before appending. The service decides `'never'` inside `request()` itself, before dispatching the waterfall (`'never'` → `'rejected'` with the audit pair still landing; no listener registration, including a later `prepend`, can precede it), states `'never'` — and only `'never'` in prose — in a per-agent prompt section, records either value with a source-owned header marker, and narrates a policy switch to the model in at most one coalesced `agent/pre-step` notice. The restart fallback reads the marker rather than deployment-controlled persona prose; attribution is positional (an override event after the last `request/header*` reads `changed by the user`, otherwise `changed by the operator/config`). +The seam also owns the per-session POLICY tier ([the sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)): `ApprovalPolicy` is `'ask'` (delegate to the answerers) or `'never'` (deterministically reject without prompting anyone; the strict CI/unattended stance), with `effective = fold(the session's 'approval/policy' events, last one wins) ?? Config.policy` — the session log is the store, written only through `setApprovalPolicy(session, policy)`, which rejects any value outside that closed vocabulary before appending. The service decides `'never'` inside `request()` itself, before dispatching the waterfall (`'never'` → `'rejected'` with the audit pair still landing; no listener registration, including a later `prepend`, can precede it), states `'never'` — and only `'never'` in prose — in a per-agent prompt section, records either value with a source-owned header marker, and narrates a policy switch to the model in at most one coalesced `agent/pre-step` notice. The restart fallback reads the marker rather than deployment-controlled persona prose; attribution is positional (an override event after the last `request/header` reads `changed by the user`, otherwise `changed by the operator/config`). One seam serves both ask paths of [the sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md): the `tools/pre-execute` `ask` decision (routed by [`@deepseek-ai/dsh-tools`](../../core/tools/) when this service is mounted; degrading to deny when it is not), and the sandbox post-denial escalated retry (the bash tool's `sandbox_permissions` gate in [`@deepseek-ai/dsh-tool-bash`](../../bash/tool-bash/) — [the sandbox RFC § Escalation](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)). The full design: [the approval-seam RFC](../../../docs/rfc/implemented/feature/2026-07-06-approval-seam.md). diff --git a/packages/ui/user-approval/src/index.ts b/packages/ui/user-approval/src/index.ts index 6b3ef962bb..45d7fa91aa 100644 --- a/packages/ui/user-approval/src/index.ts +++ b/packages/ui/user-approval/src/index.ts @@ -102,7 +102,7 @@ declare module '@deepseek-ai/dsh-session' { * from the prompt section and the narrator's notices). The LAST such * event is the session's override ({@link effectiveApprovalPolicy}); * who asked for it is derivable from position (an event after the log's - * last `request/header*` was a runtime switch by the user). + * last `request/header` was a runtime switch by the user). */ 'approval/policy': { policy: ApprovalPolicy } } @@ -328,7 +328,7 @@ export class ApprovalService extends Service { // narrated no later than the next step. What each session was last told // is in-memory with a log-derived fallback (the folded header's system // text), so restarts lose nothing. Attribution is positional: an - // override event after the log's last `request/header*` was a runtime + // override event after the log's last `request/header` was a runtime // switch by the user; otherwise the configured default moved under the // session (operator/config). const narrated = new WeakMap() @@ -341,7 +341,7 @@ export class ApprovalService extends Service { const event = events[index] as (typeof events)[number] if (overrideIndex < 0 && event.type === 'approval/policy') { overrideIndex = index - } else if (headerIndex < 0 && (event.type === 'request/header' || event.type === 'request/header-delta')) { + } else if (headerIndex < 0 && event.type === 'request/header') { headerIndex = index } } diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index 9e7dfe44bd..02e0199fbb 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -165,7 +165,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ await ctx.plugin(ToolCordis) }, note: - 'Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; the request-header ToolsDelta logs those tool-set changes.', + 'Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; a full changed request header logs those tool-set changes.', }, { pkg: '@deepseek-ai/dsh-tool-fs', diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index a219ea1b1d..874f0754a6 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -39,7 +39,6 @@ { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceEventType", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceOp", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceIntent", "source": "packages/core/session/src/types.ts" }, - { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceNode", "source": "packages/core/session/src/surface.ts" }, { "doc": "docs/core-data-structures/persistence.md", "symbol": "SessionHeader", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/persistence.md", "symbol": "CreateSessionOptions", "source": "packages/core/session/src/types.ts" }, From e481288a3a5fdf05f4bcc491dc120820975710d3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 00:04:11 +0800 Subject: [PATCH 024/359] refactor: derive snapshot session fixtures from disk --- .../2026-07-08-shared-acp-snapshot-package.md | 2 +- .../2026-06-20-discover-package-inventory.md | 5 +- examples/acp-agent/tests/acp.snapshot.ts | 10 +-- packages/support/acp-snapshot/README.md | 2 +- packages/support/acp-snapshot/src/suite.ts | 68 +++++++++++-------- .../support/acp-snapshot/tests/suite.spec.ts | 44 +++++++++--- 6 files changed, 85 insertions(+), 46 deletions(-) diff --git a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md b/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md index c622a7f1be..eca3661b33 100644 --- a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md +++ b/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md @@ -16,7 +16,7 @@ The machinery lives in [`packages/support/acp-snapshot`](../../../../packages/su **`src/normalize.ts`** — the pure normalizers, hook-free by policy: when a future event carries a new volatile field (an approval duration, say), the shared normalizer learns it in the same change, keeping one home for what "normalized" means rather than per-suite scrub extensions. -**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record/refresh fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL a `scrubSystemPrompts` fixed point, non-pinning fixtures also `scrubRequestHeaders` fixed points). The pinned-header contract ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each header class flags exactly one `pinsHeader` scenario, whose `system-prompt.golden.md` and JSONL tool list split the composed header into reviewable artifacts; the uniformity guard compares both against every live header in that class. A pinning scenario declares any legitimate changed-header count, and its Markdown artifact records every full changed prompt. The pure helpers (`childFixturePaths`, `fixtureContext`, `normalizedHeaders`, `normalizedSystemPrompts`, `formatSystemPromptSnapshot`, `headerChangeCount`) are exported from the module for direct unit coverage. +**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record/refresh fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL a `scrubSystemPrompts` fixed point, non-pinning fixtures also `scrubRequestHeaders` fixed points). A scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are its ordered primary/child inventory, so the scenario table declares policy without duplicating a child count. The pinned-header contract ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each header class flags exactly one `pinsHeader` scenario, whose `system-prompt.golden.md` and JSONL tool list split the composed header into reviewable artifacts; the uniformity guard compares both against every live header in that class. A pinning scenario declares any legitimate changed-header count, and its Markdown artifact records every full changed prompt. The pure helpers (`sessionFixtureNames`, `fixtureContext`, `normalizedHeaders`, `normalizedSystemPrompts`, `formatSystemPromptSnapshot`, `headerChangeCount`) are exported from the module for direct unit coverage. ## Alternatives considered diff --git a/docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md b/docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md index 3587393efe..a091203da9 100644 --- a/docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md +++ b/docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md @@ -4,7 +4,7 @@ Status: proposed ## Problem -Package and gate inventories are repeated by hand. The [package cookbook](../../../cookbook/adding-a-package.md) tells authors to update several files. The [package README](../../../../packages/README.md) carries a hand-written dependency graph. [CI](../../../../.github/workflows/ci.yml) and [development docs](../../../development.md) can drift from the actual `doc-sync` subcommands when new gates are added. `tsconfig.build.json` and the root `tsconfig.json` each hand-list every package as explicit project `references` — two identical sets that grow in lockstep, so a single generator can emit both — and `tsconfig.base.json`'s paths map hand-lists the per-group glob fan-out. `knip.json` restates a per-package `entry` stanza for each package that gains an `*.e2e.ts` suite — byte-identical overrides that exist only because the shared `packages/*/*` stanza omits the e2e glob (an entry glob matching no files is inert, so the default stanza could carry it for every package). The ACP snapshot suite's scenario table (`examples/acp-agent/tests/acp.snapshot.ts`) hand-maintains a `childSessions` count per scenario that duplicates the number of `session..jsonl` fixture siblings on disk. These lists are small today, but every new package or scenario class creates another manual synchronization point. +Package and gate inventories are repeated by hand. The [package cookbook](../../../cookbook/adding-a-package.md) tells authors to update several files. The [package README](../../../../packages/README.md) carries a hand-written dependency graph. [CI](../../../../.github/workflows/ci.yml) and [development docs](../../../development.md) can drift from the actual `doc-sync` subcommands when new gates are added. `tsconfig.build.json` and the root `tsconfig.json` each hand-list every package as explicit project `references` — two identical sets that grow in lockstep, so a single generator can emit both — and `tsconfig.base.json`'s paths map hand-lists the per-group glob fan-out. `knip.json` restates a per-package `entry` stanza for each package that gains an `*.e2e.ts` suite — byte-identical overrides that exist only because the shared `packages/*/*` stanza omits the e2e glob (an entry glob matching no files is inert, so the default stanza could carry it for every package). These lists are small today, but every new package creates another manual synchronization point. The [package hierarchy](../../implemented/architecture/2026-06-20-package-hierarchy.md) already removed several of these by hand: `scripts/publint-all.ts` now derives its list from the `packages//` layout, and the two `tsconfig` `paths` maps collapsed to one `@deepseek-ai/dsh-*` wildcard. What remains is the inventory that cannot be globbed away — chiefly `tsconfig.build.json`'s project `references`, which TypeScript requires as an explicit array (no wildcard form). @@ -16,7 +16,7 @@ Make the remaining package/gate inventories discoverable. A single canonical sou The hierarchy does not need to encode every fact about a package, but it should encode the broad maintenance policy: core/product packages, integrations, capability seams, and support/test/example packages should not all require a hand-maintained exception list before scripts can tell them apart. -Two of the cataloged items need no generator at all: folding the e2e entry glob into knip's default stanza deletes the per-package restatements outright, and `childSessions` can be discovered from each scenario's fixture directory, leaving the scenario table to declare only policy (`recorded`, `hasModelTurn`, `comparesLog`) — and even those track fixture-derivable facts today (`comparesLog` ⟺ the committed log has entries beyond its header line; `recorded` ⟺ `hasModelTurn` with no `replay.override.json` sibling), so each new scenario class keeps adding knobs the fixture directory already answers. +One cataloged item needs no generator at all: folding the e2e entry glob into knip's default stanza deletes the per-package restatements outright. ## Acceptance criteria @@ -25,7 +25,6 @@ Two of the cataloged items need no generator at all: folding the e2e entry glob - Docs describe the source of truth rather than repeating generated inventories. - CI invokes the aggregate commands and lets those commands own their sub-gate lists. - `knip.json` carries a per-package override only where it encodes real information (an extra entry file, an ignored dependency), never a restatement of the default stanza. -- Snapshot scenarios declare policy, not facts discoverable from their fixture directories. ## Risks diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index eaa4e0381a..b1a43b83db 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -67,14 +67,14 @@ const SCENARIOS: Scenario[] = [ // tiers (gentle at 3, detailed at 5) as context/message in transcript and log. { name: 'repeat-tool-guard', hasModelTurn: true, recorded: false }, { name: 'cancel', hasModelTurn: true, recorded: false, overridden: true }, - { name: 'subagent-spawn', hasModelTurn: true, recorded: true, childSessions: 1 }, - { name: 'subagent-multi', hasModelTurn: true, recorded: true, childSessions: 2 }, - { name: 'subagent-fork', hasModelTurn: true, recorded: true, childSessions: 1 }, - { name: 'subagent-mixed', hasModelTurn: true, recorded: true, childSessions: 2 }, + { name: 'subagent-spawn', hasModelTurn: true, recorded: true }, + { name: 'subagent-multi', hasModelTurn: true, recorded: true }, + { name: 'subagent-fork', hasModelTurn: true, recorded: true }, + { name: 'subagent-mixed', hasModelTurn: true, recorded: true }, // The workflow tool: the model writes a one-child orchestration script; the // child runs as a spawn subagent under the worker-thread engine (its session is the // child fixture), and the tool result carries the script's return value. - { name: 'workflow-run', hasModelTurn: true, recorded: true, childSessions: 1 }, + { name: 'workflow-run', hasModelTurn: true, recorded: true }, // Hook matrix — one scenario per hook point × its headline Decision outcome, // across BOTH bridges (Claude `hooks.json`, Codex `codex-hooks.json`, seeded in // workspace/). The block scenarios need no model call: a UserPromptSubmit hook diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 13dd1ab247..ac9c0ceee3 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -6,7 +6,7 @@ Three layers, importable separately: - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). -- **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Must be called at vitest collection time. +- **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. A consuming `*.snapshot.ts` is the scenario table plus one factory call: diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts index 523092bf09..6311a15031 100644 --- a/packages/support/acp-snapshot/src/suite.ts +++ b/packages/support/acp-snapshot/src/suite.ts @@ -80,14 +80,6 @@ export interface Scenario { * false (replay derives from the fixture's `assistant/chunk` events). */ overridden?: boolean - /** - * How many SUBAGENT child sessions this scenario records beyond the top-level - * one (0 for a single-session scenario). Each child rides in a sibling fixture - * `session..jsonl` (1-based); replay forwards them to `dsh-llm-replay` so - * each child session replays from its own script, and record mode writes the - * harvested child logs back to those files. Defaults to 0. - */ - childSessions?: number /** * Whether THIS scenario pins its header class's model-facing request-header * content. Its actual composed prompt is maintained as a readable @@ -150,14 +142,40 @@ export interface SnapshotSuiteOptions { } /** - * The sibling child-fixture paths for a scenario (`session.1.jsonl` …). + * Validate and order a scenario directory's session-fixture filenames. * - * @param dir The scenario's snapshots directory (`/`). - * @param childSessions How many subagent child sessions the scenario records. - * @returns One path per child, 1-based, in fixture order. + * The primary fixture is always `session.jsonl`; child sessions are discovered + * from contiguous `session.1.jsonl` … filenames. The directory is the source of + * truth, so scenario tables do not duplicate a child count that can drift from + * the files. A session-like JSONL with any other suffix fails loud. + * + * @param names File names in one scenario directory. + * @returns The primary and child fixture names in replay/harvest order. */ -export function childFixturePaths(dir: string, childSessions: number): string[] { - return Array.from({ length: childSessions }, (_, i) => join(dir, `session.${i + 1}.jsonl`)) +export function sessionFixtureNames(names: readonly string[]): string[] { + if (!names.includes('session.jsonl')) throw new Error('missing session.jsonl') + const children: { name: string; index: number }[] = [] + for (const name of names) { + if (name === 'session.jsonl') continue + if (!name.startsWith('session.') || !name.endsWith('.jsonl')) continue + const match = /^session\.([1-9]\d*)\.jsonl$/.exec(name) + if (match === null) throw new Error(`invalid child session fixture name: ${name}`) + children.push({ name, index: Number(match[1]) }) + } + children.sort((a, b) => a.index - b.index) + for (const [offset, child] of children.entries()) { + const expected = offset + 1 + if (child.index !== expected) { + throw new Error(`child session fixtures must be contiguous: expected session.${expected}.jsonl, found ${child.name}`) + } + } + return ['session.jsonl', ...children.map(child => child.name)] +} + +/** Read one scenario directory's validated session-fixture inventory. */ +async function sessionFixtures(dir: string): Promise { + const entries = await readdir(dir, { withFileTypes: true }) + return sessionFixtureNames(entries.filter(entry => entry.isFile()).map(entry => entry.name)) } /** @@ -392,7 +410,9 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { const input = JSON.parse(await readFile(join(dir, 'input.json'), 'utf8')) as InputScript const overrideFile = join(dir, 'replay.override.json') const workspaceDir = join(dir, 'workspace') - const childSessions = scenario.childSessions ?? 0 + const fixtureFiles = await sessionFixtures(dir) + const childFixtureFiles = fixtureFiles.slice(1) + const childSessions = childFixtureFiles.length const comparesLog = scenario.comparesLog ?? scenario.hasModelTurn const result = await runScenario(input, { agent, @@ -401,7 +421,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { ...existsSync(overrideFile) ? { overrideFile } : {}, // In REPLAY, forward the recorded child fixtures so each subagent session // replays from its own script. In RECORD they are harvested, not read. - ...!RECORDING && childSessions > 0 ? { childFiles: childFixturePaths(dir, childSessions) } : {}, + ...!RECORDING && childSessions > 0 ? { childFiles: childFixtureFiles.map(file => join(dir, file)) } : {}, ...existsSync(workspaceDir) ? { workspaceDir } : {}, // A scenario booting an overlay tree passes its own live config; the // bin's replay swap derives the sibling `*cordis.snapshot.yml` from it. @@ -432,7 +452,6 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { const scrub = scenario.pinsHeader === true ? scrubSystemPrompts : scrubRequestHeaders - const fixtureFiles = ['session.jsonl', ...Array.from({ length: childSessions }, (_, i) => `session.${i + 1}.jsonl`)] const existingFixtures = REFRESHING ? await Promise.all(fixtureFiles.map(file => readFile(join(dir, file), 'utf8'))) : [] @@ -543,7 +562,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { expect(onDisk).toEqual(registered) }) - it('every registered scenario has its required fixture files', () => { + it('every registered scenario has its required fixture files', async () => { // Every scenario has an input script and an stdout golden. EVERY scenario // also needs `session.jsonl`: the suite boots `llm-replay` with that path // as the replay source for ALL scenarios (the factory passes @@ -556,7 +575,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { // `overridden` flag: required when set, forbidden when not — the harness // forwards the file purely on existence, so an unregistered stray sidecar // would silently replace the derived script. - for (const { name, overridden, childSessions, pinsHeader } of scenarios) { + for (const { name, overridden, pinsHeader } of scenarios) { const dir = join(snapshotsDir, name) expect(existsSync(join(dir, 'input.json')), `${name}/input.json`).toBe(true) expect(existsSync(join(dir, 'stdout.golden.jsonl')), `${name}/stdout.golden.jsonl`).toBe(true) @@ -565,11 +584,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { .toBe(overridden === true) expect(existsSync(join(dir, SYSTEM_PROMPT_SNAPSHOT)), `${name}/${SYSTEM_PROMPT_SNAPSHOT} presence must match \`pinsHeader\``) .toBe(pinsHeader === true) - // A nested-agent scenario ships one child fixture per recorded subagent - // session (`session.1.jsonl` …), the replay source for that child session. - for (const childFixture of childFixturePaths(dir, childSessions ?? 0)) { - expect(existsSync(childFixture), childFixture).toBe(true) - } + await expect(sessionFixtures(dir), `${name}: session fixture inventory`).resolves.toBeDefined() } }) @@ -615,10 +630,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { // all header bulk. Fixed-point checks make both storage rules fail loud. for (const scenario of scenarios) { const dir = join(snapshotsDir, scenario.name) - const files = [ - 'session.jsonl', - ...Array.from({ length: scenario.childSessions ?? 0 }, (_, i) => `session.${i + 1}.jsonl`), - ] + const files = await sessionFixtures(dir) for (const file of files) { const fixture = await readFile(join(dir, file), 'utf8') expect(scrubSystemPrompts(fixture), `${scenario.name}/${file} carries an unscrubbed system prompt`) diff --git a/packages/support/acp-snapshot/tests/suite.spec.ts b/packages/support/acp-snapshot/tests/suite.spec.ts index 4ca9c8573d..f27f36c564 100644 --- a/packages/support/acp-snapshot/tests/suite.spec.ts +++ b/packages/support/acp-snapshot/tests/suite.spec.ts @@ -6,13 +6,13 @@ import { fileURLToPath } from 'node:url' import { afterAll, describe, expect, it } from 'vitest' import { defineAcpSnapshotSuite, type HarvestedLog, type Scenario } from '../src/index.ts' import { - childFixturePaths, fixtureContext, formatSystemPromptSnapshot, headerChangeCount, normalizedHeaders, normalizedSystemPrompts, refreshFixtureReplacements, + sessionFixtureNames, stabilizeRefreshLog, } from '../src/suite.ts' @@ -51,7 +51,7 @@ const RECORD_SRC = fileURLToPath(new URL('./fixtures/record-suite', import.meta. // example's code-mode scenarios). const REPLAY_SCENARIOS: Scenario[] = [ { name: 'pin-turn', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderChanges: 1, headerClass: 'main' }, - { name: 'plain-turn', hasModelTurn: true, recorded: true, childSessions: 1, headerClass: 'main', configPath: AGENT.configPath }, + { name: 'plain-turn', hasModelTurn: true, recorded: true, headerClass: 'main', configPath: AGENT.configPath }, { name: 'no-model', hasModelTurn: false, recorded: false, headerClass: 'main' }, { name: 'blocked-log', hasModelTurn: false, comparesLog: true, recorded: false, headerClass: 'main' }, { name: 'authored-error', hasModelTurn: true, recorded: false, overridden: true, headerClass: 'main' }, @@ -59,7 +59,7 @@ const REPLAY_SCENARIOS: Scenario[] = [ const RECORD_SCENARIOS: Scenario[] = [ { name: 'rec-pin', hasModelTurn: true, recorded: true, pinsHeader: true }, - { name: 'rec-child', hasModelTurn: true, recorded: true, childSessions: 1 }, + { name: 'rec-child', hasModelTurn: true, recorded: true }, // recorded:false in record mode → registered but skipped (never re-recorded). { name: 'rec-skip', hasModelTurn: true, recorded: false, overridden: true }, ] @@ -180,13 +180,41 @@ describe('defineAcpSnapshotSuite: registration contract', () => { }) }) -describe('childFixturePaths', () => { - it('yields one sibling path per child, 1-based', () => { - expect(childFixturePaths('/snap/s', 2)).toEqual(['/snap/s/session.1.jsonl', '/snap/s/session.2.jsonl']) +describe('sessionFixtureNames', () => { + it('orders the primary and contiguous child fixtures while ignoring other files', () => { + expect(sessionFixtureNames([ + 'stdout.golden.jsonl', + 'session.2.jsonl', + 'session.jsonl', + 'session.1.jsonl', + 'input.json', + ])).toEqual(['session.jsonl', 'session.1.jsonl', 'session.2.jsonl']) }) - it('yields nothing for a single-session scenario', () => { - expect(childFixturePaths('/snap/s', 0)).toEqual([]) + it('accepts a primary-only scenario', () => { + expect(sessionFixtureNames(['session.jsonl'])).toEqual(['session.jsonl']) + }) + + it('rejects a directory without the primary fixture', () => { + expect(() => sessionFixtureNames(['session.1.jsonl'])).toThrow('missing session.jsonl') + }) + + it('rejects gapped child fixtures', () => { + expect(() => sessionFixtureNames(['session.jsonl', 'session.2.jsonl'])) + .toThrow('expected session.1.jsonl, found session.2.jsonl') + }) + + it.each(['session.0.jsonl', 'session.child.jsonl', 'session.01.jsonl'])( + 'rejects invalid child fixture name %s', + (name) => { + expect(() => sessionFixtureNames(['session.jsonl', name])) + .toThrow(`invalid child session fixture name: ${name}`) + }, + ) + + it('rejects duplicate child indexes', () => { + expect(() => sessionFixtureNames(['session.jsonl', 'session.1.jsonl', 'session.1.jsonl'])) + .toThrow('expected session.2.jsonl, found session.1.jsonl') }) }) From 0e7d539bbc5b75ad224b312a11cc1e15e1ba527a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 00:18:00 +0800 Subject: [PATCH 025/359] refactor: share the ACP test launcher --- .../2026-07-08-shared-acp-snapshot-package.md | 10 +- examples/acp-agent/tests/acp.e2e.ts | 182 +++--------------- examples/acp-agent/tests/hooks.e2e.ts | 68 ++----- .../sandbox-acp-agent/tests/escalation.e2e.ts | 79 +++----- packages/support/README.md | 4 +- packages/support/acp-snapshot/README.md | 5 +- packages/support/acp-snapshot/package.json | 2 +- packages/support/acp-snapshot/src/harness.ts | 130 ++----------- packages/support/acp-snapshot/src/index.ts | 24 ++- packages/support/acp-snapshot/src/launcher.ts | 152 +++++++++++++++ .../acp-snapshot/tests/harness.spec.ts | 33 ++++ 11 files changed, 292 insertions(+), 397 deletions(-) create mode 100644 packages/support/acp-snapshot/src/launcher.ts diff --git a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md b/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md index eca3661b33..59734535b8 100644 --- a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md +++ b/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md @@ -6,13 +6,15 @@ Status: implemented The ACP snapshot tier ([snapshot RFC](2026-06-19-acp-snapshot-tests.md)) was built from three modules living inside one example's test directory: `snapshot-harness.ts` (boot the real bin subprocess, drive it over ACP JSON-RPC, harvest the persisted logs), `snapshot-normalize.ts` (the pure golden normalizers), and the ~150-line scenario body plus fixture guards in `acp.snapshot.ts` (record/replay modes, the stdout-golden and log compares, the pinned-header uniformity guard, the orphan/required-file/single-pin meta-tests). -A second ACP example wanting snapshot coverage — the sandbox/approval composition is the immediate consumer — could only copy those modules, forking exactly the logic that must not drift: record write-back, header scrubbing, child-session harvest ordering. The spawn/client glue was already triplicated across `acp.e2e.ts`, `hooks.e2e.ts`, and the harness (`TODO(acp-test-harness)`). Location also decided test rigor: the per-file 100% coverage gate measures `packages/*/*/src` only, so none of this machinery was measured — the same gap that had moved `dsh-llm-replay` out of `examples/` into [packages/support](../../../../packages/support/README.md). And the harness's ACP client hardcoded `requestPermission → cancelled`, so an approval round-trip — the headline behavior of the sandbox composition — could not be expressed at the snapshot tier at all. +A second ACP example wanting snapshot coverage — the sandbox/approval composition is the immediate consumer — could only copy those modules, forking exactly the logic that must not drift: record write-back, header scrubbing, child-session harvest ordering. The spawn/client glue was also triplicated across `acp.e2e.ts`, `hooks.e2e.ts`, and the harness. Location decided test rigor: the per-file 100% coverage gate measures `packages/*/*/src` only, so none of this machinery was measured — the same gap that had moved `dsh-llm-replay` out of `examples/` into [packages/support](../../../../packages/support/README.md). And the harness's ACP client hardcoded `requestPermission → cancelled`, so an approval round-trip — the headline behavior of the sandbox composition — could not be expressed at the snapshot tier at all. ## Decision The machinery lives in [`packages/support/acp-snapshot`](../../../../packages/support/acp-snapshot/README.md) (`@deepseek-ai/dsh-acp-snapshot`); an example's `*.snapshot.ts` is its scenario table, its agent paths, and one factory call, over its own `snapshots/` fixtures and `cordis.snapshot.yml` overlay ([single-source replay config](2026-07-04-single-source-acp-replay-config.md)). Reading `DSH_SNAPSHOT` stays at that edge — the library takes a resolved `mode`. -**`src/harness.ts`** — `runScenario` and the input-script/result types, parameterized by an `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath`; absolute paths the consuming suite resolves from its own `import.meta.url`). The client's `session/request_permission` handler consumes an optional `InputScript.permissionAnswers` FIFO queue, each entry selecting by option **kind** (ids are agent-issued randoms a committed script cannot know; kinds are the ACP-stable vocabulary, mapped to the offered `optionId` at answer time); an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run — the agent itself is answered `cancelled`, so the scenario bug fails the harness rather than being absorbed as an agent-side denial. This is what lets an approval suite drive allow/reject round-trips deterministically from `input.json`. +**`src/launcher.ts`** — `launchAcpTestAgent` owns the common unbuilt-process boundary: absolute tsx loader resolution, `TSX_TSCONFIG_PATH`, isolated harness homes, stdio wiring, a raw-byte stdout tee, stderr and update capture, fail-closed permission fallback, update waiters, and graceful or signalled shutdown. Snapshot scenarios and ordinary e2e suites supply the same `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath`); a test that plays a user supplies only its permission handler. The ACP and hook e2e suites plus the sandbox/approval e2e suite use this launcher instead of rebuilding the SDK client boundary. + +**`src/harness.ts`** — `runScenario` and the input-script/result types layer deterministic steps, temp workspaces, snapshot environment, and persisted-log harvest over the launcher. Its `session/request_permission` handler consumes an optional `InputScript.permissionAnswers` FIFO queue, each entry selecting by option **kind** (ids are agent-issued randoms a committed script cannot know; kinds are the ACP-stable vocabulary, mapped to the offered `optionId` at answer time); an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run — the agent itself is answered `cancelled`, so the scenario bug fails the harness rather than being absorbed as an agent-side denial. This is what lets an approval suite drive allow/reject round-trips deterministically from `input.json`. **`src/normalize.ts`** — the pure normalizers, hook-free by policy: when a future event carries a new volatile field (an approval duration, say), the shared normalizer learns it in the same change, keeping one home for what "normalized" means rather than per-suite scrub extensions. @@ -29,8 +31,8 @@ The machinery lives in [`packages/support/acp-snapshot`](../../../../packages/su ## Testing -Extraction parity was proven mechanically: after the move, `pnpm run test:snapshot` matched the base commit's result with zero byte changes under `examples/acp-agent/tests/snapshots/`. The package's `src/` holds per-file 100% statements/branches/functions/lines under the gating unit run, driven through the REAL spawn path by a scripted fake ACP bin (`tests/fixtures/fake-acp-agent.ts`, behavior scripted per scenario via a `behavior.json` beside the fixture): `harness.spec.ts` covers every step op, both expect-error arms, the permission queue (selection, fallback, impossible-click), env forwarding, workspace seeding, and the harvest ordering/noise/fallback branches; `suite.spec.ts` runs the factory for real at collection time — a replay suite over committed synthetic fixtures and a record suite over a temp copy (write-back never touches the committed tree; `ACP_SNAPSHOT_SPEC_BOOTSTRAP=1` re-bootstraps it) — plus direct cases for the pure helpers. Two structurally unreachable guards carry reasoned `v8 ignore` comments. The fake bin substitutes the `session/new` cwd, not `process.cwd()`, into scripted logs, matching what the real bin's header carries (darwin realpaths `/var/folders/…` to `/private/var/folders/…`). +Extraction parity was proven mechanically: after the move, `pnpm run test:snapshot` matched the base commit's result with zero byte changes under `examples/acp-agent/tests/snapshots/`. The package's `src/` holds per-file 100% statements/branches/functions/lines under the gating unit run, driven through the real launcher by a scripted fake ACP bin (`tests/fixtures/fake-acp-agent.ts`, behavior scripted per scenario via a `behavior.json` beside the fixture): `harness.spec.ts` directly covers launcher defaults, captures, update waiting, shutdown, and environment/config variants, then covers every scenario step op, both expect-error arms, the permission queue (selection, fallback, impossible-click), workspace seeding, and the harvest ordering/noise/fallback branches; `suite.spec.ts` runs the factory for real at collection time — a replay suite over committed synthetic fixtures and a record suite over a temp copy (write-back never touches the committed tree; `ACP_SNAPSHOT_SPEC_BOOTSTRAP=1` re-bootstraps it) — plus direct cases for the pure helpers. The fake bin substitutes the `session/new` cwd, not `process.cwd()`, into scripted logs, matching what the real bin's header carries (darwin realpaths `/var/folders/…` to `/private/var/folders/…`). ## Consequences -A new example gets the whole snapshot tier from a scenario table plus fixtures — the sandbox branch merges master down and adds its own suite (own pin scenario, own overlay, fixtures via `test:snapshot:record`, approvals via `permissionAnswers`). The costs: `suite.ts` imports vitest, so the package is importable only inside a vitest run — a shape no other package has, stated in its README; each suite pins its own ~8 KB header fixture (a genuinely distinct composition deserves its own pin; an identical one would be caught by that suite's uniformity guard); and the e2e launcher duplication remains (`TODO(acp-test-harness)`) — the harness is the extraction target when that migration lands. +A new example gets the whole snapshot tier from a scenario table plus fixtures, while an ordinary ACP e2e gets the same tested process/client boundary from one launcher call. The costs: `suite.ts` imports vitest, so the package entry is importable only inside a vitest run — a shape no other package has, stated in its README; and each suite pins its own ~8 KB header fixture (a genuinely distinct composition deserves its own pin; an identical one would be caught by that suite's uniformity guard). diff --git a/examples/acp-agent/tests/acp.e2e.ts b/examples/acp-agent/tests/acp.e2e.ts index 8ff012c2c3..4b6c675208 100644 --- a/examples/acp-agent/tests/acp.e2e.ts +++ b/examples/acp-agent/tests/acp.e2e.ts @@ -1,20 +1,14 @@ -import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process' -import { Readable, Writable } from 'node:stream' import { mkdtemp, rm, readFile } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' import { afterEach, describe, expect, it } from 'vitest' +import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { - ClientSideConnection, - ndJsonStream, - PROTOCOL_VERSION, - type Agent as AcpAgent, - type Client, - type RequestPermissionRequest, - type RequestPermissionResponse, - type SessionNotification, -} from '@agentclientprotocol/sdk' + launchAcpTestAgent, + type AgentUnderTest, + type LaunchedAcpTestAgent, +} from '@deepseek-ai/dsh-acp-snapshot' /** * End-to-end: boot examples/acp-agent as a real subprocess speaking ACP over @@ -26,127 +20,18 @@ import { * WITHOUT a key, since it only needs the server to boot and answer initialize. */ -// The dsh-acp-agent bin (the demo:acp entry) and this example's cordis.yml. The -// bin resolves its config-path arg from CWD; the subprocess runs from a temp -// workdir, so pass the example config's ABSOLUTE path. -const binScript = fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)) -const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) -// Resolve tsx's loader to an ABSOLUTE path: the subprocess runs with cwd set to -// a temp workdir (this test launches there and uses it as the session cwd; the -// bridge no longer requires cwd === the launch dir, but a temp dir keeps the -// test hermetic), where a bare `--import tsx` would not resolve from -// node_modules. import.meta.resolve gives the worktree's tsx regardless of cwd. -const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) -// Absolute path to the repo-root tsconfig. Dev/test/demo run UNBUILT: the -// `@deepseek-ai/dsh-*` workspace imports resolve through the `paths` map in the -// root tsconfig (tsx reads it), NOT through built `lib/` output. But tsx finds -// that tsconfig by searching UP from the child's cwd — and the child's cwd is a -// temp workdir OUTSIDE the repo, so the search misses and the dsh-* imports fail -// (the child dies before writing a byte). Point tsx at the repo tsconfig -// explicitly via TSX_TSCONFIG_PATH so resolution is cwd-independent. (Without -// this the suite only passed by accident when a stale built `lib/` happened to -// exist — exactly the contamination that masked the inject bug this suite now -// guards.) The repo root is four levels up from this file (examples/acp-agent/tests). -const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) - -interface Spawned { - child: ChildProcessWithoutNullStreams - client: ClientSideConnection - updates: SessionNotification['update'][] - stderr: string[] +const AGENT: AgentUnderTest = { + binScript: fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)), + configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)), + tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)), } -// TODO(acp-test-harness): this subprocess/client boot glue is duplicated with -// hooks.e2e.ts and partly with dsh-acp-snapshot's harness. Migrate both e2e -// files onto that launcher before the TSX/env/permission-stub details drift. -function spawnAcpAgent(cwd: string, env: NodeJS.ProcessEnv = process.env): Spawned { - const child = spawn( - process.execPath, - ['--import', tsxLoader, binScript, configPath], - { - cwd, - env: { - ...env, - TSX_TSCONFIG_PATH: repoTsconfig, - DSH_HOME: join(cwd, '.dsh'), - DSH_AGENTS_HOME: join(cwd, '.agents'), - }, - stdio: ['pipe', 'pipe', 'pipe'], - }, - ) - const stderr: string[] = [] - child.stderr.setEncoding('utf8') - child.stderr.on('data', (chunk: string) => stderr.push(chunk)) - - const updates: SessionNotification['update'][] = [] - const stream = ndJsonStream( - Writable.toWeb(child.stdin) as WritableStream, - Readable.toWeb(child.stdout) as ReadableStream, - ) - const makeClient = (_agent: AcpAgent): Client => ({ - sessionUpdate(params: SessionNotification): Promise { - updates.push(params.update) - return Promise.resolve() - }, - requestPermission(_params: RequestPermissionRequest): Promise { - // This example composes no ask-producing policy (no hooks), so the - // bridge never prompts here; answer cancelled (fail closed) if it ever - // does — an unexpected prompt must not grant anything. - return Promise.resolve({ outcome: { outcome: 'cancelled' } }) - }, - }) - const client = new ClientSideConnection(makeClient, stream) - return { child, client, updates, stderr } -} - -let spawned: Spawned | undefined +let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined -function hasStdoutLine(out: string[]): boolean { - return out.join('').split('\n').some(line => line.trim().length > 0) -} - -async function waitForStdoutLine(child: ChildProcessWithoutNullStreams, out: string[], stderr: string[], timeoutMs: number): Promise { - await new Promise((resolve, reject) => { - const cleanup = () => { - clearTimeout(timeout) - child.stdout.off('data', onData) - child.off('exit', onExit) - child.off('error', onError) - } - const pass = () => { - cleanup() - resolve() - } - const fail = (reason: string) => { - cleanup() - reject(new Error(`${reason}; stderr: ${stderr.join('')}`)) - } - const onData = () => { - if (hasStdoutLine(out)) pass() - } - const onExit = (code: number | null, signal: NodeJS.Signals | null) => { - fail(`ACP child exited before emitting a stdout frame (code ${code ?? 'null'}, signal ${signal ?? 'null'})`) - } - const onError = (error: Error) => { - fail(`ACP child failed before emitting a stdout frame: ${error.message}`) - } - const timeout = setTimeout(() => { - fail(`ACP child did not emit a stdout frame within ${timeoutMs}ms`) - }, timeoutMs) - - child.stdout.on('data', onData) - child.on('exit', onExit) - child.on('error', onError) - onData() - }) -} - afterEach(async () => { - if (spawned) { - spawned.child.kill('SIGKILL') - spawned = undefined - } + await spawned?.close('SIGKILL') + spawned = undefined if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) workdir = undefined }) @@ -154,39 +39,18 @@ afterEach(async () => { describe('acp-agent over real stdio (no key required)', () => { it('emits only framed JSON-RPC on stdout', async () => { workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-')) - // Collect raw stdout bytes directly (bypass the SDK framing) to inspect. + // Inspect the launcher's raw-byte tee in addition to driving its SDK client. // A dummy key lets the deepseek adapter APPLY (it only checks the key is // present at boot, not valid — the key is used only on a real model call, // which this purity test never triggers). So this runs WITHOUT real creds. - const child = spawn(process.execPath, ['--import', tsxLoader, binScript, configPath], { + spawned = launchAcpTestAgent({ + agent: AGENT, cwd: workdir, - env: { - ...process.env, - DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot', - TSX_TSCONFIG_PATH: repoTsconfig, - DSH_HOME: join(workdir, '.dsh'), - DSH_AGENTS_HOME: join(workdir, '.agents'), - }, - stdio: ['pipe', 'pipe', 'pipe'], + env: { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' }, }) - const out: string[] = [] - const stderr: string[] = [] - child.stdout.setEncoding('utf8') - child.stderr.setEncoding('utf8') - child.stdout.on('data', (c: string) => out.push(c)) - child.stderr.on('data', (c: string) => stderr.push(c)) + await spawned.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) - // Send a single initialize request as a newline-delimited JSON-RPC frame. - const req = JSON.stringify({ jsonrpc: '2.0', id: 1, method: 'initialize', params: { protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} } }) - child.stdin.write(req + '\n') - - try { - await waitForStdoutLine(child, out, stderr, 15_000) - } finally { - child.kill('SIGKILL') - } - - const lines = out.join('').split('\n').filter(l => l.trim().length > 0) + const lines = spawned.rawStdout().split('\n').filter(line => line.trim().length > 0) expect(lines.length).toBeGreaterThan(0) for (const line of lines) { // Every stdout line MUST parse as JSON (a JSON-RPC frame). A non-JSON @@ -210,7 +74,11 @@ describe('acp-agent over real stdio (no key required)', () => { workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-')) // A dummy key lets the deepseek adapter boot (it only checks presence, not // validity, at apply time); no model call is made, so the key is never used. - spawned = spawnAcpAgent(workdir, { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' }) + spawned = launchAcpTestAgent({ + agent: AGENT, + cwd: workdir, + env: { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' }, + }) const { client } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) @@ -223,7 +91,7 @@ describe('acp-agent over real stdio (no key required)', () => { describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: real prompt over ACP', () => { it('runs a real turn and the agent writes the requested file (verified on disk)', async () => { workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-')) - spawned = spawnAcpAgent(workdir) + spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir }) const { client, updates } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) @@ -264,7 +132,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: real prompt over it('with the terminal_output capability, a real bash call renders as a terminal card (content + _meta + exit)', async () => { workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-')) - spawned = spawnAcpAgent(workdir) + spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir }) const { client, updates } = spawned // Advertise the Zed `_meta.terminal_output` capability so the bridge emits diff --git a/examples/acp-agent/tests/hooks.e2e.ts b/examples/acp-agent/tests/hooks.e2e.ts index bdb800186a..a553addc96 100644 --- a/examples/acp-agent/tests/hooks.e2e.ts +++ b/examples/acp-agent/tests/hooks.e2e.ts @@ -1,20 +1,14 @@ -import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process' -import { Readable, Writable } from 'node:stream' import { mkdtemp, rm, writeFile, access } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' import { afterEach, describe, expect, it } from 'vitest' +import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { - ClientSideConnection, - ndJsonStream, - PROTOCOL_VERSION, - type Agent as AcpAgent, - type Client, - type RequestPermissionRequest, - type RequestPermissionResponse, - type SessionNotification, -} from '@agentclientprotocol/sdk' + launchAcpTestAgent, + type AgentUnderTest, + type LaunchedAcpTestAgent, +} from '@deepseek-ai/dsh-acp-snapshot' /** * With-key e2e: the Claude Code hook bridge running against the REAL acp-agent @@ -34,54 +28,18 @@ import { * only a real model deciding to call bash exercises the PreToolUse seam live. */ -const binScript = fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)) -const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) -const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) -const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) - -interface Spawned { - child: ChildProcessWithoutNullStreams - client: ClientSideConnection - updates: SessionNotification['update'][] - stderr: string[] +const AGENT: AgentUnderTest = { + binScript: fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)), + configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)), + tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)), } -function spawnAcpAgent(cwd: string): Spawned { - const child = spawn( - process.execPath, - ['--import', tsxLoader, binScript, configPath], - { cwd, env: { ...process.env, TSX_TSCONFIG_PATH: repoTsconfig }, stdio: ['pipe', 'pipe', 'pipe'] }, - ) - const stderr: string[] = [] - child.stderr.setEncoding('utf8') - child.stderr.on('data', (chunk: string) => stderr.push(chunk)) - - const updates: SessionNotification['update'][] = [] - const stream = ndJsonStream( - Writable.toWeb(child.stdin) as WritableStream, - Readable.toWeb(child.stdout) as ReadableStream, - ) - const makeClient = (_agent: AcpAgent): Client => ({ - sessionUpdate(params: SessionNotification): Promise { - updates.push(params.update) - return Promise.resolve() - }, - requestPermission(_params: RequestPermissionRequest): Promise { - return Promise.resolve({ outcome: { outcome: 'cancelled' } }) - }, - }) - const client = new ClientSideConnection(makeClient, stream) - return { child, client, updates, stderr } -} - -let spawned: Spawned | undefined +let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - if (spawned) { - spawned.child.kill('SIGKILL') - spawned = undefined - } + await spawned?.close('SIGKILL') + spawned = undefined if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) workdir = undefined }) @@ -96,7 +54,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: a PreToolUse hook hooks: { PreToolUse: [{ hooks: [{ type: 'command', command: 'echo "bash blocked by policy" >&2; exit 2' }] }] }, })) - spawned = spawnAcpAgent(workdir) + spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir }) const { client, updates } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) diff --git a/examples/sandbox-acp-agent/tests/escalation.e2e.ts b/examples/sandbox-acp-agent/tests/escalation.e2e.ts index 93915717a1..a7e8787e36 100644 --- a/examples/sandbox-acp-agent/tests/escalation.e2e.ts +++ b/examples/sandbox-acp-agent/tests/escalation.e2e.ts @@ -1,20 +1,18 @@ -import { spawn, spawnSync, type ChildProcessWithoutNullStreams } from 'node:child_process' -import { Readable, Writable } from 'node:stream' +import { spawnSync } from 'node:child_process' import { mkdtemp, readFile, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' import { afterEach, describe, expect, it } from 'vitest' import { - ClientSideConnection, - ndJsonStream, PROTOCOL_VERSION, - type Agent as AcpAgent, - type Client, type RequestPermissionRequest, - type RequestPermissionResponse, - type SessionNotification, } from '@agentclientprotocol/sdk' +import { + launchAcpTestAgent, + type AgentUnderTest, + type LaunchedAcpTestAgent, +} from '@deepseek-ai/dsh-acp-snapshot' /** * examples/sandbox-acp-agent end to end. @@ -35,12 +33,11 @@ import { * escalation target the model picks can land the write. */ -const binScript = fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)) -const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) -const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) -// The subprocess runs from a temp cwd OUTSIDE the repo; point tsx at the repo -// tsconfig so the unbuilt `paths` map resolves (see examples/AGENTS.md). -const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) +const AGENT: AgentUnderTest = { + binScript: fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)), + configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)), + tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)), +} // A usable confining runner, probed the same way the executor suites do: // bwrap on Linux, Seatbelt's sandbox-exec on macOS. Without one the strict @@ -56,44 +53,19 @@ const hasSeatbelt = process.platform === 'darwin' && spawnSync('sandbox-exec', [ }).status === 0 const hasRunner = hasBwrap || hasSeatbelt -interface Spawned { - child: ChildProcessWithoutNullStreams - client: ClientSideConnection - updates: SessionNotification['update'][] +interface Spawned extends LaunchedAcpTestAgent { permissionRequests: RequestPermissionRequest[] - stderr: string[] } /** Boot the example as an ACP subprocess; the scripted client answers every permission prompt with `answer`. */ -function spawnSandboxAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once'): Spawned { - const child = spawn( - process.execPath, - ['--import', tsxLoader, binScript, configPath], - { - cwd, - // A dummy key lets the deepseek adapter boot keyless (presence-checked at - // apply, used only on a real model call); the with-key tests carry the - // real key, so the fallback is inert there. - env: { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot', TSX_TSCONFIG_PATH: repoTsconfig }, - stdio: ['pipe', 'pipe', 'pipe'], - }, - ) - const stderr: string[] = [] - child.stderr.setEncoding('utf8') - child.stderr.on('data', (chunk: string) => stderr.push(chunk)) - - const updates: SessionNotification['update'][] = [] +function launchSandboxAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once'): Spawned { const permissionRequests: RequestPermissionRequest[] = [] - const stream = ndJsonStream( - Writable.toWeb(child.stdin) as WritableStream, - Readable.toWeb(child.stdout) as ReadableStream, - ) - const makeClient = (_agent: AcpAgent): Client => ({ - sessionUpdate(params: SessionNotification): Promise { - updates.push(params.update) - return Promise.resolve() - }, - requestPermission(params: RequestPermissionRequest): Promise { + const launched = launchAcpTestAgent({ + agent: AGENT, + cwd, + // A dummy key lets the adapter boot keylessly; live tests carry the real key. + env: { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' }, + requestPermission(params) { permissionRequests.push(params) const option = params.options.find(o => o.optionId === answer) // The scripted human: pick the requested option when the prompt offers @@ -102,15 +74,14 @@ function spawnSandboxAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once') return Promise.resolve({ outcome: { outcome: 'selected', optionId: option.optionId } }) }, }) - const client = new ClientSideConnection(makeClient, stream) - return { child, client, updates, permissionRequests, stderr } + return Object.assign(launched, { permissionRequests }) } let spawned: Spawned | undefined let workdir: string | undefined afterEach(async () => { - if (spawned !== undefined && spawned.child.exitCode === null) spawned.child.kill('SIGKILL') + await spawned?.close('SIGKILL') spawned = undefined if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) workdir = undefined @@ -119,7 +90,7 @@ afterEach(async () => { describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () => { it('boots the tree — sandbox executor + approval service + bridge — and opens a session', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-smoke-')) - spawned = spawnSandboxAcpAgent(workdir, 'reject-once') + spawned = launchSandboxAcpAgent(workdir, 'reject-once') const { client } = spawned // A dummy key boots the adapter; no prompt is ever sent, so no model call // and no sandbox runner probe happen. This drives the fiber tree the same @@ -132,7 +103,7 @@ describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () it('advertises both session config options and honors a switch end to end (no key, no model)', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-config-')) - spawned = spawnSandboxAcpAgent(workdir, 'reject-once') + spawned = launchSandboxAcpAgent(workdir, 'reject-once') const { client } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) // This tree composes bash-sandbox (mode: read-only) + approval → both @@ -164,7 +135,7 @@ describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () describe.skipIf(!process.env.DEEPSEEK_API_KEY || !hasRunner)('sandbox-acp-agent e2e: the live approval loop', () => { it('denial → model escalation → editor prompt → allow-once → the retried write lands on disk', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-e2e-')) - spawned = spawnSandboxAcpAgent(workdir, 'allow-once') + spawned = launchSandboxAcpAgent(workdir, 'allow-once') const { client, permissionRequests } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) @@ -193,7 +164,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || !hasRunner)('sandbox-acp-agent it('a rejected escalation stays denied: no write lands, the turn still ends', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-e2e-')) - spawned = spawnSandboxAcpAgent(workdir, 'reject-once') + spawned = launchSandboxAcpAgent(workdir, 'reject-once') const { client, permissionRequests } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) diff --git a/packages/support/README.md b/packages/support/README.md index c8883a89ff..9a05ad3c9a 100644 --- a/packages/support/README.md +++ b/packages/support/README.md @@ -4,9 +4,9 @@ Packages that exist to serve development, testing, and the examples rather than | Package | Role | ctx key | |---|---|---| -| `acp-snapshot/` | ACP snapshot suite kit: subprocess scenario harness + golden normalizers + the `defineAcpSnapshotSuite` factory | (library — imported by example `*.snapshot.ts` suites) | +| `acp-snapshot/` | ACP test kit: shared subprocess/client launcher + snapshot harness, normalizers, and suite factory | (library — imported by ACP e2e and `*.snapshot.ts` suites) | | `invariants/` | Dev-mode event-contract assertions | (listens on `session/*`, `agent/*`) | | `llm-replay/` | Record/replay adapter: short-circuits `llm/stream` from a recorded session JSONL (keyless snapshot tests) | (listens on `llm/stream`) | | `subagent-mock/` | Scripted `SubagentProvider` for deterministic seam/tool tests | (registers on `ctx.subagents`) | -`invariants` runs only in dev mode (contract checks, not runtime behavior). `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the snapshot tier's harness/normalizer/suite machinery so every example's suite is a scenario table over one shared, gate-covered implementation. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers. +`invariants` runs only in dev mode (contract checks, not runtime behavior). `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the ACP subprocess/client boundary plus the snapshot harness, normalizers, and suite machinery, so e2e tests share one launcher and every snapshot suite is a scenario table over one gate-covered implementation. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers. diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index ac9c0ceee3..4a43d0eef9 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -2,8 +2,9 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tier (`pnpm run test:snapshot`, [testing policy](../../../docs/testing.md)). An example gets a full snapshot suite from a scenario table plus a fixtures directory; every compare/guard mechanic lives here, under the per-file coverage gate, instead of being copied per example. -Three layers, importable separately: +Four layers, importable separately: +- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. @@ -39,4 +40,4 @@ A scenario booting a differently-composed tree sets its own `configPath` (an ove The example also ships a `cordis.snapshot.yml` replay overlay next to its `cordis.yml` (the bin swaps them under `DSH_SNAPSHOT=replay` — [single-source replay config RFC](../../../docs/rfc/implemented/testing/2026-07-04-single-source-acp-replay-config.md)); replay fixtures are served by [`dsh-llm-replay`](../llm-replay/README.md), which this package points at via the `DSH_SNAPSHOT_*` env vars it sets on the child. `pnpm run test:snapshot:record` calls the live LLM and rewrites the recorded scenarios' model fixtures; `pnpm run test:snapshot:refresh` stays keyless, runs the replay overlay, and rewrites stdout, comparable session-log goldens, and each pin's Markdown prompt snapshot from the committed model scripts. Fixture roles, record/replay/refresh semantics, and scenario-table fields are documented on `Scenario` and in the [snapshot RFC](../../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md). -Constraints: `suite.ts` imports vitest, so the package is importable only inside a vitest run (the harness and normalizers have no such dependency but ship from the same entry). ACP-specific by design — the harness speaks the SDK's `ClientSideConnection`. Permission round-trips are scriptable: `InputScript.permissionAnswers` is a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) the client maps to the agent-issued `optionId` at answer time; an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run (the agent is answered `cancelled`, so a tolerant agent cannot absorb the scenario bug). Session config options are scriptable too: the `setConfigOption` step switches a knob over `session/set_config_option`, and `setConfigOptionExpectError` asserts the bridge rejects an unknown id or out-of-vocabulary value (the error frame stays in the transcript). +Constraints: `suite.ts` imports vitest, so the package entry is importable only inside a vitest run (the launcher, harness, and normalizers have no such dependency but ship from the same entry). ACP-specific by design — the launcher speaks the SDK's `ClientSideConnection`. Permission round-trips are scriptable: `InputScript.permissionAnswers` is a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) the client maps to the agent-issued `optionId` at answer time; an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run (the agent is answered `cancelled`, so a tolerant agent cannot absorb the scenario bug). Session config options are scriptable too: the `setConfigOption` step switches a knob over `session/set_config_option`, and `setConfigOptionExpectError` asserts the bridge rejects an unknown id or out-of-vocabulary value (the error frame stays in the transcript). diff --git a/packages/support/acp-snapshot/package.json b/packages/support/acp-snapshot/package.json index 363bc86e25..b14be09c5b 100644 --- a/packages/support/acp-snapshot/package.json +++ b/packages/support/acp-snapshot/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-acp-snapshot", - "description": "ACP snapshot suite kit: real-subprocess scenario harness, golden normalizers, and the suite factory behind the keyless snapshot tier", + "description": "ACP test kit: shared subprocess launcher, snapshot scenario harness, golden normalizers, and suite factory", "version": "0.0.1", "private": true, "type": "module", diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index 491d3ea884..93bb556ba6 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -16,54 +16,20 @@ * @module @deepseek-ai/dsh-acp-snapshot/harness */ -import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process' import { cp, mkdtemp, readFile, readdir, rm } from 'node:fs/promises' import { existsSync } from 'node:fs' import { tmpdir } from 'node:os' import { join, delimiter } from 'node:path' -import { fileURLToPath } from 'node:url' -import { Readable, Writable } from 'node:stream' import { ClientSideConnection, - ndJsonStream, PROTOCOL_VERSION, - type Agent as AcpAgent, - type Client, type RequestPermissionRequest, type RequestPermissionResponse, type SessionNotification, } from '@agentclientprotocol/sdk' +import { launchAcpTestAgent, type AgentUnderTest, type LaunchedAcpTestAgent } from './launcher.ts' -// Resolve tsx's ESM loader to an ABSOLUTE path once: the child runs with its -// cwd in a temp dir OUTSIDE the repo, where a bare `--import tsx` would not -// resolve from node_modules. import.meta.resolve gives this package's tsx -// regardless of the child cwd. -const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) - -/** - * The agent composition a scenario runs against: which bin to boot and which - * leaf config it loads. All paths are ABSOLUTE — the subprocess cwd is a temp - * dir outside the repo, so relative resolution would miss; a suite resolves - * them from its own `import.meta.url`. - */ -export interface AgentUnderTest { - /** The agent bin entry (e.g. `packages/ui/acp-agent/src/bin.ts`), run unbuilt via tsx. */ - binScript: string - /** - * The example's live `cordis.yml`. Under `DSH_SNAPSHOT=replay` the bin swaps - * it for the sibling `cordis.snapshot.yml` (the keyless replay overlay), so - * one path serves both modes. - */ - configPath: string - /** - * The repo-root tsconfig whose `paths` map resolves the unbuilt workspace - * imports. Passed to the child as `TSX_TSCONFIG_PATH`: tsx finds a tsconfig - * by searching UP from the child's cwd — a temp dir outside the repo — so - * without the explicit pin the dsh-* imports fail before the bin writes a - * byte. - */ - tsconfigPath: string -} +export type { AgentUnderTest } from './launcher.ts' /** * One step of a scenario's deterministic input script (`input.json`). The @@ -194,11 +160,9 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise // Everything past the temp-dir creation runs under a try/finally that always // removes both dirs — so a failure in workspace seeding, spawn, or any step // never leaks them (the "e2e tests own their resources" rule). - let child: ChildProcessWithoutNullStreams | undefined + let launched: LaunchedAcpTestAgent | undefined let sessionId: string | undefined let sessionLogs: HarvestedLog[] = [] - const rawBuffers: Buffer[] = [] - const stderrChunks: string[] = [] try { // Seed the workspace if the scenario ships one (a file the agent reads/edits). // Copied into the temp cwd so the agent's bash tools see it; the goldens @@ -207,51 +171,15 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise await cp(opts.workspaceDir, cwd, { recursive: true }) } const env: NodeJS.ProcessEnv = { - ...process.env, - TSX_TSCONFIG_PATH: opts.agent.tsconfigPath, DSH_SNAPSHOT: opts.mode, DSH_SNAPSHOT_FILE: opts.fixtureFile, DSH_SNAPSHOT_SESSIONS_ROOT: sessionsRoot, - DSH_HOME: join(cwd, '.dsh'), - DSH_AGENTS_HOME: join(cwd, '.agents'), ...opts.overrideFile !== undefined ? { DSH_SNAPSHOT_OVERRIDE: opts.overrideFile } : {}, ...opts.childFiles !== undefined && opts.childFiles.length > 0 ? { DSH_SNAPSHOT_CHILD_FILES: opts.childFiles.join(delimiter) } : {}, } - child = spawn( - process.execPath, - ['--import', tsxLoader, opts.agent.binScript, opts.configPath ?? opts.agent.configPath], - { cwd, env, stdio: ['pipe', 'pipe', 'pipe'] }, - ) - - child.stderr.setEncoding('utf8') - child.stderr.on('data', (c: string) => stderrChunks.push(c)) - - // Tee raw stdout: accumulate the bytes for the golden + purity check, and ALSO - // feed the same bytes to the SDK client through a passthrough. Buffer the raw - // bytes (not per-chunk utf8 strings) and decode once at the end, so a - // multibyte sequence split across two 'data' events can't corrupt the golden. - const passthrough = new Readable({ read() {} }) - child.stdout.on('data', (buf: Buffer) => { - rawBuffers.push(buf) - passthrough.push(buf) - }) - child.stdout.on('end', () => passthrough.push(null)) - - const stream = ndJsonStream( - Writable.toWeb(child.stdin) as WritableStream, - Readable.toWeb(passthrough) as ReadableStream, - ) - // Watcher so a step can block until the client OBSERVES a particular - // session/update — used by promptAndCancel to pin frame order (send cancel - // only after the streamed agent_message_chunk has arrived, so those frames - // deterministically precede the cancelled prompt response). - const updateWaiters: { match: (u: SessionNotification['update']) => boolean; resolve: () => void }[] = [] - const waitForUpdate = (match: (u: SessionNotification['update']) => boolean): Promise => - new Promise(resolve => updateWaiters.push({ match, resolve })) - // Permission answers are consumed FIFO across the whole run; exhaustion // falls back to `cancelled` so approval-free scenarios keep the plain stub. const permissionQueue = [...input.permissionAnswers ?? []] @@ -263,22 +191,11 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise // callback answers `cancelled` (a well-defined path for the agent), // captures the error here, and the step loop fails the run on it. let scriptError: Error | undefined - const makeClient = (_agent: AcpAgent): Client => ({ - sessionUpdate(params: SessionNotification): Promise { - for (let i = updateWaiters.length - 1; i >= 0; i--) { - const waiter = updateWaiters[i] - // The index is always in-bounds (i only decreases; splice removes at - // i, so lower entries stay valid); the guard satisfies - // noUncheckedIndexedAccess. - /* v8 ignore next 1 -- unreachable in-bounds guard, see above */ - if (waiter === undefined) continue - if (waiter.match(params.update)) { - updateWaiters.splice(i, 1) - waiter.resolve() - } - } - return Promise.resolve() - }, + launched = launchAcpTestAgent({ + agent: opts.agent, + cwd, + ...opts.configPath !== undefined ? { configPath: opts.configPath } : {}, + env, requestPermission(params: RequestPermissionRequest): Promise { const answer = permissionQueue.shift() if (answer === undefined) return Promise.resolve({ outcome: { outcome: 'cancelled' } }) @@ -296,10 +213,11 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise return Promise.resolve({ outcome: { outcome: 'selected', optionId: option.optionId } }) }, }) - const client = new ClientSideConnection(makeClient, stream) + const active = launched + const { client } = active for (const step of input.steps) { - await runStep(client, step, cwd, waitForUpdate, () => sessionId, (id) => { sessionId = id }) + await runStep(client, step, cwd, match => active.waitForUpdate(match), () => sessionId, (id) => { sessionId = id }) // A permission exchange happens while a step's request is in flight, so // by the time the step settles any script bug it exposed is captured — // fail the run HERE, as a harness error, rather than hoping the agent's @@ -308,26 +226,22 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise } // Done driving: close stdin so the server disposes gracefully (flushing // persistence) and exits. Then await exit so the harvested log is complete. - child.stdin.end() - await waitForExit(child) + await active.close() // Harvest EVERY persisted log (parent + any subagent children) while the // temp dirs still exist, ordered primary-first. sessionLogs = await harvestSessionLogs(sessionsRoot) } finally { // Failure-safe teardown: kill a still-running child and drop the temp dirs // even if seeding/spawn/a step/harvest threw, so a flaky run never leaks a - // process or dir. `child` is undefined only if spawn itself threw. - if (child !== undefined && child.exitCode === null && child.signalCode === null) { - child.kill('SIGKILL') - await waitForExit(child) - } + // process or dir. `launched` is undefined only if launch itself threw. + await launched?.close('SIGKILL') await rm(cwd, { recursive: true, force: true }) await rm(sessionsRoot, { recursive: true, force: true }) } return { - rawStdout: Buffer.concat(rawBuffers).toString('utf8'), - stderr: stderrChunks.join(''), + rawStdout: launched.rawStdout(), + stderr: launched.stderr(), cwd, ...sessionId !== undefined ? { sessionId } : {}, sessionLogs, @@ -339,7 +253,7 @@ async function runStep( client: ClientSideConnection, step: InputStep, cwd: string, - waitForUpdate: (match: (u: SessionNotification['update']) => boolean) => Promise, + waitForUpdate: (match: (u: SessionNotification['update']) => boolean) => Promise, getSessionId: () => string | undefined, setSessionId: (id: string) => void, ): Promise { @@ -433,16 +347,6 @@ async function runStep( } } -/** Resolve once the child process exits (any code/signal). */ -function waitForExit(child: ChildProcessWithoutNullStreams): Promise { - // Race guard: both call sites run within one synchronous frame of - // stdin.end()/kill(), so the exit event cannot have been delivered yet; - // kept for any future caller that awaits in between. - /* v8 ignore next 1 -- unreachable race guard, see above */ - if (child.exitCode !== null || child.signalCode !== null) return Promise.resolve() - return new Promise(resolve => child.once('exit', () => { resolve() })) -} - /** * Harvest EVERY persisted `.jsonl` session log under a sessions root, parse each * header line, and return them ordered primary-first: the top-level session (no diff --git a/packages/support/acp-snapshot/src/index.ts b/packages/support/acp-snapshot/src/index.ts index 74bee95385..402bd3aa3d 100644 --- a/packages/support/acp-snapshot/src/index.ts +++ b/packages/support/acp-snapshot/src/index.ts @@ -1,13 +1,14 @@ /** * ACP snapshot suite kit — the shared machinery behind the keyless snapshot - * tier (`pnpm run test:snapshot`). Three layers, composable per example: - * the subprocess scenario harness ({@link runScenario}), the pure golden - * normalizers ({@link normalizeStdout} / {@link normalizeSessionLog} / - * {@link scrubRequestHeaders} / {@link scrubSystemPrompts}), and the suite factory - * ({@link defineAcpSnapshotSuite}) that registers a scenario table as a full - * describe/it tree. An example's `*.snapshot.ts` supplies only its - * {@link AgentUnderTest} paths, its snapshots directory, and its - * {@link Scenario} table. + * tier (`pnpm run test:snapshot`). Four layers, composable per example: the + * shared subprocess/client launcher ({@link launchAcpTestAgent}), the scripted + * scenario harness ({@link runScenario}), the pure golden normalizers + * ({@link normalizeStdout} / {@link normalizeSessionLog} / + * {@link scrubRequestHeaders} / {@link scrubSystemPrompts}), and the suite + * factory ({@link defineAcpSnapshotSuite}) that registers a scenario table as a + * full describe/it tree. Ordinary ACP e2e tests can use the launcher directly; + * an example's `*.snapshot.ts` supplies only its {@link AgentUnderTest} paths, + * snapshots directory, and {@link Scenario} table. * * NOTE: ./suite.ts imports vitest, so this package is importable only inside a * vitest run — a support-tier constraint stated in the README. @@ -17,7 +18,6 @@ export { runScenario, - type AgentUnderTest, type HarvestedLog, type InputScript, type InputStep, @@ -25,6 +25,12 @@ export { type RunOptions, type RunResult, } from './harness.ts' +export { + launchAcpTestAgent, + type AcpTestLaunchOptions, + type AgentUnderTest, + type LaunchedAcpTestAgent, +} from './launcher.ts' export { normalizeSessionLog, normalizeStdout, diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts new file mode 100644 index 0000000000..635a02ca35 --- /dev/null +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -0,0 +1,152 @@ +/** + * Shared launcher for ACP tests that drive an unbuilt agent subprocess over + * JSON-RPC stdio. It owns the tsx loader, workspace-resolution environment, + * stdout tee, SDK client, update collection, permission fallback, and process + * shutdown so e2e and snapshot suites do not each reconstruct that boundary. + * + * @module @deepseek-ai/dsh-acp-snapshot/launcher + */ + +import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process' +import { join } from 'node:path' +import { fileURLToPath } from 'node:url' +import { Readable, Writable } from 'node:stream' +import { + ClientSideConnection, + ndJsonStream, + type Agent as AcpAgent, + type Client, + type RequestPermissionRequest, + type RequestPermissionResponse, + type SessionNotification, +} from '@agentclientprotocol/sdk' + +// The child runs from a temp directory outside the repo, where a bare +// `--import tsx` cannot resolve. Resolve this package's loader once instead. +const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) + +/** The unbuilt agent entry, leaf config, and workspace tsconfig an ACP test boots. */ +export interface AgentUnderTest { + /** The agent bin entry (for example `packages/ui/acp-agent/src/bin.ts`). */ + binScript: string + /** The leaf `cordis.yml` loaded by the bin. */ + configPath: string + /** The repo tsconfig whose paths resolve unbuilt workspace imports. */ + tsconfigPath: string +} + +/** Options for one ACP test subprocess. */ +export interface AcpTestLaunchOptions { + /** The agent composition to boot. */ + agent: AgentUnderTest + /** Process cwd and default session-home root. */ + cwd: string + /** Alternate leaf config for this launch. */ + configPath?: string + /** Extra environment values layered over the parent environment. */ + env?: NodeJS.ProcessEnv + /** Permission handler; omitted requests fail closed as `cancelled`. */ + requestPermission?: (params: RequestPermissionRequest) => Promise +} + +/** A running ACP test process and its captured client-side surfaces. */ +export interface LaunchedAcpTestAgent { + /** The child process, exposed for process-level assertions. */ + child: ChildProcessWithoutNullStreams + /** The SDK connection backed by the child's stdio. */ + client: ClientSideConnection + /** Session updates in receive order. */ + updates: SessionNotification['update'][] + /** Decode all stdout bytes captured so far. */ + rawStdout(): string + /** Decode all stderr chunks captured so far. */ + stderr(): string + /** Resolve when a future session update matches the predicate. */ + waitForUpdate(match: (update: SessionNotification['update']) => boolean): Promise + /** Gracefully close stdin, or send a signal, and wait for process exit. */ + close(signal?: NodeJS.Signals): Promise +} + +/** + * Boot an ACP agent subprocess and connect an SDK client to its stdio. + * + * @param options Agent paths, cwd, environment, and optional permission handler. + * @returns The running process, connected client, captures, and shutdown handle. + */ +export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTestAgent { + const { agent, cwd } = options + const child = spawn( + process.execPath, + ['--import', tsxLoader, agent.binScript, options.configPath ?? agent.configPath], + { + cwd, + env: { + ...process.env, + ...options.env, + TSX_TSCONFIG_PATH: agent.tsconfigPath, + DSH_HOME: join(cwd, '.dsh'), + DSH_AGENTS_HOME: join(cwd, '.agents'), + }, + stdio: ['pipe', 'pipe', 'pipe'], + }, + ) + + const stderrChunks: string[] = [] + child.stderr.setEncoding('utf8') + child.stderr.on('data', (chunk: string) => stderrChunks.push(chunk)) + + const rawBuffers: Buffer[] = [] + const passthrough = new Readable({ read() {} }) + child.stdout.on('data', (buffer: Buffer) => { + rawBuffers.push(buffer) + passthrough.push(buffer) + }) + child.stdout.on('end', () => passthrough.push(null)) + + const updates: SessionNotification['update'][] = [] + const updateWaiters: { + match: (update: SessionNotification['update']) => boolean + resolve: (update: SessionNotification['update']) => void + }[] = [] + const stream = ndJsonStream( + Writable.toWeb(child.stdin) as WritableStream, + Readable.toWeb(passthrough) as ReadableStream, + ) + const makeClient = (_agent: AcpAgent): Client => ({ + sessionUpdate(params: SessionNotification): Promise { + updates.push(params.update) + for (let index = updateWaiters.length - 1; index >= 0; index--) { + const waiter = updateWaiters[index] + /* v8 ignore next 1 -- index is bounded by the array length */ + if (waiter === undefined) continue + if (!waiter.match(params.update)) continue + updateWaiters.splice(index, 1) + waiter.resolve(params.update) + } + return Promise.resolve() + }, + requestPermission: options.requestPermission + ?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' } })), + }) + const client = new ClientSideConnection(makeClient, stream) + + return { + child, + client, + updates, + rawStdout: () => Buffer.concat(rawBuffers).toString('utf8'), + stderr: () => stderrChunks.join(''), + waitForUpdate: match => new Promise(resolve => updateWaiters.push({ match, resolve })), + async close(signal?: NodeJS.Signals): Promise { + if (child.exitCode !== null || child.signalCode !== null) return + if (signal === undefined) child.stdin.end() + else child.kill(signal) + await waitForExit(child) + }, + } +} + +/** Resolve once a running child exits. */ +function waitForExit(child: ChildProcessWithoutNullStreams): Promise { + return new Promise(resolve => child.once('exit', () => { resolve() })) +} diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index b0817a8d04..ec1ed5cf6f 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -3,7 +3,9 @@ import { tmpdir } from 'node:os' import { delimiter, join } from 'node:path' import { fileURLToPath } from 'node:url' import { afterAll, describe, expect, it } from 'vitest' +import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { runScenario, type AgentUnderTest, type InputStep } from '../src/harness.ts' +import { launchAcpTestAgent } from '../src/launcher.ts' /** * Unit tests for the subprocess harness, driven through the REAL spawn path @@ -38,6 +40,37 @@ async function scenario(behavior: object): Promise<{ dir: string; fixtureFile: s const boot: InputStep[] = [{ op: 'initialize' }, { op: 'newSession' }] describe('runScenario', () => { + it('centralizes ACP boot, captures, updates, fail-closed permissions, and shutdown', { timeout: 20_000 }, async () => { + const { dir, fixtureFile } = await scenario({ permissionProbe: true, echoEnv: true, stderrNote: 'launcher stderr' }) + const sessionsRoot = await mkdtemp(join(tmpdir(), 'acp-launcher-sessions-')) + tempDirs.push(sessionsRoot) + const launched = launchAcpTestAgent({ + agent: AGENT, + cwd: dir, + configPath: AGENT.configPath, + env: { + DSH_SNAPSHOT: 'replay', + DSH_SNAPSHOT_FILE: fixtureFile, + DSH_SNAPSHOT_SESSIONS_ROOT: sessionsRoot, + }, + }) + await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const { sessionId } = await launched.client.newSession({ cwd: dir, mcpServers: [] }) + const nextChunk = launched.waitForUpdate(update => update.sessionUpdate === 'agent_message_chunk') + await launched.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) + expect((await nextChunk).sessionUpdate).toBe('agent_message_chunk') + expect(launched.updates.some(update => update.sessionUpdate === 'agent_message_chunk')).toBe(true) + expect(launched.rawStdout()).toContain('permission:{\\"outcome\\":\\"cancelled\\"}') + expect(launched.stderr()).toContain('launcher stderr') + await launched.close() + await launched.close('SIGKILL') + + // The minimal shape needs no environment or config override. + const minimal = launchAcpTestAgent({ agent: AGENT, cwd: dir }) + await minimal.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + await minimal.close() + }) + it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ permissionProbe: true, From b579a13db759c38c41541a021bbbac188f4bf8a8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 00:28:20 +0800 Subject: [PATCH 026/359] test: trim PostToolUse snapshot retries --- .../2026-07-04-hook-snapshot-matrix.md | 4 +- examples/acp-agent/tests/acp.snapshot.ts | 3 - .../hook-cc-posttool-block/input.json | 2 +- .../hook-cc-posttool-block/session.jsonl | 694 +----------------- .../stdout.golden.jsonl | 434 +---------- .../hook-codex-posttool-block/input.json | 2 +- .../hook-codex-posttool-block/session.jsonl | 2 +- 7 files changed, 16 insertions(+), 1125 deletions(-) diff --git a/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md b/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md index 47db2cd793..1b3e70eb13 100644 --- a/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md +++ b/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md @@ -29,6 +29,8 @@ Thirteen scenarios under `examples/acp-agent/tests/snapshots/`, naming `hook- Date: Tue, 14 Jul 2026 00:46:46 +0800 Subject: [PATCH 027/359] fix: let snapshot recording create fixture inventory --- packages/support/acp-snapshot/src/suite.ts | 38 ++++++++++++++----- .../support/acp-snapshot/tests/suite.spec.ts | 17 ++++++++- 2 files changed, 44 insertions(+), 11 deletions(-) diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts index 6311a15031..4d87093c8a 100644 --- a/packages/support/acp-snapshot/src/suite.ts +++ b/packages/support/acp-snapshot/src/suite.ts @@ -31,7 +31,7 @@ * @module @deepseek-ai/dsh-acp-snapshot/suite */ -import { readFile, readdir, writeFile } from 'node:fs/promises' +import { readFile, readdir, rm, writeFile } from 'node:fs/promises' import { existsSync } from 'node:fs' import { join } from 'node:path' import { describe, expect, it } from 'vitest' @@ -410,9 +410,12 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { const input = JSON.parse(await readFile(join(dir, 'input.json'), 'utf8')) as InputScript const overrideFile = join(dir, 'replay.override.json') const workspaceDir = join(dir, 'workspace') - const fixtureFiles = await sessionFixtures(dir) + // Replay/refresh need the committed inventory up front because those + // files drive the model scripts. Record mode creates that inventory + // from the harvested live logs, so it must also work for a brand-new + // scenario with no session.jsonl yet. + let fixtureFiles = RECORDING ? [] : await sessionFixtures(dir) const childFixtureFiles = fixtureFiles.slice(1) - const childSessions = childFixtureFiles.length const comparesLog = scenario.comparesLog ?? scenario.hasModelTurn const result = await runScenario(input, { agent, @@ -421,7 +424,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { ...existsSync(overrideFile) ? { overrideFile } : {}, // In REPLAY, forward the recorded child fixtures so each subagent session // replays from its own script. In RECORD they are harvested, not read. - ...!RECORDING && childSessions > 0 ? { childFiles: childFixtureFiles.map(file => join(dir, file)) } : {}, + ...!RECORDING && childFixtureFiles.length > 0 ? { childFiles: childFixtureFiles.map(file => join(dir, file)) } : {}, ...existsSync(workspaceDir) ? { workspaceDir } : {}, // A scenario booting an overlay tree passes its own live config; the // bin's replay swap derives the sibling `*cordis.snapshot.yml` from it. @@ -460,18 +463,35 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { || (REFRESHING && comparesLog) if (writesSessionFixtures) { expect(result.sessionLogs.length, `${mode} produced no session log to harvest`).toBeGreaterThan(0) - expect(result.sessionLogs.length, `expected ${childSessions + 1} session logs (parent + children)`) - .toBe(childSessions + 1) + if (REFRESHING) { + expect(result.sessionLogs.length, `expected ${fixtureFiles.length} session logs (parent + children)`) + .toBe(fixtureFiles.length) + } + const outputFixtureFiles = [ + 'session.jsonl', + ...Array.from({ length: result.sessionLogs.length - 1 }, (_, i) => `session.${i + 1}.jsonl`), + ] const primary = (result.sessionLogs[0] as HarvestedLog).content - await writeFile(join(dir, 'session.jsonl'), scrub( + await writeFile(join(dir, outputFixtureFiles[0] as string), scrub( REFRESHING ? stabilizeRefreshLog(primary, existingFixtures[0] as string, replacements) : primary, )) for (let i = 1; i < result.sessionLogs.length; i++) { const child = (result.sessionLogs[i] as HarvestedLog).content - await writeFile(join(dir, `session.${i}.jsonl`), scrub( + await writeFile(join(dir, outputFixtureFiles[i] as string), scrub( REFRESHING ? stabilizeRefreshLog(child, existingFixtures[i] as string, replacements) : child, )) } + if (RECORDING) { + const outputNames = new Set(outputFixtureFiles) + const entries = await readdir(dir, { withFileTypes: true }) + await Promise.all(entries + .filter(entry => entry.isFile() + && entry.name.startsWith('session.') + && entry.name.endsWith('.jsonl') + && !outputNames.has(entry.name)) + .map(entry => rm(join(dir, entry.name)))) + fixtureFiles = outputFixtureFiles + } if (scenario.pinsHeader === true) { const primary = result.sessionLogs[0] as HarvestedLog const prompts = normalizedSystemPrompts(primary.content, ctx) @@ -498,7 +518,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { // prompt becomes the fixture's `{{system}}`; non-pinning scenarios // additionally tokenize tools/prefix. The dedicated header guard below // compares those omitted values against their class's pin artifacts. - expect(result.sessionLogs.length, 'this scenario must persist a session log').toBe(childSessions + 1) + expect(result.sessionLogs.length, 'this scenario must persist one log per session fixture').toBe(fixtureFiles.length) for (let i = 0; i < fixtureFiles.length; i++) { const harvested = scrub((result.sessionLogs[i] as HarvestedLog).content) const fixture = scrub(await readFile(join(dir, fixtureFiles[i] as string), 'utf8')) diff --git a/packages/support/acp-snapshot/tests/suite.spec.ts b/packages/support/acp-snapshot/tests/suite.spec.ts index f27f36c564..7aa218526c 100644 --- a/packages/support/acp-snapshot/tests/suite.spec.ts +++ b/packages/support/acp-snapshot/tests/suite.spec.ts @@ -1,4 +1,4 @@ -import { cpSync, mkdtempSync, readFileSync, writeFileSync } from 'node:fs' +import { cpSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from 'node:fs' import { rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' @@ -69,7 +69,13 @@ const RECORD_SCENARIOS: Scenario[] = [ // committed record fixtures/goldens in place. const BOOTSTRAP = process.env.ACP_SNAPSHOT_SPEC_BOOTSTRAP === '1' const recordDir = BOOTSTRAP ? RECORD_SRC : mkdtempSync(join(tmpdir(), 'acp-snap-record-suite-')) -if (!BOOTSTRAP) cpSync(RECORD_SRC, recordDir, { recursive: true }) +if (!BOOTSTRAP) { + cpSync(RECORD_SRC, recordDir, { recursive: true }) + // Record mode owns its output inventory: a new scenario has no primary yet, + // while a changed child count can leave old numbered fixtures behind. + rmSync(join(recordDir, 'rec-pin', 'session.jsonl')) + writeFileSync(join(recordDir, 'rec-child', 'session.2.jsonl'), 'stale child\n') +} const refreshDir = mkdtempSync(join(tmpdir(), 'acp-snap-refresh-suite-')) cpSync(REPLAY_DIR, refreshDir, { recursive: true }) staleRefreshFixtures(refreshDir) @@ -141,6 +147,13 @@ describe('defineAcpSnapshotSuite: refresh write-back', () => { }) }) +describe('defineAcpSnapshotSuite: record inventory write-back', () => { + it('creates a missing primary fixture and prunes stale child fixtures', () => { + expect(readFileSync(join(recordDir, 'rec-pin', 'session.jsonl'), 'utf8')).toContain('"type":"session"') + expect(() => readFileSync(join(recordDir, 'rec-child', 'session.2.jsonl'), 'utf8')).toThrow() + }) +}) + describe('defineAcpSnapshotSuite: registration contract', () => { it("throws when a scenario's header class has no pinning scenario", () => { expect(() => { From b35d66b86dcbb814f0183174c4d42c303a963178 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 00:59:25 +0800 Subject: [PATCH 028/359] fix: reject legacy session events on every path --- .../session-persistence/src/coordinator.ts | 7 +- .../tests/persistence.spec.ts | 43 ++++++++++++ .../advanced/result.json | 66 +++++++++++-------- .../advanced/session.jsonl | 4 +- 4 files changed, 91 insertions(+), 29 deletions(-) diff --git a/packages/session-persistence/session-persistence/src/coordinator.ts b/packages/session-persistence/session-persistence/src/coordinator.ts index 4c42751816..b80e4c8d23 100644 --- a/packages/session-persistence/session-persistence/src/coordinator.ts +++ b/packages/session-persistence/session-persistence/src/coordinator.ts @@ -251,11 +251,15 @@ export class PersistenceCoordinator { if (batch === undefined) { throw new TypeError('session event batch is not losslessly JSON-serializable because it contains non-JSON-serializable data') } - assertSupportedEvents(batch, id) return this.serialize(id, () => this.appendCore(id, batch)) } private async appendCore(id: SessionId, events: readonly SessionEvent[]): Promise { + // Every append route converges here: the public service, live write-behind + // drains, and HMR seed/suffix adoption. Keep vocabulary rejection at that + // shared boundary so a stale JavaScript plugin cannot persist an event that + // this same backend will refuse to load. + assertSupportedEvents(events, id) if (events.length === 0) return let state = this.states.get(id) if (state === undefined) state = await this.adopt(id) // calls loadCore, not load @@ -528,6 +532,7 @@ export class PersistenceCoordinator { private async adoptLivePrefix(session: Session, seed: readonly SessionEvent[], stored: StoredPrefix): Promise { const { meta, events, tornMarker } = stored this.assertVersion(meta) + assertSupportedEvents(events, session.header.id) if (!seedCoversPrefix(seed, events)) { throw new Error(`session "${session.header.id}" already has a persisted log on disk that does not match this live session (id collision)`) } diff --git a/packages/session-persistence/session-persistence/tests/persistence.spec.ts b/packages/session-persistence/session-persistence/tests/persistence.spec.ts index e28bd32851..a20d850d83 100644 --- a/packages/session-persistence/session-persistence/tests/persistence.spec.ts +++ b/packages/session-persistence/session-persistence/tests/persistence.spec.ts @@ -12,6 +12,16 @@ import { runCoordinatorContract, type CoordinatorFixture } from './coordinator-c /** The durable store shape: materialized sessions only (no lazy entries). */ type MemoryStore = Map +/** An obsolete event fixture that emulates an untyped pre-change producer. */ +function legacyHeaderDelta(seq = 0): SessionEvent { + return { + type: 'request/header-delta', + seq, + time: 1, + data: { config: { model: 'legacy' } }, + } as unknown as SessionEvent +} + /** Optional plugin config: an EXTERNAL store shared across backend instances. */ interface MemoryConfig { store?: MemoryStore } @@ -164,4 +174,37 @@ describe('SessionPersistence service registration', () => { .rejects.toThrow('session metadata must be losslessly JSON-serializable') await fiber.dispose() }) + + it('rejects a legacy header delta buffered by a pre-change live producer', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + const fiber = await ctx.plugin(MemoryPersistence) + const session = ctx.sessions.create(SessionId('legacy-live'), { meta: { cwd: '/legacy' } }) + // Model the runtime shape available to JavaScript or a hot-loaded plugin + // compiled against the obsolete event vocabulary. + const appendLegacy = session.append.bind(session) as (type: string, data: unknown) => SessionEvent + appendLegacy('request/header-delta', { config: { model: 'legacy' } }) + + await expect(ctx.sessions.flush(session)) + .rejects.toThrow(/unsupported legacy request\/header-delta event at seq 0/) + await fiber.dispose() + }) + + it('rejects a legacy stored prefix during live HMR adoption', async () => { + const id = SessionId('legacy-hmr') + const m = meta(id, '/legacy') + const legacy = legacyHeaderDelta() + const store: MemoryStore = new Map([[id, { meta: m, events: [legacy] }]]) + const ctx = new Context() + await ctx.plugin(SessionStore) + // A current live session cannot carry the obsolete event in its seed, but + // HMR still has to identify the persisted prefix as unsupported rather than + // treating it as an ordinary live-prefix collision. + const session = ctx.sessions.create(id, { meta: { cwd: '/legacy' } }) + const fiber = await ctx.plugin(MemoryPersistence, { store }) + + await expect(ctx.sessions.flush(session)) + .rejects.toThrow(/unsupported legacy request\/header-delta event at seq 0/) + await Promise.allSettled([fiber.dispose()]) + }) }) diff --git a/scripts/snapshots/python-sdk-single-exe/advanced/result.json b/scripts/snapshots/python-sdk-single-exe/advanced/result.json index 2ecfc76a2e..75aa113cec 100644 --- a/scripts/snapshots/python-sdk-single-exe/advanced/result.json +++ b/scripts/snapshots/python-sdk-single-exe/advanced/result.json @@ -253,7 +253,7 @@ "workflow" ] }, - "reason": "fallback" + "reason": "change" } }, { @@ -916,22 +916,29 @@ } }, { - "type": "request/header-delta", + "type": "request/header", "seq": 56, "time": 0, "data": { - "system": { - "keepStart": 62, - "keepEnd": 34, - "insert": [] + "header": { + "config": { + "model": "smoke-model" + }, + "system": "{{system}}", + "tools": [ + "bash", + "bash_kill", + "bash_output", + "cordis_inspect", + "cordis_mount", + "cordis_unmount", + "run_code", + "skill", + "subagent", + "workflow" + ] }, - "tools": { - "added": [], - "removed": [ - "snapshot_double" - ], - "changed": [] - } + "reason": "change" } }, { @@ -1397,7 +1404,7 @@ "workflow" ] }, - "reason": "fallback" + "reason": "change" } } } @@ -2360,22 +2367,29 @@ "payload": { "sessionId": "{{parent}}", "event": { - "type": "request/header-delta", + "type": "request/header", "seq": 56, "time": 0, "data": { - "system": { - "keepStart": 62, - "keepEnd": 34, - "insert": [] + "header": { + "config": { + "model": "smoke-model" + }, + "system": "{{system}}", + "tools": [ + "bash", + "bash_kill", + "bash_output", + "cordis_inspect", + "cordis_mount", + "cordis_unmount", + "run_code", + "skill", + "subagent", + "workflow" + ] }, - "tools": { - "added": [], - "removed": [ - "snapshot_double" - ], - "changed": [] - } + "reason": "change" } } } diff --git a/scripts/snapshots/python-sdk-single-exe/advanced/session.jsonl b/scripts/snapshots/python-sdk-single-exe/advanced/session.jsonl index bb0ee1d4d0..6f984e294a 100644 --- a/scripts/snapshots/python-sdk-single-exe/advanced/session.jsonl +++ b/scripts/snapshots/python-sdk-single-exe/advanced/session.jsonl @@ -13,7 +13,7 @@ {"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"mounted dyn-1 (plugin \"\", state: active)"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"} {"type":"step/end","seq":12,"time":0,"data":{"turn":1,"step":1}} {"type":"step/start","seq":13,"time":0,"data":{"turn":1,"step":2}} -{"type":"request/header","seq":14,"time":0,"data":{"header":{"config":{"model":"smoke-model"},"system":"{{system}}","tools":["bash","bash_kill","bash_output","cordis_inspect","cordis_mount","cordis_unmount","run_code","skill","snapshot_double","subagent","workflow"]},"reason":"fallback"}} +{"type":"request/header","seq":14,"time":0,"data":{"header":{"config":{"model":"smoke-model"},"system":"{{system}}","tools":["bash","bash_kill","bash_output","cordis_inspect","cordis_mount","cordis_unmount","run_code","skill","snapshot_double","subagent","workflow"]},"reason":"change"}} {"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-code","name":"run_code","argumentsDelta":"{\"code\": \"return await tools.snapshot_double({ value: 21 })\"}"}}} {"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.snapshot_double({ value: 21 })\"}"}}}} @@ -55,7 +55,7 @@ {"type":"tool/result","seq":53,"time":0,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"unmounted dyn-1 (plugin \"\")"}],"isError":false},"sourceEventSeqs":[52],"surfaceOp":"append"} {"type":"step/end","seq":54,"time":0,"data":{"turn":1,"step":5}} {"type":"step/start","seq":55,"time":0,"data":{"turn":1,"step":6}} -{"type":"request/header-delta","seq":56,"time":0,"data":{"system":{"keepStart":62,"keepEnd":34,"insert":[]},"tools":{"added":[],"removed":["snapshot_double"],"changed":[]}}} +{"type":"request/header","seq":56,"time":0,"data":{"header":{"config":{"model":"smoke-model"},"system":"{{system}}","tools":["bash","bash_kill","bash_output","cordis_inspect","cordis_mount","cordis_unmount","run_code","skill","subagent","workflow"]},"reason":"change"}} {"type":"assistant/chunk","seq":57,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":58,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"text-delta","index":0,"text":"ADVANCED_EXECUTABLE_OK"}}} {"type":"assistant/chunk","seq":59,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_EXECUTABLE_OK"}}}} From f95a411b0ac7d5f347c602308df1123dc1aecd5f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 01:09:07 +0800 Subject: [PATCH 029/359] fix: record self-limiting hook snapshot --- .../2026-07-04-hook-snapshot-matrix.md | 2 +- .../hook-cc-posttool-block/input.json | 2 +- .../hook-cc-posttool-block/session.jsonl | 253 ++++++++++++------ .../stdout.golden.jsonl | 83 +++++- .../workspace/hooks.json | 2 +- .../workspace/posttool-once.sh | 7 + 6 files changed, 259 insertions(+), 90 deletions(-) create mode 100644 examples/acp-agent/tests/snapshots/hook-cc-posttool-block/workspace/posttool-once.sh diff --git a/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md b/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md index 1b3e70eb13..0327662d3d 100644 --- a/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md +++ b/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md @@ -29,7 +29,7 @@ Thirteen scenarios under `examples/acp-agent/tests/snapshots/`, naming `hook-&2; exit 2" } + { "type": "command", "command": "sh posttool-once.sh" } ] } ] diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/workspace/posttool-once.sh b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/workspace/posttool-once.sh new file mode 100644 index 0000000000..2acc98bb58 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/workspace/posttool-once.sh @@ -0,0 +1,7 @@ +#!/bin/sh +if test -e .posttool-blocked; then + exit 0 +fi +: > .posttool-blocked +printf '%s\n' 'tool output rejected by policy: retry once' >&2 +exit 2 From d7de8a8d138b70d79e7066195ac11a512cbf4249 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 01:24:20 +0800 Subject: [PATCH 030/359] refactor: narrow compaction surface --- docs/cordis-catalog/services.md | 4 +- docs/core-data-structures/compaction.md | 14 +- .../2026-06-18-compaction-capability-seam.md | 4 +- packages/compact/compact-basic/README.md | 2 +- packages/compact/compact-basic/src/index.ts | 24 ++- .../compact-basic/tests/compact-basic.spec.ts | 147 +++++++----------- packages/compact/compact/README.md | 2 +- packages/compact/compact/src/index.ts | 11 +- packages/compact/compact/src/types.ts | 8 - .../compact/compact/tests/compact.spec.ts | 23 ++- .../cordis/tool-cordis/src/api-catalog.ts | 4 +- 11 files changed, 95 insertions(+), 148 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index ecb68913df..bfb31749d5 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -113,12 +113,12 @@ Implementations MUST honor: ```ts cordis-catalog abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise -abstract compactRegion( session: Session, start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise +abstract compactRegion( start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise ``` Types: [Message](../core-data-structures/core.md) -Source: [`packages/compact/compact/src/index.ts:65`](../../packages/compact/compact/src/index.ts) +Source: [`packages/compact/compact/src/index.ts:66`](../../packages/compact/compact/src/index.ts) ## `ctx.fs` — `FileSystem` (abstract seam) diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 2f402be57d..de350df9f3 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -1,6 +1,6 @@ # Compaction -The compaction seam — a [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md) split like bash: interface ([dsh-compact](../../packages/compact/compact), `ctx.compact`), implementation (a backend such as [dsh-compact-basic](../../packages/compact/compact-basic)), and consumer (a `/compact` tool, deferred). Compaction is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A tokenizer- or template-based backend is a sibling package implementing the same interface. Unlike bash, the interface necessarily depends on `dsh-session` and `dsh-llm`: its verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary (see the [compaction capability-seam RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)). +The compaction seam — a [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md) split like bash: interface ([dsh-compact](../../packages/compact/compact), `ctx.compact`), implementation (a backend such as [dsh-compact-basic](../../packages/compact/compact-basic)), and consumer (a `/compact` tool, deferred). Compaction is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A tokenizer- or template-based backend is a sibling package implementing the same interface. Unlike bash, the interface necessarily depends on `dsh-session` and `dsh-llm`: its verbs act on an agent-owned `Session`, and its durable summary event uses the `ContentBlock` vocabulary (see the [compaction capability-seam RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)). Source: [`packages/compact/compact/src/types.ts`](../../packages/compact/compact/src/types.ts) @@ -20,18 +20,10 @@ These variants are merged inside a `declare module '@deepseek-ai/dsh-session'` b ## `CompactionResult` -What a successful compaction returns to its caller: the seqs of the three appended `compact/*` events, the summary blocks, and the shadowed range/seqs plus the estimated token count. +What a successful compaction returns to its caller: the shadowed range and seqs plus the estimated token count. The durable `compact/summary` event owns the raw summary and bookkeeping-event identity. ```ts type-equiv interface CompactionResult { - /** The seq of the appended `compact/start` event. */ - startSeq: number - /** The seq of the appended `compact/summary` event. */ - summarySeq: number - /** The seq of the appended `compact/end` event. */ - endSeq: number - /** The summary content blocks produced by the backend. */ - summary: ContentBlock[] /** * The surface-boundary pair that was shadowed: the seqs of the first * (`start`) and last (`end`) surface nodes of the replaced range. A @@ -50,6 +42,6 @@ interface CompactionResult { ## The service -`CompactService` (`ctx.compact`, abstract — defined in [`packages/compact/compact/src/index.ts`](../../packages/compact/compact/src/index.ts)) declares two abstract methods: `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` checks token pressure and compacts an older range if the history is too large (returning `null` when nothing needs it), and `compactRegion(session, start, end, agent, signal?)` forcibly summarizes surface nodes `[start, end]` into a single replacement node. `compactIfNeeded`'s parameters are all required — the loop's `agent/pre-step` checkpoint supplies the agent, the assembled `fullSystemPrompt`, the instance's composed `sessionPrefix` (request-only messages the derived history omits, so the pressure estimate must count them), and the turn `signal`. A backend summarizing via `ctx.llm.stream()` must forward `signal` into the call's `GenerateOptions.signal`, so an abort or dispose tears down the in-flight summarization. The entire strategy — token estimation, retention policy, event sequencing, summarization — is a HOW decision owned by the implementation. +`CompactService` (`ctx.compact`, abstract — defined in [`packages/compact/compact/src/index.ts`](../../packages/compact/compact/src/index.ts)) declares two abstract methods: `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` checks token pressure and compacts an older range if the history is too large (returning `null` when nothing needs it), and `compactRegion(start, end, agent, signal?)` forcibly summarizes surface nodes `[start, end]` from `agent.session` into a single replacement node. `compactIfNeeded`'s parameters are all required — the loop's `agent/pre-step` checkpoint supplies the agent, the assembled `fullSystemPrompt`, the instance's composed `sessionPrefix` (request-only messages the derived history omits, so the pressure estimate must count them), and the turn `signal`. A backend summarizing via `ctx.llm.stream()` must forward `signal` into the call's `GenerateOptions.signal`, so an abort or dispose tears down the in-flight summarization. The entire strategy — token estimation, retention policy, event sequencing, summarization — is a HOW decision owned by the implementation. Auto-compaction runs on the serial `agent/pre-step` loop seam (fired once per step, after `turn/start` and BEFORE the step opens and its request history is derived), not the `agent/request` waterfall: compaction mutates the session surface in place — with its log-only `compact/*` records landing cleanly outside any step — and the loop derives the request from the already-compacted surface. Retention is turn-agnostic — the only structural guard is tool-pairing balance (a compacted region's edges are balanced cuts on the surface, so it never splits a step's tool-calls from their results), so a single runaway turn that alone exceeds the window compacts its own early closed steps rather than being retained verbatim. The backend that ships this (`dsh-compact-basic`) documents the retention walk, summary shrink validation, bounded re-compaction, and the crash/recoverable failure taxonomy. diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index e0835dcaa6..b99bdfc3b3 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -22,7 +22,7 @@ Per the [capability-seams RFC](../../implemented/architecture/2026-06-13-capabil ### The contract depends on `dsh-session` and `dsh-llm` — a deliberate deviation -The capability-seams RFC states the interface package "depends only on cordis" (true of `dsh-bash`, whose vocabulary is self-contained). Compaction **cannot** honor that: its verbs are defined *over* a `Session` (`compactRegion(session, start, end)`) and its output *is* the content vocabulary (`CompactionResult.summary: ContentBlock[]`). There is no way to express the contract without naming `Session`/`SessionEvent` (from `dsh-session`) and `ContentBlock` (from `dsh-llm`). +The capability-seams RFC states the interface package "depends only on cordis" (true of `dsh-bash`, whose vocabulary is self-contained). Compaction **cannot** honor that: its verbs act on an agent-owned `Session` (`compactRegion(start, end, agent)`) and the durable `compact/summary` event carries `ContentBlock[]`. There is no way to express the contract without naming `Session`/`SessionEvent` (from `dsh-session`) and `ContentBlock` (from `dsh-llm`). This is not a coupling smell — it is the contract's domain. The "only cordis" guidance was always shorthand for "the interface depends only on what the contract genuinely names, and never on an implementation." `dsh-session` and `dsh-llm` are themselves interface/vocabulary packages, not implementations; `dsh-compact` still imports no backend. The seam's real invariant — *consumers and implementations evolve independently behind an abstract service* — holds intact. @@ -30,7 +30,7 @@ This is not a coupling smell — it is the contract's domain. The "only cordis" An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface, with only `estimateContentTokens()` and `summarize()` abstract. That recouples the contract to one strategy: a backend that wants a different retention policy or a different event-sequencing would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend, where it belongs, and keeps the interface a pure statement of *what*. The backend remains internally factored — `estimateContentTokens()` and `summarize()` are `protected` hooks a sub-backend can override without reimplementing the walk — but that factoring is the backend's private concern, not the contract's. -`compactIfNeeded(agent, turn, step, fullSystemPrompt, signal)` takes **required** parameters (not the original all-optional shape). The auto-compaction seam (below) always supplies the agent, lifecycle context, assembled system prompt (counted toward the estimate), and the turn's abort signal, so optionality would only invite a hidden default at the seam. The session being compacted comes from the agent context. `compactRegion(session, start, end, agent, turn, step, signal?)` keeps an optional signal (a manual caller may omit it). Passing lifecycle context rather than a concrete model keeps router agents honest: the backend's summarization request can run through `agent/request`, where model-routing plugins already choose the actual model. +`compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` takes required inputs from the auto-compaction seam: the agent, assembled system prompt, composed request prefix, and turn abort signal. `compactRegion(start, end, agent, signal?)` uses `agent.session` as its single session identity and keeps an optional signal for manual callers. The backend's summarization request is a direct `ctx.llm.stream()` call; the configured summarization model falls back to the agent's model, and adapters can still route through the LLM seam. ### Auto-compaction runs on `agent/pre-step`, a dedicated surface-mutation seam diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index a06e74b818..c956b1e9de 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -17,7 +17,7 @@ The abstract contract states only WHAT compaction does; this backend owns every - **Auto-compaction** — an `agent/pre-step` listener delegates to `compactIfNeeded()` before every step (not just a turn's first — a tool-heavy turn grows the surface mid-turn, so a runaway turn still compacts, and per-step firing is the only moment to rescue it before overflow). `agent/pre-step` is a serial (awaited, in-order) surface-mutation checkpoint that fires after `turn/start` and BEFORE the step opens (`step/start`) and its request history is derived, so compaction mutates the surface — with its log-only `compact/*` records landing cleanly outside any step — and the loop derives once from the result: no double-derive, and the listener cannot see (or need to rewrite) an already-assembled `messages` array. The listener owns no threshold logic of its own (the single token-pressure check lives in `compactIfNeeded()`); because Cordis `serial` bails early on non-void return values, the listener returns `void` and does not use the dispatcher's bail channel as a veto surface. - **Failure handling** — the `compact/start … compact/end` bracket is a log-recorded lock: it makes a crash mid-summarization a detectable orphan (a `compact/start` with no `compact/end`), records provenance, and prevents a concurrent compaction. Two failure paths: a **crash** (the loop dies mid-summarization) leaves a dangling `compact/start` that is inert — `compact/*` events are log-only, the surface replacement never landed, so the full history derives fine and generic turn-repair closes the turn; a **recoverable** failure (summarization throws but the loop survives) appends `compact/end` with its `error` field set, leaving the surface untouched so the call proceeds with full history. Core session repair stays compaction-agnostic by design — it never learns about `compact/*`. -`estimateContentTokens()` and `summarize()` are overridable hooks: a tokenizer-based or template-based backend can subclass `BasicCompactService` and override just those, reusing the retention walk and surface plumbing. `summarize()` returns the summary blocks together with the call envelope it actually used (`{ summary, model, maxTokens? }`) — the caller logs that envelope on the `compact/summary` provenance event, so an overriding backend reports its own envelope honestly. +The protected `estimateContentTokens()` and `summarize()` methods are overridable hooks: a tokenizer-based or template-based backend can subclass `BasicCompactService` and override just those, reusing the private retention/pressure accounting and surface plumbing. `summarize()` returns the summary blocks together with the call envelope it actually used (`{ summary, model, maxTokens? }`) — the caller logs that envelope on the `compact/summary` provenance event, so an overriding backend reports its own envelope honestly. ## Config (`BasicCompactConfig`) diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index 0b0300472c..27e81cd3d9 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -41,12 +41,11 @@ import type { BasicCompactConfig, ResolvedConfig } from './types.ts' import { resolveConfig } from './types.ts' export type { BasicCompactConfig, ResolvedConfig } from './types.ts' -export { resolveConfig } from './types.ts' /** Per-block structural overhead for JSON framing / type tag. */ const BLOCK_OVERHEAD = 4 -/** Role-field framing overhead added per message in {@link BasicCompactService.estimateTokens}. */ +/** Role-field framing overhead added per message in the request estimator. */ const ROLE_OVERHEAD = 4 /** Tags wrapping the structured summary inside the landed checkpoint node. */ @@ -222,7 +221,7 @@ export class BasicCompactService extends CompactService { * their JSON-stringified length. * @returns the estimated token count. */ - estimateContentTokens(blocks: readonly ContentBlock[]): number { + protected estimateContentTokens(blocks: readonly ContentBlock[]): number { const { charsPerToken } = this.config let tokens = 0 for (const block of blocks) { @@ -257,7 +256,8 @@ export class BasicCompactService extends CompactService { * @returns the estimated token count of the event's content, or 0 for a * non-message event. */ - estimateEventTokens(event: SessionEvent): number { + private estimateEventTokens(event: SessionEvent): number { + /* v8 ignore next -- callers traverse surface nodes, whose event types are the five cases below */ switch (event.type) { case 'user/message': case 'assistant/message': @@ -278,7 +278,7 @@ export class BasicCompactService extends CompactService { * @param systemPrompt - counted at chars / `charsPerToken` when provided. * @returns the estimated token footprint of the whole request. */ - estimateTokens(messages: readonly Message[], systemPrompt?: string): number { + private estimateTokens(messages: readonly Message[], systemPrompt?: string): number { let total = 0 for (const msg of messages) { total += this.estimateContentTokens(msg.content) @@ -318,7 +318,7 @@ export class BasicCompactService extends CompactService { * @returns the text-only summary blocks plus the call envelope used * (`model`, and `maxTokens` when the summarizer has a cap). */ - async summarize( + protected async summarize( text: string, agent: Agent, signal?: AbortSignal, ): Promise<{ summary: ContentBlock[]; model: string; maxTokens?: number }> { const assembler = new BlockAssembler() @@ -417,7 +417,7 @@ export class BasicCompactService extends CompactService { break } - result = await this.compactRegion(session, range.start, range.end, agent, signal) + result = await this.compactRegion(range.start, range.end, agent, signal) } const totalTokens = this.estimatePressure(session, fullSystemPrompt, sessionPrefix) @@ -439,17 +439,17 @@ export class BasicCompactService extends CompactService { * @param sessionPrefix - the instance's composed session prefix (counts toward pressure). * @returns the estimated token total the next request will carry. */ - estimatePressure(session: Session, fullSystemPrompt: string, sessionPrefix: readonly Message[]): number { + private estimatePressure(session: Session, fullSystemPrompt: string, sessionPrefix: readonly Message[]): number { return this.estimateTokens([...sessionPrefix, ...session.deriveMessages()], fullSystemPrompt) } override async compactRegion( - session: Session, start: number, end: number, agent: Agent, signal?: AbortSignal, ): Promise { + const session = agent.session // Resolve the range by surface POSITION, not numeric seq interval. A prior // replace lands a fresh high-seq summary node AT the shadowed range's // position, so the surface order (head→tail) no longer tracks seq order — @@ -556,13 +556,9 @@ export class BasicCompactService extends CompactService { // compact/start and here leaves a detectable orphaned lock (a compact/start // with no matching compact/end) rather than a compact/end that falsely // claims compaction finished before the surface replacement landed. - const endEvent = session.append('compact/end', { turn: openTurn }) + session.append('compact/end', { turn: openTurn }) return { - startSeq: startEvent.seq, - summarySeq: summaryEvent.seq, - endSeq: endEvent.seq, - summary, shadowedRange: { start, end }, shadowedSeqs, shadowedTokenCount, diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 1a30cc9fc9..46bcb9911c 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -5,7 +5,7 @@ import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic' import type { ContentBlock, GenerateOptions, Message, StreamChunk } from '@deepseek-ai/dsh-llm' import { CallId, LlmAdapter, LlmService } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' -import type { SessionEvent, SurfaceEvent } from '@deepseek-ai/dsh-session' +import type { SurfaceEvent } from '@deepseek-ai/dsh-session' import * as Invariants from '@deepseek-ai/dsh-invariants' import type { Agent } from '@deepseek-ai/dsh-agent' @@ -68,6 +68,20 @@ class TestCompactService extends BasicCompactService { } } +/** Expose the backend's protected extension hooks for their focused contract tests. */ +class InspectableCompactService extends BasicCompactService { + estimateContent(blocks: readonly ContentBlock[]): number { + return this.estimateContentTokens(blocks) + } + + summarizeForTest( + text: string, + agent: Agent, + ): Promise<{ summary: ContentBlock[]; model: string; maxTokens?: number }> { + return this.summarize(text, agent) + } +} + function isFramedCheckpoint(blocks: readonly ContentBlock[]): boolean { const first = blocks[0] const last = blocks[blocks.length - 1] @@ -333,51 +347,6 @@ describe('BasicCompactService step-alignment (never split a tool-call/result pai }) }) -describe('BasicCompactService.estimateEventTokens', () => { - it('returns 0 for non-message events (boundary, chunk, step/end, tool/call)', () => { - const svc = createTestService() - expect(svc.estimateEventTokens({ type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'step/start', seq: 1, time: 2, data: { turn: 1, step: 1 } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'assistant/chunk', seq: 2, time: 3, data: { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'h' } } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'step/end', seq: 3, time: 4, data: { turn: 1, step: 1 } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'tool/call', seq: 4, time: 5, data: { turn: 1, step: 1, callId: CallId('c1'), name: 'read', arguments: '{}' } })).toBe(0) - }) - - it('returns estimate for message-producing events', () => { - const svc = createTestService() - const userEvent: SessionEvent = { type: 'user/message', seq: 0, time: 1, data: { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } } } - expect(svc.estimateEventTokens(userEvent)).toBe(10) - - const asstEvent: SessionEvent = { type: 'assistant/message', seq: 1, time: 2, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }, { type: 'text', text: 'b' }] } } - expect(svc.estimateEventTokens(asstEvent)).toBe(20) - - const toolEvent: SessionEvent = { type: 'tool/result', seq: 2, time: 3, data: { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'output' }], isError: false } } - expect(svc.estimateEventTokens(toolEvent)).toBe(10) - }) -}) - -describe('BasicCompactService.estimateTokens', () => { - it('sums token estimates across messages', () => { - const svc = createTestService() - const messages: Message[] = [ - { role: 'user', content: [{ type: 'text', text: 'hello' }] }, - { role: 'assistant', content: [{ type: 'text', text: 'hi' }, { type: 'text', text: 'there' }] }, - ] - // 1 block * 10 + 4 (role) + 2 blocks * 10 + 4 (role) = 10 + 4 + 20 + 4 = 38 - expect(svc.estimateTokens(messages)).toBe(38) - }) - - it('includes system prompt in the estimate', () => { - const svc = createTestService() - const messages: Message[] = [ - { role: 'user', content: [{ type: 'text', text: 'hi' }] }, - ] - const systemPrompt = 'You are a helpful assistant.' - // 1 block * 10 + 4 (role) + ceil(28/4) = 10 + 4 + 7 = 21 - expect(svc.estimateTokens(messages, systemPrompt)).toBe(21) - }) -}) - describe('BasicCompactService.compactRegion', () => { it('shadows surface nodes and inserts a summary via user/message', async () => { const svc = createTestService() @@ -393,7 +362,7 @@ describe('BasicCompactService.compactRegion', () => { expect(result.shadowedSeqs).toEqual([firstSeq, secondSeq]) expect(result.shadowedRange.start).toBe(firstSeq) expect(result.shadowedRange.end).toBe(secondSeq) - expect(result.summary).toEqual(svc.mockSummary) + expect(result.shadowedTokenCount).toBe(20) const events = session.events const startEvent = events.findLast(e => e.type === 'compact/start') @@ -405,6 +374,7 @@ describe('BasicCompactService.compactRegion', () => { // The provenance record carries the summarize call's envelope, so "which // model wrote this summary" is answerable from the log alone. expect(summaryEvent?.type === 'compact/summary' && summaryEvent.data.model).toBe('test-model') + expect(summaryEvent?.type === 'compact/summary' && summaryEvent.data.summary).toEqual(svc.mockSummary) // compact/* events are log-only — no surfaceOp (type system enforces this). const startRaw = startEvent as unknown as { surfaceOp?: unknown } @@ -509,10 +479,9 @@ describe('BasicCompactService.compactRegion', () => { const session = multiTurnSession(3, 1) const nodes = session.surface.nodes - const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm') + await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm') // Provenance (compact/summary) carries the RAW, unframed summary. - expect(result.summary).toEqual([{ type: 'text', text: 'STRUCTURED SUMMARY' }]) const summaryEvent = session.events.findLast(e => e.type === 'compact/summary')! expect(summaryEvent.data).toMatchObject({ summary: [{ type: 'text', text: 'STRUCTURED SUMMARY' }] }) @@ -590,7 +559,6 @@ describe('BasicCompactService.compactIfNeeded', () => { expect(result).not.toBeNull() expect(session.events.filter(e => e.type === 'compact/summary')).toHaveLength(1) - expect(svc.estimateTokens(session.deriveMessages(), '')).toBeLessThan(70) }) it('walks tail→head and retains nodes within token budget', async () => { @@ -716,7 +684,6 @@ describe('BasicCompactService.compactIfNeeded', () => { expect(result).not.toBeNull() expect(svc.summarizeCalls).toHaveLength(2) expect(session.events.filter(e => e.type === 'compact/summary')).toHaveLength(2) - expect(svc.estimateTokens(session.deriveMessages(), '')).toBeLessThan(50) }) it('throws after the configured re-compaction attempts still leave the surface above threshold', async () => { @@ -801,53 +768,51 @@ describe('BasicCompactService blocking (compaction in progress)', () => { describe('BasicCompactService token estimation (char/4 heuristic)', () => { it('estimates text blocks with char/4 + overhead', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // 'this is a somewhat longer text block' = 36 → ceil(36/4)+4 = 13; 'short' = 5 → 2+4 = 6 const blocks: ContentBlock[] = [ { type: 'text', text: 'this is a somewhat longer text block' }, { type: 'text', text: 'short' }, ] - expect(svc.estimateContentTokens(blocks)).toBe(19) + expect(svc.estimateContent(blocks)).toBe(19) }) it('estimates reasoning blocks same as text', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // 'thinking about this...' = 22 → ceil(22/4)+4 = 10 - expect(svc.estimateContentTokens([{ type: 'reasoning', text: 'thinking about this...' }])).toBe(10) + expect(svc.estimateContent([{ type: 'reasoning', text: 'thinking about this...' }])).toBe(10) }) it('estimates tool-call blocks from name + arguments', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // 'bash' = 4 → 1; '{"command":"ls"}' = 16 → 4; + 4 overhead = 9 - expect(svc.estimateContentTokens([ + expect(svc.estimateContent([ { type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{"command":"ls"}' }, ])).toBe(9) }) it('estimates tool-result blocks recursively', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // inner text 5 → 2+4 = 6; outer 6 + 4 overhead = 10 - expect(svc.estimateContentTokens([ + expect(svc.estimateContent([ { type: 'tool-result', toolCallId: CallId('c1'), content: [{ type: 'text', text: 'hello' }], isError: false }, ])).toBe(10) }) it('returns 0 for empty content blocks', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) - expect(svc.estimateContentTokens([])).toBe(0) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) + expect(svc.estimateContent([])).toBe(0) }) it('honors a configured charsPerToken (fractional densities included)', () => { // 'this is a somewhat longer text block' = 36 chars. const blocks: ContentBlock[] = [{ type: 'text', text: 'this is a somewhat longer text block' }] // charsPerToken 2: ceil(36/2)+4 = 22 — a CJK-density config doubles the estimate. - const dense = new BasicCompactService(new Context(), cfg({ auto: false, charsPerToken: 2 })) - expect(dense.estimateContentTokens(blocks)).toBe(22) + const dense = new InspectableCompactService(new Context(), cfg({ auto: false, charsPerToken: 2 })) + expect(dense.estimateContent(blocks)).toBe(22) // Fractional density is legal: ceil(36/1.5)+4 = 28. - const fractional = new BasicCompactService(new Context(), cfg({ auto: false, charsPerToken: 1.5 })) - expect(fractional.estimateContentTokens(blocks)).toBe(28) - // The system-prompt term scales with the same knob: 36-char prompt at density 2 → ceil(36/2) = 18. - expect(dense.estimateTokens([], 'this is a somewhat longer text block')).toBe(18) + const fractional = new InspectableCompactService(new Context(), cfg({ auto: false, charsPerToken: 1.5 })) + expect(fractional.estimateContent(blocks)).toBe(28) }) }) @@ -1013,17 +978,17 @@ function compactRegion( model: string, signal?: AbortSignal, ) { - return svc.compactRegion(session, start, end, stubAgent(session, model), signal) + return svc.compactRegion(start, end, stubAgent(session, model), signal) } -function summarize(svc: BasicCompactService, text: string, model: string) { - return svc.summarize(text, stubAgent(new Session(SessionId('summary')), model)) +function summarize(svc: InspectableCompactService, text: string, model: string) { + return svc.summarizeForTest(text, stubAgent(new Session(SessionId('summary')), model)) } describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { it('summarizes via the registered adapter and returns its content', async () => { const { ctx, adapter } = await ctxWithModel('SUMMARY TEXT') - const svc = new BasicCompactService(ctx, cfg({ auto: false, maxTokens: 512 })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false, maxTokens: 512 })) const { summary, model, maxTokens } = await summarize(svc, 'User: hi\n\nAssistant: hello', 'test-model') expect(summary).toEqual([{ type: 'text', text: 'SUMMARY TEXT' }]) @@ -1041,7 +1006,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { it('uses maxTokens as the summarization provider cap', async () => { const { ctx, adapter } = await ctxWithModel('SUMMARY TEXT') - const svc = new BasicCompactService(ctx, cfg({ + const svc = new InspectableCompactService(ctx, cfg({ auto: false, maxTokens: 50, })) @@ -1059,7 +1024,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { // synthesized user/message summary as an orphaned call. { type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }, ]) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) const { summary } = await summarize(svc, 'User: hi', 'test-model') @@ -1068,26 +1033,26 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { it('throws when no text block remains after filtering', async () => { const { ctx } = await ctxWithBlocks([{ type: 'reasoning', text: 'private only' }]) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'User: hi', 'test-model')).rejects.toThrow(/no text summary content/) }) it('throws when no model is provided', async () => { const { ctx } = await ctxWithModel('x') - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'text', '')).rejects.toThrow(/no model available/) }) it('rethrows when the stream ends with a finish-error chunk', async () => { const ctx = await ctxWithFinish({ kind: 'error', message: 'provider 401', code: 'UNAUTHORIZED' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'text', 'test-model')).rejects.toMatchObject({ message: 'provider 401', code: 'UNAUTHORIZED' }) }) it('rethrows a finish-error chunk without a code (code stays undefined)', async () => { const ctx = await ctxWithFinish({ kind: 'error', message: 'opaque failure' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) const error = await summarize(svc, 'text', 'test-model').then(() => null, (e: unknown) => e as Error & { code?: string }) expect(error?.message).toBe('opaque failure') expect(error?.code).toBeUndefined() @@ -1095,13 +1060,13 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { it('rethrows when the stream ends with a finish-aborted chunk', async () => { const ctx = await ctxWithFinish({ kind: 'aborted' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'text', 'test-model')).rejects.toMatchObject({ message: 'summarization stream aborted', code: 'ABORTED' }) }) it('fails closed on a max-tokens finish (an incomplete checkpoint must not commit)', async () => { const ctx = await ctxWithFinish({ kind: 'max-tokens' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'text', 'test-model')).rejects.toMatchObject({ code: 'MAX_TOKENS' }) }) @@ -1129,8 +1094,9 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { const session = multiTurnSession(2, 1) const nodes = session.surface.nodes - const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') - expect(result.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) + await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') + const summaryEvent = session.events.findLast(e => e.type === 'compact/summary')! + expect(summaryEvent.data.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) // The raw summary is wrapped in the checkpoint framing on the surface. expect(session.deriveMessages()[0]!.content).toContainEqual({ type: 'text', text: 'CONDENSED' }) }) @@ -1392,10 +1358,10 @@ describe('BasicCompactService edge cases', () => { }) it('estimates unknown block types via JSON length (default branch)', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // A block whose type is none of the known kinds — exercises the default arm. const unknown = { type: 'custom-widget', payload: 'some data' } as unknown as ContentBlock - expect(svc.estimateContentTokens([unknown])).toBeGreaterThan(0) + expect(svc.estimateContent([unknown])).toBeGreaterThan(0) }) it('auto-compaction reports bounded retry exhaustion after committing a smaller summary', async () => { @@ -1604,14 +1570,15 @@ describe('BasicCompactService positional range (surface seqs are not monotonic a // First compaction: shadow the two oldest surface nodes. const nodes0 = session.surface.nodes - const first = await compactRegion(svc, session, nodes0[0]!, nodes0[1]!, 'm') + await compactRegion(svc, session, nodes0[0]!, nodes0[1]!, 'm') + const firstSummarySeq = session.events.findLast(e => e.type === 'compact/summary')!.seq // The summary node now sits at the head with a seq HIGHER than the // retained older nodes that follow it — the non-monotonic surface. (The // head is the user/message replace node, appended after the compact/summary - // provenance event, so its seq is at least first.summarySeq.) + // provenance event. const nodes1 = session.surface.nodes - expect(nodes1[0]!).toBeGreaterThanOrEqual(first.summarySeq) + expect(nodes1[0]!).toBeGreaterThan(firstSummarySeq) expect(nodes1[0]!).toBeGreaterThan(nodes1[1]!) // Second compaction: shadow [summary(head) … turn-2's step end]. The start @@ -1623,13 +1590,14 @@ describe('BasicCompactService positional range (surface seqs are not monotonic a const endSeq = nodes1[2]! expect(startSeq).toBeGreaterThan(endSeq) const second = await compactRegion(svc, session, startSeq, endSeq, 'm') + const secondSummarySeq = session.events.findLast(e => e.type === 'compact/summary')!.seq // Exactly the three nodes at surface positions [0..2] are shadowed, in // surface order — the positional slice, regardless of their seq values. expect(second.shadowedSeqs).toEqual([nodes1[0]!, nodes1[1]!, nodes1[2]!]) // The surface still derives cleanly: a new head replace node + the rest. const finalNodes = session.surface.nodes - expect(finalNodes[0]!).toBeGreaterThanOrEqual(second.summarySeq) + expect(finalNodes[0]!).toBeGreaterThan(secondSummarySeq) expect(session.deriveMessages().length).toBe(finalNodes.length) }) @@ -1679,8 +1647,9 @@ describe('BasicCompactService llm inject (real plugin-load path)', () => { const svc = ctx.compact as BasicCompactService const session = multiTurnSession(2, 1) const nodes = session.surface.nodes - const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') - expect(result.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) + await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') + const summaryEvent = session.events.findLast(e => e.type === 'compact/summary')! + expect(summaryEvent.data.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) // Tear the fiber down so this test owns no leaked registration; the // dedicated cleanup assertion lives in the "HMR safety" suite. diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index e98f00899f..fafcad76b8 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -19,7 +19,7 @@ Both methods are **abstract** — the backend owns the entire strategy (token es | Member | Semantics | |---|---| | `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` | Estimate the surface-derived history size; if over the backend's threshold, compact an older range via `compactRegion`, keeping recent context intact. Returns the `CompactionResult`, or `null` if nothing needed compacting. All parameters required — the loop's `agent/pre-step` checkpoint supplies the agent, assembled `fullSystemPrompt`, composed `sessionPrefix` (request-only messages every request carries but the derived history omits — the pressure estimate must count them), and turn `signal`. A backend's summarization request is a direct `ctx.llm.stream()` call (not a loop step), so per-call interception happens at `llm/stream`. | -| `compactRegion(session, start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. | +| `compactRegion(start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) from `agent.session` into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. | `compactIfNeeded` takes a required `signal`; `compactRegion`'s is optional. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The session being compacted comes from the agent context; the turn that the `compact/*` events belong to is recoverable from the log (the currently-open turn), so the backend stamps it from the log rather than trusting a caller-supplied value. diff --git a/packages/compact/compact/src/index.ts b/packages/compact/compact/src/index.ts index 7d1138314c..1eb73c60db 100644 --- a/packages/compact/compact/src/index.ts +++ b/packages/compact/compact/src/index.ts @@ -14,7 +14,8 @@ * implementation (deferred) / consumer (a `/compact` tool, deferred) — modeled * on the bash trio. Unlike `dsh-bash`, this interface necessarily * depends on `dsh-session` and `dsh-llm`: the contract's verbs are defined over - * a `Session` and its output is the `ContentBlock` vocabulary. That deviation + * an agent-owned `Session` and the durable summary event uses the + * `ContentBlock` vocabulary. That deviation * from the "interface depends only on cordis" guidance is intentional and * recorded in the [compaction capability-seam RFC](../../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). * @@ -132,10 +133,10 @@ export abstract class CompactService extends Service { * open (unclosed) tail step is invalid — its tool-calls have no results yet. * `dsh-session` exports `isToolPairingBalanced` for this check. * - * @param session - the session whose surface is mutated. * @param start - inclusive seq of the first surface node to compact. * @param end - inclusive seq of the last surface node to compact. - * @param agent - agent context used by router-aware summarizers. + * @param agent - agent context whose session is mutated and whose routing + * options are used by summarizers. * @param signal - optional cancellation signal. A backend that summarizes via * `ctx.llm.stream()` MUST forward this into the call's `GenerateOptions.signal` * so an abort/dispose tears down the in-flight summarization rather than @@ -146,10 +147,10 @@ export abstract class CompactService extends Service { * prior replace can leave the surface non-monotonic in seq order), or if * either boundary is not a balanced tool-pairing cut (would split a step's * tool-call/result pair). - * @returns what the compaction did (the replaced range and its summary node). + * @returns the replaced range and its token accounting. The durable + * `compact/summary` event owns the summary and bookkeeping-event identity. */ abstract compactRegion( - session: Session, start: number, end: number, agent: CompactAgentContext, diff --git a/packages/compact/compact/src/types.ts b/packages/compact/compact/src/types.ts index ba9834910f..78e94173a3 100644 --- a/packages/compact/compact/src/types.ts +++ b/packages/compact/compact/src/types.ts @@ -49,14 +49,6 @@ declare module '@deepseek-ai/dsh-session' { /** Result of a successful compaction operation. */ export interface CompactionResult { - /** The seq of the appended `compact/start` event. */ - startSeq: number - /** The seq of the appended `compact/summary` event. */ - summarySeq: number - /** The seq of the appended `compact/end` event. */ - endSeq: number - /** The summary content blocks produced by the backend. */ - summary: ContentBlock[] /** * The surface-boundary pair that was shadowed: the seqs of the first * (`start`) and last (`end`) surface nodes of the replaced range. A diff --git a/packages/compact/compact/tests/compact.spec.ts b/packages/compact/compact/tests/compact.spec.ts index c4daa8cc5a..e34c8420d9 100644 --- a/packages/compact/compact/tests/compact.spec.ts +++ b/packages/compact/compact/tests/compact.spec.ts @@ -27,28 +27,24 @@ class StubCompactService extends CompactService { } override async compactRegion( - session: Session, start: number, end: number, - _agent: CompactAgentContext, + agent: CompactAgentContext, signal?: AbortSignal, ): Promise { this.lastSignal = signal + const session = agent.session // Minimal stub honoring the lock + log-only event contract. - const startEvent = session.append('compact/start', { turn: 0 }) - const summaryEvent = session.append('compact/summary', { + session.append('compact/start', { turn: 0 }) + session.append('compact/summary', { summary: [{ type: 'text', text: 'stub' }], shadowedRange: { start, end }, shadowedSeqs: [], shadowedTokenCount: 0, model: 'stub', }) - const endEvent = session.append('compact/end', { turn: 0 }) + session.append('compact/end', { turn: 0 }) return { - startSeq: startEvent.seq, - summarySeq: summaryEvent.seq, - endSeq: endEvent.seq, - summary: [{ type: 'text', text: 'stub' }], shadowedRange: { start, end }, shadowedSeqs: [], shadowedTokenCount: 0, @@ -88,7 +84,7 @@ describe('CompactService seam', () => { const svc = new StubCompactService(ctx) const session = new Session(SessionId('s')) - const result = await svc.compactRegion(session, 0, 0, stubAgent(session, 'm')) + const result = await svc.compactRegion(0, 0, stubAgent(session, 'm')) const startEvent = session.events.find(e => e.type === 'compact/start') expect(startEvent).toBeDefined() @@ -96,8 +92,9 @@ describe('CompactService seam', () => { // verify the runtime value is absent. const raw = startEvent as unknown as { surfaceOp?: unknown } expect(raw.surfaceOp).toBeUndefined() - expect(result.summarySeq).toBeGreaterThan(result.startSeq) - expect(result.endSeq).toBeGreaterThan(result.summarySeq) + expect(result.shadowedRange).toEqual({ start: 0, end: 0 }) + expect(session.events.filter(e => e.type.startsWith('compact/')).map(e => e.type)) + .toEqual(['compact/start', 'compact/summary', 'compact/end']) }) it('threads the cancellation signal through to the backend', async () => { @@ -106,7 +103,7 @@ describe('CompactService seam', () => { const session = new Session(SessionId('s')) const controller = new AbortController() - await svc.compactRegion(session, 0, 0, stubAgent(session, 'm'), controller.signal) + await svc.compactRegion(0, 0, stubAgent(session, 'm'), controller.signal) expect(svc.lastSignal).toBe(controller.signal) await svc.compactIfNeeded(stubAgent(session), '', [], controller.signal) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index b4420e80c7..3d6ade301f 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -109,7 +109,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ summary: 'Abstract compaction service.', methods: [ 'abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise', - 'abstract compactRegion( session: Session, start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise', + 'abstract compactRegion( start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise', ], }, { @@ -624,7 +624,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'CompactionResult', - declaration: 'export interface CompactionResult {\n startSeq: number;\n summarySeq: number;\n endSeq: number;\n summary: ContentBlock[];\n shadowedRange: {\n start: number;\n end: number;\n };\n shadowedSeqs: number[];\n shadowedTokenCount: number;\n}', + declaration: 'export interface CompactionResult {\n shadowedRange: {\n start: number;\n end: number;\n };\n shadowedSeqs: number[];\n shadowedTokenCount: number;\n}', }, { name: 'ConfinedArgv', From 7a33ee94be9f4338369f388c5efe3deb4965b50d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 01:29:16 +0800 Subject: [PATCH 031/359] refactor: remove agent entry mirror --- packages/core/agent/src/index.ts | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index 7864f5938c..edb7f59a37 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -202,9 +202,6 @@ interface FactorySlot { */ export class AgentRegistry extends Service { private store = new Map() - // TODO(agent-entry-mirror): derive exact-object checks from store.get(agent.id) - // plus entry.agent identity; this WeakMap mirrors the authoritative id map. - private entries = new WeakMap() private factory: FactorySlot | undefined constructor(ctx: Context) { @@ -334,7 +331,7 @@ export class AgentRegistry extends Service { const carrier = scopeTarget(agent, agent) // This is the authoritative collision boundary. Concurrent create/resume // operations may both prepare, but only one exact entry can publish. - if (this.entries.has(agent) || this.store.has(id)) throw new Error(`agent "${id}" is already registered`) + if (this.store.has(id)) throw new Error(`agent "${id}" is already registered`) const entry: AgentEntry = { id, agent, @@ -344,7 +341,6 @@ export class AgentRegistry extends Service { detachRequested: false, } this.store.set(id, entry) - this.entries.set(agent, entry) let entered = true const detach = (): void => { if (!entered) return @@ -371,7 +367,6 @@ export class AgentRegistry extends Service { /* v8 ignore next -- enter() rejects replacement while this single-shot detach capability is live. */ if (this.store.get(entry.id) !== entry) return this.store.delete(entry.id) - this.entries.delete(entry.agent) // An insertion rolled back before announce was never externally created, // so emitting disposed would invent an impossible lifecycle edge. Marking // happens before the created emit: if a later created listener throws, @@ -403,8 +398,8 @@ export class AgentRegistry extends Service { * creation listener). */ announce(agent: Agent): void { - const entry = this.entries.get(agent) - if (entry === undefined || this.store.get(entry.id) !== entry) { + const entry = this.store.get(agent.id) + if (entry === undefined || entry.agent !== agent) { throw new Error(`agent "${agent.id}" is not live in this registry`) } if (entry.announced || entry.announcing) { From 709cc7200eb2b3ac64090c67833a25a367a1b3df Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 01:59:21 +0800 Subject: [PATCH 032/359] refactor: unify agent and session identity --- docs/config-catalog.md | 18 +- docs/cookbook/extension-cookbook.md | 4 +- docs/cordis-catalog/events.md | 34 +-- docs/cordis-catalog/services.md | 12 +- docs/core-data-structures/approval.md | 2 +- docs/core-data-structures/bash.md | 2 +- docs/core-data-structures/core.md | 8 +- docs/core-data-structures/subagent.md | 2 +- docs/event-producer-consumer.md | 34 +-- .../2026-06-11-content-block-vocabulary.md | 2 +- .../2026-06-14-session-persistence.md | 2 +- .../architecture/2026-06-20-branded-ids.md | 10 +- .../2026-06-30-event-domain-semantics.md | 2 +- .../2026-07-08-agent-scope-contexts.md | 3 +- .../feature/2026-07-08-repeat-tool-guard.md | 5 +- ...-20-remove-agent-boundary-mirror-events.md | 8 +- ...claude-code-and-codex-subagent-backends.md | 2 +- .../2026-06-20-unify-agent-and-session-id.md | 6 +- examples/coding-agent/tests/code-mode.e2e.ts | 7 +- .../coding-agent/tests/coding-task.e2e.ts | 4 +- examples/coding-agent/tests/compaction.e2e.ts | 4 +- examples/coding-agent/tests/full-loop.e2e.ts | 4 +- examples/coding-agent/tests/resume.e2e.ts | 3 - examples/coding-agent/tests/todo-write.e2e.ts | 4 +- .../cordis-agent/tests/cordis-tools.e2e.ts | 8 +- .../bash/tool-bash/tests/integration.spec.ts | 11 +- packages/bash/tool-bash/tests/tools.spec.ts | 2 +- .../tests/compact-loop-repro.spec.ts | 7 +- .../cordis/tool-cordis/src/api-catalog.ts | 16 +- .../tool-cordis/tests/integration.spec.ts | 7 +- packages/core/agent-core/README.md | 2 +- .../core/agent-core/tests/agent-core.spec.ts | 12 +- packages/core/agent-loop/README.md | 10 +- packages/core/agent-loop/src/agent.ts | 8 +- packages/core/agent-loop/src/index.ts | 29 ++- packages/core/agent-loop/tests/agent.spec.ts | 53 +++-- packages/core/agent-loop/tests/cancel.spec.ts | 35 ++-- .../tests/config-session-id.spec.ts | 29 +-- .../agent-loop/tests/coverage-edges.spec.ts | 21 +- .../agent-loop/tests/interception.spec.ts | 62 +++--- packages/core/agent-loop/tests/loop.spec.ts | 85 ++++---- .../core/agent-loop/tests/properties.spec.ts | 11 +- .../agent-loop/tests/request-cache.e2e.ts | 7 +- .../tests/request-reconstruction.spec.ts | 22 +- packages/core/agent-loop/tests/resume.spec.ts | 85 ++++---- .../agent-loop/tests/review-fixes.spec.ts | 83 ++++---- .../agent-loop/tests/scope-lifecycle.spec.ts | 193 ++++++++---------- .../core/agent-loop/tests/tool-order.spec.ts | 9 +- .../core/agent-loop/tests/turn-stop.spec.ts | 19 +- packages/core/agent/README.md | 2 +- packages/core/agent/src/index.ts | 28 ++- packages/core/agent/src/types.ts | 20 +- packages/core/agent/tests/agent.spec.ts | 29 +-- packages/core/session/src/index.ts | 7 +- packages/core/tools/tests/code-mode.spec.ts | 3 +- packages/core/tools/tests/scoped.spec.ts | 14 +- packages/fs/tool-fs/tests/fs-tools.e2e.ts | 4 +- packages/guard/repeat-tool-guard/README.md | 4 +- packages/guard/repeat-tool-guard/src/index.ts | 19 +- .../tests/repeat-tool-guard.spec.ts | 39 ++-- .../hooks/hooks-claude/tests/bridge.spec.ts | 31 +-- .../hooks/hooks-claude/tests/coverage.spec.ts | 73 +++---- .../hooks/hooks-codex/tests/bridge.spec.ts | 17 +- .../hooks/hooks-codex/tests/coverage.spec.ts | 73 +++---- packages/subagent/subagent-acp/src/run.ts | 4 +- .../tests/multi-subagent.spec.ts | 7 +- .../subagent-fork/tests/subagent-fork.spec.ts | 7 +- .../subagent/subagent-inprocess/src/index.ts | 7 +- .../tests/structured.spec.ts | 9 +- .../tests/subagent-inprocess.spec.ts | 7 +- .../subagent-spawn/tests/spawn.e2e.ts | 4 +- .../tests/subagent-spawn.spec.ts | 13 +- packages/subagent/subagent/src/index.ts | 7 +- packages/subagent/subagent/src/types.ts | 5 +- .../subagent/subagent/tests/service.spec.ts | 12 +- .../tool-subagent/tests/tool-subagent.spec.ts | 24 ++- packages/support/subagent-mock/src/index.ts | 4 +- .../subagent-mock/tests/subagent-mock.spec.ts | 6 +- .../todo/tool-todo/tests/integration.spec.ts | 9 +- .../todo/tool-todo/tests/tool-todo.spec.ts | 5 +- packages/ui/acp/src/index.ts | 3 - packages/ui/acp/tests/approval.spec.ts | 6 +- packages/ui/acp/tests/bridge.spec.ts | 24 +-- packages/ui/acp/tests/dispose.spec.ts | 43 ++-- packages/ui/acp/tests/edges.spec.ts | 3 +- packages/ui/acp/tests/load.spec.ts | 9 +- packages/ui/acp/tests/multi-session.spec.ts | 6 +- packages/ui/acp/tests/turns.spec.ts | 6 +- packages/ui/jsonrpc/src/server.ts | 2 - packages/ui/jsonrpc/tests/server.spec.ts | 27 +-- packages/ui/stdio-agent/README.md | 8 +- packages/ui/stdio-agent/src/index.ts | 23 +-- packages/ui/stdio-agent/src/stdio-chat.ts | 40 ++-- .../ui/stdio-agent/tests/readline.spec.ts | 2 +- .../ui/stdio-agent/tests/stdio-agent.spec.ts | 16 +- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 60 +++--- packages/util/brand/README.md | 4 +- packages/util/brand/src/index.ts | 8 +- .../tool-workflow/tests/tool-workflow.spec.ts | 6 +- .../workflow-workerthread/src/runtime.ts | 4 +- .../tests/integration.spec.ts | 9 +- .../tests/source-worker.compat.spec.ts | 4 +- .../tests/workflow-workerthread.e2e.ts | 8 +- .../tests/workflow-workerthread.spec.ts | 20 +- packages/workflow/workflow/src/types.ts | 5 +- 105 files changed, 899 insertions(+), 948 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 9d4b8038b5..94d613bc4e 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -31,7 +31,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:250`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:249`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-agent` @@ -117,8 +117,8 @@ Requires: `agents` · `sessions` · `llm` · `tools` · `systemPrompt` export interface Config { /** Agents created or resumed at plugin startup. */ agents: (AgentOptions & { - /** Registry identity for the live agent. */ - id: AgentId + /** Stable config label used in logs and as the fresh combined-id prefix. */ + id: string /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -127,9 +127,9 @@ export interface Config { } ``` -Depends on: [`AgentId`](../packages/core/agent/src/index.ts) · [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) +Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:325`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:324`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` @@ -611,7 +611,7 @@ Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-l ```ts config-catalog /** * App config: the swappable per-demo values, each routed to where the app wires - * it. `model`/`resumeSessionId` configure the pre-created `main` agent (through + * it. `model`/`resumeSessionId` configure the pre-created agent (through * {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list); `persona` is * the deployment persona (forwarded to the system-prompt plugin); `toolOrder` * is the explicit model-facing tool order (forwarded to the system-prompt plugin); @@ -620,7 +620,7 @@ Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-l * `welcome` is the UI banner. */ export interface Config { - /** Model name for the `main` agent (must have a registered adapter). */ + /** Model name for the pre-created agent (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ persona?: string @@ -635,7 +635,7 @@ export interface Config { /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-core. */ skills?: agentCore.SkillConfig /** - * If set, the `main` agent RESUMES this persisted session id instead of + * If set, the pre-created agent RESUMES this persisted session id instead of * starting fresh. Sourced from an env var in the leaf `cordis.yml` * (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`). */ @@ -645,7 +645,7 @@ export interface Config { Depends on: [`agentCore`](../packages/core/agent-core/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/ui/stdio-agent/src/index.ts:65`](../packages/ui/stdio-agent/src/index.ts) +Source: [`packages/ui/stdio-agent/src/index.ts:64`](../packages/ui/stdio-agent/src/index.ts) ## `@deepseek-ai/dsh-subagent-acp` diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index e2677e463a..1db5e85828 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -36,7 +36,7 @@ A UI plugin renders from the `session/event` feed (the assistant token stream as ```ts import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' declare function render(text: string): void declare function onUserInput(handler: (text: string) => void): void @@ -50,7 +50,7 @@ export function apply(ctx: Context) { render(event.data.chunk.text) } }) - onUserInput(text => ctx.agents.get(AgentId('main'))?.send([{ type: 'text', text }])) + onUserInput(text => ctx.agents.get(SessionId('client-session'))?.send([{ type: 'text', text }])) } ``` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 5a3398f9a8..a5e018079a 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -23,7 +23,7 @@ An agent's fully composed scoped world was published in the AgentRegistry. Its s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:316`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:304`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -35,7 +35,7 @@ An agent was removed from the registry. The concrete AgentLoop lifecycle emits t Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:331`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:319`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:605`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:593`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -61,7 +61,7 @@ Serial (awaited in registration order), not a waterfall: a listener mutates the Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:438`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:426`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -73,7 +73,7 @@ Waterfall: decide what happens to ONE drained queued message before it becomes a Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:456`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:444`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -85,7 +85,7 @@ A message entered the agent's inbox (queued or steering). Content and the resolv Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:360`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:348`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -97,7 +97,7 @@ Waterfall: shape the step's call configuration — model switching, sampling ove Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:485`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:473`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -113,7 +113,7 @@ The seed is a frozen empty list; a contributing listener returns a NEW array — Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:537`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:525`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -125,7 +125,7 @@ The agent's session lifecycle began, fired once before its first turn. `source` Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:381`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:369`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -137,7 +137,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). Drive lifecycle Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:345`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:333`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -149,7 +149,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:552`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:540`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -161,7 +161,7 @@ Waterfall: override the turn-continuation decision via a typed ContinuationDecis Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:570`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:558`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -173,7 +173,7 @@ Serial terminal-stop checkpoint after the ordinary `agent/turn-continuation` wat Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:588`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/types.ts) ## `approval/*` @@ -317,7 +317,7 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c 'subagent/end'(this: Scoped, info: SubagentRunEndInfo): void ``` -Source: [`packages/subagent/subagent/src/index.ts:90`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:91`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-added` — emit @@ -327,7 +327,7 @@ A provider became resolvable in the registry. 'subagent/provider-added'(provider: SubagentProvider): void ``` -Source: [`packages/subagent/subagent/src/index.ts:66`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:67`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-removed` — emit @@ -337,7 +337,7 @@ A provider left the registry. Accepted runs remain holder-owned. 'subagent/provider-removed'(name: string): void ``` -Source: [`packages/subagent/subagent/src/index.ts:72`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:73`](../../packages/subagent/subagent/src/index.ts) ### `subagent/start` — emit @@ -347,7 +347,7 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( 'subagent/start'(this: Scoped, info: SubagentRunInfo): void ``` -Source: [`packages/subagent/subagent/src/index.ts:82`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:83`](../../packages/subagent/subagent/src/index.ts) ## `system-prompt/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index bfb31749d5..4d162a55f5 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -14,12 +14,12 @@ The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary Concrete ReactLoopAgent factory and driver service. ```ts cordis-catalog -create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent +create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:338`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:337`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` @@ -32,13 +32,13 @@ async resume(options: ResumeAgentOptions): Promise register(agent: Agent): () => void enter(agent: Agent): () => void announce(agent: Agent): void -get(id: AgentId): Agent | undefined +get(id: SessionId): Agent | undefined list(): Agent[] ``` Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/index.ts:203`](../../packages/core/agent/src/index.ts) +Source: [`packages/core/agent/src/index.ts:199`](../../packages/core/agent/src/index.ts) ## `ctx.approval` — `ApprovalService` @@ -218,7 +218,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:592`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:597`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` @@ -244,7 +244,7 @@ list(): string[] async start(name: string, request: SubagentStartRequest): Promise ``` -Source: [`packages/subagent/subagent/src/index.ts:123`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:124`](../../packages/subagent/subagent/src/index.ts) ## `ctx.systemPrompt` — `SystemPrompt` diff --git a/docs/core-data-structures/approval.md b/docs/core-data-structures/approval.md index c5fa1fe13b..e8820ccfeb 100644 --- a/docs/core-data-structures/approval.md +++ b/docs/core-data-structures/approval.md @@ -6,7 +6,7 @@ Source: [`packages/ui/user-approval/src/index.ts`](../../packages/ui/user-approv ## Identity and outcome -Every request receives a fresh `ApprovalRequestId`. The brand pairs the `approval/asked` and `approval/decided` audit events without making approval ids interchangeable with tool-call, session, or agent ids. +Every request receives a fresh `ApprovalRequestId`. The brand pairs the `approval/asked` and `approval/decided` audit events without making approval ids interchangeable with tool-call or agent/session ids. ```ts type-equiv type ApprovalRequestId = Branded<'ApprovalRequestId'> diff --git a/docs/core-data-structures/bash.md b/docs/core-data-structures/bash.md index 51f7cb0696..df6c5ab16b 100644 --- a/docs/core-data-structures/bash.md +++ b/docs/core-data-structures/bash.md @@ -110,7 +110,7 @@ The `owner` token is the isolation key: the executor stores it but never interpr `stdin` and `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its JSON payload on stdin and its `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` env. The model-facing `dsh-tool-bash` tool does not expose them as parameters — its request is built from `command`/`workdir`/`timeoutMs`/`signal`/`owner` only — because a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), so duplicating them as tool params would be redundant. This is NOT a security boundary: the credential scrub in `dsh-bash-local` is what stops the harness's ambient secrets reaching a spawned command, and it works regardless of these fields (a model cannot read a value the scrub removed, and tool-call args are static JSON, never shell-evaluated). A guard test asserts the tool doesn't forward model `env`/`stdin` — to catch a future `...args` spread, not to defend a trust wall. `env` is merged AFTER the scrub so an explicit caller entry (a value it already holds) wins even on a credential-shaped name. See [the bash-stdin-env RFC](../rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). -Both ids the seam handles are [branded](core.md) (zero-cost `string` brands, the same machinery as `SessionId`/`AgentId`): `BashTaskId` (a tracked background task, generated `bash-N` by the local executor) and `OwnerToken` (the opaque isolation key). `OwnerToken` is deliberately a DISTINCT brand from `SessionId`, not an alias: the bash seam is a capability seam that must not know what an owner token *means*, so it never imports `dsh-session`'s vocabulary — the `dsh-tool-bash` consumer is the single boundary that casts the owning agent's `SessionId` into an `OwnerToken`. Branding both stops a raw `string` (or a `BashTaskId` where an `OwnerToken` is expected, or vice versa) from slipping through the type checker on the model-facing `task_id` path. +Both ids the seam handles are [branded](core.md) (zero-cost `string` brands, the same machinery as `SessionId`): `BashTaskId` (a tracked background task, generated `bash-N` by the local executor) and `OwnerToken` (the opaque isolation key). `OwnerToken` is deliberately a DISTINCT brand from `SessionId`, not an alias: the bash seam is a capability seam that must not know what an owner token *means*, so it never imports `dsh-session`'s vocabulary — the `dsh-tool-bash` consumer is the single boundary that casts the owning agent's `SessionId` into an `OwnerToken`. Branding both stops a raw `string` (or a `BashTaskId` where an `OwnerToken` is expected, or vice versa) from slipping through the type checker on the model-facing `task_id` path. ## Foreground runs: `BashRunResult` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 168d727c8d..c6b74ed3c0 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -73,7 +73,7 @@ Two large discriminated unions are the ones consumers `switch` over most: **`Str ## Branded IDs -IDs that cross package boundaries are **branded** — structurally strings, but non-interchangeable at the type level (an `AgentId` can't be passed where a `CallId` is expected). Construction goes through a per-type factory; comparison, logging, and JSON behave as ordinary strings. +IDs that cross package boundaries are **branded** — structurally strings, but non-interchangeable at the type level (a `SessionId` cannot be passed where a `CallId` is expected). Construction goes through a per-type factory; comparison, logging, and JSON behave as ordinary strings. The `Branded` primitive lives in its own type-only package, [dsh-brand](../../packages/util/brand) (no runtime code, no harness-package dependency), so any package can brand the ids it owns without depending on an unrelated capability package (e.g. dsh-bash brands `BashTaskId`/`OwnerToken` via dsh-brand alone, never pulling in dsh-llm). @@ -83,7 +83,7 @@ Source: [`packages/util/brand/src/index.ts`](../../packages/util/brand/src/index type Branded = string & { readonly [BRAND]: B } ``` -The three core IDs: `CallId` (correlates a tool call with its result; dsh-llm), `SessionId` (dsh-session), `AgentId` (dsh-agent). Each is `Branded<'CallId'>` etc. plus a same-named factory function. Capability seams brand their own ids too — see `BashTaskId`/`OwnerToken` in [bash.md](bash.md). +The two core IDs are `CallId` (correlates a tool call with its result; dsh-llm) and `SessionId` (the shared live agent and durable session identity; dsh-session). Each is a `Branded<'…'>` plus a same-named factory function. Capability seams brand their own ids too — see `BashTaskId`/`OwnerToken` in [bash.md](bash.md). ## Content blocks and messages @@ -254,7 +254,7 @@ Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types ```ts type-equiv interface Agent { - readonly id: AgentId + readonly id: SessionId readonly options: AgentOptions readonly session: Session readonly status: AgentStatus @@ -353,7 +353,7 @@ interface Agent { } ``` -`AgentStatus` is `'idle' | 'running' | 'disposed'`. `AgentId` is a branded string. `AgentOptions` (`model?`) is merge-extensible — plugins add creation options by declaration merging. Persona is not an agent option: the `dsh-system-prompt` config supplies the global default, and an agent-scoped `deployment:persona` section may shadow it. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, serial `agent/pre-step`/`agent/turn-stop` checkpoints, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits. +`AgentStatus` is `'idle' | 'running' | 'disposed'`. `Agent.id` and `Agent.session.id` are the same branded `SessionId`. `AgentOptions` (`model?`) is merge-extensible — plugins add creation options by declaration merging. Persona is not an agent option: the `dsh-system-prompt` config supplies the global default, and an agent-scoped `deployment:persona` section may shadow it. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, serial `agent/pre-step`/`agent/turn-stop` checkpoints, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits. ## Interception decisions diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 5454f326b3..883c33020a 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -68,7 +68,7 @@ The handle the consumer holds after a provider has established a ready child. Th ```ts type-equiv interface SubagentRun { - readonly id: AgentId + readonly id: SessionId readonly result: Promise dispose(): Promise sendMessage?(content: ContentBlock[]): void diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index a7e2c8bb37..80389608cc 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,19 +7,19 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:316`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:331`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:605`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:438`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:456`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:360`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:485`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:537`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:381`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:345`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:552`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:570`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:588`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:444`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:348`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:473`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:525`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:540`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:558`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:576`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:70`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:123`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:138`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | @@ -31,10 +31,10 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:100`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | | `skill/provider-added` | `emit` | [`packages/skill/skill/src/index.ts:131`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - | | `skill/provider-removed` | `emit` | [`packages/skill/skill/src/index.ts:137`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - | -| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:90`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | -| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:66`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:72`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:82`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | +| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:91`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | +| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:67`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | +| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:73`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | +| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:49`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:59`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:173`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | diff --git a/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md b/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md index 42efb34774..fb272c5df9 100644 --- a/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md +++ b/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md @@ -21,4 +21,4 @@ In-session context injection (`context/message`, `steering/message`) renders as - Reasoning has a home without provider contortions. Multimodal content deliberately has NO core block type: the core set is limited to blocks every shipping path honors, and a multimodal feature adds its block type through the merge-extensible map in the same coordinated change that maps it in the adapters, surfaces it in the UI bridges, and prices it in compaction — see [the drop-image RFC](../simplification/2026-07-04-drop-image-content-block.md). Block cache hints likewise have no core field: DeepSeek prompt caching is automatic, so no shipping adapter can transmit a hint; a caching feature adds a `cache` field together with the adapter that honors it — see [the producer-less-variants RFC](../simplification/2026-07-04-prune-producerless-vocabulary-variants.md). Assistant-prefix continuation (prefill) likewise has no request field: DeepSeek's chat-prefix completion is a Beta feature on a base URL neither shipping adapter targets, so a prefill feature adds `GenerateOptions.prefill` together with the adapter that honors it — see [the inert-request-knobs RFC](../simplification/2026-07-04-drop-inert-request-knobs.md). - Every adapter pays a translation cost; the first real adapters have since validated the streaming protocol, and new adapters should continue proving their provider-specific mapping in adapter-local tests. -- IDs that cross package boundaries are branded (`CallId`, `SessionId`, `AgentId`) — nominal typing at zero runtime cost. +- IDs that cross package boundaries are branded (`CallId`, the shared agent/session `SessionId`) — nominal typing at zero runtime cost. diff --git a/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md b/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md index 03d8a30b37..824e59a172 100644 --- a/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md +++ b/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md @@ -23,7 +23,7 @@ Key choices recorded here because they are durable, contested, and surprising: - **Append-only; a crashed turn is closed, never truncated.** Committed events — those at or below a flushed `turn/end` — are never rewritten. The loop only flushes at `turn/end`, so a crash can leave a durable log whose final turn never closed: real, fully-written events sit after the last `turn/end`. **A single turn can be huge in a long-horizon task** (many steps, large tool output spanning a long autonomous run), so discarding the interrupted turn would silently destroy a large amount of real work — truncating a turn is wrong. Instead, on reload `load` PRESERVES those events and CLOSES the orphaned turn by durably appending the minimal synthetic boundary events: an error `tool/result` for every `tool-call` the crash left unanswered, then a `step/end` if a step was still open, then a `turn/end` carrying the merge-extensible `{ kind: 'interrupted' }` reason (a marker that records the turn was cut short by a crash, not completed by the model — no loop ever emits it). The synthetic tool results matter for resume correctness: the loop logs the `assistant/message` (carrying the `tool-call` blocks) BEFORE running the tools, so a crash mid-tool leaves calls without results; `deriveMessages()` would then replay a dangling assistant tool-call, which every provider rejects as an invalid transcript on the next request. Answering each orphaned call with an error result keeps the rehydrated history valid. `load` returns the balanced log, so a resumed session is immediately usable. The ONLY thing discarded is a never-fully-written **torn tail fragment** — a final record whose bytes (JSONL) or row were never completely flushed; that fragment is not a valid event and is dropped before the synthetic closers are written. A parse error or `seq` gap in the COMMITTED region (at or before the last real `turn/end`) is genuine corruption and makes the session unloadable. - **File backend canonical, DB backend a proven drop-in.** `SessionEvent` maps 1:1 onto a row `(session_id, seq, type, time, data)` — `append` is INSERT (in a transaction asserting the contiguous-seq contract), `load` is SELECT … ORDER BY seq. `dsh-session-persistence-sqlite` is exactly this: a `SessionPersistence` subclass with no interface change (opencode runs this exact shape on SQLite/WAL), and it passes the same `runPersistenceContract` suite as the JSONL backend — so the contract holds both backends to identical semantics (lazy materialization, interrupted-turn close on load, contiguous-seq), expressed once over file bytes and once over rows. - **Metadata is out-of-log.** Format version, cwd, and lineage are storage concerns, not replayable conversation state, so they live in a `SessionHeader` owned by `dsh-session` and attached to a `Session` via a new readonly `session.header` — never in `SessionEventMap`, never reaching `deriveMessages()`. The alternative (a merge-extensible `session/meta` event as log line 0) was rejected: an in-log event would ride along with a seeded/forked session for free, but metadata is not replayable state, so the explicit out-of-log header seam is the cleaner cost. (The header was originally split into an immutable `SessionHeader` plus a mutable `SessionSummary` whose union was `SessionMeta`; the mutable summary was later removed as dead state — see [Drop the mutable session summary](../simplification/2026-06-19-drop-mutable-session-summary.md).) -- **`ctx.agents.create()` and `ctx.agents.resume()` are async factories; resume additionally crosses the persistence boundary.** `ctx.agents.resume({ resumeSessionId })` awaits `ctx.sessionPersistence.load`, recreates the live session with the loaded events (so `lastTurnNumber`/`deriveMessages` continue), and starts a fresh agent on the resumed id (NOT `${agentId}-session`). The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent. +- **`ctx.agents.create()` and `ctx.agents.resume()` are async factories; resume additionally crosses the persistence boundary.** `ctx.agents.resume({ resumeSessionId })` awaits `ctx.sessionPersistence.load`, recreates the live session with the loaded events (so `lastTurnNumber`/`deriveMessages` continue), and registers the fresh agent under the exact resumed id. The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent. ## Alternatives considered diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 8171a05d30..5fe8224644 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -4,23 +4,23 @@ Status: implemented ## Problem -The harness already brands three identifiers — `CallId` (`packages/llm/llm/src/brand.ts`), `SessionId` (`packages/core/session/src/types.ts`), and `AgentId` (`packages/core/agent/src/types.ts`) — using the `Branded = string & { readonly [BRAND]: B }` machinery (owned by the type-only `@deepseek-ai/dsh-brand` package at `packages/util/brand/` — see its [README](../../../../packages/util/brand/README.md)) and a zero-cost cast factory per type. `dsh-brand` also states the governing policy: *"Branding is for ids that cross package boundaries and could plausibly be confused; not every string needs a brand."* That policy is right; the problem is that it is only half-applied. Two gaps let a structurally-identical-but-semantically-wrong string slip through the type checker today. +The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared agent/session `SessionId` (`packages/core/session/src/types.ts`) using the `Branded = string & { readonly [BRAND]: B }` machinery (owned by the type-only `@deepseek-ai/dsh-brand` package at `packages/util/brand/` — see its [README](../../../../packages/util/brand/README.md)) and a zero-cost cast factory per type. `dsh-brand` also states the governing policy: *"Branding is for ids that cross package boundaries and could plausibly be confused; not every string needs a brand."* That policy is right; the problem is that it is only half-applied. Two gaps let a structurally-identical-but-semantically-wrong string slip through the type checker today. **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias that the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal calls the "bash owner-token alias hole". -**Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId`/`SessionId`/`AgentId` decay back to bare `string` at exactly the places confusion is most likely: the registry/store `Map` key types and most public method params. Representative sites: `SessionStore.store = new Map()` and `create`/`prepare(id?: string)`/`get(id: string)` (`packages/core/session/src/index.ts`); `AgentRegistry.store = new Map()` and `register`/`get(id: string)` (`packages/core/agent/src/index.ts`); `ToolPresenter.pending = new Map()` keyed by call id and `call(callId: string)`/`result(callId: string)` (`packages/ui/acp/src/index.ts`); the ACP session-id surface beyond the store map — `SessionRecord.sessionId: string`, `bySession = new WeakMap()`, `loadingIds = new Set()`, `requireSession(sessionId: string)`, and the exported `streamSessionEventUpdate(sessionId: string, …)` (`packages/ui/acp/src/index.ts`); and the persistence coordinator's `Map` keyed by session id (`packages/session-persistence/session-persistence/src/coordinator.ts`). A brand that is dropped at the `Map` key buys nothing on lookups — the value of the existing brands is partly unrealized. +**Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. ## Decision A type-only change. Brands are zero-cost casts; nothing about runtime behavior, serialization, comparison, or the wire format changes. The work is in three parts, all honoring the existing "not every string" policy. -- **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-brand` exactly as `SessionId`/`AgentId` already do. The brand primitive lives in the dependency-free `dsh-brand` utility package precisely so `dsh-bash` can brand its ids by depending on it alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). +- **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-brand` exactly as `SessionId` does. The brand primitive lives in the dependency-free `dsh-brand` utility package precisely so `dsh-bash` can brand its ids by depending on it alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). - **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's `session.header.id` (a `SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash seam never imports `dsh-session`. (Rationale in the next section.) -- **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `get(id: SessionId)`, `Map`, `Map`, the ACP `SessionRecord.sessionId: SessionId` surface, the coordinator's `Map`. This is the larger mechanical share of the diff and the part that makes the *existing* brands actually load-bearing on lookups, not just on the struct fields. +- **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `Map`, `get(id: SessionId)`, `Map`, ACP's `SessionId` surface, and the coordinator's `Map`. This is the larger mechanical share of the diff and the part that makes the *existing* brands actually load-bearing on lookups, not just on struct fields. Illustrative shape (the factory pattern is identical to the three existing brands): @@ -58,7 +58,7 @@ Kept deliberately narrow per the "not every string needs a brand" policy. Each o ## Verification -The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` and threaded end-to-end (executor seam, the `dsh-bash-local` generation site, the `dsh-tool-bash` model-facing surface) with no `dsh-bash` dependency on `dsh-session`; no collection keyed by an in-scope branded id (`CallId`/`SessionId`/`AgentId`/`BashTaskId`) is keyed by bare `string` — `Map` keys, `WeakMap` value slots, `Set` membership (the ACP `bySession`/`loadingIds`), public method params, and exported signatures (`streamSessionEventUpdate`) all take the brand; and brands are constructed via the cast factory at each boundary where a raw string enters (provider call id, ACP session id, model-supplied `task_id`), never as scattered `as` casts. +The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` and threaded end-to-end (executor seam, the `dsh-bash-local` generation site, the `dsh-tool-bash` model-facing surface) with no `dsh-bash` dependency on `dsh-session`; no collection keyed by an in-scope branded id (`CallId`/`SessionId`/`BashTaskId`) is keyed by bare `string`; public method params and exported signatures keep the brand; and brands are constructed via the cast factory at each boundary where a raw string enters (provider call id, ACP session id, model-supplied `task_id`), never as scattered `as` casts. ## Consequences diff --git a/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md b/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md index f0ab95ca80..f785851237 100644 --- a/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md +++ b/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md @@ -24,7 +24,7 @@ This is the foundational change in a stack that adds a Hooks subsystem; it estab **The boundary rule:** a durable, replayable fact is a `SessionEvent`; a live interception or a transient/live-object signal is an `agent`/`tools` Cordis event. A turn or step boundary is a durable fact, so it lives in the session log and is read off the `session/event` feed — it is NOT mirrored as an `agent/*` emit. -**Applying the rule to the boundary twins:** all four boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are **REMOVED**. No production consumer needs the live `Agent` at a boundary: the ACP bridge settles from `session/event` `turn/end` plus `agent/status`, and the only turn-mirror consumer (`dsh-ui-stdio`, a disposable test REPL) was migrated to render boundaries from `session/event`, recovering the short agent label from an `agent/created`→id map. The step mirrors were removed first (they had no consumer at all); the turn mirrors followed once ui-stdio was migrated — see [the remove-boundary-mirror-events RFC](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md), which owns that decision. Removing the emits also simplifies the loop's `closeStep`/`closeTurn` (one append each, no paired emit). +**Applying the rule to the boundary twins:** all four boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are **REMOVED**. No production consumer needs the live `Agent` at a boundary: the ACP bridge settles from `session/event` `turn/end` plus `agent/status`, and the only turn-mirror consumer (`dsh-ui-stdio`, a disposable test REPL) renders boundaries from `session/event` while retaining its live target object for the fixed `main` label. The step mirrors were removed first (they had no consumer at all); the turn mirrors followed once ui-stdio was migrated — see [the remove-boundary-mirror-events RFC](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md), which owns that decision. Removing the emits also simplifies the loop's `closeStep`/`closeTurn` (one append each, no paired emit). ## Consequences diff --git a/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md b/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md index dcff4d3220..15477e023a 100644 --- a/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md +++ b/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md @@ -60,8 +60,7 @@ The ordinary contributor pattern is to register the complete local world during ```js const handle = await ctx.agents.create({ - agentId: AgentId('reviewer'), - sessionId: SessionId('reviewer-session'), + sessionId: SessionId('reviewer'), agentOptions: { model: 'model-name' }, setup(agentCtx) { agentCtx.systemPrompt.section({ diff --git a/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md b/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md index 9d0446dcad..6961883318 100644 --- a/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md +++ b/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md @@ -12,11 +12,10 @@ The harness already has every seam the pi extension uses, and better ones: [the The guard is a loop-hygiene plugin, not a model-facing tool: it never appears in the tool list, never vetoes or rewrites a call, and adds exactly one behavior — it watches each agent's stream of tool calls, counts runs of consecutive calls to the same tool with identical canonicalized arguments, and at configured run lengths injects an escalating advisory reminder telling the model to stop repeating itself, re-read the last result, and either change approach or conclude. The purpose is to break unproductive loops within a few wasted steps instead of letting them run to the turn's natural end — while leaving the decision (retry differently, gather more evidence, or finish) entirely with the model, so a legitimately repeated call is delayed by nothing and blocked by nothing. -The plugin is `@deepseek-ai/dsh-repeat-tool-guard` at `packages/guard/repeat-tool-guard/`, opening the `guard/` group for loop-hygiene plugins (single-package groups have precedent: [the todo-write RFC](2026-06-29-todo-write-tool.md) shipped `todo/tool-todo`). It registers three listeners and holds all state in plugin-local maps keyed by `AgentId` — the tool registry is a context-level singleton whose waterfalls interleave every agent's calls (subagents run on the same context), so per-agent keying is correctness, not polish. +The plugin is `@deepseek-ai/dsh-repeat-tool-guard` at `packages/guard/repeat-tool-guard/`, opening the `guard/` group for loop-hygiene plugins (single-package groups have precedent: [the todo-write RFC](2026-06-29-todo-write-tool.md) shipped `todo/tool-todo`). It registers two listeners and holds state in a `WeakMap` keyed by the live `Agent` object — the tool registry is a context-level singleton whose waterfalls interleave every agent's calls (subagents run on the same context), so per-agent keying is correctness, not polish; weak object keys also make a disposal-only cleanup listener unnecessary. - **`tools/post-execute` (waterfall)** — the one detection point. The listener receives `(exec, result)` together, so counting and reminder delivery need no cross-event pending map (the pi extension needs one only because its `tool_call`/`tool_result` hooks are separate events). It always delegates via `next()` and, when a threshold is hit, folds a reminder onto the downstream decision's `additionalContext` — the observe-and-enrich posture [the hooks bridges](2026-06-30-hook-bridges.md) already use, honoring the waterfall contract. Counting happens here rather than in `tools/pre-execute` because post-execute also runs for denied calls (`ToolRegistry.execute` routes a deny through the same pipeline), and a model hammering a denied call is exactly the loop worth breaking. - **`agent/prompt-submit` (waterfall)** — pure reset hook: delegate via `next()`, clear the submitting agent's chain. A user interjection changes the context; repetition across it is not a loop. -- **`agent/status` (emit)** — on `disposed`, drop the agent's state, bounding the maps over harness lifetime. ### Detection semantics @@ -25,7 +24,7 @@ The chain key is `(tool name, canonical arguments)`; a call identical to the pre Two deliberate rules, both documented in [the package README](../../../../packages/guard/repeat-tool-guard/README.md) because they are behavior a reader would otherwise guess at: - **Untracked calls are transparent to the chain.** A call excluded by `include`/`exclude` neither increments nor resets the counter, so `grep X → todo_write → grep X` still counts as two consecutive `grep X` when `todo_write` is excluded. This is what makes exclusion useful — bookkeeping tools interleaved into a loop must not launder it — and it is the pi extension's (undocumented) semantics, kept on purpose and written down. -- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller (tests, non-loop consumers) has no model to remind and no `AgentId` to key on. +- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller (tests, non-loop consumers) has no model to remind and no live agent object to key on. ### Reminder delivery diff --git a/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md b/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md index dbef22f3a3..f4b49281ea 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md +++ b/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md @@ -21,9 +21,9 @@ This duplication is not free. Every lifecycle change had to update the session e Make `session/event` the single live boundary/transcript stream. Consumers that render turns, tool calls, tool results, assistant messages, and durable boundaries subscribe to `session/event` and derive their UI from the same event vocabulary persistence uses. -The four durable-boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are removed from the agent event taxonomy. A UI that wants the agent handle (or its short id) at a boundary keeps a small map from session id to agent id built from `agent/created`/`agent/disposed`; `dsh-ui-stdio` does exactly this to label its `[ turn N]` header, since the `turn/start` session event carries only the turn number. The canonical record remains the event-sourced session log. +The four durable-boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are removed from the agent event taxonomy. A UI that wants the agent handle at a boundary retains the live target object from `agent/created`/`agent/disposed` and compares its session directly; `dsh-ui-stdio` uses this to label the app-owned agent's `[main turn N]` header while other sessions render their durable id. The canonical record remains the event-sourced session log. -The step mirrors (which had no consumer at all) were removed first, in [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md); that RFC KEPT the turn mirrors on the stated justification that the stdio UI needed the `Agent` handle at the turn boundary. This RFC finishes the job: `dsh-ui-stdio` is a disposable test REPL whose rendering can change freely, so "ui-stdio needs it" is not a reason to keep a mirror — it was migrated to `session/event` + the id map, and the turn mirrors were removed too. +The step mirrors (which had no consumer at all) were removed first, in [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md); that RFC KEPT the turn mirrors on the stated justification that the stdio UI needed the `Agent` handle at the turn boundary. This RFC finishes the job: `dsh-ui-stdio` is a disposable test REPL whose rendering can change freely, so "ui-stdio needs it" is not a reason to keep a mirror — it reads `session/event` and retains only its live target object. ## Scope: what is and isn't removed @@ -38,8 +38,8 @@ RETAINED — NOT durable-boundary mirrors, so out of scope for this decision: ## Alternatives considered - **Bundling `agent/steering` into the removal** — the original proposal's shape; narrowed out as scope creep: it mirrors the durable `steering/message` control record, not a boundary, and was removed by [its own later decision](2026-07-04-remove-agent-steering-mirror.md) (as was `agent/stream-chunk`, by [the stream-chunk-mirror RFC](2026-07-02-remove-stream-chunk-mirror.md)). -- **Keeping the turn mirrors for the stdio UI** — [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md)'s original stance; rejected here because `dsh-ui-stdio` is a disposable test REPL, not a load-bearing consumer, and it renders boundaries from `session/event` + the id map instead. +- **Keeping the turn mirrors for the stdio UI** — [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md)'s original stance; rejected here because `dsh-ui-stdio` is a disposable test REPL, not a load-bearing consumer, and it renders boundaries from `session/event` plus its live target object instead. ## Consequences -A plugin can no longer observe turn/step boundaries from a convenient `Agent`-first event. It must either subscribe to `session/event` or maintain a session-to-agent association. That is an acceptable trade: boundary consumers should not depend on a second event feed that can drift from the durable log. +A plugin can no longer observe turn/step boundaries from a convenient `Agent`-first event. It subscribes to `session/event` and, if it needs the live object, resolves the shared id through `ctx.agents` or retains the object it already owns. That is an acceptable trade: boundary consumers should not depend on a second event feed that can drift from the durable log. diff --git a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md b/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md index 3de3c7d9be..911d28cf1f 100644 --- a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md +++ b/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md @@ -14,7 +14,7 @@ Two sibling provider packages, structural variants of the ACP backend, plus one - `@deepseek-ai/dsh-subagent-codex` — spawns `codex app-server` and drives one thread/turn over its JSON-RPC-over-stdio protocol with a hand-rolled newline-JSON client (~200–300 lines) in the package. - `@deepseek-ai/dsh-subagent-process` — a pure library (the `subagent-inprocess` precedent) extracting what `dsh-subagent-acp` already carries and both new backends need: the credential env scrub (`SENSITIVE_ENV_PATTERN`/`buildChildEnv`), the EOF → SIGTERM → SIGKILL dispose ladder, and new isolated-config-dir helpers (`mkdtemp` create, best-effort remove). The ACP backend migrates onto it; `bash-local`'s sibling copy is left alone to bound the change. -Both providers copy the ACP backend's seam posture verbatim: fresh child per `start`, exactly one prompt round-trip, capabilities all `false`, `inheritsParentContext: false`, `request.parent`/`request.agentOptions` ignored, `id = AgentId(randomUUID())`, `result` never rejects — child-level failure flattens to a stop reason and the original error goes to `ctx.logger` via an `onError` spec callback. Model exposure is zero new code: `dsh-tool-subagent` is loaded once per provider with a distinct `toolName` (`subagent_claude_code`, `subagent_codex`). No new session events are needed — the only model-visible artifact is the tool result, so reconstructability holds exactly as it did for ACP. To be explicit about the boundary: the session log reconstructs the model-visible transcript, not workspace mutation history — a child granted write access mutates files as an ambient side effect outside the log, exactly as the bash tools and the ACP backend already do; replay reproduces requests, not the disk. +Both providers copy the ACP backend's seam posture verbatim: fresh child per `start`, exactly one prompt round-trip, capabilities all `false`, `inheritsParentContext: false`, `request.parent`/`request.agentOptions` ignored, `id = SessionId(randomUUID())`, `result` never rejects — child-level failure flattens to a stop reason and the original error goes to `ctx.logger` via an `onError` spec callback. Model exposure is zero new code: `dsh-tool-subagent` is loaded once per provider with a distinct `toolName` (`subagent_claude_code`, `subagent_codex`). No new session events are needed — the only model-visible artifact is the tool result, so reconstructability holds exactly as it did for ACP. To be explicit about the boundary: the session log reconstructs the model-visible transcript, not workspace mutation history — a child granted write access mutates files as an ambient side effect outside the log, exactly as the bash tools and the ACP backend already do; replay reproduces requests, not the disk. ## Verified interface facts (pinned versions) diff --git a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md index 1a69f9ebe6..6e3eea1515 100644 --- a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md @@ -16,13 +16,13 @@ Session itself repeats the same fact as `Session.id` and `Session.header.id`. Co Make an agent's registry id equal its session id. `CreateAgentOptions` accepts one id used for both final registry entries; resume registers the agent under the resumed session id; subagent creation mints one combined id; Session keeps one identity home by deriving `id` from `header.id` or removing the alias. Keep the existing creation transaction, final-entry collision checks, and exact-entry detach semantics; remove only maps and fields whose sole job is translating between the ids. -The config-driven path must first settle its currently hidden resume-or-create policy. Today it uses a stable agent label and fresh UUID-suffixed session id to avoid colliding with a durable log on the next run. Under unification it must deliberately resume the fixed id, mint a fresh combined id, or expose an explicit policy; implementation must not pick silently. +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. `agent/created` and `agent/disposed` remain outside this proposal. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. ## Alternatives considered -**Keep separate routing and log identities.** The config-driven loop uses a stable configured agent id with a fresh UUID session on each fresh process start. That is a real use of the distinction: a stable routing/display label plus a new durable conversation. Unification can proceed only after choosing whether this path resumes a fixed identity, mints a combined per-run identity, or exposes the policy explicitly. If the stable label is a required product contract, reject this proposal rather than hiding it in another map. +**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. ## Acceptance criteria @@ -35,4 +35,4 @@ The config-driven path must first settle its currently hidden resume-or-create p ## Risks -This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. The config restart decision is blocking, not mechanical. If separate routing identity is a real requirement, reject this RFC and retain the current caller-supplied pair plus final-entry arbitration. +This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/examples/coding-agent/tests/code-mode.e2e.ts b/examples/coding-agent/tests/code-mode.e2e.ts index 512688d88d..22446f0dc3 100644 --- a/examples/coding-agent/tests/code-mode.e2e.ts +++ b/examples/coding-agent/tests/code-mode.e2e.ts @@ -4,11 +4,12 @@ import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' @@ -72,7 +73,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p it('collapses the wire tool list to [run_code], bridges sub-calls, and returns curated output', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-e2e-')) ctx = await codeModeHarness(workdir) - const agent = ctx.agentLoop.create(AgentId('e2e-code-mode'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/coding-task.e2e.ts b/examples/coding-agent/tests/coding-task.e2e.ts index ce716bdb2c..e1ae9804ac 100644 --- a/examples/coding-agent/tests/coding-task.e2e.ts +++ b/examples/coding-agent/tests/coding-task.e2e.ts @@ -4,8 +4,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The swebench-style smoke test: a real model fixes a real bug in a temp @@ -54,7 +54,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test expect(before.status).not.toBe(0) ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-task'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-task'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/compaction.e2e.ts b/examples/coding-agent/tests/compaction.e2e.ts index 854cf49d2a..a0e71aacc4 100644 --- a/examples/coding-agent/tests/compaction.e2e.ts +++ b/examples/coding-agent/tests/compaction.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The compaction smoke test: a real model runs a multi-step bash task with a @@ -64,7 +64,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa }, persistenceRoot: join(workdir, '.sessions'), }) - const agent = ctx.agentLoop.create(AgentId('e2e-compaction'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-compaction'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/full-loop.e2e.ts b/examples/coding-agent/tests/full-loop.e2e.ts index 8718139ced..9a01713222 100644 --- a/examples/coding-agent/tests/full-loop.e2e.ts +++ b/examples/coding-agent/tests/full-loop.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The first place a REAL model meets the REAL bash tool: the cheap canary @@ -28,7 +28,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bas it('runs a bash command on request and reports its output', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-full-loop-e2e-')) ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-loop'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-loop'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }]) await waitForIdle(ctx, agent) diff --git a/examples/coding-agent/tests/resume.e2e.ts b/examples/coding-agent/tests/resume.e2e.ts index 70382b4beb..48e135ad92 100644 --- a/examples/coding-agent/tests/resume.e2e.ts +++ b/examples/coding-agent/tests/resume.e2e.ts @@ -4,7 +4,6 @@ import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' import type { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' @@ -40,7 +39,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses // log on disk survives. ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root }) const first = (await ctx.agents.create({ - agentId: AgentId('resume-1'), sessionId: SESSION_ID, agentOptions: { model: 'deepseek-v4-flash' }, })).agent as ReactLoopAgent @@ -54,7 +52,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses // run 1's exchange as conversation history. ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root }) const resumed = (await ctx.agents.resume({ - agentId: AgentId('resume-2'), resumeSessionId: SESSION_ID, agentOptions: { model: 'deepseek-v4-flash' }, })).agent as ReactLoopAgent diff --git a/examples/coding-agent/tests/todo-write.e2e.ts b/examples/coding-agent/tests/todo-write.e2e.ts index 698fbd9e9e..7f3c3c1e4a 100644 --- a/examples/coding-agent/tests/todo-write.e2e.ts +++ b/examples/coding-agent/tests/todo-write.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, TODO_SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * A REAL model drives the REAL todo_write tool: verify the WORLD (the session @@ -26,7 +26,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a it('appends a todo/write event with the model-produced task list', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-todo-write-e2e-')) ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-todo'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-todo'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Use the todo_write tool to record a plan of exactly two steps: first ' diff --git a/examples/cordis-agent/tests/cordis-tools.e2e.ts b/examples/cordis-agent/tests/cordis-tools.e2e.ts index 388fcb0058..ffe9a290eb 100644 --- a/examples/cordis-agent/tests/cordis-tools.e2e.ts +++ b/examples/cordis-agent/tests/cordis-tools.e2e.ts @@ -1,8 +1,8 @@ import { afterEach, describe, expect, it, vi } from 'vitest' import type { Context } from 'cordis' import { CallId } from '@deepseek-ai/dsh-llm' -import { AgentId } from '@deepseek-ai/dsh-agent' import { cordisHarness, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * With-key smoke for the self-referential cordis tools: a REAL model drives @@ -38,7 +38,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('mounts a status listener whose tagged output actually fires, then unmounts it', async () => { ctx = await cordisHarness() const log = vi.spyOn(console, 'log').mockImplementation(() => {}) - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-listener'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-listener'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', @@ -66,7 +66,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('builds itself a reverse_text tool and actually calls it', async () => { ctx = await cordisHarness() - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-selftool'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-selftool'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', @@ -114,7 +114,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('composes two mounts through provide/inject, and unmounting the provider parks the consumer', async () => { ctx = await cordisHarness() - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-compose'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-compose'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index a22e86bd99..3ab3ae6628 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -1,11 +1,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import { BashTaskId } from '@deepseek-ai/dsh-bash' @@ -74,7 +75,7 @@ describe('bash tool through the agent loop', () => { textResponse('The command printed integration-ok.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-fg'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-fg'), { model: 'mock' }) agent.send([{ type: 'text', text: 'run echo integration-ok' }]) await waitForIdle(ctx, agent) @@ -106,7 +107,7 @@ describe('bash tool through the agent loop', () => { textResponse('It failed with code 9.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-exit'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-exit'), { model: 'mock' }) agent.send([{ type: 'text', text: 'run exit 9' }]) await waitForIdle(ctx, agent) @@ -128,7 +129,7 @@ describe('bash tool through the agent loop', () => { let taskId = '' const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-bg'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-bg'), { model: 'mock' }) // Capture the generated id so the deterministic fixture is checked against // the real executor instead of silently assuming it. diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index 12b4a53958..c68c445f0a 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -57,7 +57,7 @@ async function setup() { const fakeAgentDisposers = new Map Promise | void)[]>() function registerFakeAgent(ctx: Context, sessionId: string, inject: (...args: unknown[]) => void): Agent { // The registry KEY (agent.id) is deliberately DIFFERENT from the session - // token (session.header.id) — a config agent has `agentId !== sessionId`. The + // token (session.header.id), which is also the agent's durable id. The // owner token IS the session id, so the notice path must find the agent by // `session.header.id`, NOT the registry key. Using distinct values here makes // the test fail if a regression matched on the wrong field (a same-value fake diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index bb77e44a9c..52a2ecd134 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -3,11 +3,12 @@ import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import { isToolPairingBalanced } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' @@ -119,7 +120,7 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () it('the head checkpoint the loop lands is a balanced cut on both sides', async () => { const { ctx } = await harness(8) try { - const agent = ctx.agentLoop.create(AgentId('repro'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('repro'), { model: 'mock' }) agent.send([{ type: 'text', text: 'do a long multi-step task' }]) await waitForIdle(ctx, agent) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 3d6ade301f..5721bd97d9 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -56,7 +56,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ key: 'agentLoop', summary: 'Concrete ReactLoopAgent factory and driver service.', methods: [ - 'create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent', + 'create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent', 'async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise', 'async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise', ], @@ -71,7 +71,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'register(agent: Agent): () => void', 'enter(agent: Agent): () => void', 'announce(agent: Agent): void', - 'get(id: AgentId): Agent | undefined', + 'get(id: SessionId): Agent | undefined', 'list(): Agent[]', ], }, @@ -488,7 +488,7 @@ export const EVENT_API: readonly EventApiEntry[] = [ export const TYPE_API: readonly TypeApiEntry[] = [ { name: 'Agent', - declaration: 'export interface Agent {\n readonly id: AgentId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: SendOptions): void;\n cancel(reason?: string): void;\n whenIdle(): Promise;\n}', + declaration: 'export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: SendOptions): void;\n cancel(reason?: string): void;\n whenIdle(): Promise;\n}', }, { name: 'AgentFactory', @@ -498,10 +498,6 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'AgentHandle', declaration: 'export interface AgentHandle {\n agent: Agent;\n dispose(): Promise;\n}', }, - { - name: 'AgentId', - declaration: 'export type AgentId = Branded<\'AgentId\'>;', - }, { name: 'AgentOptions', declaration: 'export interface AgentOptions {\n model?: string;\n}', @@ -644,7 +640,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'CreateAgentOptions', - declaration: 'export interface CreateAgentOptions {\n readonly agentId: AgentId;\n readonly sessionId: SessionId;\n readonly meta?: {\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n };\n readonly seed?: readonly SessionEvent[];\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', + declaration: 'export interface CreateAgentOptions {\n readonly sessionId: SessionId;\n readonly meta?: {\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n };\n readonly seed?: readonly SessionEvent[];\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', }, { name: 'CreateSessionOptions', @@ -756,7 +752,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'ResumeAgentOptions', - declaration: 'export interface ResumeAgentOptions {\n readonly agentId: AgentId;\n readonly resumeSessionId: SessionId;\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', + declaration: 'export interface ResumeAgentOptions {\n readonly resumeSessionId: SessionId;\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', }, { name: 'SandboxEnforcement', @@ -868,7 +864,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SubagentRun', - declaration: 'export interface SubagentRun {\n readonly id: AgentId;\n readonly result: Promise;\n dispose(): Promise;\n sendMessage?(content: ContentBlock[]): void;\n resume?(content: ContentBlock[]): Promise;\n}', + declaration: 'export interface SubagentRun {\n readonly id: SessionId;\n readonly result: Promise;\n dispose(): Promise;\n sendMessage?(content: ContentBlock[]): void;\n resume?(content: ContentBlock[]): Promise;\n}', }, { name: 'SubagentStartRequest', diff --git a/packages/cordis/tool-cordis/tests/integration.spec.ts b/packages/cordis/tool-cordis/tests/integration.spec.ts index 94331df7c0..0d4c6c5c18 100644 --- a/packages/cordis/tool-cordis/tests/integration.spec.ts +++ b/packages/cordis/tool-cordis/tests/integration.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as ToolCordis from '../src/index.ts' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -51,7 +52,7 @@ describe('cordis tools through the agent loop', () => { textResponse('Done.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-cordis'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-cordis'), { model: 'mock' }) agent.send([{ type: 'text', text: 'give yourself reverse_text, use it, clean up' }]) await waitForIdle(ctx, agent) diff --git a/packages/core/agent-core/README.md b/packages/core/agent-core/README.md index 33cd0faddd..accbf66a7c 100644 --- a/packages/core/agent-core/README.md +++ b/packages/core/agent-core/README.md @@ -43,7 +43,7 @@ import type { Config } from '@deepseek-ai/dsh-agent-core' // so validation and defaulting can never drift from the owners. ``` -The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure. +The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates one under the `main` config label; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure. ## Why a code bundle, not a shared YAML include diff --git a/packages/core/agent-core/tests/agent-core.spec.ts b/packages/core/agent-core/tests/agent-core.spec.ts index 855bb28d49..058191c88f 100644 --- a/packages/core/agent-core/tests/agent-core.spec.ts +++ b/packages/core/agent-core/tests/agent-core.spec.ts @@ -6,8 +6,10 @@ import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import * as agentCore from '../src/index.ts' -import { AgentId, agentEvents, type Agent } from '@deepseek-ai/dsh-agent' +import { agentEvents, type Agent } from '@deepseek-ai/dsh-agent' + import type { Message } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' async function composePrefix(ctx: Context, cwd: string): Promise { const agent = { session: { header: { cwd } } } as unknown as Agent @@ -102,16 +104,18 @@ describe('dsh-agent-core bundle', () => { it('defaults the agents list to empty (no pre-created agents)', async () => { const ctx = await mount() - expect(ctx.get('agents')?.get(AgentId('main'))).toBeUndefined() + expect(ctx.get('agents')?.get(SessionId('main'))).toBeUndefined() await ctx.fiber.dispose() }) it('forwards a pre-created agent to the loop and the persona to system-prompt', async () => { const ctx = await mount({ - agents: [{ id: AgentId('main'), model: 'mock' }], + agents: [{ id: 'main', model: 'mock' }], persona: 'You are main.', }) - expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() + const agent = ctx.get('agents')?.list()[0] + expect(agent?.id).toBe(agent?.session.id) + expect(agent?.id).toMatch(/^main-session-/) const assembly = await ctx.get('systemPrompt')!.assemble() expect(assembly.sections.find(s => s.name === 'deployment:persona')?.text).toBe('You are main.') await ctx.fiber.dispose() diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 6832800d2e..f40577bb95 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -12,14 +12,14 @@ Creation and resume are one rollback-covered transaction: construct a private se The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createAgent(ownerCtx, options)` and `resume(ownerCtx, options)` receive caller ownership explicitly, while the factory keeps its own dependency context for `sessions`/`llm`/`tools`/`systemPrompt`; this lets a caller inject only `agents` without shrinking the new agent's service surface. Caller unload, handle disposal, or provider unload converge on one memoized quiescence boundary. Provider shutdown waits both resource teardown and the public create/resume wrapper that observed deactivation, so no continuation can publish after dependencies disappear. -IDs are caller-chosen and assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same agent or session id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; IDs become reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. +Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: string, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create, used directly by programs and by `cordis.yml`-configured agents. It creates a fresh per-run session id `${id}-session-` with optional metadata; the uuid avoids colliding with a prior durable log. Each call is a new session (a deliberate demo simplification — a real resume-or-create policy is a TODO). Disposed with the calling fiber. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and mints `${label}-session-` before calling this boundary; `resumeSessionId` instead loads and registers the exact persisted id. This keeps fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): -- `ctx.agents.create({ agentId, sessionId, meta?, seed?, agentOptions?, setup?, signal? }): Promise` — programmatic create on a caller-supplied `sessionId`, NOT `${id}-session`. It awaits the unpublished setup transaction before returning; `meta` carries cwd/lineage/seed-boundary metadata and `seed` reconstructs a forked child prefix after the session boundary validates and snapshots the durable values. `signal` applies only until this promise settles. The resolved [`AgentHandle`](../agent/README.md) owns exact teardown. -- `ctx.agents.resume({ agentId, resumeSessionId, agentOptions?, setup?, signal? }): Promise` — load a persisted session via `ctx.sessionPersistence` ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), reconstruct its history, then await setup against a fresh unpublished agent scope before rollback-covered publication. The live session id is the resumed id; turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a clear error when persistence is absent). `signal` is creation-only. Returns an `AgentHandle`. +- `ctx.agents.create({ sessionId, meta?, seed?, agentOptions?, setup?, signal? }): Promise` — programmatic create under the caller-supplied shared id. It awaits the unpublished setup transaction before returning; `meta` carries cwd/lineage/seed-boundary metadata and `seed` reconstructs a forked child prefix after the session boundary validates and snapshots the durable values. `signal` applies only until this promise settles. The resolved [`AgentHandle`](../agent/README.md) owns exact teardown. +- `ctx.agents.resume({ resumeSessionId, agentOptions?, setup?, signal? }): Promise` — load a persisted session via `ctx.sessionPersistence` ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), register the agent under that same id, reconstruct its history, then await setup against a fresh unpublished agent scope before rollback-covered publication. Turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a clear error when persistence is absent). `signal` is creation-only. Returns an `AgentHandle`. The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loop fiber (it discards the handle). For a programmatic agent, the handle holder is the only consumer-facing teardown capability; AgentLoop provider unload is the independent structural teardown edge, not another handle exposed to application code. @@ -32,7 +32,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo ```ts interface Config { agents: Array<{ - id: string // required + id: string // required stable label; prefixes fresh combined ids model?: string resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index ff66f942be..d54baab597 100644 --- a/packages/core/agent-loop/src/agent.ts +++ b/packages/core/agent-loop/src/agent.ts @@ -8,11 +8,11 @@ import type { Context } from 'cordis' import { agentEvents } from '@deepseek-ai/dsh-agent' -import type { AgentId, AgentOptions, AgentStatus, SendOptions } from '@deepseek-ai/dsh-agent' +import type { AgentOptions, AgentStatus, SendOptions } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { deepFreeze } from '@deepseek-ai/dsh-llm' import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm' -import { snapshotJsonValue, type Session } from '@deepseek-ai/dsh-session' +import { snapshotJsonValue, type Session, type SessionId } from '@deepseek-ai/dsh-session' import { Inbox, type InboxMessage } from './inbox.ts' import { isTurnOpen, lastTurnNumber, runLoop } from './loop.ts' @@ -59,7 +59,7 @@ export interface PreparedReactLoopAgent { * @returns the agent and closures bound only to that exact instance. */ export function prepareReactLoopAgent( - ctx: Context, id: AgentId, options: AgentOptions, session: Session, + ctx: Context, id: SessionId, options: AgentOptions, session: Session, ): PreparedReactLoopAgent { if (claimedDriverSessions.has(session)) { throw new Error(`session "${session.id}" already has a concrete agent driver`) @@ -163,7 +163,7 @@ export class ReactLoopAgent implements Agent { constructor( private loopCtx: Context, - public readonly id: AgentId, + public readonly id: SessionId, public readonly options: AgentOptions, public readonly session: Session, ) { diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 4ad4779176..33276c01f8 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -14,7 +14,6 @@ import { agentEvents } from '@deepseek-ai/dsh-agent' import type { AgentFactory, AgentHandle, - AgentId, AgentOptions, CreateAgentOptions, ResumeAgentOptions, @@ -68,7 +67,7 @@ class FactoryOwnership { } /** Build the public cancellation error while preserving a caller-supplied cause. */ -function signalAbortError(id: AgentId, signal: AbortSignal): Error { +function signalAbortError(id: SessionId, signal: AbortSignal): Error { if (signal.reason instanceof Error) return signal.reason return new Error(`agent "${id}" creation aborted`, { cause: signal.reason }) } @@ -108,7 +107,7 @@ class AgentCreationTransaction { private readonly loopCtx: Context, private readonly ownerCtx: Context, private readonly ownership: FactoryOwnership, - readonly id: AgentId, + readonly id: SessionId, signal?: AbortSignal, ) { ownerCtx.fiber.assertActive() @@ -325,8 +324,8 @@ declare module 'cordis' { export interface Config { /** Agents created or resumed at plugin startup. */ agents: (AgentOptions & { - /** Registry identity for the live agent. */ - id: AgentId + /** Stable config label used in logs and as the fresh combined-id prefix. */ + id: string /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -363,13 +362,13 @@ export class AgentLoop extends Service implements AgentFactory { for (const { id, cwd, resumeSessionId, ...options } of config.agents) { if (resumeSessionId === undefined || resumeSessionId === '') { - this.create(id, options, cwd === undefined ? {} : { cwd }) + const sessionId = SessionId(`${id}-session-${randomUUID()}`) + this.create(sessionId, options, cwd === undefined ? {} : { cwd }) continue } ctx.effect(() => { const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => { void this.resumeWith(ctx, childCtx.sessionPersistence, { - agentId: id, resumeSessionId, agentOptions: options, }).catch((error: unknown) => { @@ -382,19 +381,19 @@ export class AgentLoop extends Service implements AgentFactory { } /** - * Create an agent on a fresh per-run session, owned by the accessing fiber. - * Constructor-driven config calls use the loop fiber itself. - * @param id - agent registry id. + * Create an agent and session under one caller-supplied identity, owned by + * the accessing fiber. Constructor-driven config calls mint a fresh combined + * id before entering this boundary. + * @param id - shared agent/session identity. * @param options - concrete loop options. * @param meta - optional fresh-session workspace metadata. * @returns the published running agent. */ - create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent { + create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent { const loopCtx = this.runtime.ctx const transaction = new AgentCreationTransaction(loopCtx, this.ctx, this.ownership, id) try { - const sessionId = SessionId(`${id}-session-${randomUUID()}`) - const session = loopCtx.sessions.prepare(sessionId, { meta }) + const session = loopCtx.sessions.prepare(id, { meta }) const agent = transaction.prepare(options, session) transaction.publish('startup') return agent @@ -417,7 +416,7 @@ export class AgentLoop extends Service implements AgentFactory { this.runtime.ctx, ownerCtx, this.ownership, - options.agentId, + options.sessionId, options.signal, ) try { @@ -461,7 +460,7 @@ export class AgentLoop extends Service implements AgentFactory { this.runtime.ctx, ownerCtx, this.ownership, - options.agentId, + options.resumeSessionId, options.signal, ) try { diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 7f65bbc5f3..56d6489fbe 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -1,6 +1,5 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' @@ -53,10 +52,10 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('exclusive-driver')) - const prepared = prepareReactLoopAgent(ctx, AgentId('first-driver'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('first-driver'), { model: 'mock' }, session) expect(() => prepared.agent.ctx).toThrow('context is not bound') - expect(() => prepareReactLoopAgent(ctx, AgentId('second-driver'), { model: 'mock' }, session)) + expect(() => prepareReactLoopAgent(ctx, SessionId('second-driver'), { model: 'mock' }, session)) .toThrow('already has a concrete agent driver') await prepared.dispose() @@ -66,11 +65,11 @@ describe('ReactLoopAgent', () => { it('borrows caller options and binds its scoped context exactly once', async () => { const ctx = await harness(new MockAdapter([textResponse('unused')])) const options = { model: 'mock' } - const agent = ctx.agentLoop.create(AgentId('owned-bindings'), options) + const agent = ctx.agentLoop.create(SessionId('owned-bindings'), options) expect(agent.options).toBe(options) expect(agent.id).toBe('owned-bindings') - expect(agent.session.id).toMatch(/^owned-bindings-session-/) + expect(agent.session.id).toBe(agent.id) expect(() => { bindReactLoopAgentContext(agent, new Context()) }).toThrow(/context is already bound/) await ctx.fiber.dispose() @@ -81,7 +80,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -96,7 +95,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -111,7 +110,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -124,7 +123,7 @@ describe('ReactLoopAgent', () => { it('inject() decides enclosure from the LOG (open turn), not agent status', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Simulate an OPEN turn in the log while the agent is idle (status is not a // reliable open-turn signal). inject must append into that open turn, NOT @@ -150,7 +149,7 @@ describe('ReactLoopAgent', () => { // A persistence-like listener whose flush rejects. ctx.on('session/flush', () => { throw new Error('disk gone') }) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // inject() is synchronous and fires a fire-and-forget flush; a rejecting // flush must be contained (logged), never thrown into the caller. @@ -163,7 +162,7 @@ describe('ReactLoopAgent', () => { it('idle inject() closes its one-shot turn AND still checkpoints even if the append throws', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) @@ -183,7 +182,7 @@ describe('ReactLoopAgent', () => { it('idle inject() still checkpoints when a listener throws on the synthetic turn/end', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) // Session contains a throwing post-commit turn/end observer. The accepted @@ -206,7 +205,7 @@ describe('ReactLoopAgent', () => { // A non-Error rejection exercises the String() normalization branch. ctx.on('session/flush', () => { throw 'disk gone' }) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const errors: { turn: number; step: number; message: string }[] = [] ctx.on('agent/error', (_a, turn, step, error) => void errors.push({ turn, step, message: error.message })) @@ -225,7 +224,7 @@ describe('ReactLoopAgent', () => { it('idle inject() with a non-serializable source opens no turn (nothing to close)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A non-serializable source makes the turn/start append throw BEFORE the // event is pushed (Session.append validates before push), so NO turn opens. @@ -240,7 +239,7 @@ describe('ReactLoopAgent', () => { it('steer() when idle falls through to send() and starts a turn', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // steer while idle delegates to send agent.steer([{ type: 'text', text: 'steer idle' }], { source: { kind: 'plugin', plugin: 'test' } }) @@ -258,7 +257,7 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('test')) - const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('bare'), { model: 'mock' }, session) const { agent } = prepared // Start the loop to get the disposer; the agent waits for messages @@ -280,7 +279,7 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('pre-start-dispose')) - const prepared = prepareReactLoopAgent(ctx, AgentId('pre-start-dispose'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('pre-start-dispose'), { model: 'mock' }, session) await prepared.dispose() expect(prepared.agent.status).toBe('disposed') @@ -294,7 +293,7 @@ describe('ReactLoopAgent', () => { it('setting the same status does not emit agent/status again', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const statuses: string[] = [] ctx.on('agent/status', (subject, status) => { @@ -313,7 +312,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() resolves immediately when the agent is not running', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Fresh agent is idle — whenIdle() takes the not-running fast path and // resolves without subscribing. await must not hang. @@ -324,7 +323,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() waits for queued work that has not flipped status yet', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'queued') let settled = false @@ -342,8 +341,8 @@ describe('ReactLoopAgent', () => { it('whenIdle() awaits the running→idle transition, ignoring other subjects/running events', async () => { const adapter = new MockAdapter([textResponse('ok'), textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - const other = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) + const other = ctx.agentLoop.create(SessionId('a2'), { model: 'mock' }) // Drive `agent` into `running`, then await whenIdle() — it subscribes to // agent/status and resolves on the first transition out of running. @@ -379,7 +378,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter(['hang']) ctx.llm.registerAdapter(['mock'], adapter) const session = ctx.sessions.create(SessionId('bare')) - const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('bare'), { model: 'mock' }, session) const { agent } = prepared prepared.markPublished() const dispose = prepared.startDriver() @@ -404,7 +403,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -425,7 +424,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -446,7 +445,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/status', (_subject, status) => { if (status === 'running') throw new Error('bad running listener') }) @@ -464,7 +463,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/status', (_subject, status) => { if (status === 'idle') throw new Error('bad idle listener') }) diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index 56376b69a7..82b1f6c58c 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -16,7 +16,8 @@ import LlmService, { type Message } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -57,7 +58,7 @@ describe('Agent.cancel()', () => { it('cancel() on an idle agent with nothing queued is a no-op; the next prompt runs (F2 leak guard)', async () => { const adapter = new MockAdapter([textResponse('reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // The loop is parked at the idle wait with nothing queued. A cancel here must // NOT arm the marker — otherwise the next legitimate prompt would be dropped. @@ -74,7 +75,7 @@ describe('Agent.cancel()', () => { it('pre-step cancel drops the about-to-start turn (no turn is opened)', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // send() queues synchronously (status still idle, loop microtask not yet // resumed). Cancel in that pre-step window: the queued turn must not run. @@ -93,7 +94,7 @@ describe('Agent.cancel()', () => { it('a whenIdle() waiter registered BEFORE a pre-step cancel resolves (F1 hang guard)', async () => { const adapter = new MockAdapter([textResponse('x')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Queue work, then register a whenIdle() waiter while in the pre-step window // (status idle, hasQueued true) — it does NOT take the fast path. Then cancel. @@ -114,7 +115,7 @@ describe('Agent.cancel()', () => { it('cancel() mid-step aborts the in-flight model call; the turn ends aborted', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -131,7 +132,7 @@ describe('Agent.cancel()', () => { it('cancel() with no reason defaults to "cancelled" when aborting an in-flight step', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -147,7 +148,7 @@ describe('Agent.cancel()', () => { it('a prompt sent AFTER a cancelled turn settles runs normally (marker reset)', async () => { const adapter = new MockAdapter(['hang', textResponse('second reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // First turn hangs; cancel it mid-step. send(agent, 'first') @@ -169,7 +170,7 @@ describe('Agent.cancel()', () => { it('cancel from inside the agent/session-prefix waterfall drops the step (prefix-composition window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Prefix composition runs before the pre-step seam on the instance's first // step; a cancel landing inside it must drop the about-to-start step @@ -203,7 +204,6 @@ describe('Agent.cancel()', () => { ctx.llm.registerAdapter(['mock'], adapter) const handle = await ctx.agents.create({ - agentId: AgentId('a-dispose-prefix'), sessionId: SessionId('dispose-prefix-session'), agentOptions: { model: 'mock' }, }) @@ -232,7 +232,7 @@ describe('Agent.cancel()', () => { it('a cancel-interrupted prefix composition is discarded: the next send recomposes and ships the fresh prefix (stale-cache guard)', async () => { const adapter = new MockAdapter([textResponse('reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // The first composition is interrupted mid-waterfall and — like an // abort-aware listener bailing on a firing signal — contributes nothing. @@ -266,7 +266,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous turn/start session-event listener drops the step (step-start window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A turn/start listener fires right after turn/start is appended, BEFORE any // AbortController is installed for the step. Cancelling there must still drop @@ -295,7 +295,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous step/start session-event listener drops the step (post-step-start window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A step/start session-event listener fires AFTER step/start is appended // (and after the pre-step seam), so cancelling there lands in the SECOND @@ -334,7 +334,6 @@ describe('Agent.cancel()', () => { ctx.llm.registerAdapter(['mock'], adapter) const handle = await ctx.agents.create({ - agentId: AgentId('a-dispose-step-start'), sessionId: SessionId('dispose-step-start-session'), agentOptions: { model: 'mock' }, }) @@ -366,7 +365,7 @@ describe('Agent.cancel()', () => { // `aborted` and run NO second step. const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steps = 0 const reasons: TurnEndReason[] = [] @@ -398,7 +397,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous agent/status(running) listener drops the turn (window 2)', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // setStatus('running') emits agent/status SYNCHRONOUSLY, so a running // listener can cancel in the gap between the loop's pre-step check and @@ -428,7 +427,7 @@ describe('Agent.cancel()', () => { // so whenIdle() resolves on the replacement turn's running→idle, not before. const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let replaced = false const dispose = ctx.on('agent/status', (subject, status) => { @@ -458,7 +457,7 @@ describe('Agent.cancel()', () => { // settle (the quiescence contract), not resolve before B's first event. const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'A') // queues A (status still idle, loop microtask pending) const idle = agent.whenIdle() // registers a waiter (idle + hasQueued → no fast path) @@ -478,7 +477,7 @@ describe('Agent.cancel()', () => { it("cancel clears the turn's steering — it is not re-enqueued as a fresh turn", async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 07d6cd9e9b..134ea68c32 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -7,7 +7,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -32,7 +33,7 @@ describe('config-driven session id', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) const loopFiber = await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('deferred') }], + agents: [{ id: 'main', model: 'mock', resumeSessionId: SessionId('deferred') }], }) const resumeEffect = loopFiber.getEffects().find(effect => effect.label === 'agentLoop.resume(main)') @@ -53,11 +54,13 @@ describe('config-driven session id', () => { await ctx1.plugin(SystemPrompt) await ctx1.plugin(ToolRegistry) await ctx1.plugin(AgentRegistry) - await ctx1.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] }) + await ctx1.plugin(AgentLoop, { agents: [{ id: 'cfg', model: 'mock' }] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg')])) - const a1 = ctx1.agents.get(AgentId('cfg')) as ReactLoopAgent + const a1 = ctx1.agents.list()[0] as ReactLoopAgent + expect(a1.id).toBe(a1.session.id) expect(a1.session.id).toMatch(idPattern) + expect(ctx1.agents.get(SessionId('cfg'))).toBeUndefined() a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -70,10 +73,11 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] }) + await ctx2.plugin(AgentLoop, { agents: [{ id: 'cfg', model: 'mock' }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg2')])) - const a2 = ctx2.agents.get(AgentId('cfg')) as ReactLoopAgent + const a2 = ctx2.agents.list()[0] as ReactLoopAgent + expect(a2.id).toBe(a2.session.id) expect(a2.session.id).toMatch(idPattern) expect(a2.session.id).not.toBe(a1.session.id) a2.send([{ type: 'text', text: 'q2' }], { source: { kind: 'user' } }) @@ -96,7 +100,7 @@ describe('config-driven session id', () => { await ctx1.plugin(AgentLoop, { agents: [] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first')])) - const a1 = (await ctx1.agents.create({ agentId: AgentId('main'), sessionId: SessionId('sticky-1') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('sticky-1') })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -110,7 +114,7 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) + await ctx2.plugin(AgentLoop, { agents: [{ id: 'main', model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')])) @@ -118,11 +122,12 @@ describe('config-driven session id', () => { let resumed: ReactLoopAgent | undefined for (let i = 0; i < 50 && !resumed; i++) { await new Promise(r => setTimeout(r, 5)) - resumed = ctx2.agents.get(AgentId('main')) as ReactLoopAgent | undefined + resumed = ctx2.agents.get(SessionId('sticky-1')) as ReactLoopAgent | undefined } expect(resumed).toBeDefined() // The live session id IS the resumed id (NOT a fresh ${id}-session-), // and the prior turn's user message is in the derived history. + expect(resumed!.id).toBe(SessionId('sticky-1')) expect(resumed!.session.id).toBe('sticky-1') const derived = resumed!.session.deriveMessages() expect(JSON.stringify(derived)).toContain('remember me') @@ -138,16 +143,16 @@ describe('config-driven session id', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) + await ctx.plugin(AgentLoop, { agents: [{ id: 'main', model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) const warn = vi.spyOn((ctx.agentLoop as unknown as { ctx: { logger: { warn: (...a: unknown[]) => void } } }).ctx.logger, 'warn') .mockImplementation(() => undefined) await ctx.plugin(SessionPersistenceJsonl, { root }) ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('x')])) // The deferred resume fails (no such session on disk). It must be contained: - // a warning is logged, no 'main' agent is registered, and the app stays up. + // a warning is logged, no agent is registered, and the app stays up. await new Promise(r => setTimeout(r, 200)) - expect(ctx.agents.get(AgentId('main'))).toBeUndefined() + expect(ctx.agents.list()).toEqual([]) expect(warn).toHaveBeenCalledWith(expect.stringContaining('config-driven resume of "does-not-exist" failed')) warn.mockRestore() await ctx.fiber.dispose() diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index 23e5670f85..4e82e398f1 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -1,11 +1,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, LlmError, StreamChunk } from '@deepseek-ai/dsh-llm' -import SessionStore, { TurnEndReason } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -40,7 +41,7 @@ describe('inbox acceptance', () => { it('rejects non-serializable content or source synchronously before notification or enqueue', async () => { const adapter = new MockAdapter([textResponse('turn 1')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let queued = 0 ctx.on('agent/queued', () => { queued += 1 }) @@ -80,7 +81,7 @@ describe('tool JSON parse', () => { return [{ type: 'text', text: typeof args === 'string' ? `raw: ${args}` : JSON.stringify(args) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -113,7 +114,7 @@ describe('tool JSON parse', () => { return [{ type: 'text', text: 'ran with empty args' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -126,7 +127,7 @@ describe('toError normalization', () => { it('normalizes non-Error throws from pre-commit dispatch validation via the runLoop backstop', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('internal/dispatch', (_mode, name, args) => { @@ -152,7 +153,7 @@ describe('toError normalization', () => { it('normalizes non-Error throws from agent/request waterfall via inline toError in runStep catch', async () => { const adapter = new MockAdapter([textResponse('irrelevant')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('agent/request', async (_agent, _turn, _step, _options, _next) => { @@ -180,7 +181,7 @@ describe('coded error data emission', () => { it('errorData includes code when a coded error (LlmError) is thrown from a plugin', async () => { const adapter = new MockAdapter([textResponse('turn 1')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('agent/request', async (_agent, _turn, _step, _options, next) => { @@ -214,7 +215,7 @@ describe('disposed vs aborted branching', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -242,7 +243,7 @@ describe('structured tool error propagation (the runtime-validation RFC, part 2) textResponse('done'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'boom', description: 'always fails', diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index 1ec48e553f..8c95be0d82 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -1,15 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, type Message } from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { - AgentId, - type ContinuationDecision, - type PromptDecision, - type SessionStartSource, -} from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -57,7 +53,7 @@ describe('agent/prompt-submit', () => { it('allow (default via next) records the user/message unchanged', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const seen: string[] = [] ctx.on('agent/prompt-submit', async (_agent, content, _source, next) => { @@ -76,7 +72,7 @@ describe('agent/prompt-submit', () => { it('allow with content REWRITES the prompt before it is recorded', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ kind: 'allow', content: [{ type: 'text', text: 'REWRITTEN' }] })) @@ -94,7 +90,7 @@ describe('agent/prompt-submit', () => { it('allow with additionalContext injects a separate context/message into the turn', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ @@ -127,7 +123,7 @@ describe('agent/prompt-submit', () => { // elsewhere; this asserts they see each other's effects on the same turn). const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ @@ -157,7 +153,7 @@ describe('agent/prompt-submit', () => { it('block drops the (only) prompt → zero-step turn ends rejected, model never called', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ kind: 'block', reason: 'blocked by policy' })) @@ -194,7 +190,7 @@ describe('agent/prompt-submit', () => { // vetoed prompt and its reason would vanish from the log entirely. const adapter = new MockAdapter([textResponse('ran once')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (_agent, content, _source, next): Promise => { const text = content.map(b => (b.type === 'text' ? b.text : '')).join('') @@ -230,7 +226,7 @@ describe('agent/prompt-submit', () => { it('a throwing prompt-submit listener ends the turn balanced (error), loop survives', async () => { const adapter = new MockAdapter([textResponse('after')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threw = false ctx.on('agent/prompt-submit', async () => { @@ -263,7 +259,7 @@ describe('agent/session-start', () => { const sources: SessionStartSource[] = [] ctx.on('agent/session-start', (_agent, source) => void sources.push(source)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // fires synchronously at create, before any turn expect(sources).toEqual(['startup']) expect(events(agent).some(e => e.type === 'turn/start')).toBe(false) @@ -282,7 +278,7 @@ describe('agent/session-start', () => { agent.inject([{ type: 'text', text: 'session preamble' }], { source: { kind: 'plugin', plugin: 'test' } }) }) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -300,8 +296,8 @@ describe('agent/session-start', () => { ctx.on('agent/session-start', () => { throw new Error('session-start hook broke') }) // create must not throw — the listener error is contained/logged - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - expect(agent.id).toBe(AgentId('a1')) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) + expect(agent.id).toBe(SessionId('a1')) // and the agent still runs send(agent, 'go') @@ -314,8 +310,8 @@ describe('agent/session-prefix', () => { it('dispatches to global and matching agent-scope listeners only', async () => { const adapter = new MockAdapter([textResponse('a done'), textResponse('b done')]) const ctx = await harness(adapter) - const agentA = ctx.agentLoop.create(AgentId('prefix-a'), { model: 'mock' }) - const agentB = ctx.agentLoop.create(AgentId('prefix-b'), { model: 'mock' }) + const agentA = ctx.agentLoop.create(SessionId('prefix-a'), { model: 'mock' }) + const agentB = ctx.agentLoop.create(SessionId('prefix-b'), { model: 'mock' }) const seen: string[] = [] ctx.on('agent/session-prefix', async (agent, _prefix, _signal, next) => { seen.push(`global:${agent.id}`) @@ -352,7 +348,7 @@ describe('agent/session-prefix', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'catalog' }] } let composed = 0 @@ -385,7 +381,7 @@ describe('agent/session-prefix', () => { it('composes before the first pre-step and hands the prefix to the seam (pressure gates see the real value)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'opener' }] } const order: string[] = [] @@ -412,7 +408,7 @@ describe('agent/session-prefix', () => { it('the canonical prepend pattern composes contributions in registration order', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Both listeners use the canonical `[mine, ...await next()]` prepend: the // waterfall unwinds innermost-first (the second listener's array is built @@ -434,7 +430,7 @@ describe('agent/session-prefix', () => { it('with no contributions the header omits messagePrefix and the request is the bare derivation', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A listener that delegates without contributing — the canonical no-op. ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => next()) @@ -450,7 +446,7 @@ describe('agent/session-prefix', () => { it('the frozen seed rejects in-place mutation — a contribution is a returned extension', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let mutationError: unknown ctx.on('agent/session-prefix', async (_agent, prefix, _signal, next): Promise => { @@ -479,7 +475,7 @@ describe('agent/session-prefix', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const held: Message = { role: 'user', content: [{ type: 'text', text: 'v1' }] } ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise => [...await next(), held]) @@ -500,7 +496,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => { it('a continue decision with a reason records next-step steering in the same turn', async () => { const adapter = new MockAdapter([textResponse('step 1 no tools'), textResponse('step 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let forced = false ctx.on('agent/turn-continuation', async (_agent, _turn, _default, next): Promise => { @@ -533,7 +529,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/turn-continuation', async (): Promise => ({ action: 'stop' })) @@ -563,7 +559,7 @@ describe('tools/post-execute additionalContext buffering across a multi-call ste name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Each call attaches additionalContext naming itself. ctx.on('tools/post-execute', async (exec, _result): Promise => @@ -599,7 +595,7 @@ describe('tools/pre-execute gate (native-plugin permission pattern, end-to-end t name: 'danger', description: 'danger', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('tools/pre-execute', async (exec, next): Promise => { if (exec.name === 'danger') return { kind: 'deny', reason: 'blocked dangerous tool' } @@ -663,7 +659,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'please echo hi') await waitForIdle(ctx, agent) @@ -686,7 +682,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) await ctx.plugin(NativeGuard) - const agent = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a2'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event: SessionEvent) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -705,7 +701,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se await fiber.dispose() // After disposal, a destructive prompt is NOT blocked (the listener is gone). - const agent = ctx.agentLoop.create(AgentId('a3'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a3'), { model: 'mock' }) send(agent, 'run rm -rf /') await waitForIdle(ctx, agent) // the prompt ran (not rejected) — proving the prompt-submit listener was disposed diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index 71be5b339e..c4e49e0fa5 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -4,7 +4,8 @@ import LlmService, { CallId, StreamChunk } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -44,7 +45,7 @@ describe('agent loop', () => { it('runs a simple turn: queued message → model → idle, with ordered events', async () => { const adapter = new MockAdapter([textResponse('hello there')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // All boundaries — turn and step — are durable session events on the // session/event feed (no agent/* mirror). Record them in fire order to @@ -92,7 +93,7 @@ describe('agent loop', () => { return [{ type: 'text', text: `echo: ${args.text}` }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -131,7 +132,7 @@ describe('agent loop', () => { return { content: [{ type: 'text', text: 'ok' }], meta: { diffs: [{ path: 'a.txt', oldText: null, newText: 'x' }] } } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -155,7 +156,7 @@ describe('agent loop', () => { return [] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -169,7 +170,6 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter, 'Working in {{cwd}}.') const handle = await ctx.agents.create({ - agentId: AgentId('a-cwd'), sessionId: SessionId('s-cwd'), meta: { cwd: '/work/space' }, agentOptions: { model: 'mock' }, @@ -192,7 +192,7 @@ describe('agent loop', () => { const ctx = await harness(adapter, 'In {{cwd}}.') const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -233,7 +233,7 @@ describe('agent loop', () => { ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { return { ...config, model: 'mock' } }) - const agent = ctx.agentLoop.create(AgentId('a-late-model'), {}) + const agent = ctx.agentLoop.create(SessionId('a-late-model'), {}) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -259,7 +259,7 @@ describe('agent loop', () => { parameters: {}, execute: () => Promise.resolve({ content: [{ type: 'text' as const, text: 'apparent success' }], meta }), })) - const agent = ctx.agentLoop.create(AgentId('bad-meta-agent'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('bad-meta-agent'), { model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -288,7 +288,7 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) ctx.on('system-prompt/assemble', async () => ({ sections: [], tools: [], variables: {} })) - const agent = ctx.agentLoop.create(AgentId('a-no-system'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-no-system'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -300,7 +300,7 @@ describe('agent loop', () => { it('records raw chunks for replay as assistant/chunk session events', async () => { const adapter = new MockAdapter([textResponse('abc')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -324,7 +324,7 @@ describe('agent loop', () => { ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'slow', description: '', @@ -356,7 +356,7 @@ describe('agent loop', () => { it('steering while idle behaves like send (starts a turn)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.steer([{ type: 'text', text: 'hello' }]) await waitForIdle(ctx, agent) @@ -366,7 +366,7 @@ describe('agent loop', () => { it('inject() while idle wraps context in a one-shot turn, visible to the next request', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.inject([{ type: 'text', text: 'file changed: a.ts' }], { source: { kind: 'plugin', plugin: 'watcher' } }) // The idle inject records a self-contained turn (turn/start → context/message @@ -393,7 +393,7 @@ describe('agent loop', () => { textResponse('done'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A tool that injects mid-execution: at this point the agent is running, so // inject must append the context/message into the ALREADY-open turn rather // than wrap it in its own one-shot turn. @@ -427,7 +427,7 @@ describe('agent loop', () => { textResponse('step 3'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steps = 0 ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ }) @@ -453,7 +453,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/turn-continuation', async () => ({ action: 'stop' }) as const) @@ -469,7 +469,7 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) ctx.llm.registerAdapter(['other-model'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { // The seed is frozen — config is not a mutable per-call knob; a switch @@ -502,7 +502,7 @@ describe('agent loop', () => { name: 'echo', description: 'echo', parameters: {}, async execute() { return [{ type: 'text', text: 'echoed' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const fires: { turn: number; step: number; fullSystemPrompt: string }[] = [] ctx.on('agent/pre-step', (subject, turn, step, fullSystemPrompt) => { @@ -527,7 +527,7 @@ describe('agent loop', () => { // the derived request for that step (derive happens after step/start). const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let injected = false ctx.on('agent/pre-step', (subject) => { @@ -563,7 +563,7 @@ describe('agent loop', () => { // The loop survives and a follow-up prompt still runs. const adapter = new MockAdapter([textResponse('second turn ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let throwOnce = true ctx.on('agent/pre-step', () => { @@ -597,7 +597,7 @@ describe('agent loop', () => { it('cancel() mid-stream ends the turn with reason aborted', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -617,7 +617,7 @@ describe('agent loop', () => { // turn stops by default and ends max-tokens, not completed. const adapter = new MockAdapter([maxTokensResponse('truncat')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -642,7 +642,7 @@ describe('agent loop', () => { textResponse('second half'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steps = 0 ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ }) @@ -673,7 +673,7 @@ describe('agent loop', () => { // stop. The per-turn reason must be independent — turn 2 ends completed. const adapter = new MockAdapter([maxTokensResponse('cut'), textResponse('clean')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -706,7 +706,7 @@ describe('agent loop', () => { return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -748,7 +748,7 @@ describe('agent loop', () => { parameters: { text: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -767,7 +767,7 @@ describe('agent loop', () => { // on the normal step path suppresses a pure trace-only empty assistant/message. const adapter = new MockAdapter([[{ type: 'finish', reason: { kind: 'stop' } }]]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -797,7 +797,7 @@ describe('agent loop', () => { expect(message.content).toEqual([{ type: 'text', text: 'partial text' }]) return next() }) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -824,7 +824,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threw = false // Post-commit session observers cannot control the loop. The tool call still // drives the second model request, and the turn completes normally. @@ -843,7 +843,7 @@ describe('agent loop', () => { it('chains queued messages into consecutive turns', async () => { const adapter = new MockAdapter([textResponse('first'), textResponse('second')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const turns: number[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/start') turns.push(event.data.turn) }) @@ -868,7 +868,7 @@ describe('agent loop', () => { it('awaits session/flush at turn end (persistence checkpoint)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let flushed = 0 let flushedBeforeIdle = false @@ -888,7 +888,7 @@ describe('agent loop', () => { it('errors from the model surface as agent/error and end the turn', async () => { const adapter = new MockAdapter([]) // script exhausted → throws const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const errors: Error[] = [] const reasons: TurnEndReason[] = [] @@ -913,10 +913,10 @@ describe('agent loop', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) - expect(ctx.agents.get(AgentId('scoped'))).toBe(agent) + expect(ctx.agents.get(SessionId('scoped'))).toBe(agent) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') @@ -925,7 +925,7 @@ describe('agent loop', () => { await agent.done expect(agent.status).toBe('disposed') - expect(ctx.agents.get(AgentId('scoped'))).toBeUndefined() + expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() expect(() => { send(agent, 'too late') }).toThrow('disposed') }) @@ -938,13 +938,14 @@ describe('agent loop', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('config-agent'), model: 'mock' }], + agents: [{ id: 'config-agent', model: 'mock' }], }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent + const agent = ctx.agents.list()[0]! as ReactLoopAgent expect(agent).toBeDefined() - expect(agent.id).toBe('config-agent') + expect(agent.id).toBe(agent.session.id) + expect(agent.id).toMatch(/^config-agent-session-/) expect(agent.options.model).toBe('mock') // the agent is alive: send triggers a turn @@ -961,10 +962,10 @@ describe('agent loop', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('config-agent'), model: 'mock', cwd: '/work/project' }], + agents: [{ id: 'config-agent', model: 'mock', cwd: '/work/project' }], }) - const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent + const agent = ctx.agents.list()[0]! as ReactLoopAgent expect(agent.session.header.cwd).toBe('/work/project') }) @@ -982,7 +983,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'run') await waitForIdle(ctx, agent) diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index 1e603a1cc4..b3653d6540 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -14,10 +14,11 @@ import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { LlmAdapter } from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import fc from 'fast-check' @@ -95,7 +96,7 @@ describe('agent loop scheduling properties', () => { async (texts) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) const { seen: trace } = recordStatus(ctx, agent) const idle = nextIdle(ctx, agent) // Send all in one synchronous tick: they queue before the loop wakes. @@ -120,7 +121,7 @@ describe('agent loop scheduling properties', () => { async (texts) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) for (const text of texts) { const idle = nextIdle(ctx, agent) agent.send([{ type: 'text', text }]) @@ -145,7 +146,7 @@ describe('agent loop scheduling properties', () => { async (steps) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) // Capture an idle waiter before EACH send; the last one is guaranteed // to resolve because the final send always triggers (or joins) a turn // that ends idle. Awaiting an already-resolved waiter is a no-op, so a diff --git a/packages/core/agent-loop/tests/request-cache.e2e.ts b/packages/core/agent-loop/tests/request-cache.e2e.ts index 5ccaa7e797..7eddb6be39 100644 --- a/packages/core/agent-loop/tests/request-cache.e2e.ts +++ b/packages/core/agent-loop/tests/request-cache.e2e.ts @@ -1,10 +1,11 @@ import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -71,7 +72,7 @@ function waitForIdle(context: Context, agent: Agent): Promise { describe.skipIf(!process.env.DEEPSEEK_API_KEY)('log-derived request cache hits (real API)', () => { it('every request after the first hits the provider prefix cache', async () => { ctx = await loopHarness() - const agent = ctx.agentLoop.create(AgentId('cache-e2e'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cache-e2e'), { model: 'deepseek-v4-flash' }) // Turn 1: forces a tool call → at least two steps (two model requests). agent.send([{ type: 'text', text: 'Look up the key "deploy-color" with the lookup tool and tell me the value.' }]) diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index 7054b683cb..202a8f6795 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -15,7 +15,8 @@ import type { GenerateOptions } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -74,7 +75,7 @@ describe('request stability across the loop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -95,7 +96,7 @@ describe('request stability across the loop', () => { it('a later turn append-extends the previous turn (one conversation, one log)', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -109,7 +110,7 @@ describe('request stability across the loop', () => { it('a compaction replace rewrites the resend, and the log explains it', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -142,7 +143,7 @@ describe('request stability across the loop', () => { it('a real system-prompt change is a full changed-header snapshot; a stable prompt logs nothing', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two'), textResponse('three')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -166,7 +167,7 @@ describe('request stability across the loop', () => { it('an inject() during the agent/request waterfall joins the NEXT request (the step/start boundary)', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let injected = false ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => { @@ -194,7 +195,7 @@ describe('request stability across the loop', () => { it('a mutation attempt on the frozen request content throws into the step (loud, not silent)', async () => { const adapter = new MockAdapter([textResponse('one')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) @@ -215,7 +216,7 @@ describe('request stability across the loop', () => { it('a fresh loop instance over a seeded log anchors with a resume snapshot and stays cache-aligned', async () => { const adapter = new MockAdapter([textResponse('one')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('gen1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('gen1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -224,7 +225,6 @@ describe('request stability across the loop', () => { const adapter2 = new MockAdapter([textResponse('two')]) const ctx2 = await harness(adapter2) const handle = await ctx2.agents.create({ - agentId: AgentId('gen2'), sessionId: SessionId('gen2-session'), seed: [...agent.session.events], agentOptions: { model: 'mock' }, @@ -244,7 +244,7 @@ describe('request stability across the loop', () => { it('a delegating listener cannot mutate the seed through next() — the fold stays log-true', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => { const config = await next() @@ -278,7 +278,7 @@ describe('request stability across the loop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) diff --git a/packages/core/agent-loop/tests/resume.spec.ts b/packages/core/agent-loop/tests/resume.spec.ts index 93605008ec..f5809575ab 100644 --- a/packages/core/agent-loop/tests/resume.spec.ts +++ b/packages/core/agent-loop/tests/resume.spec.ts @@ -8,7 +8,8 @@ import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -83,11 +84,10 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('session/created', () => throwUnknown(failure)) await expect(ctx.agents.resume({ - agentId: AgentId('unknown-resume-failure'), resumeSessionId: sessionId, })).rejects.toBe(failure) - expect(ctx.agents.get(AgentId('unknown-resume-failure'))).toBeUndefined() + expect(ctx.agents.get(SessionId('unknown-resume-failure'))).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() await ctx.fiber.dispose() }) @@ -95,27 +95,26 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { it('createAgent uses the caller-supplied sessionId (not ${id}-session)', async () => { const adapter = new MockAdapter([textResponse('hi')]) const { ctx } = await persistentHarness(adapter) - const { agent } = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('custom-session'), meta: { cwd: '/w' } }) + const { agent } = await ctx.agents.create({ sessionId: SessionId('custom-session'), meta: { cwd: '/w' } }) expect(agent.session.id).toBe('custom-session') expect(agent.session.header.cwd).toBe('/w') await ctx.fiber.dispose() }) - it('createAgent rejects a duplicate agent id BEFORE creating the session (no orphan)', async () => { + it('createAgent rejects a duplicate identity without orphaning a session', async () => { const adapter = new MockAdapter([textResponse('hi')]) const { ctx } = await persistentHarness(adapter) - await ctx.agents.create({ agentId: AgentId('dup'), sessionId: SessionId('sess-a') }) - // A second create with the SAME agent id but a fresh session id must reject - // up front — and must NOT leave an orphaned 'sess-b' session behind. - await expect(ctx.agents.create({ agentId: AgentId('dup'), sessionId: SessionId('sess-b') })).rejects.toThrow(/already registered/) - expect(ctx.sessions.get(SessionId('sess-b'))).toBeUndefined() + const sessionId = SessionId('sess-a') + await ctx.agents.create({ sessionId }) + await expect(ctx.agents.create({ sessionId })).rejects.toThrow(/already exists/) + expect(ctx.sessions.list()).toHaveLength(1) await ctx.fiber.dispose() }) it('createAgent works without meta (no cwd)', async () => { const adapter = new MockAdapter([textResponse('hi')]) const { ctx } = await persistentHarness(adapter) - const { agent } = await ctx.agents.create({ agentId: AgentId('a-nometa'), sessionId: SessionId('nometa-session') }) + const { agent } = await ctx.agents.create({ sessionId: SessionId('nometa-session') }) expect(agent.session.id).toBe('nometa-session') expect(agent.session.header.cwd).toBeUndefined() await ctx.fiber.dispose() @@ -125,7 +124,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // Lifecycle 1: create a no-cwd session and run a turn. const adapter1 = new MockAdapter([textResponse('a')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -141,7 +140,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent expect(a2.session.header.cwd).toBeUndefined() await ctx2.fiber.dispose() }) @@ -152,7 +151,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { const { ctx: ctx1, root } = await persistentHarness(adapter1) const sources1: string[] = [] ctx1.on('agent/session-start', (_agent, source) => void sources1.push(source)) - const a1 = (await ctx1.agents.create({ agentId: AgentId('s'), sessionId: SessionId('start-sess') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('start-sess') })).agent as ReactLoopAgent expect(sources1).toEqual(['startup']) a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) @@ -171,7 +170,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx2.llm.registerAdapter(['mock'], adapter2) const sources2: string[] = [] ctx2.on('agent/session-start', (_agent, source) => void sources2.push(source)) - await ctx2.agents.resume({ agentId: AgentId('s'), resumeSessionId: SessionId('start-sess') }) + await ctx2.agents.resume({ resumeSessionId: SessionId('start-sess') }) expect(sources2).toEqual(['resume']) await ctx2.fiber.dispose() }) @@ -186,7 +185,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('session/created', (session) => { expect(ctx.sessions.get(session.id)).toBe(session) - expect(ctx.agents.get(AgentId('resumed-atomic'))?.session).toBe(session) + expect(ctx.agents.get(sessionId)?.session).toBe(session) order.push('session/created') }) ctx.on('agent/created', (agent) => { @@ -199,11 +198,10 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { }) const resuming = ctx.agents.resume({ - agentId: AgentId('resumed-atomic'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, setup: async (agentCtx) => { - expect(agentCtx.agent?.id).toBe(AgentId('resumed-atomic')) + expect(agentCtx.agent?.id).toBe(sessionId) expect(agentCtx.agent?.session.events).toHaveLength(2) agentCtx.on('session/created', () => void order.push('setup-listener:session/created')) agentCtx.on('agent/created', () => void order.push('setup-listener:agent/created')) @@ -215,7 +213,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { }) await setupStarted.promise - expect(ctx.agents.get(AgentId('resumed-atomic'))).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() expect(order).toEqual(['setup:start']) @@ -236,17 +234,15 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { it('successful resume disposal retires its caller-owned transaction effects', async () => { const sessionId = SessionId('resume-retired-effects-s') - const agentId = AgentId('resume-retired-effects') const root = await persistSession(sessionId) const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')])) const handle = await ctx.agents.resume({ - agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' }, }) const transactionLabels = [ - `agentLoop.owner(${agentId})`, - `agentLoop.lifecycle(${agentId})`, + `agentLoop.owner(${sessionId})`, + `agentLoop.lifecycle(${sessionId})`, ] expect(ctx.fiber.getEffects().map(effect => effect.label)).toEqual(expect.arrayContaining(transactionLabels)) @@ -255,7 +251,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.fiber.dispose() }) - it('resume setup rejection publishes nothing, unwinds, and releases both identities', async () => { + it('resume setup rejection publishes nothing, unwinds, and releases the identity', async () => { const sessionId = SessionId('resume-setup-reject') const root = await persistSession(sessionId) const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')])) @@ -265,7 +261,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('agent/session-start', () => void published.push('agent/session-start')) await expect(ctx.agents.resume({ - agentId: AgentId('resume-reject'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, setup: async () => { @@ -275,10 +270,9 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { })).rejects.toThrow('resume setup failed') expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('resume-reject'))).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() const retry = await ctx.agents.resume({ - agentId: AgentId('resume-reject'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, }) @@ -299,7 +293,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { let resuming!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { resuming = inner.agents.resume({ - agentId: AgentId('resume-owner-race'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, setup: async () => { @@ -313,7 +306,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await owner.dispose() await expect(resuming).rejects.toThrow(/owner disposed during setup/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('resume-owner-race'))).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() gate.resolve(undefined) @@ -322,9 +315,8 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.fiber.dispose() }) - it('owner unload aborts a never-settling persistence load, releases identities, and blocks late publication', async () => { + it('owner unload aborts a never-settling persistence load, releases the identity, and blocks late publication', async () => { const sessionId = SessionId('resume-load-owner-unload') - const agentId = AgentId('resume-load-race') const root = await persistSession(sessionId) const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')])) const snapshot = await ctx.sessionPersistence.load(sessionId) @@ -348,19 +340,19 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { let resuming!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { - resuming = inner.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) + resuming = inner.agents.resume({ resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) }, { inject: ['agents'] })) await loadStarted.promise const rejection = expect(promptly(resuming)).rejects.toThrow(/owner disposed during setup/) await promptly(owner.dispose()) expect(published).toEqual([]) - expect(ctx.agents.get(agentId)).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() - // owner.dispose() awaited transaction settlement, so the same identities - // can be reused before awaiting the public rejection. - const retry = await promptly(ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } })) + // owner.dispose() awaited transaction settlement, so the identity can be + // reused before awaiting the public rejection. + const retry = await promptly(ctx.agents.resume({ resumeSessionId: sessionId, agentOptions: { model: 'mock' } })) await rejection expect(loads).toBe(2) expect(published).toEqual(['session/created', 'agent/created', 'agent/session-start']) @@ -370,7 +362,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { lateLoad.resolve(structuredClone(snapshot)) await Promise.resolve() await Promise.resolve() - expect(ctx.agents.get(agentId)).toBe(retry.agent) + expect(ctx.agents.get(sessionId)).toBe(retry.agent) expect(ctx.sessions.get(sessionId)).toBe(retry.agent.session) expect(published).toEqual(['session/created', 'agent/created', 'agent/session-start']) @@ -380,7 +372,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { it('AgentLoop unload aborts persistence load and awaits wrapper settlement', async () => { const sessionId = SessionId('resume-load-factory-unload') - const agentId = AgentId('resume-load-factory-race') const root = await persistSession(sessionId) const ctx = new Context() await ctx.plugin(LlmService) @@ -404,14 +395,14 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('session/created', () => void published.push('session/created')) ctx.on('agent/created', () => void published.push('agent/created')) - const resuming = ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) + const resuming = ctx.agents.resume({ resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) await loadStarted.promise const rejection = expect(promptly(resuming)).rejects.toThrow(/agent loop is not active/) await promptly(loopFiber.dispose()) await rejection expect(published).toEqual([]) - expect(ctx.agents.get(agentId)).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() lateLoad.resolve(structuredClone(snapshot)) await Promise.resolve() @@ -452,7 +443,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('forked-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('forked-sess') })).agent as ReactLoopAgent expect(a2.session.header.parentSession).toBe('parent-sess') expect(a2.session.header.cwd).toBe('/w') expect(a2.session.header.seedLength).toBe(seed.length) @@ -466,7 +457,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // disk, since a crash before the next turn would otherwise lose it. const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) @@ -491,7 +482,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // drop it on reload (the bug this guards). const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) @@ -509,7 +500,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('inject-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('inject-sess') })).agent as ReactLoopAgent const flat = JSON.stringify(a2.session.deriveMessages()) expect(flat).toContain('background task 42 finished') await ctx2.fiber.dispose() @@ -519,7 +510,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // Lifecycle 1: run one full turn, persisting it. const adapter1 = new MockAdapter([textResponse('first answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('main'), sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'first question' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) const events1 = [...a1.session.events] @@ -539,7 +530,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('main'), resumeSessionId: SessionId('sess-resume') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('sess-resume') })).agent as ReactLoopAgent // The resumed session carries the prior history… expect(a2.session.id).toBe('sess-resume') expect(a2.session.events.length).toBe(events1.length) @@ -567,7 +558,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) - await expect(ctx.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('nope') })) + await expect(ctx.agents.resume({ resumeSessionId: SessionId('nope') })) .rejects.toThrow(/session persistence is not configured/) await ctx.fiber.dispose() }) diff --git a/packages/core/agent-loop/tests/review-fixes.spec.ts b/packages/core/agent-loop/tests/review-fixes.spec.ts index 5898a82ee2..942199e9eb 100644 --- a/packages/core/agent-loop/tests/review-fixes.spec.ts +++ b/packages/core/agent-loop/tests/review-fixes.spec.ts @@ -4,7 +4,8 @@ import LlmService, { CallId, ContentBlock, MessageSource, StreamChunk } from '@d import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type ContinuationDecision } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type ContinuationDecision } from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { prepareReactLoopAgent } from '../src/agent.ts' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -53,7 +54,7 @@ describe('HIGH: session log records what agent/step-result actually produced', ( return [{ type: 'text', text: 'ran' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Plugin rewrites the message: replaces the text AND adds a tool call. let rewritten = false @@ -104,7 +105,7 @@ describe('HIGH: abort during tool execution ends the turn', () => { ]) const ctx = await harness(adapter) const executed: string[] = [] - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'aborter', description: '', @@ -148,7 +149,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { textResponse('continued because of steering'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steeredOnce = false ctx.on('agent/turn-continuation', async (_agent, _turn, _decision, next) => { @@ -188,7 +189,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { textResponse('after goal reminder'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steeredOnce = false ctx.on('session/event', (subject, event) => { @@ -218,7 +219,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { it('steer() from a turn/end session-event listener becomes a queued message for the next turn', async () => { const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const turns: number[] = [] let steeredOnce = false @@ -244,7 +245,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { it('steering queued during an aborted step is re-delivered, not silently consumed', async () => { const adapter = new MockAdapter(['hang', textResponse('recovered')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -267,7 +268,7 @@ describe('HIGH: plugin exceptions are contained', () => { it('a throwing agent/turn-continuation listener ends the turn with an error, loop survives', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('agent/turn-continuation', async (): Promise => { @@ -295,7 +296,7 @@ describe('HIGH: plugin exceptions are contained', () => { it('a rejecting session/flush listener is reported but does not kill the agent', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let rejectedOnce = false ctx.on('session/flush', async () => { @@ -325,7 +326,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const statuses: string[] = [] @@ -348,7 +349,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) ctx.on('agent/status', (_agent, status) => { @@ -361,7 +362,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { await agent.done // must not hang expect(agent.status).toBe('disposed') - expect(ctx.agents.get(AgentId('scoped'))).toBeUndefined() // unregistered despite the throw + expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() // unregistered despite the throw }) }) @@ -380,7 +381,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('an agent without a model fails the step with a clear error (not NO_ADAPTER for "default")', async () => { const adapter = new MockAdapter([textResponse('never')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), {}) // no model + const agent = ctx.agentLoop.create(SessionId('a1'), {}) // no model const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) @@ -395,7 +396,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('the agent/request waterfall can supply the model for a model-less agent', async () => { const adapter = new MockAdapter([textResponse('routed')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), {}) // no model — router plugin decides + const agent = ctx.agentLoop.create(SessionId('a1'), {}) // no model — router plugin decides ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { return { ...config, model: 'mock' } @@ -410,7 +411,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('agent/queued carries the resolved source; steering/message records its source', async () => { const adapter = new MockAdapter([toolCallResponse('c1', 'noop', {}), textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'noop', description: '', @@ -438,7 +439,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('send() owns content and source before notification and delivery', async () => { const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('owned-send'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-send'), { model: 'mock' }) const content = [{ type: 'text' as const, text: 'accepted-send' }] const source = { kind: 'plugin' as const, plugin: 'accepted-source' } let notifiedContent: ContentBlock[] | undefined @@ -474,7 +475,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('running steer() owns content and source before notification and delivery', async () => { const adapter = new MockAdapter([toolCallResponse('c1', 'gate', {}), textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('owned-steer'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-steer'), { model: 'mock' }) const entered = Promise.withResolvers() const release = Promise.withResolvers() ctx.tools.register(defineTool({ @@ -528,7 +529,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () it('a forked agent continues turn numbers after the seed log', async () => { const first = new MockAdapter([textResponse('turn one')]) const ctx = await harness(first) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -544,7 +545,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () ctx2.llm.registerAdapter(['mock'], second) const seeded = ctx2.sessions.create(SessionId('forked'), { seed: [...agent.session.events] }) - const prepared = prepareReactLoopAgent(ctx2, AgentId('forked-agent'), { model: 'mock' }, seeded) + const prepared = prepareReactLoopAgent(ctx2, SessionId('forked-agent'), { model: 'mock' }, seeded) const forked = prepared.agent prepared.markPublished() ctx2.effect(() => prepared.startDriver()) @@ -591,7 +592,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([errorStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-error'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-error'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -616,7 +617,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([abortedStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-aborted'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-aborted'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -634,7 +635,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([errorStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-error-nocode'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-error-nocode'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -650,7 +651,7 @@ describe('step boundary publication order', () => { it('the step/start event is in session.events when its session/event listener fires', async () => { const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-step-order'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-step-order'), { model: 'mock' }) // Session.append pushes the event BEFORE notifying session/event listeners, // so a step/start listener always finds the matching event already in the @@ -711,7 +712,7 @@ describe('turn and step boundary recovery', () => { it('a throwing step/start observer cannot change a successful turn', async () => { const adapter = new MockAdapter([textResponse('request completed')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepstart'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepstart'), { model: 'mock' }) // Session owns post-commit containment. The loop sees a successful append, // runs the request, and balances the ordinary step and turn boundaries. @@ -740,7 +741,7 @@ describe('turn and step boundary recovery', () => { it('a pre-commit step/start validation failure does not invent a step boundary', async () => { const adapter = new MockAdapter([textResponse('never reached')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepstart-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepstart-veto'), { model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -771,7 +772,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider failed' } }] const adapter = new MockAdapter([errorStream]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-turnend-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-turnend-veto'), { model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -805,7 +806,7 @@ describe('turn and step boundary recovery', () => { it('a one-shot step/end validation failure keeps the step open until retry succeeds', async () => { const adapter = new MockAdapter([textResponse('completed before close validation')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepend-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepend-veto'), { model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -839,7 +840,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }] const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-errorlistener'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-errorlistener'), { model: 'mock' }) let threw = false ctx.on('agent/error', () => { if (!threw) { threw = true; throw new Error('boom error-listener') } }) @@ -872,7 +873,7 @@ describe('turn and step boundary recovery', () => { const ctx = await balancedHarness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -901,7 +902,7 @@ describe('turn and step boundary recovery', () => { const ctx = await balancedHarness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-prestep-dispose-throw'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-prestep-dispose-throw'), { model: 'mock' }) }, { inject: ['agentLoop'] })) let threw = false @@ -935,7 +936,7 @@ describe('turn and step boundary recovery', () => { it('a throwing turn/start observer cannot starve the loop or later turns', async () => { const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-preturn'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-preturn'), { model: 'mock' }) let threw = false ctx.on('session/event', (_session, event) => { @@ -966,7 +967,7 @@ describe('turn and step boundary recovery', () => { it('a throwing step/end observer cannot rewrite the turn outcome', async () => { const adapter = new MockAdapter([textResponse('all good'), textResponse('turn 2 ok')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepend-throw'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepend-throw'), { model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1008,7 +1009,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }] const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stependthrow'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stependthrow'), { model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1038,7 +1039,7 @@ describe('turn and step boundary recovery', () => { // boundary stays authoritative and the loop continues normally. const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-turnendappend'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-turnendappend'), { model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1085,7 +1086,7 @@ describe('tool result call identity', () => { return Promise.resolve({ kind: 'accept', content: [{ type: 'text', text: 'ok' }] }) }, { prepend: true }) - const agent = ctx.agentLoop.create(AgentId('a-callid'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-callid'), { model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -1120,7 +1121,7 @@ describe('surface: assistant/message omits sourceEventSeqs when no chunks stream const adapter = new MockAdapter([[]]) const ctx = await harness(adapter) await ctx.plugin(Invariants) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/step-result', async (_agent, _turn, _step, _message, _next) => ({ role: 'assistant' as const, @@ -1171,7 +1172,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-assemble'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-assemble'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1227,7 +1228,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-cancel-assemble'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-cancel-assemble'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1282,7 +1283,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-prestep'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-prestep'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1334,7 +1335,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-cancel-prestep'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-cancel-prestep'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1384,7 +1385,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-no-leak'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-no-leak'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index 2c478ad1f0..c68d96e525 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -4,7 +4,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' + import type { Agent } from '@deepseek-ai/dsh-agent' import { scopeOf } from '@deepseek-ai/dsh-scope' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' @@ -57,33 +58,31 @@ function disposeCurrentLifecycle(ownerCtx: Context): void { } describe('agent scope lifecycle', () => { - it('rejects an already-aborted creation signal before publishing either identity', async () => { + it('rejects an already-aborted creation signal before publishing either object', async () => { const ctx = await harness() const reason = new Error('cancelled before creation') const controller = new AbortController() controller.abort(reason) await expect(ctx.agents.create({ - agentId: AgentId('pre-aborted'), sessionId: SessionId('pre-aborted-s'), signal: controller.signal, })).rejects.toBe(reason) - expect(ctx.agents.get(AgentId('pre-aborted'))).toBeUndefined() + expect(ctx.agents.get(SessionId('pre-aborted-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('pre-aborted-s'))).toBeUndefined() const valueController = new AbortController() valueController.abort('plain cancellation reason') await expect(ctx.agents.create({ - agentId: AgentId('pre-aborted-value'), sessionId: SessionId('pre-aborted-value-s'), signal: valueController.signal, })).rejects.toMatchObject({ - message: 'agent "pre-aborted-value" creation aborted', + message: 'agent "pre-aborted-value-s" creation aborted', cause: 'plain cancellation reason', }) - expect(ctx.agents.get(AgentId('pre-aborted-value'))).toBeUndefined() + expect(ctx.agents.get(SessionId('pre-aborted-value-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('pre-aborted-value-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -100,12 +99,11 @@ describe('agent scope lifecycle', () => { }) await expect(ctx.agents.create({ - agentId: AgentId('prepare-abort'), sessionId: SessionId('prepare-abort-s'), signal: controller.signal, })).rejects.toBe(reason) - expect(ctx.agents.get(AgentId('prepare-abort'))).toBeUndefined() + expect(ctx.agents.get(SessionId('prepare-abort-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('prepare-abort-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -124,7 +122,7 @@ describe('agent scope lifecycle', () => { thrown = createFailure let createCaught: unknown try { - ctx.agentLoop.create(AgentId('unknown-create')) + ctx.agentLoop.create(SessionId('unknown-create')) } catch (error: unknown) { createCaught = error } @@ -133,28 +131,27 @@ describe('agent scope lifecycle', () => { const ownedFailure = { source: 'createAgent' } thrown = ownedFailure await expect(ctx.agents.create({ - agentId: AgentId('unknown-owned-create'), sessionId: SessionId('unknown-owned-create-s'), })).rejects.toBe(ownedFailure) - expect(ctx.agents.get(AgentId('unknown-create'))).toBeUndefined() - expect(ctx.agents.get(AgentId('unknown-owned-create'))).toBeUndefined() + expect(ctx.agents.get(SessionId('unknown-create'))).toBeUndefined() + expect(ctx.agents.get(SessionId('unknown-owned-create-s'))).toBeUndefined() await ctx.fiber.dispose() }) it('wires agent.ctx: tagged with the agent, DX field set, ctx.agent safe elsewhere', async () => { const ctx = await harness() - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) expect(scopeOf(agent.ctx)).toBe(agent) expect(agent.ctx.agent).toBe(agent) // The root accessor default: a plain context answers undefined, not a throw. expect(ctx.agent).toBeUndefined() - await ctx.agents.get(AgentId('a1'))?.whenIdle() + await ctx.agents.get(SessionId('a1'))?.whenIdle() }) it('scoped registrations live in the agent world and die with the agent', async () => { const ctx = await harness() - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) const { agent } = handle agent.ctx.systemPrompt.section({ name: 'deployment:persona', order: 0, text: 'You run tests.' }) agent.ctx.tools.register({ @@ -179,8 +176,8 @@ describe('agent scope lifecycle', () => { it('agent.ctx listeners hear only their own agent (scoped dispatch end to end)', async () => { const ctx = await harness(new MockAdapter([textResponse('one'), textResponse('two')])) - const a = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) - const b = ctx.agentLoop.create(AgentId('b'), { model: 'mock' }) + const a = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) + const b = ctx.agentLoop.create(SessionId('b'), { model: 'mock' }) const heard: string[] = [] a.ctx.on('agent/status', (subject, status) => void heard.push(`a-sees:${subject.id}:${status}`)) @@ -210,7 +207,6 @@ describe('agent scope lifecycle', () => { }) const handle = await ctx.agents.create({ - agentId: AgentId('child'), sessionId: SessionId('child-s'), agentOptions: { model: 'mock' }, setup: async (agentCtx) => { @@ -224,14 +220,14 @@ describe('agent scope lifecycle', () => { await handle.dispose() }) - it('keeps both identities unpublished until async setup completes, then announces in order', async () => { + it('keeps both objects unpublished until async setup completes, then announces in order', async () => { const ctx = await harness() const gate = Promise.withResolvers() const setupStarted = Promise.withResolvers() const order: string[] = [] ctx.on('session/created', (session) => { expect(ctx.sessions.get(session.id)).toBe(session) - expect(ctx.agents.get(AgentId('atomic'))?.session).toBe(session) + expect(ctx.agents.get(session.id)?.session).toBe(session) order.push('session/created') }) ctx.on('agent/created', () => void order.push('agent/created')) @@ -239,11 +235,10 @@ describe('agent scope lifecycle', () => { const acceptedOptions = { model: 'mock' } const creating = ctx.agents.create({ - agentId: AgentId('atomic'), - sessionId: SessionId('atomic-s'), + sessionId: SessionId('atomic'), agentOptions: acceptedOptions, setup: async (agentCtx) => { - expect(agentCtx.agent?.id).toBe(AgentId('atomic')) + expect(agentCtx.agent?.id).toBe(SessionId('atomic')) agentCtx.on('session/created', () => void order.push('setup-listener:session/created')) agentCtx.on('agent/created', () => void order.push('setup-listener:agent/created')) order.push('setup:start') @@ -253,7 +248,7 @@ describe('agent scope lifecycle', () => { }, }) await setupStarted.promise - expect(ctx.agents.get(AgentId('atomic'))).toBeUndefined() + expect(ctx.agents.get(SessionId('atomic'))).toBeUndefined() expect(ctx.sessions.get(SessionId('atomic-s'))).toBeUndefined() expect(order).toEqual(['setup:start']) gate.resolve(undefined) @@ -281,16 +276,14 @@ describe('agent scope lifecycle', () => { if (started === 2) bothStarted.resolve(undefined) await gate.promise } - const agentId = AgentId('concurrent-final-enter') + const sessionId = SessionId('concurrent-final-enter') const first = ctx.agents.create({ - agentId, - sessionId: SessionId('concurrent-final-enter-a'), + sessionId, agentOptions: { model: 'mock' }, setup, }) const second = ctx.agents.create({ - agentId, - sessionId: SessionId('concurrent-final-enter-b'), + sessionId, agentOptions: { model: 'mock' }, setup, }) @@ -304,7 +297,7 @@ describe('agent scope lifecycle', () => { const rejected = outcomes.filter((outcome): outcome is PromiseRejectedResult => outcome.status === 'rejected') expect(fulfilled).toHaveLength(1) expect(rejected).toHaveLength(1) - expect(String(rejected[0]!.reason)).toMatch(/already registered/) + expect(String(rejected[0]!.reason)).toMatch(/already exists/) expect(ctx.agents.list()).toEqual([fulfilled[0]!.value.agent]) expect(ctx.sessions.list()).toEqual([fulfilled[0]!.value.agent.session]) @@ -318,7 +311,6 @@ describe('agent scope lifecycle', () => { const pendingController = new AbortController() const setupStarted = Promise.withResolvers() const pending = ctx.agents.create({ - agentId: AgentId('signal-pending'), sessionId: SessionId('signal-pending-s'), agentOptions: { model: 'mock' }, signal: pendingController.signal, @@ -330,12 +322,11 @@ describe('agent scope lifecycle', () => { await setupStarted.promise pendingController.abort(new Error('cancel pending creation')) await expect(pending).rejects.toThrow('cancel pending creation') - expect(ctx.agents.get(AgentId('signal-pending'))).toBeUndefined() + expect(ctx.agents.get(SessionId('signal-pending-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('signal-pending-s'))).toBeUndefined() const liveController = new AbortController() const live = await ctx.agents.create({ - agentId: AgentId('signal-live'), sessionId: SessionId('signal-live-s'), agentOptions: { model: 'mock' }, signal: liveController.signal, @@ -358,7 +349,6 @@ describe('agent scope lifecycle', () => { let creating!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { creating = inner.agents.create({ - agentId: AgentId('owner-race'), sessionId: SessionId('owner-race-s'), agentOptions: { model: 'mock' }, setup: async () => { @@ -372,7 +362,7 @@ describe('agent scope lifecycle', () => { await owner.dispose() await expect(creating).rejects.toThrow(/owner disposed during setup/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('owner-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('owner-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('owner-race-s'))).toBeUndefined() // Let the losing callback settle; Promise.race already observes it. gate.resolve(undefined) @@ -386,7 +376,6 @@ describe('agent scope lifecycle', () => { let creating2!: ReturnType const owner2 = await ctx.plugin(Object.assign((inner: Context) => { creating2 = inner.agents.create({ - agentId: AgentId('owner-race-2'), sessionId: SessionId('owner-race-s-2'), agentOptions: { model: 'mock' }, setup: async () => { @@ -400,7 +389,7 @@ describe('agent scope lifecycle', () => { const unload2 = owner2.dispose() await expect(creating2).rejects.toThrow(/owner disposed during setup/) await unload2 - expect(ctx.agents.get(AgentId('owner-race-2'))).toBeUndefined() + expect(ctx.agents.get(SessionId('owner-race-s-2'))).toBeUndefined() expect(ctx.sessions.get(SessionId('owner-race-s-2'))).toBeUndefined() }) @@ -413,7 +402,6 @@ describe('agent scope lifecycle', () => { ctx.on('agent/created', () => void published.push('agent/created')) const creating = ctx.agents.create({ - agentId: AgentId('factory-setup-race'), sessionId: SessionId('factory-setup-race-s'), agentOptions: { model: 'mock' }, setup: async () => { @@ -426,7 +414,7 @@ describe('agent scope lifecycle', () => { await loopFiber.dispose() await expect(creating).rejects.toThrow(/agent loop is not active/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('factory-setup-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('factory-setup-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('factory-setup-race-s'))).toBeUndefined() gate.resolve(undefined) @@ -444,7 +432,6 @@ describe('agent scope lifecycle', () => { }) const creating = ctx.agents.create({ - agentId: AgentId('factory-scope-race'), sessionId: SessionId('factory-scope-race-s'), agentOptions: { model: 'mock' }, setup: () => { setupCalls += 1 }, @@ -452,7 +439,7 @@ describe('agent scope lifecycle', () => { await expect(creating).rejects.toThrow(/agent loop is not active/) await loopFiber.dispose() expect(setupCalls).toBe(0) - expect(ctx.agents.get(AgentId('factory-scope-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('factory-scope-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('factory-scope-race-s'))).toBeUndefined() await ctx.fiber.dispose() @@ -479,7 +466,6 @@ describe('agent scope lifecycle', () => { const owner = ctx.plugin(Object.assign((inner: Context) => { ownerFiber = inner.fiber creating = inner.agents.create({ - agentId: AgentId('caller-scope-race'), sessionId: SessionId('caller-scope-race-s'), agentOptions: { model: 'mock' }, }) @@ -495,7 +481,7 @@ describe('agent scope lifecycle', () => { await ownerDisposal await owner expect(scopeFiber?.uid).toBeNull() - expect(ctx.agents.get(AgentId('caller-scope-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('caller-scope-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('caller-scope-race-s'))).toBeUndefined() await owner.dispose() await ctx.fiber.dispose() @@ -511,17 +497,17 @@ describe('agent scope lifecycle', () => { void loopFiber.dispose() }) - expect(() => ctx.agentLoop.create(AgentId('config-scope-race'), { model: 'mock' })) + expect(() => ctx.agentLoop.create(SessionId('config-scope-race'), { model: 'mock' })) .toThrow(/agent loop is not active/) await loopFiber.dispose() - expect(ctx.agents.get(AgentId('config-scope-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('config-scope-race'))).toBeUndefined() expect(ctx.sessions.list()).toHaveLength(sessionsBefore) await ctx.fiber.dispose() }) it('synchronous create leaves no lifecycle state when session preparation fails', async () => { const ctx = await harness() - const id = AgentId('config-prepare-failure') + const id = SessionId('config-prepare-failure') expect(() => ctx.agentLoop.create(id, { model: 'mock' }, { cwd: 'relative' })) .toThrow(/absolute path/) @@ -542,12 +528,11 @@ describe('agent scope lifecycle', () => { }) await expect(ctx.agents.create({ - agentId: AgentId('factory-scope-throw'), sessionId: SessionId('factory-scope-throw-s'), agentOptions: { model: 'mock' }, })).rejects.toThrow('scope preparation failed') await loopFiber.dispose() - expect(ctx.agents.get(AgentId('factory-scope-throw'))).toBeUndefined() + expect(ctx.agents.get(SessionId('factory-scope-throw-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('factory-scope-throw-s'))).toBeUndefined() await ctx.fiber.dispose() @@ -556,23 +541,21 @@ describe('agent scope lifecycle', () => { it('AgentLoop unload is a structural co-owner of every live programmatic agent', async () => { const { ctx, loopFiber } = await harnessWithLoop() const loop = ctx.agentLoop - const agentId = AgentId('factory-live') + const sessionId = SessionId('factory-live') const handle = await ctx.agents.create({ - agentId, - sessionId: SessionId('factory-live-s'), + sessionId, agentOptions: { model: 'mock' }, }) await loopFiber.dispose() expect(handle.agent.status).toBe('disposed') - expect(ctx.agents.get(agentId)).toBeUndefined() - expect(ctx.sessions.get(SessionId('factory-live-s'))).toBeUndefined() - expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${agentId})`)).toEqual([]) + expect(ctx.agents.get(sessionId)).toBeUndefined() + expect(ctx.sessions.get(sessionId)).toBeUndefined() + expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${sessionId})`)).toEqual([]) // The consumer handle shares the provider's completed quiescence boundary. await handle.dispose() await expect(loop.createAgent(ctx, { - agentId: AgentId('factory-inactive'), sessionId: SessionId('factory-inactive-s'), })).rejects.toThrow('agent loop is not active') await ctx.fiber.dispose() @@ -583,7 +566,6 @@ describe('agent scope lifecycle', () => { let creating!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { creating = inner.agents.create({ - agentId: AgentId('dependency-origin'), sessionId: SessionId('dependency-origin-s'), agentOptions: { model: 'mock' }, setup: (agentCtx) => { @@ -623,7 +605,7 @@ describe('agent scope lifecycle', () => { }) ctx.on('session/created', (session) => { if (session.id !== SessionId('session-created-barrier-s')) return - const agent = ctx.agents.get(AgentId('session-created-barrier'))! + const agent = ctx.agents.get(SessionId('session-created-barrier-s'))! expect(ctx.sessions.get(session.id)).toBe(session) expect(agent.session).toBe(session) agent.ctx.effect(() => () => { lifecycle.push('scope-disposed') }) @@ -638,7 +620,6 @@ describe('agent scope lifecycle', () => { const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('session-created-barrier'), sessionId: SessionId('session-created-barrier-s'), agentOptions: { model: 'mock' }, }) @@ -652,7 +633,7 @@ describe('agent scope lifecycle', () => { 'session-disposed', 'scope-disposed', ]) - expect(ctx.agents.get(AgentId('session-created-barrier'))).toBeUndefined() + expect(ctx.agents.get(SessionId('session-created-barrier-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('session-created-barrier-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -666,19 +647,19 @@ describe('agent scope lifecycle', () => { if (session.id === SessionId('agent-created-barrier-s')) lifecycle.push('session-created') }) ctx.on('agent/created', (agent) => { - if (agent.id !== AgentId('agent-created-barrier')) return + if (agent.id !== SessionId('agent-created-barrier-s')) return lifecycle.push('agent-created:dispose') disposeCurrentLifecycle(ownerCtx) }) ctx.on('agent/created', (agent) => { - if (agent.id !== AgentId('agent-created-barrier')) return + if (agent.id !== SessionId('agent-created-barrier-s')) return expect(ctx.agents.get(agent.id)).toBe(agent) expect(ctx.sessions.get(agent.session.id)).toBe(agent.session) agent.ctx.effect(() => () => { lifecycle.push('scope-disposed') }) lifecycle.push('agent-created:observer') }) ctx.on('agent/disposed', (agent) => { - if (agent.id === AgentId('agent-created-barrier')) lifecycle.push('agent-disposed') + if (agent.id === SessionId('agent-created-barrier-s')) lifecycle.push('agent-disposed') }) ctx.on('session/disposed', (session) => { if (session.id === SessionId('agent-created-barrier-s')) lifecycle.push('session-disposed') @@ -687,7 +668,6 @@ describe('agent scope lifecycle', () => { const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('agent-created-barrier'), sessionId: SessionId('agent-created-barrier-s'), agentOptions: { model: 'mock' }, }) @@ -703,7 +683,7 @@ describe('agent scope lifecycle', () => { 'session-disposed', 'scope-disposed', ]) - expect(ctx.agents.get(AgentId('agent-created-barrier'))).toBeUndefined() + expect(ctx.agents.get(SessionId('agent-created-barrier-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('agent-created-barrier-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -715,13 +695,12 @@ describe('agent scope lifecycle', () => { let creating!: ReturnType ctx.on('agent/session-start', agent => void starts.push(agent.id)) ctx.on('agent/created', (agent) => { - if (agent.id === AgentId('listener-dispose')) void ownerCtx.fiber.dispose() + if (agent.id === SessionId('listener-dispose-s')) void ownerCtx.fiber.dispose() }) const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('listener-dispose'), sessionId: SessionId('listener-dispose-s'), agentOptions: { model: 'mock' }, }) @@ -730,7 +709,7 @@ describe('agent scope lifecycle', () => { await expect(creating).rejects.toThrow(/owner disposed during setup/) await owner.dispose() expect(starts).toEqual([]) - expect(ctx.agents.get(AgentId('listener-dispose'))).toBeUndefined() + expect(ctx.agents.get(SessionId('listener-dispose-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('listener-dispose-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -744,15 +723,15 @@ describe('agent scope lifecycle', () => { let scopeDisposed = false let observerSawLive = false ctx.on('agent/status', (agent, status) => { - if (agent.id === AgentId('session-start-dispose')) statuses.push(status) + if (agent.id === SessionId('session-start-dispose-s')) statuses.push(status) }) ctx.on('agent/session-start', (agent) => { - if (agent.id !== AgentId('session-start-dispose')) return + if (agent.id !== SessionId('session-start-dispose-s')) return announced = agent as ReactLoopAgent disposeCurrentLifecycle(ownerCtx) }) ctx.on('agent/session-start', (agent) => { - if (agent.id !== AgentId('session-start-dispose')) return + if (agent.id !== SessionId('session-start-dispose-s')) return expect(ctx.agents.get(agent.id)).toBe(agent) expect(ctx.sessions.get(agent.session.id)).toBe(agent.session) agent.ctx.effect(() => () => { scopeDisposed = true }) @@ -762,7 +741,6 @@ describe('agent scope lifecycle', () => { const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('session-start-dispose'), sessionId: SessionId('session-start-dispose-s'), agentOptions: { model: 'mock' }, }) @@ -775,7 +753,7 @@ describe('agent scope lifecycle', () => { expect(observerSawLive).toBe(true) expect(scopeDisposed).toBe(true) expect(announced.session.events).toEqual([]) - expect(ctx.agents.get(AgentId('session-start-dispose'))).toBeUndefined() + expect(ctx.agents.get(SessionId('session-start-dispose-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('session-start-dispose-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -787,7 +765,6 @@ describe('agent scope lifecycle', () => { ctx.on('agent/created', () => void published.push('agent/created')) ctx.on('agent/session-start', () => void published.push('agent/session-start')) await expect(ctx.agents.create({ - agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' }, setup: async () => { @@ -798,13 +775,13 @@ describe('agent scope lifecycle', () => { // Nothing leaked: no agent, no session, and the ids are reusable. expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('bad'))).toBeUndefined() + expect(ctx.agents.get(SessionId('bad-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined() - const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) + const retry = await ctx.agents.create({ sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) await retry.dispose() }) - it('rejects an exotic durable seed before publishing either identity', async () => { + it('rejects an exotic durable seed before publishing either object', async () => { const ctx = await harness() const published: string[] = [] ctx.on('session/created', () => { published.push('session') }) @@ -817,17 +794,15 @@ describe('agent scope lifecycle', () => { }] as unknown as SessionEvent[] await expect(ctx.agents.create({ - agentId: AgentId('exotic-seed'), sessionId: SessionId('exotic-seed-session'), agentOptions: { model: 'mock' }, seed, })).rejects.toThrow(/seed event at index 0 is not losslessly JSON-serializable/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('exotic-seed'))).toBeUndefined() + expect(ctx.agents.get(SessionId('exotic-seed-session'))).toBeUndefined() expect(ctx.sessions.get(SessionId('exotic-seed-session'))).toBeUndefined() const retry = await ctx.agents.create({ - agentId: AgentId('exotic-seed'), sessionId: SessionId('exotic-seed-session'), agentOptions: { model: 'mock' }, }) @@ -843,13 +818,13 @@ describe('agent scope lifecycle', () => { if (boom) { boom = false; throw new Error('boom created') } }) await expect(ctx.agents.create({ - agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' }, + sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' }, })).rejects.toThrow('boom created') - expect(ctx.agents.get(AgentId('bad'))).toBeUndefined() + expect(ctx.agents.get(SessionId('bad-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined() expect(disposed).toEqual([]) // inserted but never announced: no impossible disposed edge // The rollback also disposed the scope fiber: re-creating works cleanly. - const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) + const retry = await ctx.agents.create({ sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) expect(scopeOf(retry.agent.ctx)).toBe(retry.agent) await retry.dispose() }) @@ -866,18 +841,17 @@ describe('agent scope lifecycle', () => { ctx.on('agent/disposed', (agent) => { lifecycle.push(`agent-disposed:${agent.id}`) }) await expect(ctx.agents.create({ - agentId: AgentId('partial-agent'), sessionId: SessionId('partial-session'), agentOptions: { model: 'mock' }, })).rejects.toThrow('agent observer failed') expect(lifecycle).toEqual([ 'session-created:partial-session', - 'agent-created:partial-agent', - 'agent-disposed:partial-agent', + 'agent-created:partial-session', + 'agent-disposed:partial-session', 'session-disposed:partial-session', ]) - expect(ctx.agents.get(AgentId('partial-agent'))).toBeUndefined() + expect(ctx.agents.get(SessionId('partial-session'))).toBeUndefined() expect(ctx.sessions.get(SessionId('partial-session'))).toBeUndefined() }) @@ -892,23 +866,23 @@ describe('agent scope lifecycle', () => { } }) - expect(() => ctx.agentLoop.create(AgentId('config-bad'), { model: 'mock' })) + expect(() => ctx.agentLoop.create(SessionId('config-bad'), { model: 'mock' })) .toThrow('config publish failed') - expect(ctx.agents.get(AgentId('config-bad'))).toBeUndefined() + expect(ctx.agents.get(SessionId('config-bad'))).toBeUndefined() expect(ctx.sessions.list()).toHaveLength(sessionsBefore) }) it('registrations through a disposed agent ctx throw INACTIVE_EFFECT', async () => { const ctx = await harness() - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) await handle.dispose() expect(() => handle.agent.ctx.on('agent/status', () => {})).toThrow(/inactive context/) }) it('agentEvents fuses carrier and subject for custom drivers', async () => { const ctx = await harness() - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - const other = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) + const other = ctx.agentLoop.create(SessionId('a2'), { model: 'mock' }) const heard: string[] = [] agent.ctx.on('agent/error', (subject: Agent, turn: number) => void heard.push(`${subject.id}:${turn}`)) @@ -921,7 +895,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { - handle = await inner.agents.create({ agentId: AgentId('o1'), sessionId: SessionId('o1-s'), agentOptions: { model: 'mock' } }) + handle = await inner.agents.create({ sessionId: SessionId('o1-s'), agentOptions: { model: 'mock' } }) }, { inject: ['agents'] })) const { agent } = handle @@ -930,7 +904,7 @@ describe('agent scope lifecycle', () => { if (event.type === 'turn/end') order.push('turn-end') }) ctx.on('agent/disposed', () => { - order.push(`disposed(listed=${ctx.agents.get(AgentId('o1')) !== undefined})`) + order.push(`disposed(listed=${ctx.agents.get(SessionId('o1-s')) !== undefined})`) order.push(`session-still-stored=${ctx.sessions.get(SessionId('o1-s')) !== undefined}`) }) @@ -955,7 +929,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { - handle = await inner.agents.create({ agentId: AgentId('h1'), sessionId: SessionId('h1-s'), agentOptions: { model: 'mock' } }) + handle = await inner.agents.create({ sessionId: SessionId('h1-s'), agentOptions: { model: 'mock' } }) }, { inject: ['agents'] })) const teardownDone: string[] = [] @@ -967,23 +941,22 @@ describe('agent scope lifecycle', () => { // actually finished (the raw wrapper returns undefined on a repeat call). await handle.dispose() expect(teardownDone).toContain('unregistered') - expect(ctx.agents.get(AgentId('h1'))).toBeUndefined() + expect(ctx.agents.get(SessionId('h1-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('h1-s'))).toBeUndefined() await unload }) it('successful handle disposal retires its caller ownership effect', async () => { const ctx = await harness() - const agentId = AgentId('retired-owner-effect') + const sessionId = SessionId('retired-owner-effect') const handle = await ctx.agents.create({ - agentId, - sessionId: SessionId('retired-owner-effect-s'), + sessionId, agentOptions: { model: 'mock' }, }) - expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${agentId})`) + expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${sessionId})`) await handle.dispose() - expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${agentId})`)).toEqual([]) + expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${sessionId})`)).toEqual([]) await ctx.fiber.dispose() }) @@ -994,7 +967,6 @@ describe('agent scope lifecycle', () => { let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { handle = await inner.agents.create({ - agentId: AgentId('manual-first'), sessionId: SessionId('manual-first-s'), agentOptions: { model: 'mock' }, setup(agentCtx) { @@ -1014,7 +986,7 @@ describe('agent scope lifecycle', () => { expect(ownerSettled).toBe(false) gate.resolve(undefined) await Promise.all([disposing, unloading]) - expect(ctx.agents.get(AgentId('manual-first'))).toBeUndefined() + expect(ctx.agents.get(SessionId('manual-first-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('manual-first-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -1024,13 +996,11 @@ describe('agent scope lifecycle', () => { const gate = Promise.withResolvers() const cleanupStarted = Promise.withResolvers() const sessionDisposed = Promise.withResolvers() - const agentId = AgentId('quiescent-reuse') - const sessionId = SessionId('quiescent-reuse-s') + const sessionId = SessionId('quiescent-reuse') ctx.on('session/disposed', (session) => { if (session.id === sessionId) sessionDisposed.resolve(undefined) }) const first = await ctx.agents.create({ - agentId, sessionId, agentOptions: { model: 'mock' }, setup(agentCtx) { @@ -1043,10 +1013,10 @@ describe('agent scope lifecycle', () => { const disposing = first.dispose() await Promise.all([sessionDisposed.promise, cleanupStarted.promise]) - expect(ctx.agents.get(agentId)).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() - const replacement = await ctx.agents.create({ agentId, sessionId, agentOptions: { model: 'mock' } }) - expect(ctx.agents.get(agentId)).toBe(replacement.agent) + const replacement = await ctx.agents.create({ sessionId, agentOptions: { model: 'mock' } }) + expect(ctx.agents.get(sessionId)).toBe(replacement.agent) expect(ctx.sessions.get(sessionId)).toBe(replacement.agent.session) gate.resolve(undefined) @@ -1058,7 +1028,6 @@ describe('agent scope lifecycle', () => { it('handle.dispose() awaits an idle-injection flush before unregistering or detaching', async () => { const ctx = await harness() const handle = await ctx.agents.create({ - agentId: AgentId('idle-flush'), sessionId: SessionId('idle-flush-s'), agentOptions: { model: 'mock' }, }) @@ -1077,12 +1046,12 @@ describe('agent scope lifecycle', () => { const disposal = handle.dispose().then(() => { disposed = true }) await new Promise(resolve => setTimeout(resolve, 0)) expect(disposed).toBe(false) - expect(ctx.agents.get(AgentId('idle-flush'))).toBe(handle.agent) + expect(ctx.agents.get(SessionId('idle-flush-s'))).toBe(handle.agent) expect(ctx.sessions.get(SessionId('idle-flush-s'))).toBe(handle.agent.session) gate.resolve(undefined) await disposal - expect(ctx.agents.get(AgentId('idle-flush'))).toBeUndefined() + expect(ctx.agents.get(SessionId('idle-flush-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('idle-flush-s'))).toBeUndefined() }) }) diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index d9b0a87e1d..1085f01a4c 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -10,11 +10,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { foldRequestHeader } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' import SystemPrompt, { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -57,7 +58,7 @@ async function runTurn(registrationOrder: string[], toolOrder?: SystemPromptConf const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter, toolOrder) for (const name of registrationOrder) registerNamed(ctx, name) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) return { ctx, agent, adapter } @@ -103,7 +104,7 @@ describe('loop-level canonical tool order', () => { registerNamed(ctx, 'alpha') const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) diff --git a/packages/core/agent-loop/tests/turn-stop.spec.ts b/packages/core/agent-loop/tests/turn-stop.spec.ts index c275fee88c..c7823a2aa5 100644 --- a/packages/core/agent-loop/tests/turn-stop.spec.ts +++ b/packages/core/agent-loop/tests/turn-stop.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type TurnEndReason } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type ContinuationStop } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type ContinuationStop } from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -45,7 +46,7 @@ describe('agent/turn-stop', () => { textResponse('must not be requested'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-steering'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-steering'), { model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let steered = false @@ -72,7 +73,7 @@ describe('agent/turn-stop', () => { textResponse('must not become a late-steering turn'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-flush-steering'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-flush-steering'), { model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let injected = false @@ -98,7 +99,7 @@ describe('agent/turn-stop', () => { textResponse('queued follow-up answer'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-flush-send'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-flush-send'), { model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let queued = false @@ -124,8 +125,8 @@ describe('agent/turn-stop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const stopped = ctx.agentLoop.create(AgentId('stopped'), { model: 'mock' }) - const ordinary = ctx.agentLoop.create(AgentId('ordinary'), { model: 'mock' }) + const stopped = ctx.agentLoop.create(SessionId('stopped'), { model: 'mock' }) + const ordinary = ctx.agentLoop.create(SessionId('ordinary'), { model: 'mock' }) stopped.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) await send(stopped) @@ -145,7 +146,7 @@ describe('agent/turn-stop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('owned-listener'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-listener'), { model: 'mock' }) const disposeStop = agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) await send(agent, 'first turn') @@ -162,7 +163,7 @@ describe('agent/turn-stop', () => { textResponse('healthy later turn'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('bad-policy'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('bad-policy'), { model: 'mock' }) const reasons: TurnEndReason[] = [] const errors: string[] = [] ctx.on('session/event', (session, event) => { diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 9ee324b0c3..4eddb050d5 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -12,7 +12,7 @@ The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh- - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. - Advanced ordered lifecycle: `enter(agent): () => void` performs the authoritative ID collision check and inserts without announcing; `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. -- `ctx.agents.get(id: AgentId): Agent | undefined` +- `ctx.agents.get(id: SessionId): Agent | undefined` - `ctx.agents.list(): Agent[]` #### Factory seam (creation) diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index edb7f59a37..1306e8004d 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -9,7 +9,7 @@ import { Context, getTraceable, Service, symbols } from 'cordis' import { scopeTarget } from '@deepseek-ai/dsh-scope' import type { Scoped } from '@deepseek-ai/dsh-scope' import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session' -import type { Agent, AgentId, AgentOptions } from './types.ts' +import type { Agent, AgentOptions } from './types.ts' export * from './types.ts' export { agentEvents, assembleContextFor } from './dispatch.ts' @@ -33,15 +33,13 @@ declare module 'cordis' { /** * Options for programmatically creating an agent through the registry factory - * ({@link AgentRegistry.create}). The caller supplies the live `sessionId` - * (e.g. an ACP-generated id) and optional session metadata (the validated - * `cwd`, fork lineage); the factory creates the session, the agent, and wires - * them together. + * ({@link AgentRegistry.create}). The caller supplies the single live + * `sessionId` shared by the agent registry and session log (e.g. an + * ACP-generated id), plus optional session metadata (the validated `cwd`, fork + * lineage); the factory creates the session and agent under that identity. */ export interface CreateAgentOptions { - /** The agent's id (the registry handle). */ - readonly agentId: AgentId - /** The live session's id (NOT derived from agentId). */ + /** The live agent/session identity. */ readonly sessionId: SessionId /** * Session creation metadata: validated absolute `cwd`, `parentSession` @@ -93,9 +91,7 @@ export interface CreateAgentOptions { * ({@link AgentRegistry.resume}). */ export interface ResumeAgentOptions { - /** The agent's id (the registry handle). */ - readonly agentId: AgentId - /** The persisted session id to load and resume on. */ + /** The persisted session id to load and use as the live agent/session identity. */ readonly resumeSessionId: SessionId /** Per-agent options (model, …). */ readonly agentOptions?: AgentOptions @@ -180,7 +176,7 @@ const NO_FACTORY_MESSAGE = 'no agent factory registered (load an agent-loop plug /** All mutable lifecycle state for one exact registry entry. */ interface AgentEntry { - readonly id: AgentId + readonly id: SessionId readonly agent: Agent readonly carrier: Scoped announced: boolean @@ -201,7 +197,7 @@ interface FactorySlot { * {@link setFactory}. */ export class AgentRegistry extends Service { - private store = new Map() + private store = new Map() private factory: FactorySlot | undefined constructor(ctx: Context) { @@ -257,7 +253,7 @@ export class AgentRegistry extends Service { * agent): this constructs the agent and its session. Rejects if no factory is * registered or creation/setup fails. The resolved {@link AgentHandle} lets * the owner tear down exactly this agent. - * @param options - agent id, session id/seed/metadata, and agent options. + * @param options - shared identity, session seed/metadata, and agent options. * @returns the handle after setup, rollback-covered publication, and loop start complete. */ async create(options: CreateAgentOptions): Promise { @@ -428,10 +424,10 @@ export class AgentRegistry extends Service { /** * Look up a live agent. - * @param id - the agent id to look up. + * @param id - the shared agent/session id to look up. * @returns the agent, or undefined when no live agent has that id. */ - get(id: AgentId): Agent | undefined { + get(id: SessionId): Agent | undefined { return this.store.get(id)?.agent } diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index a990f0d67d..b0fb78ad66 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -32,7 +32,7 @@ * event. A turn/step boundary is a durable fact: it lives in the session log * and is read off the `session/event` feed — it is NOT mirrored as an `agent/*` * emit. A consumer that needs the `Agent` handle (or its short id) at a boundary - * keeps a session-id→agent map from `agent/created`/`agent/disposed`. + * looks up the agent directly by the event's session id. * See `docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md` * and `docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md`. * @@ -45,25 +45,12 @@ * @module @deepseek-ai/dsh-agent/types */ -import type { Branded } from '@deepseek-ai/dsh-brand' import type { Context } from 'cordis' import type { Scoped } from '@deepseek-ai/dsh-scope' import type { ContentBlock, LlmCallConfig, Message, MessageSource } from '@deepseek-ai/dsh-llm' +import type { Session, SessionId } from '@deepseek-ai/dsh-session' import type {} from '@deepseek-ai/dsh-system-prompt' -/** Identifies one live agent in the registry. */ -export type AgentId = Branded<'AgentId'> - -/** - * Brand a string as an {@link AgentId}. - * @param id - the raw agent id string. - * @returns the same string, branded (a compile-time cast — no runtime cost). - */ -export function AgentId(id: string): AgentId { - return id as AgentId -} -import type { Session } from '@deepseek-ai/dsh-session' - declare module '@deepseek-ai/dsh-system-prompt' { interface AssembleContext { /** @@ -186,7 +173,8 @@ export type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact' * package should depend on the implementation. */ export interface Agent { - readonly id: AgentId + /** The single identity shared with {@link session}. */ + readonly id: SessionId readonly options: AgentOptions readonly session: Session readonly status: AgentStatus diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index 5d541d56a8..cba833b212 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -2,11 +2,12 @@ import { describe, expect, expectTypeOf, it } from 'vitest' import { Context, Service, symbols } from 'cordis' import type { Events } from 'cordis' import { Session, SessionId } from '@deepseek-ai/dsh-session' -import AgentRegistry, { AgentId, agentEvents } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { agentEvents } from '@deepseek-ai/dsh-agent' + import type { Agent, AgentFactory, ContinuationStop, CreateAgentOptions, ResumeAgentOptions } from '@deepseek-ai/dsh-agent' function stubAgent(rawId: string): Agent { - const id = AgentId(rawId) + const id = SessionId(rawId) return { id, options: {}, @@ -57,7 +58,7 @@ describe('AgentRegistry', () => { ctx.on('agent/disposed', agent => void lifecycle.push(`disposed:${agent.id}`)) expect(() => ctx.agents.register(stubAgent('vetoed'))).toThrow('creation veto') - expect(ctx.agents.get(AgentId('vetoed'))).toBeUndefined() + expect(ctx.agents.get(SessionId('vetoed'))).toBeUndefined() expect(lifecycle).toEqual(['created:vetoed', 'disposed:vetoed']) }) @@ -158,11 +159,11 @@ describe('AgentRegistry factory seam', () => { const factory: AgentFactory = { async createAgent(ownerCtx, options) { calls.create.push({ ownerCtx, options }) - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.sessionId), dispose: () => Promise.resolve() } }, async resume(ownerCtx, options) { calls.resume.push({ ownerCtx, options }) - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.resumeSessionId), dispose: () => Promise.resolve() } }, } return { factory, calls } @@ -171,15 +172,15 @@ describe('AgentRegistry factory seam', () => { it('requires a factory and delegates through the calling context', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) - await expect(ctx.agents.create({ agentId: AgentId('a'), sessionId: SessionId('s') })).rejects.toThrow(/no agent factory/) + await expect(ctx.agents.create({ sessionId: SessionId('s') })).rejects.toThrow(/no agent factory/) const { factory, calls } = stubFactory() ctx.agents.setFactory(factory) let callerFiber: Context['fiber'] | undefined await ctx.plugin(Object.assign(async (inner: Context) => { callerFiber = inner.fiber - await inner.agents.create({ agentId: AgentId('create'), sessionId: SessionId('create-s') }) - await inner.agents.resume({ agentId: AgentId('resume'), resumeSessionId: SessionId('resume-s') }) + await inner.agents.create({ sessionId: SessionId('create-s') }) + await inner.agents.resume({ resumeSessionId: SessionId('resume-s') }) }, { inject: ['agents'] })) expect(calls.create[0]?.ownerCtx.fiber).toBe(callerFiber) expect(calls.resume[0]?.ownerCtx.fiber).toBe(callerFiber) @@ -192,9 +193,9 @@ describe('AgentRegistry factory seam', () => { inner.agents.setFactory(stubFactory().factory) expect(() => inner.agents.setFactory(stubFactory().factory)).toThrow(/already registered/) }, { inject: ['agents'] })) - await expect(ctx.agents.create({ agentId: AgentId('before'), sessionId: SessionId('before-s') })).resolves.toBeDefined() + await expect(ctx.agents.create({ sessionId: SessionId('before-s') })).resolves.toBeDefined() await owner.dispose() - await expect(ctx.agents.create({ agentId: AgentId('after'), sessionId: SessionId('after-s') })).rejects.toThrow(/no agent factory/) + await expect(ctx.agents.create({ sessionId: SessionId('after-s') })).rejects.toThrow(/no agent factory/) }) it('canonicalizes an already traced Service before tracing it for the caller', async () => { @@ -214,18 +215,18 @@ describe('AgentRegistry factory seam', () => { } async createAgent(_ownerCtx: Context, options: CreateAgentOptions) { this.calls().push('create') - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.sessionId), dispose: () => Promise.resolve() } } async resume(_ownerCtx: Context, options: ResumeAgentOptions) { this.calls().push('resume') - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.resumeSessionId), dispose: () => Promise.resolve() } } } await ctx.plugin(TracedFactory) const traced = (ctx as Context & { tracedFactory: TracedFactory }).tracedFactory ctx.agents.setFactory(traced) - await ctx.agents.create({ agentId: AgentId('create'), sessionId: SessionId('create-s') }) - await ctx.agents.resume({ agentId: AgentId('resume'), resumeSessionId: SessionId('resume-s') }) + await ctx.agents.create({ sessionId: SessionId('create-s') }) + await ctx.agents.resume({ resumeSessionId: SessionId('resume-s') }) const raw = (traced as unknown as { [symbols.original]?: TracedFactory })[symbols.original] expect(states.get(raw!)).toEqual(['create', 'resume']) }) diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index 06669ca85c..cb6e1304c3 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -288,7 +288,12 @@ export class Session { */ readonly header: SessionHeader - constructor(public readonly id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader) { + /** The session identity, derived from its durable header's single copy. */ + get id(): SessionId { + return this.header.id + } + + constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader) { if (seed) { // Validate the seed to the SAME invariants `append` enforces, so a // replay/fork (`ctx.sessions.create(id, { seed })`) cannot construct a diff --git a/packages/core/tools/tests/code-mode.spec.ts b/packages/core/tools/tests/code-mode.spec.ts index f9d84aadbf..2339657ec8 100644 --- a/packages/core/tools/tests/code-mode.spec.ts +++ b/packages/core/tools/tests/code-mode.spec.ts @@ -8,7 +8,6 @@ import { CodeRuntime } from '@deepseek-ai/dsh-code-runtime' import type { CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtime' import ToolRegistry, { CodeRunFailedError, RUN_CODE_NAME, defineTool } from '@deepseek-ai/dsh-tools' import type { Config, PostToolDecision, ToolExecutionResult } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { Session, SessionId } from '@deepseek-ai/dsh-session' import type { SessionEventMap } from '@deepseek-ai/dsh-session' @@ -59,7 +58,7 @@ async function setup(options: SetupOptions = {}) { /** Mint one production-shaped agent scope that can register scoped tool policy. */ async function mintAgentScope(ctx: Context, name = 'scoped'): Promise<{ scope: Scope; agent: Agent }> { - const agent = { id: AgentId(name) } as Agent + const agent = { id: SessionId(name) } as Agent let scope!: Scope await ctx.plugin(Object.assign((inner: Context) => { scope = createScope(inner, agent) }, { inject: ['tools', 'systemPrompt'] })) diff --git a/packages/core/tools/tests/scoped.spec.ts b/packages/core/tools/tests/scoped.spec.ts index 6599112c2a..8b8e1cfead 100644 --- a/packages/core/tools/tests/scoped.spec.ts +++ b/packages/core/tools/tests/scoped.spec.ts @@ -6,9 +6,11 @@ import type { Scope } from '@deepseek-ai/dsh-scope' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import type { PreToolDecision, ToolDefinition, ToolExecution, ToolExecutionInput, ToolExecutionToken } from '@deepseek-ai/dsh-tools' -import type { Agent, AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' + import { CallId } from '@deepseek-ai/dsh-llm' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import type { SessionId } from '@deepseek-ai/dsh-session' /** Mount the registry (with its systemPrompt dependency) on a fresh context. */ async function mount(): Promise { @@ -20,7 +22,7 @@ async function mount(): Promise { /** Mint a scope whose key doubles as a minimal Agent-like object. */ async function mintAgentScope(ctx: Context, name: string): Promise<{ scope: Scope; key: Agent }> { - const key = { id: name as AgentId } as Agent + const key = { id: name as SessionId } as Agent let scope!: Scope // The scoped context resolves services through the MINTING plugin's // dependency chain — the minter must inject what scope holders will reach @@ -62,7 +64,7 @@ describe('scoped tool registration', () => { it('files a scoped tool in its layer: visible/executable for that scope only', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'a') - const other = { id: 'other' as AgentId } as Agent + const other = { id: 'other' as SessionId } as Agent ctx.tools.register(tool('shared')) scope.ctx.tools.register(tool('mine')) @@ -195,7 +197,7 @@ describe('scoped execution dispatch', () => { it('an agent.ctx pre-execute listener gates only its own agent (and never subject-less calls)', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'a') - const other = { id: 'other' as AgentId } as Agent + const other = { id: 'other' as SessionId } as Agent ctx.tools.register(tool('t')) const seen: (string | undefined)[] = [] @@ -213,7 +215,7 @@ describe('scoped execution dispatch', () => { it('applies scoped guards after pre-execute and unwinds duplicate registrations independently', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'a') - const other = { id: 'other' as AgentId } as Agent + const other = { id: 'other' as SessionId } as Agent let bodyCalls = 0 ctx.tools.register({ ...tool('t'), @@ -428,7 +430,7 @@ describe('scoped execution dispatch', () => { it('uses one input snapshot for the normalized error shell', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'accepted') - const driftAgent = { id: 'drift' as AgentId } as Agent + const driftAgent = { id: 'drift' as SessionId } as Agent ctx.tools.register(tool('parent')) ctx.tools.register(tool('t')) let parent!: ToolExecutionToken diff --git a/packages/fs/tool-fs/tests/fs-tools.e2e.ts b/packages/fs/tool-fs/tests/fs-tools.e2e.ts index a270e7c6d8..dca48d65ab 100644 --- a/packages/fs/tool-fs/tests/fs-tools.e2e.ts +++ b/packages/fs/tool-fs/tests/fs-tools.e2e.ts @@ -3,7 +3,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { fsHarness, waitForIdle } from './harness.ts' @@ -35,7 +34,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => ctx = await fsHarness(workdir, SYSTEM) // agentLoop.create prepares a session with no cwd, so the provider default // (config.cwd = workdir) is the workspace. - const agent = ctx.agentLoop.create(AgentId('fs-e2e'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('fs-e2e'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Create a file named note.txt containing exactly the line: status: draft. ' @@ -65,7 +64,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => try { ctx = await fsHarness(configDir, SYSTEM) const handle = await ctx.agents.create({ - agentId: AgentId('fs-e2e-cwd'), sessionId: SessionId(`fs-e2e-cwd-${Date.now()}`), meta: { cwd: sessionDir }, agentOptions: { model: 'deepseek-v4-flash' }, diff --git a/packages/guard/repeat-tool-guard/README.md b/packages/guard/repeat-tool-guard/README.md index dc385bc033..e46f113301 100644 --- a/packages/guard/repeat-tool-guard/README.md +++ b/packages/guard/repeat-tool-guard/README.md @@ -24,8 +24,8 @@ The chain key is `(tool name, canonical arguments)` — canonicalization is a de - **Untracked calls are transparent to the chain.** A call excluded by `include`/`exclude` neither increments nor resets the counter, so `grep X → todo_write → grep X` still counts as two consecutive `grep X` when `todo_write` is excluded. This is what makes exclusion useful: bookkeeping tools interleaved into a loop must not launder it. - **Denied calls count.** Detection sits on `tools/post-execute`, which also runs for calls a `tools/pre-execute` listener denied — a model hammering a denied call is exactly the loop worth breaking. -- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller has no model to remind and no `AgentId` to key on. -- **Per-agent keying.** The tool registry is context-level and subagents interleave through the same waterfall, so chains are keyed by `AgentId`; one agent's repetition never trips another's reminder. A user prompt (`agent/prompt-submit`) resets the submitting agent's chain; agent disposal drops its state. +- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller has no model to remind and no live agent object to key on. +- **Per-agent keying.** The tool registry is context-level and subagents interleave through the same waterfall, so a `WeakMap` keys each chain by the live agent object; one agent's repetition never trips another's reminder. A user prompt (`agent/prompt-submit`) resets the submitting agent's chain, and object lifetime bounds the weak entry without a disposal listener. - **In-memory only.** A session resumed from persistence starts with a fresh chain — the guard is a heuristic nudge, not a logged invariant, later reminders are the accepted cost. ## Reminder delivery diff --git a/packages/guard/repeat-tool-guard/src/index.ts b/packages/guard/repeat-tool-guard/src/index.ts index 6a5662d693..d51df1d829 100644 --- a/packages/guard/repeat-tool-guard/src/index.ts +++ b/packages/guard/repeat-tool-guard/src/index.ts @@ -22,7 +22,7 @@ * exclude: [todo_write] # tool-name patterns transparent to the chain * ``` * - * Chain state is keyed per {@link AgentId} — the tool registry is a + * Chain state is keyed by the live agent object — the tool registry is a * context-level singleton whose waterfalls interleave every agent's calls, so * a shared counter would let one agent's repetition trip another's reminder. * State is in-memory only: a session resumed from persistence starts with a @@ -37,7 +37,7 @@ import type { Context } from 'cordis' import z from 'schemastery' -import type { AgentId, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' +import type { Agent, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' import type { MessageSource } from '@deepseek-ai/dsh-llm' import type { PostToolDecision, ToolExecution } from '@deepseek-ai/dsh-tools' @@ -202,9 +202,7 @@ export function apply(ctx: Context, config: Config): void { throw new Error(`repeat-tool-guard: invalid argumentsPreviewChars ${argumentsPreviewChars} — must be an integer >= 1`) } - // TODO(agent-keyed-repeat-chain): key a WeakMap by the Agent itself; that - // removes the disposal-only status listener and cannot collide on id reuse. - const chains = new Map() + const chains = new WeakMap() /** Whether a tool participates in the chain (untracked calls are transparent: they neither count nor reset). */ function tracked(toolName: string): boolean { @@ -227,9 +225,9 @@ export function apply(ctx: Context, config: Config): void { if (!tracked(exec.name)) return undefined const canonical = canonicalize(exec.arguments) const key = JSON.stringify([exec.name, canonical]) - const chain = chains.get(exec.agent.id) + const chain = chains.get(exec.agent) const count = chain !== undefined && chain.key === key ? chain.count + 1 : 1 - chains.set(exec.agent.id, { key, count }) + chains.set(exec.agent, { key, count }) if (!thresholdSet.has(count)) return undefined const text = count === thresholds[0] ? GENTLE_REMINDER @@ -259,12 +257,7 @@ export function apply(ctx: Context, config: Config): void { // loop. Pure reset hook: always delegates (attaching nothing, vetoing // nothing). ctx.on('agent/prompt-submit', (agent, _content, _source, next): Promise => { - chains.delete(agent.id) + chains.delete(agent) return next() }) - - // Drop state when an agent goes away, bounding the map over harness lifetime. - ctx.on('agent/status', (agent, status) => { - if (status === 'disposed') chains.delete(agent.id) - }) } diff --git a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts index 565f1076b5..9538166fc4 100644 --- a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts +++ b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId } from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as RepeatToolGuard from '@deepseek-ai/dsh-repeat-tool-guard' import type { Config } from '@deepseek-ai/dsh-repeat-tool-guard' @@ -57,7 +58,7 @@ describe('threshold escalation', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -78,7 +79,7 @@ describe('threshold escalation', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -100,7 +101,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -124,7 +125,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -142,7 +143,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -163,7 +164,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -179,7 +180,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -195,7 +196,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -215,8 +216,8 @@ describe('chain semantics', () => { toolCallResponse('b3', 'probe', { q: 1 }), textResponse('done'), ])) - const agentA = ctx.agentLoop.create(AgentId('a'), { model: 'mock-a' }) - const agentB = ctx.agentLoop.create(AgentId('b'), { model: 'mock-b' }) + const agentA = ctx.agentLoop.create(SessionId('a'), { model: 'mock-a' }) + const agentB = ctx.agentLoop.create(SessionId('b'), { model: 'mock-b' }) agentA.send([{ type: 'text', text: 'go' }]) agentB.send([{ type: 'text', text: 'go' }]) await Promise.all([waitForIdle(ctx, agentA), waitForIdle(ctx, agentB)]) @@ -235,7 +236,7 @@ describe('chain semantics', () => { textResponse('turn two done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) agent.send([{ type: 'text', text: 'again' }]) @@ -256,14 +257,14 @@ describe('chain semantics', () => { // (the loop.spec pattern): a child plugin fiber owns `first`. let first!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - first = inner.agentLoop.create(AgentId('reused'), { model: 'mock' }) + first = inner.agentLoop.create(SessionId('reused'), { model: 'mock' }) }, { inject: ['agentLoop'] })) first.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, first) await fiber.dispose() await first.done - const second = ctx.agentLoop.create(AgentId('reused'), { model: 'mock' }) + const second = ctx.agentLoop.create(SessionId('reused'), { model: 'mock' }) second.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, second) @@ -279,7 +280,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -295,7 +296,7 @@ describe('chain semantics', () => { toolCallResponse('c1', 'probe', { q: 1 }), // if the direct call had counted, this would be #2 textResponse('done'), ])) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -317,7 +318,7 @@ describe('fold onto the downstream decision', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -348,7 +349,7 @@ describe('fold onto the downstream decision', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 2cbc995ce3..2f0a2666c9 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -5,10 +5,11 @@ import { join } from 'node:path' import { Context, type Fiber } from 'cordis' import Loader from '@cordisjs/plugin-loader' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' @@ -95,7 +96,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'do something' }]) await waitForIdle(ctx, agent) @@ -118,7 +119,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -143,7 +144,7 @@ describe('hooks-claude bridge — PreToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'danger', description: 'd', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'use danger' }]) await waitForIdle(ctx, agent) @@ -166,7 +167,7 @@ describe('hooks-claude bridge — PreToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'safe', description: 's', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ran ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'use safe' }]) await waitForIdle(ctx, agent) @@ -188,7 +189,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(dir, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'raw output' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -209,7 +210,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(dir, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -233,7 +234,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -257,7 +258,7 @@ describe('hooks-claude bridge — SessionStart', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // session-start fires async (detached .then → agent.inject); wait for the // injected context/message to actually land before sending, rather than a // fixed sleep that flakes under load. @@ -294,8 +295,8 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => // Drive the observe-only lifecycle events directly (no real child needed — the // bridge just listens). No child agent is registered, so SubagentStart's // child lookup yields undefined and it simply runs the hook. - ctx.emit('subagent/start', { provider: 'inproc', id: AgentId('child-1') }) - ctx.emit('subagent/end', { provider: 'inproc', id: AgentId('child-1'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] }) + ctx.emit('subagent/start', { provider: 'inproc', id: SessionId('child-1') }) + ctx.emit('subagent/end', { provider: 'inproc', id: SessionId('child-1'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] }) // Both hooks run async (detached .then); poll for their marker files rather // than a fixed sleep that flakes under load. @@ -330,7 +331,7 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => const { ctx, hooks } = await harnessWithFiber(dir, new MockAdapter([])) const warn = vi.fn() ctx.logger.warn = warn as never - ctx.emit('subagent/start', { provider: 'inproc', id: AgentId('child-1') }) + ctx.emit('subagent/start', { provider: 'inproc', id: SessionId('child-1') }) await waitFor(() => existsSync(marker)) const pid = Number(readFileSync(pidFile, 'utf8').trim()) await hooks.dispose() @@ -359,7 +360,7 @@ describe('hooks-claude bridge — load resilience', () => { await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksClaude, { configPath: '/nonexistent/hooks.json' }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The turn ran normally — no hooks, no crash. @@ -385,7 +386,7 @@ describe('hooks-claude bridge — load resilience', () => { const fiber = await ctx.plugin(HooksClaude, { configPath: join(dir, 'hooks.json') }) await fiber.dispose() ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index 7feb46df05..16c48aa149 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -4,10 +4,11 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' @@ -72,7 +73,7 @@ describe('hooks-claude coverage — config option arms + substitution + skip war const ctx = await harness(path, adapter, { pluginRoot: d, projectDir: d }) ctx.logger.warn = warn as never ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) // substituted command ran @@ -88,7 +89,7 @@ describe('hooks-claude coverage — config option arms + substitution + skip war ctx.logger.warn = warn as never let sawArgs: unknown ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: { command: { type: 'string' } }, async execute(args) { sawArgs = args; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // updatedInput is NOT honored — the tool ran with the ORIGINAL args. @@ -104,7 +105,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ran')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The prompt proceeded unchanged; no context/message injected. @@ -134,7 +135,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -159,7 +160,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter, { stderrSummaryMaxChars: 40 }) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -175,7 +176,7 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) @@ -192,7 +193,7 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // A second model request ran → the empty-reason block forced continuation. @@ -208,9 +209,9 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const ctx = await harness(path, new MockAdapter([])) // Register a fake child agent under the id the event carries. const injected: string[] = [] - const child = { id: AgentId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters[0] + const child = { id: SessionId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters[0] ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: AgentId('child-x') }) + ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-x') }) await waitFor(() => injected.includes('child guidance')) expect(injected).toContain('child guidance') }) @@ -224,9 +225,9 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { SubagentStart: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) const warn = vi.fn(); ctx.logger.warn = warn as never - const child = { id: AgentId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters[0] + const child = { id: SessionId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters[0] ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: AgentId('child-y') }) + ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-y') }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SubagentStart hook failed'))) expect(warn).toHaveBeenCalledWith(expect.stringContaining('SubagentStart hook failed')) }) @@ -240,7 +241,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -254,7 +255,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -270,7 +271,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) const path = hooks(d, { SubagentStop: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) - ctx.emit('subagent/end', { provider: 'p', id: AgentId('child-z'), stopReason: 'completed' }) + ctx.emit('subagent/end', { provider: 'p', id: SessionId('child-z'), stopReason: 'completed' }) await waitFor(() => existsSync(marker)) expect(existsSync(marker)).toBe(true) }) @@ -283,7 +284,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('no')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const turnEnd = events(agent).findLast(e => e.type === 'turn/end') @@ -298,7 +299,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // ask (no reason) → degrades to deny with the registry's generic message. @@ -313,7 +314,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -342,7 +343,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () // the protocol lib's reference default, not a config knob). HooksClaude.apply(ctx, { configPath: join(d, 'hooks.json') }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) @@ -357,7 +358,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) @@ -372,7 +373,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -393,7 +394,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -410,7 +411,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -430,7 +431,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) // the mismatched deny was discarded → the tool ran @@ -448,7 +449,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) // NB: no projectDir // The factory create() path honors meta.cwd (the plain agentLoop.create() does not). const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) expect(events(handle.agent as ReactLoopAgent).some(e => e.type === 'context/message' @@ -466,7 +467,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(path, adapter) // A later listener that blocks every prompt (registered AFTER the bridge). - const { AgentId: AId } = await import('@deepseek-ai/dsh-agent') + const { SessionId: AId } = await import('@deepseek-ai/dsh-session') ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) const agent = ctx.agentLoop.create(AId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) @@ -492,7 +493,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => content: [{ type: 'text' as const, text: 'rewritten-prompt' }], additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) @@ -514,7 +515,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -533,7 +534,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -557,7 +558,7 @@ describe('hooks-claude coverage — executor reject + no-open-turn', () => { const bash = ctx.bash bash.run = (() => Promise.reject(new Error('executor down'))) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -573,7 +574,7 @@ describe('hooks-claude coverage — detached-listener catch handlers', () => { const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Make inject throw, forcing the SessionStart .catch path. const original = agent.inject.bind(agent) let threw = false @@ -613,7 +614,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) @@ -649,7 +650,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server // Register a live child on its own session cwd; emit subagent/end with its id. const { SessionId } = await import('@deepseek-ai/dsh-session') - const childHandle = await ctx.agents.create({ agentId: AgentId('child-stop'), sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { model: 'mock' } }) + const childHandle = await ctx.agents.create({ sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { model: 'mock' } }) ctx.emit('subagent/end', { provider: 'inproc', id: childHandle.agent.id, stopReason: 'completed' }) await waitFor(() => existsSync(marker)) @@ -670,7 +671,7 @@ describe('hooks-claude coverage — systemMessage is warned, not surfaced', () = const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) @@ -691,7 +692,7 @@ describe('hooks-claude coverage — SessionStart timing is best-effort (no-wait) const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Send immediately — do NOT wait for the session-start inject. agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) diff --git a/packages/hooks/hooks-codex/tests/bridge.spec.ts b/packages/hooks/hooks-codex/tests/bridge.spec.ts index e0677306b0..4aa678c36e 100644 --- a/packages/hooks/hooks-codex/tests/bridge.spec.ts +++ b/packages/hooks/hooks-codex/tests/bridge.spec.ts @@ -5,10 +5,11 @@ import { join } from 'node:path' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' @@ -82,7 +83,7 @@ describe('hooks-codex bridge', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'no' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'run ls' }]) await waitForIdle(ctx, agent) @@ -107,7 +108,7 @@ describe('hooks-codex bridge', () => { // Step 1 has no tool calls → would stop; the Stop hook forces step 2. const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer after goal')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -124,7 +125,7 @@ describe('hooks-codex bridge', () => { const adapter = new MockAdapter([textResponse('fine')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // Ran normally; the unknown event was dropped at parse. @@ -135,7 +136,7 @@ describe('hooks-codex bridge', () => { const dir = configDir() // no hooks.json written const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) @@ -161,7 +162,7 @@ describe('hooks-codex bridge', () => { const fiber = await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'm' }) await fiber.dispose() ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone @@ -190,7 +191,7 @@ describe('hooks-codex bridge', () => { ctx.llm.registerAdapter(['mock'], new MockAdapter([])) const warn = vi.fn() ctx.logger.warn = warn as never - ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) // fires agent/session-start + ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // fires agent/session-start await waitFor(() => existsSync(marker)) const pid = Number(readFileSync(pidFile, 'utf8').trim()) await fiber.dispose() diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index 774b308fa1..75b04d4c57 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -4,10 +4,11 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' @@ -52,7 +53,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) const adapter = new MockAdapter([textResponse('no')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) const te = events(agent).findLast(e => e.type === 'turn/end') @@ -64,7 +65,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"ctx-x"}}\'\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('ctx-x') }) @@ -78,7 +79,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) expect(events(agent).some(e => e.type === 'user/message')).toBe(false) @@ -96,7 +97,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { content: [{ type: 'text' as const, text: 'rewritten-prompt' }], additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) expect(req).toContain('from-bridge') @@ -111,7 +112,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true) @@ -125,7 +126,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.isError).toBe(true) @@ -138,7 +139,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"start-ctx"}}\'\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('start-ctx')))) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) @@ -151,7 +152,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.isError).toBe(true) @@ -164,7 +165,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('post-ctx')))).toBe(true) }) @@ -176,7 +177,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // clean-exit hook allows; commandOf returned '' }) @@ -187,7 +188,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0) @@ -200,7 +201,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true) @@ -223,7 +224,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter, { stderrSummaryMaxChars: 40 }) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary).toBe('x'.repeat(40) + '…') @@ -246,7 +247,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { // Direct apply (schema bypass) → the `model ?? ''` fallback is exercised. HooksCodex.apply(ctx, { configPath: join(d, 'hooks.json') }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) expect(warn).toHaveBeenCalledWith(expect.stringContaining('async hook')) @@ -259,7 +260,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -273,7 +274,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\ntouch "${marker}"\nexit 0\n`) }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => existsSync(marker)) // the clean no-output hook has finished agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(events(agent).some(e => e.type === 'context/message')).toBe(false) @@ -285,7 +286,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.inject = (() => { throw new Error('inject boom') }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SessionStart hook failed'))) expect(warn).toHaveBeenCalledWith(expect.stringContaining('SessionStart hook failed')) @@ -298,7 +299,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -311,7 +312,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // matcher didn't match → no hook ran → tool proceeded expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) @@ -327,7 +328,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded @@ -340,7 +341,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true) @@ -352,7 +353,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.isError).toBe(true) @@ -369,7 +370,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 7 }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'number' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_input: { command: string } } expect(payload.tool_input.command).toBe('') @@ -405,7 +406,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.bash.run = (() => Promise.reject(new Error('executor down'))) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false) @@ -419,7 +420,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { Stop: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\nexit 2\n`) }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) // empty-reason block forced continuation expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('blocked by Stop hook') @@ -432,7 +433,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho "extra guidance from a plain hook"\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('extra guidance from a plain hook') }) @@ -448,7 +449,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', `#!/usr/bin/env bash\ntouch "${marker}"\necho "stale"\nexit 2\n`) }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => existsSync(marker)) // the exit-2 hook has finished expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('stale')))).toBe(false) @@ -462,7 +463,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'e.sh', '#!/usr/bin/env bash\necho "stale"\nexit 1\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // exit 1 is non-blocking → the turn ran expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('stale') @@ -473,7 +474,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'ss.sh', '#!/usr/bin/env bash\necho "session preamble"\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('session preamble')))) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) @@ -487,7 +488,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'j.sh', '#!/usr/bin/env bash\necho \'{"unrelated":"json"}\'\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('unrelated') }) @@ -502,7 +503,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'shell', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_name: string; tool_input: { command: string } } expect(payload.tool_name).toBe('shell') @@ -518,7 +519,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(false) // the matcher fired → the hook denied the tool expect(events(agent).some(e => e.type === 'hook/invoked' && e.data.point === 'PreToolUse')).toBe(true) @@ -530,7 +531,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('heads up') @@ -553,7 +554,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { ctx.llm.registerAdapter(['mock'], adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) expect(existsSync(marker)).toBe(true) diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 5222906a2d..1e82ef85b0 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -37,8 +37,8 @@ import { type SessionNotification, type StopReason, } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' import type { SubagentResult, SubagentRun, SubagentStartRequest, SubagentStopReason } from '@deepseek-ai/dsh-subagent' import { buildChildEnv, disposeChildProcess, spawnFailure } from '@deepseek-ai/dsh-subagent-subprocess' @@ -190,7 +190,7 @@ function toError(value: unknown): Error { * @returns the ready run handle for the child subprocess. */ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpec): Promise { - const id = AgentId(randomUUID()) + const id = SessionId(randomUUID()) if (request.signal.aborted) throw new Error('subagent request was aborted before the ACP child started') diff --git a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts index 8060a77fd4..d1b9065c60 100644 --- a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts +++ b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' @@ -37,7 +38,7 @@ async function setup(script: Script) { await ctx.plugin(Spawn, { providerName: 'spawn' }) await ctx.plugin(fork, { providerName: 'fork' }) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts index e089cebe5f..360098e369 100644 --- a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts +++ b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts @@ -2,10 +2,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' @@ -43,7 +44,7 @@ async function setup(script: Script) { await ctx.plugin(SubagentService) await ctx.plugin(fork, { providerName: 'fork' }) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-inprocess/src/index.ts b/packages/subagent/subagent-inprocess/src/index.ts index f6de7200cf..965d9c8e78 100644 --- a/packages/subagent/subagent-inprocess/src/index.ts +++ b/packages/subagent/subagent-inprocess/src/index.ts @@ -9,7 +9,7 @@ import { randomUUID } from 'node:crypto' import type { Context } from 'cordis' -import { AgentId, type Agent, type AgentOptions } from '@deepseek-ai/dsh-agent' +import type { Agent, AgentOptions } from '@deepseek-ai/dsh-agent' import { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import { assertSubagentMaxDepth } from '@deepseek-ai/dsh-subagent' @@ -104,7 +104,7 @@ export async function startInProcessRun( throw new SubagentDepthError(childDepth, request.maxDepth) } - const childId = AgentId(randomUUID()) + const childId = SessionId(randomUUID()) const seedLength = options.seed?.length ?? 0 const parentHeader = parent.session.header const parentModel = parent.options.model @@ -127,8 +127,7 @@ export async function startInProcessRun( const flags = { cancelled: false } const handle = await parent.ctx.agents.create({ - agentId: childId, - sessionId: SessionId(randomUUID()), + sessionId: childId, meta: { ...parentHeader.cwd !== undefined ? { cwd: parentHeader.cwd } : {}, parentSession: parentHeader.id, diff --git a/packages/subagent/subagent-inprocess/tests/structured.spec.ts b/packages/subagent/subagent-inprocess/tests/structured.spec.ts index 3e23123622..93da5b1d51 100644 --- a/packages/subagent/subagent-inprocess/tests/structured.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/structured.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, type ContentBlock, type GenerateOptions } from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import type { ContinuationDecision } from '@deepseek-ai/dsh-agent' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -68,7 +69,7 @@ async function setup(script: Script, options: SetupOptions = {}) { start: (request: SubagentStartRequest) => startInProcessRun(request, {}), }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent, adapter, disposeProvider } } @@ -333,7 +334,7 @@ describe('in-process structured output', () => { await expect(ctx.subagents.start('spawn', structuredRequest(parent, { outputSchema: { type: 'object', oneOf: [] } as unknown as StructuredOutputSchema, }))).rejects.toThrow(/unsupported output schema/) - expect(ctx.agents.get(AgentId('parent'))).toBeDefined() + expect(ctx.agents.get(SessionId('parent'))).toBeDefined() }) it('a schema carrying non-JSON values fails as OutputSchemaError at the validation boundary', async () => { diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index 0005246523..aa0f946c89 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -24,7 +25,7 @@ async function setup(script: Script) { await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-spawn/tests/spawn.e2e.ts b/packages/subagent/subagent-spawn/tests/spawn.e2e.ts index daa032199e..b156f951ed 100644 --- a/packages/subagent/subagent-spawn/tests/spawn.e2e.ts +++ b/packages/subagent/subagent-spawn/tests/spawn.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { spawnHarness, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * With-key smoke for the in-process spawn backend: a REAL parent agent delegates @@ -29,7 +29,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('spawn backend with-key smoke', ( it('a parent delegates to a child that writes a file on disk', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-subagent-spawn-e2e-')) ctx = await spawnHarness(workdir) - const parent = ctx.agentLoop.create(AgentId('e2e-parent'), { model: 'deepseek-v4-flash' }) + const parent = ctx.agentLoop.create(SessionId('e2e-parent'), { model: 'deepseek-v4-flash' }) parent.send([{ type: 'text', text: 'Use the subagent tool to delegate this exact task: "Use the bash tool to write the text ' diff --git a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts index 9e4e489882..06aa40ca9f 100644 --- a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts +++ b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts @@ -5,7 +5,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import { SessionId } from '@deepseek-ai/dsh-session' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -36,7 +37,7 @@ async function setup(script: Script) { await ctx.plugin(SubagentService) await ctx.plugin(spawn, { providerName: 'spawn' }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent, adapter } } @@ -237,7 +238,6 @@ describe('dsh-subagent-spawn', () => { const { ctx } = await setup([textResponse('x')]) // A parent WITH a cwd (config agents have none, so create one explicitly). const parentHandle = await ctx.agents.create({ - agentId: AgentId('cwd-parent'), sessionId: SessionId('cwd-parent-session'), meta: { cwd: '/tmp/parent-workspace' }, agentOptions: { model: 'mock' }, @@ -254,7 +254,6 @@ describe('dsh-subagent-spawn', () => { const { ctx } = await setup([textResponse('explicit model child')]) // A parent with NO model (its own turns would need one supplied per-request). const parentHandle = await ctx.agents.create({ - agentId: AgentId('modelless-parent'), sessionId: SessionId('modelless-parent-session'), agentOptions: {}, }) @@ -318,7 +317,7 @@ describe('dsh-subagent-spawn', () => { await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) const controller = new AbortController() const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'q' }], @@ -349,7 +348,7 @@ describe('dsh-subagent-spawn', () => { await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) const parentEffects = parent.ctx.fiber.getEffects().length const published: string[] = [] ctx.on('session/created', () => void published.push('session/created')) @@ -442,7 +441,6 @@ describe('dsh-subagent-spawn', () => { const { ctx } = await setup([]) // A handle-owned parent we can dispose (config agents dispose with the loop fiber). const parentHandle = await ctx.agents.create({ - agentId: AgentId('doomed-parent'), sessionId: SessionId('doomed-s'), agentOptions: { model: 'mock' }, }) @@ -465,7 +463,6 @@ describe('dsh-subagent-spawn', () => { it('parent disposal during the child setup transaction prevents every publication notification', async () => { const { ctx } = await setup([]) const parentHandle = await ctx.agents.create({ - agentId: AgentId('setup-race-parent'), sessionId: SessionId('setup-race-parent-session'), agentOptions: { model: 'mock' }, }) diff --git a/packages/subagent/subagent/src/index.ts b/packages/subagent/subagent/src/index.ts index 4635de9697..e885c16469 100644 --- a/packages/subagent/subagent/src/index.ts +++ b/packages/subagent/subagent/src/index.ts @@ -18,7 +18,8 @@ import type { Scoped } from '@deepseek-ai/dsh-scope' import { assertSupportedOutputSchema } from '@deepseek-ai/dsh-tools' import { HarnessError } from '@deepseek-ai/dsh-llm' import type { ContentBlock } from '@deepseek-ai/dsh-llm' -import type { Agent, AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' +import type { SessionId } from '@deepseek-ai/dsh-session' import type { SubagentCapabilities, SubagentProvider, @@ -96,7 +97,7 @@ export interface SubagentRunInfo { /** The provider that established the run. */ readonly provider: string /** The child agent's id. */ - readonly id: AgentId + readonly id: SessionId } /** Observe-only outcome detail for a settled subagent run. */ @@ -104,7 +105,7 @@ export interface SubagentRunEndInfo { /** The provider that ran it. */ readonly provider: string /** The child agent's id. */ - readonly id: AgentId + readonly id: SessionId /** The terminal stop reason. */ readonly stopReason: SubagentResult['stopReason'] /** The child's final assistant output, absent on infrastructure rejection. */ diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 3bdc78569a..8d360b1182 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -6,8 +6,9 @@ * @module @deepseek-ai/dsh-subagent/types */ -import type { Agent, AgentId, AgentOptions } from '@deepseek-ai/dsh-agent' +import type { Agent, AgentOptions } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import type { SessionId } from '@deepseek-ai/dsh-session' import type { StructuredOutputSchema, ToolRestriction } from '@deepseek-ai/dsh-tools' /** @@ -147,7 +148,7 @@ export interface SubagentResult { */ export interface SubagentRun { /** The child agent's id (local in-process runs are already published in `ctx.agents`; remote transports need not publish locally). */ - readonly id: AgentId + readonly id: SessionId /** * Resolves with the child's terminal {@link SubagentResult} when the run * settles. Does NOT reject on a child-level failure — a model/transport diff --git a/packages/subagent/subagent/tests/service.spec.ts b/packages/subagent/subagent/tests/service.spec.ts index 3d10b425ed..ad7dbaafff 100644 --- a/packages/subagent/subagent/tests/service.spec.ts +++ b/packages/subagent/subagent/tests/service.spec.ts @@ -1,6 +1,7 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import { HarnessError } from '@deepseek-ai/dsh-llm' import { carrierKeyOf } from '@deepseek-ai/dsh-scope' import SubagentService, { @@ -12,9 +13,10 @@ import SubagentService, { type SubagentRun, type SubagentStartRequest, } from '@deepseek-ai/dsh-subagent' +import { SessionId } from '@deepseek-ai/dsh-session' function fakeParent(id = 'parent-1'): Agent { - return { id: AgentId(id) } as unknown as Agent + return { id: SessionId(id) } as unknown as Agent } const ALL_CAPS: SubagentCapabilities = { outputSchema: true, depthLimit: true, toolFilter: true, persona: true } @@ -45,7 +47,7 @@ class StubProvider implements SubagentProvider { async start(request: SubagentStartRequest): Promise { this.startCount += 1 return { - id: AgentId(`child:${this.name}:${request.parent.id}`), + id: SessionId(`child:${this.name}:${request.parent.id}`), result: Promise.resolve(this.outcome), async dispose() {}, } @@ -141,7 +143,7 @@ describe('SubagentService', () => { const starting = subagents.start('deferred', baseRequest({ parent })) await Promise.resolve() expect(events).toEqual([]) - ready.resolve({ id: AgentId('child'), result: result.promise, async dispose() {} }) + ready.resolve({ id: SessionId('child'), result: result.promise, async dispose() {} }) const run = await starting expect(events).toEqual(['start']) result.resolve({ output: [{ type: 'text', text: 'answer' }], stopReason: 'completed' }) @@ -190,7 +192,7 @@ describe('SubagentService', () => { capabilities: NO_CAPS, inheritsParentContext: false, async start() { - return { id: AgentId('infra-child'), result: failure.promise, async dispose() {} } + return { id: SessionId('infra-child'), result: failure.promise, async dispose() {} } }, }) const failedRun = await subagents.start('infra', baseRequest()) diff --git a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts index 5830513cf4..79df080657 100644 --- a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts +++ b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts @@ -4,10 +4,12 @@ import Loader from '@cordisjs/plugin-loader' import { CallId } from '@deepseek-ai/dsh-llm' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import SubagentService from '@deepseek-ai/dsh-subagent' import * as mock from '@deepseek-ai/dsh-subagent-mock' import * as tool from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * Drives the REAL plugin body: mounts `dsh-tool-subagent` on a real @@ -20,7 +22,7 @@ import * as tool from '../src/index.ts' /** A minimal parent Agent — the tool reads `agent.id` for `parent`. */ function fakeAgent(id = 'parent-1'): Agent { - return { id: AgentId(id) } as unknown as Agent + return { id: SessionId(id) } as unknown as Agent } async function setup(toolConfig: tool.Config, mockConfig: Partial = {}) { @@ -114,7 +116,7 @@ describe('dsh-tool-subagent', () => { capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('weird-child'), + id: SessionId('weird-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'partial' }], stopReason: 'frobnicated' as never }), dispose: async () => {}, }), @@ -141,7 +143,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture-child'), + id: SessionId('capture-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -170,7 +172,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('bare-child'), + id: SessionId('bare-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -297,7 +299,7 @@ describe('dsh-tool-subagent', () => { capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('spy-child'), + id: SessionId('spy-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => void disposed(), }), @@ -319,7 +321,7 @@ describe('dsh-tool-subagent', () => { capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('spy-child'), + id: SessionId('spy-child'), result: Promise.resolve({ output: [], stopReason: 'error' as const }), dispose: async () => void disposed(), }), @@ -350,7 +352,7 @@ describe('dsh-tool-subagent', () => { resolveResult({ output: [], stopReason: 'aborted' }) }, { once: true }) return { - id: AgentId('spy-child'), + id: SessionId('spy-child'), result, dispose: async () => {}, } @@ -442,7 +444,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture2-child'), + id: SessionId('capture2-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -499,7 +501,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture3-child'), + id: SessionId('capture3-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -528,7 +530,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture4-child'), + id: SessionId('capture4-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } diff --git a/packages/support/subagent-mock/src/index.ts b/packages/support/subagent-mock/src/index.ts index abc1a6c5e9..bf7bcbe2fb 100644 --- a/packages/support/subagent-mock/src/index.ts +++ b/packages/support/subagent-mock/src/index.ts @@ -13,8 +13,8 @@ import type { Context } from 'cordis' import z from 'schemastery' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' import type { SubagentCapabilities, SubagentProvider, @@ -65,7 +65,7 @@ class MockSubagentProvider implements SubagentProvider { // A deterministic child id derived from the parent — no clock/random (both // banned in deterministic paths here, and unnecessary for a scripted run). - const id = AgentId(`mock-subagent:${this.name}:${request.parent.id}`) + const id = SessionId(`mock-subagent:${this.name}:${request.parent.id}`) const resultFor = (): SubagentResult => ({ output, diff --git a/packages/support/subagent-mock/tests/subagent-mock.spec.ts b/packages/support/subagent-mock/tests/subagent-mock.spec.ts index 7fd93c62bc..b5e7180782 100644 --- a/packages/support/subagent-mock/tests/subagent-mock.spec.ts +++ b/packages/support/subagent-mock/tests/subagent-mock.spec.ts @@ -1,13 +1,15 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import * as mock from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** A minimal parent — the mock provider only reads `parent.id`. */ function fakeParent(id = 'parent-1'): Agent { - return { id: AgentId(id) } as unknown as Agent + return { id: SessionId(id) } as unknown as Agent } function baseRequest(over: Partial = {}): SubagentStartRequest { diff --git a/packages/todo/tool-todo/tests/integration.spec.ts b/packages/todo/tool-todo/tests/integration.spec.ts index 739367a699..8376a70425 100644 --- a/packages/todo/tool-todo/tests/integration.spec.ts +++ b/packages/todo/tool-todo/tests/integration.spec.ts @@ -1,11 +1,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -64,7 +65,7 @@ describe('todo_write tool through the agent loop', () => { textResponse('Plan recorded.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-todo'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-todo'), { model: 'mock' }) agent.send([{ type: 'text', text: 'plan a two-step task' }]) await waitForIdle(ctx, agent) @@ -92,7 +93,7 @@ describe('todo_write tool through the agent loop', () => { textResponse('Done planning.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-todo-2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-todo-2'), { model: 'mock' }) agent.send([{ type: 'text', text: 'plan then update' }]) await waitForIdle(ctx, agent) diff --git a/packages/todo/tool-todo/tests/tool-todo.spec.ts b/packages/todo/tool-todo/tests/tool-todo.spec.ts index 86e8814633..b426b6760c 100644 --- a/packages/todo/tool-todo/tests/tool-todo.spec.ts +++ b/packages/todo/tool-todo/tests/tool-todo.spec.ts @@ -6,7 +6,8 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import { Session, SessionId } from '@deepseek-ai/dsh-session' import type { TodoItem } from '@deepseek-ai/dsh-session' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import * as tool from '../src/index.ts' /** @@ -20,7 +21,7 @@ import * as tool from '../src/index.ts' /** A parent Agent backed by a real Session — the tool reads `agent.session`. */ function agentWithSession(id = 'parent-1'): Agent & { session: Session } { const session = new Session(SessionId(id)) - return { id: AgentId(id), session } as unknown as Agent & { session: Session } + return { id: SessionId(id), session } as unknown as Agent & { session: Session } } async function setup(): Promise { diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index a3fdc38f97..e795c7e177 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -72,7 +72,6 @@ import { import type { ContentBlock } from '@deepseek-ai/dsh-llm' import { assertNever, CallId } from '@deepseek-ai/dsh-llm' import type { Agent } from '@deepseek-ai/dsh-agent' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from '@deepseek-ai/dsh-bash' import { APPROVAL_POLICIES, effectiveApprovalPolicy, setApprovalPolicy } from '@deepseek-ai/dsh-user-approval' @@ -686,7 +685,6 @@ export function apply(ctx: Context, config: AcpConfig): void { validateMcpServers(params) const sessionId = SessionId(randomUUID()) const handle = await agents.create({ - agentId: AgentId(sessionId), sessionId, meta: { cwd: params.cwd }, agentOptions: agentOptions(config), @@ -757,7 +755,6 @@ export function apply(ctx: Context, config: AcpConfig): void { } } const handle = await agents.resume({ - agentId: AgentId(sessionId), resumeSessionId: sessionId, agentOptions: agentOptions(config), }) diff --git a/packages/ui/acp/tests/approval.spec.ts b/packages/ui/acp/tests/approval.spec.ts index ed035aaf80..36846ac728 100644 --- a/packages/ui/acp/tests/approval.spec.ts +++ b/packages/ui/acp/tests/approval.spec.ts @@ -4,9 +4,11 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { CallId } from '@deepseek-ai/dsh-llm' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import ApprovalService, { type ApprovalRequest } from '@deepseek-ai/dsh-user-approval' import { makeBridgeHarness, type BridgeHarness } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The bridge's `approval/request` answerer: an ask for an agent the bridge @@ -31,7 +33,7 @@ describe('acp bridge — approval answerer', () => { ): Promise<{ agent: Agent; request: ApprovalRequest }> { await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = h.ctx.agents.get(AgentId(sessionId)) + const agent = h.ctx.agents.get(SessionId(sessionId)) if (agent === undefined) throw new Error('newSession created no agent') // In production an ask always fires mid-turn (tool execution); open one so // request()'s turn-enclosure precondition holds for the direct drive below. diff --git a/packages/ui/acp/tests/bridge.spec.ts b/packages/ui/acp/tests/bridge.spec.ts index be05a09644..7e780348ba 100644 --- a/packages/ui/acp/tests/bridge.spec.ts +++ b/packages/ui/acp/tests/bridge.spec.ts @@ -3,8 +3,8 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse, toolCallResponse, type BridgeHarness } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * End-to-end bridge specs over an in-memory transport: a real @@ -98,7 +98,7 @@ describe('acp bridge', () => { required: [], }, }) - const toolResult = harness.ctx.agents.get(AgentId(sessionId))!.session.events.find(event => event.type === 'tool/result') + const toolResult = harness.ctx.agents.get(SessionId(sessionId))!.session.events.find(event => event.type === 'tool/result') const toolResultBlock = toolResult?.type === 'tool/result' ? toolResult.data.content[0] : undefined const toolResultText = toolResultBlock?.type === 'text' ? toolResultBlock.text : undefined expect(toolResultText).toBe('{"answers":[{"id":"language","selected":["Python"]}]}') @@ -127,7 +127,7 @@ describe('acp bridge', () => { required: ['custom'], }, }) - const toolResult = harness.ctx.agents.get(AgentId(sessionId))!.session.events.find(event => event.type === 'tool/result') + const toolResult = harness.ctx.agents.get(SessionId(sessionId))!.session.events.find(event => event.type === 'tool/result') expect(JSON.stringify(toolResult)).toContain('apollo') }) @@ -136,7 +136,7 @@ describe('acp bridge', () => { harness.onElicitation = () => ({ action: 'accept', content: { custom: 'Use Zig' } }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! const result = await harness.ctx.userInteraction.ask({ agent, @@ -167,7 +167,7 @@ describe('acp bridge', () => { harness.onElicitation = () => ({ action: 'accept', content: { choice: 'TypeScript', custom: 'Use Zig' } }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await expect(harness.ctx.userInteraction.ask({ agent, @@ -184,7 +184,7 @@ describe('acp bridge', () => { harness.onElicitation = () => ({ action: 'accept', content: { choice: ['Tests', 'Docs'] } }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await expect(harness.ctx.userInteraction.ask({ agent, @@ -201,7 +201,7 @@ describe('acp bridge', () => { harness = await makeBridgeHarness({ storageDir, withAskUser: true }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await expect(harness.ctx.userInteraction.ask({ questions: [{ id: 'x', question: 'No agent?' }] })) .rejects.toMatchObject({ name: 'UserInteractionError', code: 'NO_AGENT' }) @@ -225,7 +225,7 @@ describe('acp bridge', () => { harness = await makeBridgeHarness({ storageDir, withAskUser: true }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! const alreadyAborted = new AbortController() alreadyAborted.abort() @@ -265,8 +265,8 @@ describe('acp bridge', () => { expect(b.sessionId).toBeTruthy() expect(a.sessionId).not.toBe(b.sessionId) // Both agents are live and independently registered. - expect(harness.ctx.agents.get(AgentId(a.sessionId))).toBeDefined() - expect(harness.ctx.agents.get(AgentId(b.sessionId))).toBeDefined() + expect(harness.ctx.agents.get(SessionId(a.sessionId))).toBeDefined() + expect(harness.ctx.agents.get(SessionId(b.sessionId))).toBeDefined() }) it('rejects a non-absolute cwd but accepts any absolute cwd (per-session workspace)', async () => { @@ -281,7 +281,7 @@ describe('acp bridge', () => { const res = await harness.client.newSession({ cwd: '/tmp', mcpServers: [] }) expect(res.sessionId).toBeTruthy() // The session header records that cwd, so its bash tools run there. - expect(harness.ctx.agents.get(AgentId(res.sessionId))!.session.header.cwd).toBe('/tmp') + expect(harness.ctx.agents.get(SessionId(res.sessionId))!.session.header.cwd).toBe('/tmp') }) it('rejects non-empty additionalDirectories', async () => { @@ -321,7 +321,7 @@ describe('acp bridge', () => { ], }) expect(result.stopReason).toBe('end_turn') - const user = harness.ctx.agents.get(AgentId(sessionId))!.session.events.find(event => event.type === 'user/message') + const user = harness.ctx.agents.get(SessionId(sessionId))!.session.events.find(event => event.type === 'user/message') expect(JSON.stringify(user)).toContain('resource_link') }) diff --git a/packages/ui/acp/tests/dispose.spec.ts b/packages/ui/acp/tests/dispose.spec.ts index f02a7b0649..b5d98c0881 100644 --- a/packages/ui/acp/tests/dispose.spec.ts +++ b/packages/ui/acp/tests/dispose.spec.ts @@ -4,7 +4,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { SessionId } from '@deepseek-ai/dsh-session' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse } from './harness.ts' describe('acp bridge — disposal & HMR safety', () => { @@ -17,7 +16,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! // Start a prompt that hangs in the model stream. const promptDone = harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) @@ -62,10 +61,10 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: [] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeDefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeDefined() await harness.acpFiber.dispose() // tear down ONLY the bridge - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() await harness.dispose() }) @@ -92,7 +91,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! // Start a prompt that hangs in the model stream. The prompt RPC will never // return (its transport is severed), so do not await it. void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {}) @@ -115,7 +114,7 @@ describe('acp bridge — disposal & HMR safety', () => { // and its session removed from the store, not merely idled (the old // behavior). The services live on the root ctx, so they survive this. await harness.acpFiber.dispose() - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId(sessionId))).toBeUndefined() await harness.dispose() }) @@ -128,7 +127,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {}) await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') @@ -145,7 +144,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: [] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const session = harness.ctx.agents.get(AgentId(sessionId))!.session + const session = harness.ctx.agents.get(SessionId(sessionId))!.session await harness.ctx.fiber.dispose() const before = harness.updates.length @@ -169,12 +168,12 @@ describe('acp bridge — disposal & HMR safety', () => { await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) - const liveEvents = harness.ctx.agents.get(AgentId(sessionId))!.session.events.length + const liveEvents = harness.ctx.agents.get(SessionId(sessionId))!.session.events.length expect(liveEvents).toBeGreaterThan(0) // Tear down JUST the bridge (the AgentHandle dispose runs to quiescence). await harness.acpFiber.dispose() - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() // Re-load the session from disk: every live event (incl. the closing // turn/end) was flushed before the session was detached. @@ -201,7 +200,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {}) await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') @@ -211,7 +210,7 @@ describe('acp bridge — disposal & HMR safety', () => { // Dispose JUST the bridge: a fiber unload that must STILL honor the ordered // teardown (the composite effect runs its disposer chain as a unit). await harness.acpFiber.dispose() - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() // The loop's own `turn/end {disposed}` is on disk (re-load: the world, not // self-report) — NOT a crash-recovery `interrupted` substitute. @@ -230,21 +229,21 @@ describe('acp bridge — disposal & HMR safety', () => { // queryable, with its session still in the store. const harness = await makeBridgeHarness({ storageDir, script: [] }) const handleA = await harness.ctx.agents.create({ - agentId: AgentId('sib-a'), sessionId: SessionId('sib-a'), agentOptions: { model: 'mock' }, + sessionId: SessionId('sib-a'), agentOptions: { model: 'mock' }, }) const handleB = await harness.ctx.agents.create({ - agentId: AgentId('sib-b'), sessionId: SessionId('sib-b'), agentOptions: { model: 'mock' }, + sessionId: SessionId('sib-b'), agentOptions: { model: 'mock' }, }) - expect(harness.ctx.agents.get(AgentId('sib-a'))).toBe(handleA.agent) - expect(harness.ctx.agents.get(AgentId('sib-b'))).toBe(handleB.agent) + expect(harness.ctx.agents.get(SessionId('sib-a'))).toBe(handleA.agent) + expect(harness.ctx.agents.get(SessionId('sib-b'))).toBe(handleB.agent) await handleA.dispose() // A is gone — unregistered AND its session removed from the store. - expect(harness.ctx.agents.get(AgentId('sib-a'))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId('sib-a'))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId('sib-a'))).toBeUndefined() expect(handleA.agent.status).toBe('disposed') // B is wholly unaffected. - expect(harness.ctx.agents.get(AgentId('sib-b'))).toBe(handleB.agent) + expect(harness.ctx.agents.get(SessionId('sib-b'))).toBe(handleB.agent) expect(harness.ctx.sessions.get(SessionId('sib-b'))).toBeDefined() expect(handleB.agent.status).not.toBe('disposed') await harness.dispose() @@ -262,7 +261,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: [textResponse('ok')] }) harness.ctx.on('agent/disposed', () => { throw new Error('boom disposed listener') }) const handle = await harness.ctx.agents.create({ - agentId: AgentId('guard-a'), sessionId: SessionId('guard-a'), agentOptions: { model: 'mock' }, + sessionId: SessionId('guard-a'), agentOptions: { model: 'mock' }, }) handle.agent.send([{ type: 'text', text: 'go' }]) await handle.agent.whenIdle() @@ -270,7 +269,7 @@ describe('acp bridge — disposal & HMR safety', () => { // Dispose: the throwing listener must NOT break the chain before detach. await handle.dispose() - expect(harness.ctx.agents.get(AgentId('guard-a'))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId('guard-a'))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId('guard-a'))).toBeUndefined() // detach still ran await harness.dispose() }) @@ -283,7 +282,7 @@ describe('acp bridge — disposal & HMR safety', () => { // observe the same quiescence boundary. const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) const handle = await harness.ctx.agents.create({ - agentId: AgentId('conc-a'), sessionId: SessionId('conc-a'), agentOptions: { model: 'mock' }, + sessionId: SessionId('conc-a'), agentOptions: { model: 'mock' }, }) // Drive a turn that hangs in the model stream, so the loop is mid-turn when // disposed — its exit runs a final session/flush we can gate to hold the @@ -313,7 +312,7 @@ describe('acp bridge — disposal & HMR safety', () => { // Release the flush; both resolve together and the session is gone. releaseFlush() await Promise.all([first, second]) - expect(harness.ctx.agents.get(AgentId('conc-a'))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId('conc-a'))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId('conc-a'))).toBeUndefined() await harness.dispose() }) diff --git a/packages/ui/acp/tests/edges.spec.ts b/packages/ui/acp/tests/edges.spec.ts index e86fb9fc94..329016a69e 100644 --- a/packages/ui/acp/tests/edges.spec.ts +++ b/packages/ui/acp/tests/edges.spec.ts @@ -3,7 +3,6 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { makeBridgeHarness, textResponse, type BridgeHarness } from './harness.ts' @@ -27,7 +26,7 @@ describe('acp bridge — demux & config edges', () => { await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) const before = harness.updates.length - const { agent: foreign } = await harness.ctx.agents.create({ agentId: AgentId('foreign'), sessionId: SessionId('foreign-session'), agentOptions: { model: 'mock' } }) + const { agent: foreign } = await harness.ctx.agents.create({ sessionId: SessionId('foreign-session'), agentOptions: { model: 'mock' } }) foreign.send([{ type: 'text', text: 'hi' }]) await foreign.whenIdle() await new Promise(r => setTimeout(r, 10)) diff --git a/packages/ui/acp/tests/load.spec.ts b/packages/ui/acp/tests/load.spec.ts index 2fbc95b3d9..efc9399c75 100644 --- a/packages/ui/acp/tests/load.spec.ts +++ b/packages/ui/acp/tests/load.spec.ts @@ -4,7 +4,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { SESSION_FORMAT_VERSION, SessionId } from '@deepseek-ai/dsh-session' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse, toolCallResponse, type BridgeHarness, type CapturedUpdate } from './harness.ts' /** Concatenate the text of all agent_message_chunk updates. */ @@ -194,7 +193,7 @@ describe('acp bridge — session/load replay', () => { release() // resume() finishes AFTER teardown expect(await loadResult).toBe('rejected') // No live agent was installed for the closed connection. - expect(loader.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(loader.ctx.agents.get(SessionId(sessionId))).toBeUndefined() }) it('rejects load when the requested cwd does not match the persisted session cwd', async () => { @@ -215,11 +214,11 @@ describe('acp bridge — session/load replay', () => { await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) await expect(loader.client.loadSession({ sessionId: 'elsewhere', cwd: process.cwd(), mcpServers: [] })) .rejects.toThrow(/cwd mismatch/) - expect(loader.ctx.agents.get(AgentId('elsewhere'))).toBeUndefined() + expect(loader.ctx.agents.get(SessionId('elsewhere'))).toBeUndefined() const res = await loader.client.loadSession({ sessionId: 'elsewhere', cwd: `${otherCwd}/.`, mcpServers: [] }) expect(res).toBeDefined() - expect(loader.ctx.agents.get(AgentId('elsewhere'))!.session.header.cwd).toBe(otherCwd) + expect(loader.ctx.agents.get(SessionId('elsewhere'))!.session.header.cwd).toBe(otherCwd) }) it('rejects load for a non-absolute cwd (still required to be absolute)', async () => { @@ -254,7 +253,7 @@ describe('acp bridge — session/load replay', () => { // Rejected BEFORE resume (metadata-only check) — no agent was registered, so // the id is not wedged: a later attempt hits the same clean rejection, not a // duplicate-registration error. - expect(loader.ctx.agents.get(AgentId('legacy'))).toBeUndefined() + expect(loader.ctx.agents.get(SessionId('legacy'))).toBeUndefined() await expect(loader.client.loadSession({ sessionId: 'legacy', cwd: process.cwd(), mcpServers: [] })) .rejects.toThrow(/no absolute persisted cwd/) }) diff --git a/packages/ui/acp/tests/multi-session.spec.ts b/packages/ui/acp/tests/multi-session.spec.ts index ca11934046..0881fe4199 100644 --- a/packages/ui/acp/tests/multi-session.spec.ts +++ b/packages/ui/acp/tests/multi-session.spec.ts @@ -3,8 +3,8 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse, type BridgeHarness, type CapturedUpdate } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** Text of the agent_message_chunk updates scoped to one session id. */ function messageTextFor(updates: { sessionId?: string; update: CapturedUpdate }[], sessionId: string): string { @@ -102,8 +102,8 @@ describe('acp bridge — RFC 011 multi-session isolation', () => { await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const a = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId const b = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId - const agentA = harness.ctx.agents.get(AgentId(a))! - const agentB = harness.ctx.agents.get(AgentId(b))! + const agentA = harness.ctx.agents.get(SessionId(a))! + const agentB = harness.ctx.agents.get(SessionId(b))! // Wait deterministically for BOTH agents to enter `running` (not a fixed // sleep — agent startup latency is unbounded on a loaded worker). diff --git a/packages/ui/acp/tests/turns.spec.ts b/packages/ui/acp/tests/turns.spec.ts index f559ca36d9..000b80336d 100644 --- a/packages/ui/acp/tests/turns.spec.ts +++ b/packages/ui/acp/tests/turns.spec.ts @@ -3,7 +3,6 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { defineTool } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { errorResponse, @@ -13,6 +12,7 @@ import { toolCallResponse, type BridgeHarness, } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** Boilerplate: initialize + create one session, returning its id. */ async function newSession(h: BridgeHarness, clientCapabilities: Record = {}): Promise { @@ -279,7 +279,7 @@ describe('acp bridge — turn outcomes', () => { // OWN turn with the real model answer. harness = await makeBridgeHarness({ storageDir, script: [textResponse('real answer')] }) const sessionId = await newSession(harness) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! // On the queued prompt, synchronously inject a one-shot context turn (idle // inject writes turn/start{injection} → context/message → turn/end). Fire // once so it lands between install and the prompt turn. @@ -335,7 +335,7 @@ describe('acp bridge — turn outcomes', () => { await harness.client.cancel({ sessionId }) const res = await promptDone expect(res.stopReason).toBe('cancelled') - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await agent.whenIdle() // At most ONE turn ran (the cancelled one) — the cancel cleared the queue, so // no second turn was batched or leaked. (A best-effort abort that left queued diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 86af6645f3..4dbfeb0fa2 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -16,7 +16,6 @@ import type { Context } from 'cordis' import { resolve } from 'node:path' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { AgentHandle } from '@deepseek-ai/dsh-agent' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -255,7 +254,6 @@ export class HarnessSdkServer { private async createSession(sessionId: string): Promise { const handle = await this.ctx.agents.create({ - agentId: AgentId(sessionId), sessionId: SessionId(sessionId), meta: { cwd: this.cwd }, agentOptions: { model: this.model }, diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 1cde550f2e..9260a59aae 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -5,7 +5,8 @@ import { join } from 'node:path' import { tmpdir } from 'node:os' import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId, type Agent, type AgentHandle } from '@deepseek-ai/dsh-agent' +import { type Agent, type AgentHandle } from '@deepseek-ai/dsh-agent' + import { SessionId } from '@deepseek-ai/dsh-session' import * as agentCore from '@deepseek-ai/dsh-agent-core' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' @@ -135,7 +136,6 @@ describe('HarnessSdkServer', () => { expect(llmServer.requests).toHaveLength(2) const orphanHandle = await ctx.agents.create({ - agentId: AgentId('orphan-agent'), sessionId: SessionId('orphan-session'), meta: { cwd: storageDir }, agentOptions: { model: 'dsagent-model' }, @@ -170,8 +170,8 @@ describe('HarnessSdkServer', () => { } as unknown as Agent const mainHandle = { agent: mainAgent, dispose: vi.fn(() => Promise.resolve()) } const otherHandle = { agent: otherAgent, dispose: vi.fn(() => Promise.resolve()) } - const create = vi.fn(async (options: { agentId: AgentId }) => - String(options.agentId) === 'main' ? mainHandle : otherHandle) + const create = vi.fn(async (options: { sessionId: SessionId }) => + String(options.sessionId) === 'main' ? mainHandle : otherHandle) const ctx = { on: vi.fn(() => () => undefined), agents: { create, get: () => undefined }, @@ -263,20 +263,18 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, transport) const parentHandle = await ctx.agents.create({ - agentId: AgentId('parent-agent'), sessionId: SessionId('main'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) const handle = await ctx.agents.create({ - agentId: AgentId('child-agent'), sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', - id: AgentId('child-agent'), + id: SessionId('child-session'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], }) @@ -285,7 +283,7 @@ describe('HarnessSdkServer', () => { method: 'subagent.finished', params: { provider: 'spawn', - agentId: 'child-agent', + agentId: 'child-session', parentSessionId: 'main', childSessionId: 'child-session', status: 'ok', @@ -311,19 +309,16 @@ describe('HarnessSdkServer', () => { let failedHandle: AgentHandle | undefined try { parentHandle = await ctx.agents.create({ - agentId: AgentId('fallback-parent-agent'), sessionId: SessionId('fallback-parent'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) handle = await ctx.agents.create({ - agentId: AgentId('fallback-child-agent'), sessionId: SessionId('fallback-child-session'), meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') }, agentOptions: { model: 'deepseek' }, }) failedHandle = await ctx.agents.create({ - agentId: AgentId('failed-child-agent'), sessionId: SessionId('failed-child-session'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, @@ -333,18 +328,18 @@ describe('HarnessSdkServer', () => { await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', - id: AgentId('fallback-child-agent'), + id: SessionId('fallback-child-session'), stopReason: 'max-tokens', lastAssistantMessage: [], }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', - id: AgentId('failed-child-agent'), + id: SessionId('failed-child-session'), stopReason: 'error', }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', - id: AgentId('missing-child-agent'), + id: SessionId('missing-child-agent'), stopReason: 'error', }) @@ -352,7 +347,7 @@ describe('HarnessSdkServer', () => { method: 'subagent.finished', params: { provider: 'fork', - agentId: 'fallback-child-agent', + agentId: 'fallback-child-session', parentSessionId: 'fallback-parent', childSessionId: 'fallback-child-session', status: 'error', @@ -364,7 +359,7 @@ describe('HarnessSdkServer', () => { method: 'subagent.finished', params: { provider: 'fork', - agentId: 'failed-child-agent', + agentId: 'failed-child-session', childSessionId: 'failed-child-session', status: 'error', stopReason: 'error', diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 27f0d20be7..82da64cd81 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -11,11 +11,11 @@ A terminal chat always wants the same cluster, so the package owns it rather tha | Plugin | Why it is here | |---|---| | `@cordisjs/plugin-logger-console` | the console logger — stdout is just the terminal here, so logging to it is correct (the ACP app must NOT have this) | -| `@deepseek-ai/dsh-agent-core` | the spine, pre-creating a `main` agent from this app's `model` with `process.cwd()` as the fresh session cwd and carrying its `persona` | +| `@deepseek-ai/dsh-agent-core` | the spine, pre-creating one agent under the `main` config label from this app's `model`, with `process.cwd()` as the fresh session cwd and carrying its `persona` | | `@deepseek-ai/dsh-session-persistence-jsonl` | durable JSONL session log under `persistenceRoot` | | `@deepseek-ai/dsh-user-interaction` | the human question/answer seam used by confirmation tools | | `@deepseek-ai/dsh-tool-ask-user` | the model-facing `ask_user_question` tool | -| `stdio-chat` (in-package module) | the readline UI, bound to the `main` agent | +| `stdio-chat` (in-package module) | the readline UI, holding the app-owned agent object directly and rendering it as `main` | `@cordisjs/plugin-hmr` (the dev/demo edit-reload loop) is deliberately a **leaf** entry, NOT baked in here: it is a Loader-only, subprocess-only dev plugin — its constructor throws without `node --expose-internals` + a live `loader`, and the in-process test tier cannot even import it (so a package whose `apply` statically pulled it in could never carry the per-file coverage gate). Unlike the console logger, a stray `hmr` is not a stdout-purity footgun, so leaving it at the leaf costs no safety. The `demo:echo` / `demo:repl` leaves load it and pass `--expose-internals`. @@ -25,14 +25,14 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | Key | Default | Routed to | |---|---|---| -| `model` | (required) | the pre-created `main` agent's model | +| `model` | (required) | the pre-created agent's model | | `persona` | — | the deployment persona template (may reference `{{model}}`), routed to `dsh-system-prompt` | | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd`, so project-scoped features such as skill discovery and default bash workdir follow the directory where `dsh-stdio-agent` was started. Resumed sessions keep the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id. Resumed sessions register under the exact `resumeSessionId` and keep the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 127851eaf5..f01c48a615 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -3,11 +3,11 @@ * @deepseek-ai/dsh-agent-core}) plus the coupled front-door cluster a terminal * chat needs — a console logger, the readline UI (the in-package `stdio-chat` * module), JSONL session - * persistence, and a pre-created `main` agent the UI drives. + * persistence, and one pre-created agent the UI drives under its `main` label. * * The cluster is BAKED IN, not left to the leaf: a stdio app always logs to the - * console (stdout is just the terminal) and always pre-creates the `main` agent - * the readline UI sends to. The leaf supplies the swappable backends (the LLM + * console (stdout is just the terminal) and always pre-creates one agent the + * readline UI labels `main`. The leaf supplies the swappable backends (the LLM * adapter, the bash executor), optional product tools, the optional `hmr` * dev-reload plugin, and this app's {@link Config} (model, prompt, persistence * root, welcome banner). @@ -41,7 +41,6 @@ import type { Context } from 'cordis' import ConsoleExporter from '@cordisjs/plugin-logger-console' import z from 'schemastery' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools' import * as agentCore from '@deepseek-ai/dsh-agent-core' @@ -54,7 +53,7 @@ export const name = 'stdio-agent' /** * App config: the swappable per-demo values, each routed to where the app wires - * it. `model`/`resumeSessionId` configure the pre-created `main` agent (through + * it. `model`/`resumeSessionId` configure the pre-created agent (through * {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list); `persona` is * the deployment persona (forwarded to the system-prompt plugin); `toolOrder` * is the explicit model-facing tool order (forwarded to the system-prompt plugin); @@ -63,7 +62,7 @@ export const name = 'stdio-agent' * `welcome` is the UI banner. */ export interface Config { - /** Model name for the `main` agent (must have a registered adapter). */ + /** Model name for the pre-created agent (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ persona?: string @@ -78,7 +77,7 @@ export interface Config { /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-core. */ skills?: agentCore.SkillConfig /** - * If set, the `main` agent RESUMES this persisted session id instead of + * If set, the pre-created agent RESUMES this persisted session id instead of * starting fresh. Sourced from an env var in the leaf `cordis.yml` * (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`). */ @@ -103,9 +102,9 @@ export const Config: z = z.object({ /** * Compose the spine with the stdio front door. The console logger comes first - * (infra), then the agent-core bundle pre-creating the `main` agent from this - * app's `model`/`resumeSessionId` with the deployment `persona`, then the JSONL - * backend, then the readline UI bound to `main`. The `hmr` dev-reload plugin is + * (infra), then the agent-core bundle pre-creating one agent from this app's + * `model`/`resumeSessionId` with the deployment `persona`, then the JSONL + * backend, then the readline UI rendering that object as `main`. The `hmr` dev-reload plugin is * a leaf concern (see the module doc), so it is not mounted here. */ export function apply(ctx: Context, config: Config): void { @@ -115,7 +114,7 @@ export function apply(ctx: Context, config: Config): void { ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {}, ...config.tools !== undefined ? { tools: config.tools } : {}, agents: [{ - id: AgentId('main'), + id: 'main', model: config.model, cwd: process.cwd(), ...config.resumeSessionId !== undefined ? { resumeSessionId: SessionId(config.resumeSessionId) } : {}, @@ -125,5 +124,5 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) ctx.plugin(UserInteractionService) ctx.plugin(toolAskUser) - ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.', agent: 'main' }) + ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.' }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 8e3c1f467b..cb9ce0bc10 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -19,7 +19,7 @@ import { createInterface } from 'node:readline' import type { Readable, Writable } from 'node:stream' import type { Context } from 'cordis' import z from 'schemastery' -import { AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' import { UserInteractionError, type AskUserQuestionAnswer, @@ -36,15 +36,10 @@ export const inject = ['agents', 'userInteraction'] export interface Config { /** Banner printed once on start, before the first `> ` prompt. */ welcome?: string - // TODO(fixed-stdio-agent): this app-internal plugin is mounted only for the - // precreated `main` agent; remove configurability and its config-only test. - /** Id of the agent stdin drives (`send`/`steer`) and whose status gates the EOF exit; rendering is global. Defaults to `'main'`. */ - agent?: string } export const Config: z = z.object({ welcome: z.string().default('ready.'), - agent: z.string().default('main'), }) /** @@ -98,23 +93,16 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt // Loader validation, so it must be self-contained rather than trusting the // cast — `config.welcome as string` would otherwise be `undefined` on `{}`. const welcome = config.welcome ?? 'ready.' - const agentId = AgentId(config.agent ?? 'main') const { input, output, exit } = runtime - // Render label lookup: the `turn/start` session event carries only the turn - // number, so to print the short agent id (`[main turn 1]`) we map the - // session's id to its agent's id. The session id is not reliably the agent id - // (a session can be created with an explicit/client-supplied id), so build the - // map from `agent/created` rather than parsing the id string. Seed from the - // registry's current agents first: an agent registered before this plugin - // installed (e.g. the pre-created `main` agent, or any agent surviving an HMR - // reload of just this fiber) already fired its `agent/created`, so the live - // listener alone would miss it and its turns would fall back to the raw - // session id. - const labelBySession = new Map() - for (const agent of ctx.agents.list()) labelBySession.set(agent.session.header.id, agent.id) - ctx.on('agent/created', (agent) => { labelBySession.set(agent.session.header.id, agent.id) }) - ctx.on('agent/disposed', (agent) => { labelBySession.delete(agent.session.header.id) }) + // This app owns exactly one pre-created agent. Hold the live object directly: + // its per-run id is intentionally fresh, while `main` remains only the + // terminal's fixed display label. + let target: Agent | undefined = ctx.agents.list()[0] + ctx.on('agent/created', (agent) => { target ??= agent }) + ctx.on('agent/disposed', (agent) => { + if (target === agent) target = undefined + }) // Transcript rendering off the durable `session/event` feed — the assistant // token stream, turn/step boundaries, tool activity, and todos all come from @@ -136,7 +124,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt output.write(chunk.text) } } else if (event.type === 'turn/start') { - const label = labelBySession.get(session.header.id) ?? session.header.id + const label = target?.session === session ? 'main' : session.id output.write(`\n[${label} turn ${event.data.turn}] `) } else if (event.type === 'turn/end') { if (inReasoning) output.write('\x1B[0m') @@ -187,7 +175,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt // Work submitted: wait until a turn has run and the agent is idle. if (submittedWork) { if (!sawRunning) return - const agent = ctx.agents.get(agentId) + const agent = target if (agent && agent.status !== 'idle') return // a turn is still running } // Let any final output flush, then exit. The handle is tracked so the @@ -201,7 +189,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt } const disposeStatusListener = ctx.on('agent/status', (subject, status) => { - if (subject.id !== agentId) return + if (subject !== target) return if (status === 'running') sawRunning = true if (status === 'idle') maybeExit() }) @@ -354,9 +342,9 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt } const text = line.trim() if (!text) return - const agent = ctx.agents.get(agentId) + const agent = target if (!agent) { - ctx.logger.error('ui-stdio: agent "%s" is not running', agentId) + ctx.logger.error('ui-stdio: main agent is not running') return } submittedWork = true diff --git a/packages/ui/stdio-agent/tests/readline.spec.ts b/packages/ui/stdio-agent/tests/readline.spec.ts index a958c435c1..6116aa356f 100644 --- a/packages/ui/stdio-agent/tests/readline.spec.ts +++ b/packages/ui/stdio-agent/tests/readline.spec.ts @@ -16,7 +16,7 @@ function fakeContext(): Context { return { on: vi.fn(() => vi.fn()), effect: vi.fn((callback: () => () => void) => callback()), - // The UI seeds its label map from the registry at install; this suite only + // The UI seeds its target object from the registry at install; this suite only // exercises readline terminal-mode selection, so an empty roster suffices. agents: { list: vi.fn(() => []) }, userInteraction: { registerProvider: vi.fn(() => vi.fn()) }, diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 0668d25fb0..5c5c0d2667 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -4,7 +4,8 @@ import { join } from 'node:path' import { tmpdir } from 'node:os' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import { AgentId, agentEvents, type Agent } from '@deepseek-ai/dsh-agent' +import { agentEvents, type Agent } from '@deepseek-ai/dsh-agent' + import type { Message } from '@deepseek-ai/dsh-llm' import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import * as stdioAgent from '../src/index.ts' @@ -82,9 +83,12 @@ describe('dsh-stdio-agent app', () => { expect(ctx.get('sessionPersistence')).toBeDefined() expect(ctx.get('userInteraction')).toBeDefined() expect(ctx.get('tools')?.get('ask_user_question')).toBeDefined() - // The pre-created `main` agent the UI drives. - const agent = ctx.get('agents')?.get(AgentId('main')) + // The sole pre-created agent the UI drives. `main` is its stable config + // label; each fresh process mints a durable combined agent/session id. + const agent = ctx.get('agents')?.list()[0] expect(agent).toBeDefined() + expect(agent?.id).toBe(agent?.session.id) + expect(agent?.id).toMatch(/^main-session-/) expect(agent?.session.header.cwd).toBe(process.cwd()) await ctx.fiber.dispose() }) @@ -99,7 +103,7 @@ describe('dsh-stdio-agent app', () => { stdioAgent.apply(ctx, { model: 'mock', skills: await isolatedSkillsConfig() }) await new Promise(resolve => setTimeout(resolve, 80)) expect(ctx.get('sessionPersistence')).toBeDefined() - expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() + expect(ctx.get('agents')?.list()).toHaveLength(1) await ctx.fiber.dispose() }) @@ -116,7 +120,7 @@ describe('dsh-stdio-agent app', () => { it('forwards resumeSessionId onto the pre-created agent when set', async () => { // A resume id defers agent creation until persistence loads; with no backing - // session the resume is contained + logged, so no `main` agent registers — + // session the resume is contained + logged, so no agent registers — // the branch that maps resumeSessionId through is what this covers. const ctx = await mount({ model: 'mock', @@ -125,7 +129,7 @@ describe('dsh-stdio-agent app', () => { resumeSessionId: 'no-such-session', skills: await isolatedSkillsConfig(), }) - expect(ctx.get('agents')?.get(AgentId('main'))).toBeUndefined() + expect(ctx.get('agents')?.list()).toEqual([]) await ctx.fiber.dispose() }) diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 93683d0768..69ca5f8837 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -57,17 +57,16 @@ function makeAgent(id: string, status: AgentStatus = 'idle'): Agent & { status, sent, steered, - // A minimal session stub: the UI reads only `session.header.id` (to map the - // session back to its agent id for the turn-boundary label). - session: { header: { id: `${id}-session` } }, + // A minimal session stub with the agent's shared durable identity. + session: { id, header: { id } }, send: (content: ContentBlock[]) => void sent.push(content), steer: (content: ContentBlock[]) => void steered.push(content), } as never } /** A session stub whose `header.id` matches an agent's, for `session/event` emits. */ -function makeSession(agentId: string): Session { - return { header: { id: `${agentId}-session` } } as Session +function makeSession(id: string): Session { + return { id, header: { id } } as Session } /** An `assistant/chunk` session event carrying one raw stream chunk. */ @@ -75,7 +74,7 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { return { type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 0, chunk } } } -const CONFIG: Config = { welcome: 'hi there', agent: 'main' } +const CONFIG: Config = { welcome: 'hi there' } async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() @@ -99,12 +98,11 @@ describe('createStdioChat rendering', () => { expect(out.text()).toBe('hi there\n> ') }) - it('falls back to default welcome/agent when called with empty config', async () => { + it('falls back to the default welcome when called with empty config', async () => { // createStdioChat is exported and may be driven directly (bypassing the - // Loader's schemastery validation), so it must default welcome/agent itself. + // Loader's schemastery validation), so it must default the welcome itself. const { out } = await setup({}) expect(out.text()).toBe('ready.\n> ') - // And it drives the default agent id 'main'. }) it('detects readline terminal mode from both stream TTY flags', async () => { @@ -156,9 +154,9 @@ describe('createStdioChat rendering', () => { it('renders turn/start and turn/end markers from the session feed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') - // agent/created populates the session-id → agent-id label map. + // agent/created supplies the app-owned target object. ctx.emit('agent/created', agent) - const session = makeSession('main') + const session = agent.session ctx.emit('session/event', session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 3, trigger: { kind: 'message' } }, } as SessionEvent) @@ -169,21 +167,20 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('\n> ') }) - it('falls back to the session id as the label when no agent is mapped', async () => { + it('uses the session id as the label for a non-target session', async () => { const { ctx, out } = await setup() - // No agent/created emitted, so the label map is empty — the header id shows. + // No target exists, so the event's durable identity is the label. ctx.emit('session/event', makeSession('orphan'), { type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, } as SessionEvent) - expect(out.text()).toContain('[orphan-session turn 1] ') + expect(out.text()).toContain('[orphan turn 1] ') }) - it('seeds labels for agents already registered before the UI installs', async () => { + it('uses an agent already registered before the UI installs as its target', async () => { // The pre-created `main` agent (and any agent surviving an HMR reload of just // this fiber) fired its `agent/created` before the UI's listener existed, so // the live listener alone would miss it. Seeding from `ctx.agents.list()` at - // install time is what keeps its turn header showing `[main turn N]` instead - // of the raw session id. + // install time preserves the terminal's fixed `[main turn N]` label. const ctx = new Context() await ctx.plugin(AgentRegistry) await ctx.plugin(UserInteractionService) @@ -193,7 +190,7 @@ describe('createStdioChat rendering', () => { await ctx.plugin(Object.assign((inner: Context) => { createStdioChat(inner, CONFIG, runtime) }, { inject: ['agents', 'userInteraction'] })) - ctx.emit('session/event', makeSession('main'), { + ctx.emit('session/event', agent.session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 5, trigger: { kind: 'message' } }, } as SessionEvent) expect(out.text()).toContain('[main turn 5] ') @@ -209,17 +206,28 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('\x1B[2mmid\x1B[0m') }) - it('drops the label mapping on agent/disposed', async () => { + it('drops the target object on agent/disposed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') ctx.emit('agent/created', agent) ctx.emit('agent/disposed', agent) - // After disposal the map no longer resolves the agent id — fall back to the - // session header id. - ctx.emit('session/event', makeSession('main'), { + // After disposal the event belongs to a non-target session, so its durable + // identity is rendered directly. + ctx.emit('session/event', agent.session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, } as SessionEvent) - expect(out.text()).toContain('[main-session turn 1] ') + expect(out.text()).toContain('[main turn 1] ') + }) + + it('keeps the target when a different agent is disposed', async () => { + const { ctx, out } = await setup() + const target = makeAgent('target') + ctx.emit('agent/created', target) + ctx.emit('agent/disposed', makeAgent('other')) + ctx.emit('session/event', target.session, { + type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, + } as SessionEvent) + expect(out.text()).toContain('[main turn 1] ') }) it('renders tool/call and tool/result session events', async () => { @@ -666,11 +674,11 @@ describe('createStdioChat input', () => { const spy = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) input.feed('nobody home') await new Promise(r => setImmediate(r)) - expect(spy).toHaveBeenCalledWith('ui-stdio: agent "%s" is not running', 'main') + expect(spy).toHaveBeenCalledWith('ui-stdio: main agent is not running') }) - it('drives the agent named in config, not a hardcoded id', async () => { - const { ctx, input } = await setup({ welcome: 'w', agent: 'worker' }) + it('drives the app-owned agent without a duplicate id config', async () => { + const { ctx, input } = await setup({ welcome: 'w' }) const agent = makeAgent('worker') ctx.agents.register(agent) input.feed('hi') diff --git a/packages/util/brand/README.md b/packages/util/brand/README.md index 8f7943def7..be25edd55e 100644 --- a/packages/util/brand/README.md +++ b/packages/util/brand/README.md @@ -4,7 +4,7 @@ The `Branded` nominal-typing primitive — a tiny, **type-only** package (no ## What `Branded` is -A brand makes structurally-identical strings non-interchangeable at the type level: an `AgentId` cannot be passed where a `CallId` is expected, even though both are plain `string`s at runtime. +A brand makes structurally-identical strings non-interchangeable at the type level: a `SessionId` cannot be passed where a `CallId` is expected, even though both are plain `string`s at runtime. ```ts import type { Branded } from '@deepseek-ai/dsh-brand' @@ -21,6 +21,6 @@ Construction goes through the per-id factory in the OWNING package (a plain cast ## Policy: brand ids that cross package boundaries -A package brands the ids it OWNS — `CallId` in `dsh-llm` (tool-call correlation), `SessionId` in `dsh-session`, `AgentId` in `dsh-agent`, `BashTaskId`/`OwnerToken` in `dsh-bash`. Branding is for ids that cross package boundaries and could plausibly be confused; **not every string needs a brand.** +A package brands the ids it OWNS — `CallId` in `dsh-llm` (tool-call correlation), the shared agent/session `SessionId` in `dsh-session`, and `BashTaskId`/`OwnerToken` in `dsh-bash`. Branding is for ids that cross package boundaries and could plausibly be confused; **not every string needs a brand.** This package owns ONLY the primitive — no concrete id, no runtime code beyond the (erased) type. Keeping the primitive dependency-free is the point: a capability package can brand its ids without depending on an unrelated package. `dsh-bash`, for example, brands `BashTaskId`/`OwnerToken` by depending on `dsh-brand` alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. diff --git a/packages/util/brand/src/index.ts b/packages/util/brand/src/index.ts index 051ced94b7..d8c28846b3 100644 --- a/packages/util/brand/src/index.ts +++ b/packages/util/brand/src/index.ts @@ -4,15 +4,15 @@ * cross-boundary id. * * A brand makes structurally-identical strings non-interchangeable at the type - * level: an `AgentId` cannot be passed where a `CallId` is expected, even + * level: a `SessionId` cannot be passed where a `CallId` is expected, even * though both are plain strings at runtime. Construction goes through a per-id * factory in the OWNING package (a plain cast inside — zero runtime cost); * comparison, logging, and serialization all behave as ordinary strings. * * Policy: a package brands the ids it owns — `CallId` in dsh-llm (tool-call - * correlation), `SessionId` in dsh-session, `AgentId` in dsh-agent, - * `BashTaskId`/`OwnerToken` in dsh-bash. Branding is for ids that cross package - * boundaries and could plausibly be confused; not every string needs a brand. + * correlation), and `SessionId` in dsh-session; `BashTaskId`/`OwnerToken` live + * in dsh-bash. Branding is for ids that cross package boundaries and could + * plausibly be confused; not every string needs a brand. * This package owns ONLY the primitive — no concrete id, no runtime code beyond * the (erased) type — so the brand vocabulary stays dependency-free and a * package can brand its ids without depending on an unrelated capability diff --git a/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts b/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts index 0585889617..ac7112a0f0 100644 --- a/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts +++ b/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts @@ -4,7 +4,6 @@ import Loader from '@cordisjs/plugin-loader' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import type { ToolExecutionResult } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { WorkflowRunId, WorkflowService } from '@deepseek-ai/dsh-workflow' import type { WorkflowResult, WorkflowRun, WorkflowStartRequest } from '@deepseek-ai/dsh-workflow' @@ -12,6 +11,7 @@ import { CallId } from '@deepseek-ai/dsh-llm' import SubagentService from '@deepseek-ai/dsh-subagent' import WorkerWorkflowEngine from '@deepseek-ai/dsh-workflow-workerthread' import * as toolWorkflow from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** A controllable engine standing in behind ctx.workflows (the tool's only seam). */ class StubEngine extends WorkflowService { @@ -51,7 +51,7 @@ async function setup(config?: { toolName?: string; maxResultChars?: number }) { await ctx.plugin(StubEngine) await ctx.plugin(toolWorkflow, config ?? {}) const engine = ctx.workflows as StubEngine - const parent = { id: AgentId('caller'), options: {} } as unknown as Agent + const parent = { id: SessionId('caller'), options: {} } as unknown as Agent return { ctx, engine, parent } } @@ -237,7 +237,7 @@ describe('dsh-tool-workflow', () => { await ctx.plugin(SubagentService) await ctx.plugin(WorkerWorkflowEngine, { disposeGraceMs: 30 }) await ctx.plugin(toolWorkflow, {}) - const parent = { id: AgentId('caller'), options: {} } as unknown as Agent + const parent = { id: SessionId('caller'), options: {} } as unknown as Agent const controller = new AbortController() const pending = execute(ctx, { script: 'await new Promise(() => {})\nreturn 1', diff --git a/packages/workflow/workflow-workerthread/src/runtime.ts b/packages/workflow/workflow-workerthread/src/runtime.ts index 94282cb173..7dbdccbb43 100644 --- a/packages/workflow/workflow-workerthread/src/runtime.ts +++ b/packages/workflow/workflow-workerthread/src/runtime.ts @@ -38,8 +38,8 @@ */ import * as vm from 'node:vm' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' import { assertSupportedOutputSchema, OutputSchemaError } from '@deepseek-ai/dsh-tools' import type { StructuredOutputSchema } from '@deepseek-ai/dsh-tools' import { isFatalWorkflowError, WorkflowError } from '@deepseek-ai/dsh-workflow' @@ -319,7 +319,7 @@ export class WorkflowExecution { await run.dispose() throw this.cancelledError() } - const info: WorkflowAgentInfo = { seq, label, ...phase !== undefined ? { phase } : {}, childId: AgentId(run.id) } + const info: WorkflowAgentInfo = { seq, label, ...phase !== undefined ? { phase } : {}, childId: SessionId(run.id) } this.observer.agentStart(info) try { let result diff --git a/packages/workflow/workflow-workerthread/tests/integration.spec.ts b/packages/workflow/workflow-workerthread/tests/integration.spec.ts index 0e1727f877..2e13ddcb8b 100644 --- a/packages/workflow/workflow-workerthread/tests/integration.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/integration.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -37,7 +38,7 @@ async function setup(script: Script) { await ctx.plugin(spawn, { providerName: 'spawn' }) await ctx.plugin(WorkerWorkflowEngine, {}) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent, adapter } } @@ -73,7 +74,7 @@ return { prose, verdict: judged.verdict, confidence: judged.confidence }`, // Both children were disposed to quiescence — no live child agents remain. expect(childIds.length).toBe(2) for (const childId of childIds) { - expect(ctx.agents.get(AgentId(childId))).toBeUndefined() + expect(ctx.agents.get(SessionId(childId))).toBeUndefined() } }) diff --git a/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts b/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts index 7f34396d52..673a43ee0a 100644 --- a/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts @@ -6,10 +6,10 @@ import { expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import SubagentService from '@deepseek-ai/dsh-subagent' import WorkerWorkflowEngine from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' // A fresh thread compiles the source runtime. Leave contention headroom on // shared CI runners without weakening any engine-level timeout assertion. @@ -19,7 +19,7 @@ it('runs the default config through the source worker', async () => { const ctx = new Context() const subagents = await ctx.plugin(SubagentService) const engine = await ctx.plugin(WorkerWorkflowEngine, {}) - const parent = { id: AgentId('workflow-compat-parent'), options: {} } as unknown as Agent + const parent = { id: SessionId('workflow-compat-parent'), options: {} } as unknown as Agent try { const run = ctx.workflows.start({ script: 'return 6 * 7', diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts index 1d6f61432a..169d80cda7 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts @@ -1,10 +1,11 @@ import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -62,7 +63,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('worker workflow engine with-key it('runs a two-phase script in a worker thread over real children, one through the structured runtime', async () => { ctx = await harness() const parentHandle = await ctx.agents.create({ - agentId: AgentId('wf-worker-e2e-parent'), sessionId: 'wf-worker-e2e-session' as never, agentOptions: { model: 'deepseek-v4-flash' }, }) @@ -95,7 +95,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('worker workflow engine with-key expect(childIds.length).toBe(2) // The children were disposed to quiescence after collection. for (const childId of childIds) { - expect(ctx.agents.get(AgentId(childId))).toBeUndefined() + expect(ctx.agents.get(SessionId(childId))).toBeUndefined() } await parentHandle.dispose() }, 240_000) diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts index 4ad00ee02f..09fb606d69 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts @@ -3,17 +3,17 @@ import { fileURLToPath } from 'node:url' import type { Worker } from 'node:worker_threads' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import SubagentService from '@deepseek-ai/dsh-subagent' import type { SubagentCapabilities, SubagentProvider, SubagentResult, SubagentRun, SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import type { WorkflowMeta, WorkflowResult, WorkflowResultInfo, WorkflowRunInfo } from '@deepseek-ai/dsh-workflow' import * as workerEngineModule from '../src/index.ts' import WorkerWorkflowEngine, { HostToWorkerType, WorkerToHostType, type Config } from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** A minimal parent stand-in: the engine only threads it through to the provider. */ function fakeParent(): Agent { - return { id: AgentId('workflow-parent'), options: {} } as unknown as Agent + return { id: SessionId('workflow-parent'), options: {} } as unknown as Agent } // Worker-thread startup is CPU-bound (a fresh thread compiles the runtime on @@ -117,7 +117,7 @@ class StubProvider implements SubagentProvider { } if (request.signal.aborted) throw new Error('child start aborted before publication') return { - id: AgentId(`stub-child-${index}`), + id: SessionId(`stub-child-${index}`), result: terminal.promise, dispose: () => { controlled.disposeCalls += 1 @@ -366,7 +366,7 @@ describe('dsh-workflow-workerthread', () => { capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('reject-child'), + id: SessionId('reject-child'), result: Promise.reject(new Error('backend exploded')), dispose: () => Promise.resolve(), }), @@ -400,7 +400,7 @@ describe('dsh-workflow-workerthread', () => { stopReason: 'completed', } as unknown as SubagentResult const start = vi.spyOn(ctx.subagents, 'start').mockResolvedValue({ - id: AgentId('raw-invalid-child'), + id: SessionId('raw-invalid-child'), result: Promise.resolve(invalid), dispose: () => Promise.resolve(), }) @@ -423,7 +423,7 @@ describe('dsh-workflow-workerthread', () => { capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('bad-dispose-child'), + id: SessionId('bad-dispose-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'fine' }], stopReason: 'completed' }), cancel: () => { /* settled already */ }, dispose: () => { throw new Error('dispose exploded') }, @@ -444,7 +444,7 @@ describe('dsh-workflow-workerthread', () => { capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('trap-child'), + id: SessionId('trap-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'fine' }], stopReason: 'completed' }), cancel: () => { /* settled already */ }, // The rejection VALUE's own coercion throws: a warn built with bare @@ -771,7 +771,7 @@ describe('dsh-workflow-workerthread', () => { settle({ output: [], stopReason: 'aborted' }) }, { once: true }) return { - id: AgentId('signal-only-child'), + id: SessionId('signal-only-child'), result, dispose: () => Promise.resolve(), } @@ -1092,7 +1092,7 @@ describe('dsh-workflow-workerthread', () => { expect(request.signal.reason).toBe('workflow worker gone') ready.resolve({ - id: AgentId('late-ready-child'), + id: SessionId('late-ready-child'), result: Promise.resolve({ output: [], stopReason: 'aborted' }), dispose: () => { disposeCalls += 1 @@ -1128,7 +1128,7 @@ describe('dsh-workflow-workerthread', () => { handle.cancel('reentered from worker-death signal cleanup') }, { once: true }) return { - id: AgentId('doomed-child'), + id: SessionId('doomed-child'), result: new Promise(() => { /* never settles; the reap is the teardown */ }), dispose: () => Promise.reject(new Error('dispose exploded during reap')), } diff --git a/packages/workflow/workflow/src/types.ts b/packages/workflow/workflow/src/types.ts index 981a2da172..35ea4fb053 100644 --- a/packages/workflow/workflow/src/types.ts +++ b/packages/workflow/workflow/src/types.ts @@ -7,7 +7,8 @@ */ import type { Branded } from '@deepseek-ai/dsh-brand' -import type { Agent, AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' +import type { SessionId } from '@deepseek-ai/dsh-session' /** Identifies one workflow run. */ export type WorkflowRunId = Branded<'WorkflowRunId'> @@ -145,7 +146,7 @@ export interface WorkflowAgentInfo { /** The phase this agent belongs to (the `phase` option, else the current `phase()` title). */ phase?: string /** The child agent's id on the subagent seam. */ - childId: AgentId + childId: SessionId } /** How one `agent()` call settled: clean result, child failure (script sees `null`), or run cancellation. */ From 61136b22bbfabae49227843f924cc4832a07fe51 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:09:09 +0800 Subject: [PATCH 033/359] refactor: remove UI identity translations --- docs/config-catalog.md | 4 +- docs/rfc/INDEX.md | 2 +- .../architecture/2026-06-20-branded-ids.md | 4 +- .../2026-06-20-unify-agent-and-session-id.md | 38 ++++++++++++++ .../2026-06-20-unify-agent-and-session-id.md | 38 -------------- packages/ui/acp/README.md | 4 +- packages/ui/acp/src/index.ts | 52 ++++++++----------- packages/ui/acp/tests/approval.spec.ts | 9 ++-- packages/ui/acp/tests/bridge.spec.ts | 3 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 34 ++++-------- packages/ui/jsonrpc/tests/server.spec.ts | 20 ++++--- 12 files changed, 100 insertions(+), 110 deletions(-) create mode 100644 docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md delete mode 100644 docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 94d613bc4e..4ae020f0be 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -11,7 +11,7 @@ A `Requires:` line lists the service keys the plugin `inject`s: its `cordis.yml` ## `@deepseek-ai/dsh-acp` -Requires: `agents` · `sessions` · `sessionPersistence` · `tools` · `userInteraction` +Requires: `agents` · `sessionPersistence` · `tools` · `userInteraction` ```ts config-catalog /** Plugin config: the agent template ACP sessions are created from. */ @@ -31,7 +31,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:249`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:246`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-agent` diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index a5334a63e1..5ed8c6ae6d 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -17,7 +17,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | Title | First proposed | |---|---| -| [Unify the agent id and the session id](proposed/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | | [Drop unconsumed skill provider events](proposed/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 | | [Prune unused web seam fields](proposed/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 | @@ -87,6 +86,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Prune dead methods from the persistence seam](implemented/simplification/2026-06-20-prune-dead-seam-methods.md) | 2026-06-20 | | [Keep one public stop primitive](implemented/simplification/2026-06-20-public-agent-stop-surface.md) | 2026-06-20 | | [Stop mirroring durable boundaries as agent events](implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md) | 2026-06-20 | +| [Unify the agent id and the session id](implemented/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Split the filesystem seam — provider text mutations plus the `dsh-fs-policy` plugin](implemented/simplification/2026-06-26-fsspec-style-fs-seam.md) | 2026-06-26 | | [Stop mirroring the token stream as an agent event](implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md) | 2026-07-02 | | [Drop the `image` content block until a path can honor it](implemented/simplification/2026-07-04-drop-image-content-block.md) | 2026-07-04 | diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 5fe8224644..4fe7f58168 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -8,7 +8,7 @@ The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared age **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. -The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias that the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal calls the "bash owner-token alias hole". +The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). **Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. @@ -62,6 +62,6 @@ The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` a ## Consequences -- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal (both touch the session-id / owner-token boundary); if that proposal lands, `OwnerToken` still stays distinct from the unified id for the decoupling reason above. +- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md) because both touch the session-id / owner-token boundary; `OwnerToken` stays distinct from the unified id for the decoupling reason above. - **Brands do not validate.** A brand is a confusability guard, not a correctness proof: a *wrong* session id that is still a well-formed string passes the type checker exactly as before. This RFC does not close that gap (see Out of scope) — it only stops the *category* error of passing the wrong *kind* of id. - **The "where to stop" line stays a judgment call.** Branding `BashTaskId` but not `ToolName`, `OwnerToken` but not `ModelId`, is a taste call about which strings "could plausibly be confused." Reasonable reviewers may want more or fewer; the policy in `brand.ts` is the tie-breaker, and this RFC errs toward the ids that are model-facing or used for access control. diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md new file mode 100644 index 0000000000..79d7332553 --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -0,0 +1,38 @@ +# RFC: Unify the agent id and the session id + +Status: implemented + +## Problem + +The agent factory previously carried two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` took both; `ResumeAgentOptions` took `agentId` plus `resumeSessionId`; in-process subagents minted two independent UUIDs despite recording lineage separately. + +ACP already used the same value for both identities. Where they diverged, stdio kept `labelBySession` solely to recover an agent label from session events, and hooks exposed both values for authors to reconcile. No production path reattached one live agent object to several sessions or drove one session through several agent ids. + +The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) had no reservation side tables: create and resume used one `AgentCreationTransaction`, and agent/session entries used the same final-entry collision rule. Separate ids therefore did not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification was only an API and representation simplification: it deleted one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. + +Session itself repeated the same fact as `Session.id` and `Session.header.id`. Construction rejected a header whose id differed, so the aliases were constrained equal; the durable boundary nevertheless had to validate the duplicate, and production consumers chose between its two homes. + +## Decision + +An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; subagent creation mints one combined id; and `Session.id` derives from `header.id`. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between the ids are gone. + +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. + +`agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. + +## Alternatives considered + +**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. + +## Verification + +- Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. +- The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. ACP verifies exact `Agent` ownership from the forward session map; JSON-RPC caches only disposable-child parent lineage. +- The config-driven resume-or-create policy is explicit and covered across a durable restart. +- A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. +- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. + +## Consequences + +This forecloses latent multi-session-actor and session-handoff designs and makes persisted client-chosen session identity the registry identity. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md deleted file mode 100644 index 6e3eea1515..0000000000 --- a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md +++ /dev/null @@ -1,38 +0,0 @@ -# RFC: Unify the agent id and the session id - -Status: proposed - -## Problem - -The agent factory carries two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` takes both; `ResumeAgentOptions` takes `agentId` plus `resumeSessionId`; in-process subagents mint two independent UUIDs despite recording lineage separately. - -ACP already uses the same value for both identities. Where they diverge, stdio keeps `labelBySession` solely to recover an agent label from session events, and hooks expose both values for authors to reconcile. No production path reattaches one live agent object to several sessions or drives one session through several agent ids. - -The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) has no reservation side tables: create and resume use one `AgentCreationTransaction`, and agent/session entries use the same final-entry collision rule. Separate ids therefore do not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification is only an API and representation simplification: it deletes one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. - -Session itself repeats the same fact as `Session.id` and `Session.header.id`. Construction rejects a header whose id differs, so the aliases are constrained equal; the durable boundary must nevertheless validate the duplicate, and production consumers choose between its two homes. - -## Proposal - -Make an agent's registry id equal its session id. `CreateAgentOptions` accepts one id used for both final registry entries; resume registers the agent under the resumed session id; subagent creation mints one combined id; Session keeps one identity home by deriving `id` from `header.id` or removing the alias. Keep the existing creation transaction, final-entry collision checks, and exact-entry detach semantics; remove only maps and fields whose sole job is translating between the ids. - -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. - -`agent/created` and `agent/disposed` remain outside this proposal. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. - -## Alternatives considered - -**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. - -## Acceptance criteria - -- Agent create/resume and subagent creation carry one identity; `Session` stores it in one place. -- The existing creation transaction keeps final-entry collision, exact-entry detach, rollback, and quiescence guarantees without adding identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage need no agent/session id translation. -- The config-driven resume-or-create policy is explicit and covered across a durable restart. -- `agent/created`/`agent/disposed` are removed only if a post-change production search finds no listener; otherwise they and their publication semantics stay. -- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. - -## Risks - -This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index f4947e5d25..31a865c068 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -8,7 +8,7 @@ It is a **client-driver / UI plugin**, the structured analogue of the readline ` `apply(ctx, config)` — wires an `AgentSideConnection` (from `@agentclientprotocol/sdk`) to `process.stdin`/`process.stdout` and implements the ACP `Agent` method surface. -`inject: ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction']` — programs against the interface packages only (never `dsh-agent-loop`). `sessionPersistence` is required because `initialize` advertises `loadSession: true`; `tools` lets a tool own how its calls render (`presentCall`/`presentResult`) — the bridge looks the definition up by name and falls back to a generic presentation when a tool declares none (see Tool-call presentation). `userInteraction` lets agent-owned `ask_user_question` calls become ACP form elicitations routed to the owning session. +`inject: ['agents', 'sessionPersistence', 'tools', 'userInteraction']` — programs against the interface packages only (never `dsh-agent-loop`). `sessionPersistence` is required because `initialize` advertises `loadSession: true`; `tools` lets a tool own how its calls render (`presentCall`/`presentResult`) — the bridge looks the definition up by name and falls back to a generic presentation when a tool declares none (see Tool-call presentation). `userInteraction` lets agent-owned `ask_user_question` calls become ACP form elicitations routed to the owning session. ### Config @@ -36,7 +36,7 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name: ## Multi-session -The bridge multiplexes N sessions over one connection. Live sessions are held in a `Map` (forward) with a `WeakMap` reverse map so agent-scoped approval events demultiplex in O(1). Every `session/event` is routed strictly to its owning record, so concurrent sessions never cross-settle or interleave their `session/update` notifications. State is per session: one in-flight prompt each, `session/cancel` aborts and settles only its own agent/prompt, and disposal drains every live session in parallel to quiescence. Permission prompts follow the same ownership: the `approval/request` answerer resolves the owning session through the reverse map and prompts only there. +The bridge multiplexes N sessions over one connection. Live sessions are held in a `Map` keyed by the shared agent/session id. Agent-scoped events derive that id from `agent.session.id` and verify the record owns the exact agent object, so a foreign same-id object cannot claim the bridge's session. Every `session/event` is routed strictly to its owning record, so concurrent sessions never cross-settle or interleave their `session/update` notifications. State is per session: one in-flight prompt each, `session/cancel` aborts and settles only its own agent/prompt, and disposal drains every live session in parallel to quiescence. Permission prompts follow the same ownership and prompt only the matching session. ## Session config options diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index e795c7e177..369c8ae166 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -18,12 +18,11 @@ * turn about to start) + settle the in-flight prompt * * Multi-session (RFC 011): N concurrent sessions per connection, each mapped to - * its own `ReactLoopAgent`. Sessions are keyed by id in `sessions` (forward) with an - * `agent→sessionId` reverse map for O(1) demux of `agent/*` events; every - * `session/event` and `agent/*` event is routed strictly to its owning session - * record, so two sessions streaming at once never interleave their - * `session/update` notifications. Permission prompts ride the same ownership - * map: the bridge answers `approval/request` for its own agents over + * its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id; + * every `session/event` and `agent/*` event is routed strictly to its owning + * session record, so two sessions streaming at once never interleave their + * `session/update` notifications. Permission prompts use the same identity: the + * bridge answers `approval/request` for its own agents over * `session/request_permission` (see the approval answerer below) — whether a * call ASKS is policy (a hook or plugin returning `ask`), not the bridge's. * @@ -106,9 +105,7 @@ export const name = 'acp' // because `initialize` advertises `loadSession: true`. `tools` lets a tool own // how its calls render (`presentCall`/`presentResult`); the bridge looks up the // definition by name and falls back to a generic presentation when absent. -// TODO(acp-session-inject): drop `sessions`; this bridge never reads -// ctx.sessions, and agent/session ownership is already behind ctx.agents. -export const inject = ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction'] +export const inject = ['agents', 'sessionPersistence', 'tools', 'userInteraction'] /** * Build an ACP "invalid params" error whose human detail rides in the message. @@ -268,7 +265,6 @@ export const Config: Schema = Schema.object({ * map keyed by id (RFC 011 multi-session). */ interface SessionRecord { - sessionId: SessionId agent: Agent /** * The owned-agent disposer (from the {@link AgentHandle} the factory returned). @@ -353,15 +349,8 @@ export function apply(ctx: Context, config: AcpConfig): void { // this warn sink so a throwing tool presenter is logged, not propagated. const makePresenter = (agent?: Agent): ToolPresenter => new ToolPresenter(tools, (message) => { logger.warn(message) }, agent) - // TODO(derive-acp-session-id): derive an event's id from agent.session and - // verify sessions.get(id)?.agent === agent; then remove this reverse map and - // SessionRecord.sessionId, whose sole read duplicates the same identity. - // Live sessions keyed by id (RFC 011 multi-session), plus an agent→sessionId - // reverse map so `agent/*` events (which carry only the Agent) demux in O(1). - // The forward record and weak reverse entry are installed together; removing - // the record releases its strong Agent reference, so the WeakMap entry expires. + // Live sessions keyed by their shared agent/session id (RFC 011 multi-session). const sessions = new Map() - const bySession = new WeakMap() // Session ids whose `session/load` is mid-`resume()` (the slot is reserved // before the async resume so a pipelined load/new for the SAME id can't create // two agents). Distinct ids load concurrently; a given id loads once at a time. @@ -382,20 +371,26 @@ export function apply(ctx: Context, config: AcpConfig): void { // `notify` never observes it unset — no undefined guard needed. let conn: AgentSideConnection + /** Return the bridge-owned record for an agent, rejecting same-id impostors. */ + const ownedRecord = (agent: Agent): SessionRecord | undefined => { + const rec = sessions.get(agent.session.id) + return rec?.agent === agent ? rec : undefined + } + userInteraction.registerProvider({ async ask(request: AskUserQuestionRequest): Promise { if (request.agent === undefined) { throw new UserInteractionError('ACP user questions must come from an agent-owned request', 'NO_AGENT') } - const sessionId = bySession.get(request.agent) - if (sessionId === undefined) { + const rec = ownedRecord(request.agent) + if (rec === undefined) { throw new UserInteractionError('ACP user question has no matching session', 'NO_SESSION') } const answers: AskUserQuestionAnswerItem[] = [] for (const question of request.questions) { const options = question.options ?? [] const response = await withAbort(conn.unstable_createElicitation( - elicitationForQuestion(sessionId, question, options), + elicitationForQuestion(rec.agent.session.id, question, options), ), request.signal).catch((error: unknown) => { if (error instanceof UserInteractionError) throw error throw new UserInteractionError('ACP elicitation request failed', 'ASK_FAILED', { cause: error }) @@ -496,7 +491,7 @@ export function apply(ctx: Context, config: AcpConfig): void { const rec = sessions.get(session.header.id) if (rec === undefined) return try { - streamSessionEventUpdate(rec.sessionId, event, notify, rec.presenter, { + streamSessionEventUpdate(rec.agent.session.id, event, notify, rec.presenter, { enabled: rec.terminalEnabled, cwd: session.header.cwd, }, { includeUserMessages: false }) @@ -527,12 +522,12 @@ export function apply(ctx: Context, config: AcpConfig): void { // allow_always is a grant-storage design the approval RFC defers, so the // prompt never offers a durable grant the harness could not honor. ctx.on('approval/request', (req, next) => { - const sessionId = bySession.get(req.agent) + const rec = ownedRecord(req.agent) // The protocol requires `toolCall` (the prompt renders attached to it), so // a request without a callId has nothing to attach to — delegate. - if (sessionId === undefined || req.callId === undefined) return next() + if (rec === undefined || req.callId === undefined) return next() return conn.requestPermission({ - sessionId, + sessionId: rec.agent.session.id, toolCall: { toolCallId: req.callId }, options: [ { optionId: 'allow-once', name: 'Allow once', kind: 'allow_once' }, @@ -639,8 +634,7 @@ export function apply(ctx: Context, config: AcpConfig): void { // turn) leaves the switch pending — it runs no step, so nothing executes // or assembles under a stale value. ctx.on('agent/prompt-submit', (agent, _content, _source, next) => { - const sessionId = bySession.get(agent) - const rec = sessionId === undefined ? undefined : sessions.get(sessionId) + const rec = ownedRecord(agent) if (rec !== undefined) flushPendingSwitches(rec) return next() }) @@ -699,9 +693,7 @@ export function apply(ctx: Context, config: AcpConfig): void { await handle.dispose() throw internalError('connection closed during session/new') } - bySession.set(handle.agent, sessionId) sessions.set(sessionId, { - sessionId, agent: handle.agent, dispose: () => handle.dispose(), presenter: makePresenter(handle.agent), @@ -773,13 +765,11 @@ export function apply(ctx: Context, config: AcpConfig): void { throw invalidParams('connection closed during session/load') } const agent = handle.agent - bySession.set(agent, sessionId) // Snapshot the terminal capability ONCE for this session (used by both // the replay below and the post-load live stream) so a later // `initialize` can't desync the call/result of a tool card. const terminalEnabled = terminalOutputCap const record: SessionRecord = { - sessionId, agent, dispose: () => handle.dispose(), presenter: makePresenter(agent), diff --git a/packages/ui/acp/tests/approval.spec.ts b/packages/ui/acp/tests/approval.spec.ts index 36846ac728..65679cd905 100644 --- a/packages/ui/acp/tests/approval.spec.ts +++ b/packages/ui/acp/tests/approval.spec.ts @@ -90,9 +90,12 @@ describe('acp bridge — approval answerer', () => { await harness.ctx.plugin(ApprovalService) harness.onPermission = () => ({ outcome: { outcome: 'selected', optionId: 'allow-once' } }) - // Not created through the bridge: no bySession entry, so the answerer must - // call next() — nobody else answers, so the seam fails closed. - const foreign = { session: { events: [{ type: 'turn/start' }], append: () => ({}) } } as unknown as Agent + const { agent } = await ownedAgentRequest(harness) + // Even an impostor that claims the bridge-owned session id must delegate: + // ownership requires the exact Agent object stored in the session record. + const foreign = { + session: { id: agent.session.id, events: [{ type: 'turn/start' }], append: () => ({}) }, + } as unknown as Agent await expect(harness.ctx.approval.request({ agent: foreign, toolName: 'echo', callId: CallId('c') })) .resolves.toBe('unavailable') expect(harness.permissionRequests).toHaveLength(0) diff --git a/packages/ui/acp/tests/bridge.spec.ts b/packages/ui/acp/tests/bridge.spec.ts index 7e780348ba..e7170c380f 100644 --- a/packages/ui/acp/tests/bridge.spec.ts +++ b/packages/ui/acp/tests/bridge.spec.ts @@ -205,7 +205,8 @@ describe('acp bridge', () => { await expect(harness.ctx.userInteraction.ask({ questions: [{ id: 'x', question: 'No agent?' }] })) .rejects.toMatchObject({ name: 'UserInteractionError', code: 'NO_AGENT' }) - await expect(harness.ctx.userInteraction.ask({ agent: { id: 'other' } as typeof agent, questions: [{ id: 'x', question: 'No session?' }] })) + const impostor = { session: { id: agent.session.id } } as typeof agent + await expect(harness.ctx.userInteraction.ask({ agent: impostor, questions: [{ id: 'x', question: 'No session?' }] })) .rejects.toMatchObject({ code: 'NO_SESSION' }) harness.onElicitation = () => ({ action: 'cancel' }) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 007bd1a5f1..933023a2d9 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`) and demuxes `subagent/end` through the registry. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 4dbfeb0fa2..cfa083c394 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -58,11 +58,6 @@ interface SessionRecord { activePrompt: boolean } -interface SubagentRecord { - childSessionId: string - parentSessionId: string | undefined -} - /** * The SDK server over a booted harness context. Constructing it subscribes to * the context's `session/event`, `session/created`, `agent/created`, and @@ -76,7 +71,7 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly subagentSessions = new Map() + private readonly subagentParents = new Map() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -100,29 +95,22 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache agent → session lineage on creation: by the time `subagent/end` - // fires the child agent may already be disposed and gone from the registry. + // Cache parent lineage on creation: by the time `subagent/end` fires the + // child agent may already be disposed and gone from the registry. The child + // session id needs no cache because it is the shared agent/session id. this.disposers.push(ctx.on('agent/created', (agent) => { - this.subagentSessions.set(String(agent.id), { - childSessionId: String(agent.session.id), - parentSessionId: agent.session.header.parentSession === undefined - ? undefined - : String(agent.session.header.parentSession), - }) + const parentSessionId = agent.session.header.parentSession + if (parentSessionId !== undefined) this.subagentParents.set(agent.id, parentSessionId) })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { - const rec = this.subagentSessions.get(String(info.id)) const agent = this.ctx.agents.get(info.id) - const childSessionId = rec?.childSessionId ?? (agent === undefined ? undefined : String(agent.session.id)) - const parentSessionId = rec?.parentSessionId ?? ( - agent?.session.header.parentSession === undefined ? undefined : String(agent.session.header.parentSession) - ) - if (childSessionId === undefined) return + const parentSessionId = this.subagentParents.get(info.id) ?? agent?.session.header.parentSession + this.subagentParents.delete(info.id) this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), - ...(parentSessionId === undefined ? {} : { parentSessionId }), - childSessionId, + ...(parentSessionId === undefined ? {} : { parentSessionId: String(parentSessionId) }), + childSessionId: String(info.id), status: info.stopReason === 'completed' ? 'ok' : 'error', stopReason: info.stopReason, ...(info.lastAssistantMessage === undefined ? {} : { lastAssistantMessage: info.lastAssistantMessage }), @@ -195,7 +183,7 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.subagentSessions.clear() + this.subagentParents.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 9260a59aae..433119e046 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -272,6 +272,9 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) + // The backend may dispose the child before publishing its run outcome; + // only the cached parent lineage should be needed at this point. + await handle.dispose() await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), @@ -292,7 +295,6 @@ describe('HarnessSdkServer', () => { }, }) - await handle.dispose() await parentHandle.dispose() await server.shutdown() } finally { @@ -301,7 +303,7 @@ describe('HarnessSdkServer', () => { } }) - it('falls back to live agent lineage for uncached subagent end events', async () => { + it('falls back to live lineage and treats the shared id as the child session id', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) let parentHandle: AgentHandle | undefined @@ -365,10 +367,16 @@ describe('HarnessSdkServer', () => { stopReason: 'error', }, }) - expect(transport.notifications.some(n => - n.method === 'subagent.finished' - && n.params?.agentId === 'missing-child-agent', - )).toBe(false) + expect(transport.notifications).toContainEqual({ + method: 'subagent.finished', + params: { + provider: 'fork', + agentId: 'missing-child-agent', + childSessionId: 'missing-child-agent', + status: 'error', + stopReason: 'error', + }, + }) await server.shutdown() } finally { From 17c99efcc14c76bbc548f64ec536d95a2dbb25c5 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:22:20 +0800 Subject: [PATCH 034/359] fix: complete unified subagent identity --- docs/module-graph.md | 12 ++++-- docs/rfc/INDEX.md | 2 +- .../architecture/2026-06-20-branded-ids.md | 4 +- .../2026-06-20-unify-agent-and-session-id.md | 38 +++++++++++++++++++ .../2026-06-20-unify-agent-and-session-id.md | 38 ------------------- packages/subagent/subagent-acp/package.json | 2 + packages/subagent/subagent-acp/src/run.ts | 16 ++++---- .../subagent-acp/tests/mock-acp-server.ts | 2 +- .../subagent-acp/tests/subagent-acp.spec.ts | 3 +- packages/subagent/subagent/package.json | 2 + packages/support/subagent-mock/package.json | 2 + packages/workflow/workflow/package.json | 1 + pnpm-lock.yaml | 9 +++++ 13 files changed, 77 insertions(+), 54 deletions(-) create mode 100644 docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md delete mode 100644 docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md diff --git a/docs/module-graph.md b/docs/module-graph.md index e4d0b3367d..8ac71b11cc 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -179,6 +179,7 @@ flowchart TD pkg_workflow --> pkg_agent pkg_workflow --> pkg_brand pkg_workflow --> pkg_llm + pkg_workflow --> pkg_session pkg_tools --> pkg_agent pkg_tools --> pkg_code_runtime pkg_tools --> pkg_llm @@ -215,6 +216,7 @@ flowchart TD pkg_subagent --> pkg_agent pkg_subagent --> pkg_llm pkg_subagent --> pkg_scope + pkg_subagent --> pkg_session pkg_subagent --> pkg_tools pkg_tool_web --> pkg_llm pkg_tool_web --> pkg_system_prompt @@ -265,6 +267,7 @@ flowchart TD pkg_agent_core --> pkg_tools pkg_subagent_acp --> pkg_agent pkg_subagent_acp --> pkg_llm + pkg_subagent_acp --> pkg_session pkg_subagent_acp --> pkg_subagent pkg_subagent_acp --> pkg_subagent_subprocess pkg_subagent_inprocess --> pkg_agent @@ -285,6 +288,7 @@ flowchart TD pkg_hooks_claude --> pkg_tools pkg_subagent_mock --> pkg_agent pkg_subagent_mock --> pkg_llm + pkg_subagent_mock --> pkg_session pkg_subagent_mock --> pkg_subagent pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm @@ -362,14 +366,14 @@ flowchart TD | [`invariants`](../packages/support/invariants) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session) | | [`user-approval`](../packages/ui/user-approval) | `ui` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) | | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) | -| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) | +| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) | | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) | | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | -| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | +| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) | | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | @@ -380,11 +384,11 @@ flowchart TD | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) | | [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`agent-core`](../packages/core/agent-core) | `core` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tools`](../packages/core/tools) | -| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | +| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | -| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) | +| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index a5334a63e1..5ed8c6ae6d 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -17,7 +17,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | Title | First proposed | |---|---| -| [Unify the agent id and the session id](proposed/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | | [Drop unconsumed skill provider events](proposed/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 | | [Prune unused web seam fields](proposed/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 | @@ -87,6 +86,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Prune dead methods from the persistence seam](implemented/simplification/2026-06-20-prune-dead-seam-methods.md) | 2026-06-20 | | [Keep one public stop primitive](implemented/simplification/2026-06-20-public-agent-stop-surface.md) | 2026-06-20 | | [Stop mirroring durable boundaries as agent events](implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md) | 2026-06-20 | +| [Unify the agent id and the session id](implemented/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Split the filesystem seam — provider text mutations plus the `dsh-fs-policy` plugin](implemented/simplification/2026-06-26-fsspec-style-fs-seam.md) | 2026-06-26 | | [Stop mirroring the token stream as an agent event](implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md) | 2026-07-02 | | [Drop the `image` content block until a path can honor it](implemented/simplification/2026-07-04-drop-image-content-block.md) | 2026-07-04 | diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 5fe8224644..4fe7f58168 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -8,7 +8,7 @@ The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared age **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. -The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias that the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal calls the "bash owner-token alias hole". +The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). **Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. @@ -62,6 +62,6 @@ The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` a ## Consequences -- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal (both touch the session-id / owner-token boundary); if that proposal lands, `OwnerToken` still stays distinct from the unified id for the decoupling reason above. +- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md) because both touch the session-id / owner-token boundary; `OwnerToken` stays distinct from the unified id for the decoupling reason above. - **Brands do not validate.** A brand is a confusability guard, not a correctness proof: a *wrong* session id that is still a well-formed string passes the type checker exactly as before. This RFC does not close that gap (see Out of scope) — it only stops the *category* error of passing the wrong *kind* of id. - **The "where to stop" line stays a judgment call.** Branding `BashTaskId` but not `ToolName`, `OwnerToken` but not `ModelId`, is a taste call about which strings "could plausibly be confused." Reasonable reviewers may want more or fewer; the policy in `brand.ts` is the tie-breaker, and this RFC errs toward the ids that are model-facing or used for access control. diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md new file mode 100644 index 0000000000..be1052830a --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -0,0 +1,38 @@ +# RFC: Unify the agent id and the session id + +Status: implemented + +## Problem + +The agent factory previously carried two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` took both; `ResumeAgentOptions` took `agentId` plus `resumeSessionId`; in-process subagents minted two independent UUIDs despite recording lineage separately. + +ACP already used the same value for both identities. Where they diverged, stdio kept `labelBySession` solely to recover an agent label from session events, and hooks exposed both values for authors to reconcile. No production path reattached one live agent object to several sessions or drove one session through several agent ids. + +The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) had no reservation side tables: create and resume used one `AgentCreationTransaction`, and agent/session entries used the same final-entry collision rule. Separate ids therefore did not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification was only an API and representation simplification: it deleted one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. + +Session itself repeated the same fact as `Session.id` and `Session.header.id`. Construction rejected a header whose id differed, so the aliases were constrained equal; the durable boundary nevertheless had to validate the duplicate, and production consumers chose between its two homes. + +## Decision + +An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process and ACP subagent creation use the child session id; and `Session.id` derives from `header.id`. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between the ids are gone. + +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. + +`agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. + +## Alternatives considered + +**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. + +## Verification + +- Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. +- The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id. +- The config-driven resume-or-create policy is explicit and covered across a durable restart. +- A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. +- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. + +## Consequences + +This forecloses latent multi-session-actor and session-handoff designs and makes persisted client-chosen session identity the registry identity. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md deleted file mode 100644 index 6e3eea1515..0000000000 --- a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md +++ /dev/null @@ -1,38 +0,0 @@ -# RFC: Unify the agent id and the session id - -Status: proposed - -## Problem - -The agent factory carries two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` takes both; `ResumeAgentOptions` takes `agentId` plus `resumeSessionId`; in-process subagents mint two independent UUIDs despite recording lineage separately. - -ACP already uses the same value for both identities. Where they diverge, stdio keeps `labelBySession` solely to recover an agent label from session events, and hooks expose both values for authors to reconcile. No production path reattaches one live agent object to several sessions or drives one session through several agent ids. - -The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) has no reservation side tables: create and resume use one `AgentCreationTransaction`, and agent/session entries use the same final-entry collision rule. Separate ids therefore do not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification is only an API and representation simplification: it deletes one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. - -Session itself repeats the same fact as `Session.id` and `Session.header.id`. Construction rejects a header whose id differs, so the aliases are constrained equal; the durable boundary must nevertheless validate the duplicate, and production consumers choose between its two homes. - -## Proposal - -Make an agent's registry id equal its session id. `CreateAgentOptions` accepts one id used for both final registry entries; resume registers the agent under the resumed session id; subagent creation mints one combined id; Session keeps one identity home by deriving `id` from `header.id` or removing the alias. Keep the existing creation transaction, final-entry collision checks, and exact-entry detach semantics; remove only maps and fields whose sole job is translating between the ids. - -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. - -`agent/created` and `agent/disposed` remain outside this proposal. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. - -## Alternatives considered - -**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. - -## Acceptance criteria - -- Agent create/resume and subagent creation carry one identity; `Session` stores it in one place. -- The existing creation transaction keeps final-entry collision, exact-entry detach, rollback, and quiescence guarantees without adding identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage need no agent/session id translation. -- The config-driven resume-or-create policy is explicit and covered across a durable restart. -- `agent/created`/`agent/disposed` are removed only if a post-change production search finds no listener; otherwise they and their publication semantics stay. -- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. - -## Risks - -This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/packages/subagent/subagent-acp/package.json b/packages/subagent/subagent-acp/package.json index e73d861a79..4c34ebe3fc 100644 --- a/packages/subagent/subagent-acp/package.json +++ b/packages/subagent/subagent-acp/package.json @@ -24,6 +24,7 @@ "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "@deepseek-ai/dsh-subagent-subprocess": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -35,6 +36,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", "@deepseek-ai/dsh-subagent-subprocess": "workspace:^", "@cordisjs/plugin-loader": "^1.0.0-rc.4", diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 1e82ef85b0..1cc220204f 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -23,7 +23,6 @@ */ import { spawn } from 'node:child_process' -import { randomUUID } from 'node:crypto' import { Readable, Writable } from 'node:stream' import { ClientSideConnection, @@ -190,8 +189,6 @@ function toError(value: unknown): Error { * @returns the ready run handle for the child subprocess. */ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpec): Promise { - const id = SessionId(randomUUID()) - if (request.signal.aborted) throw new Error('subagent request was aborted before the ACP child started') // Spawn the child ACP agent. stdin = ACP request channel, stdout = ACP @@ -260,7 +257,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe ), ) - let sessionId: string | undefined + let sessionId: SessionId | undefined // Resolves when a cancel is requested, so `result` can settle `aborted` even // if the child never cooperates with `session/cancel` (it ignores the notify, // or the prompt wedges). The result path races this against the ACP drive: the @@ -309,7 +306,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe clientCapabilities: {}, }) const session = await conn.newSession({ cwd: spec.cwd, mcpServers: [] }) - sessionId = session.sessionId + sessionId = SessionId(session.sessionId) if (flags.cancelled) throw new Error('subagent cancelled before the ACP session started') })(), spawnFailed.then((err): never => { throw err }), @@ -321,6 +318,11 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe if (flags.cancelled) throw new Error('subagent request was aborted before the ACP child started') throw toError(error) } + // The startup race can fulfill only after newSession assigned the id; this + // guard keeps that cross-closure invariant explicit for TypeScript. + /* v8 ignore next */ + if (sessionId === undefined) throw new Error('ACP child published without a session id') + const runId = sessionId const result: Promise = (async (): Promise => { try { @@ -332,7 +334,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe // succeeds, transport/process failure rejects the in-flight prompt RPC. const prompt = async (): Promise => { // The startup phase cannot fulfill without assigning the session id. - const promptResult = await conn.prompt({ sessionId: sessionId as string, prompt: toAcpPrompt(request.prompt) }) + const promptResult = await conn.prompt({ sessionId: runId, prompt: toAcpPrompt(request.prompt) }) return { output: collectOutput(), stopReason: acpStopReason(promptResult.stopReason) } } return await Promise.race([ @@ -366,7 +368,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe let disposal: Promise | undefined return { - id, + id: runId, result, dispose(): Promise { if (disposal !== undefined) return disposal diff --git a/packages/subagent/subagent-acp/tests/mock-acp-server.ts b/packages/subagent/subagent-acp/tests/mock-acp-server.ts index fb200f3505..5145941526 100644 --- a/packages/subagent/subagent-acp/tests/mock-acp-server.ts +++ b/packages/subagent/subagent-acp/tests/mock-acp-server.ts @@ -99,7 +99,7 @@ function makeAgent(conn: AgentSideConnection): Agent { writeFileSync(NEWSESSION_GATE.ready, 'at-newSession') while (!existsSync(NEWSESSION_GATE.go)) await new Promise(r => setTimeout(r, 10)) } - return { sessionId: randomUUID() } + return { sessionId: process.env.MOCK_SESSION_ID ?? randomUUID() } }, authenticate(_params: AuthenticateRequest): Promise { // No auth methods advertised; nothing to do. diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index eed3cfe1ed..115d5c3e97 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -122,8 +122,9 @@ describe('buildChildEnv', () => { describe('dsh-subagent-acp', () => { it('drives a child process to completion and returns its streamed output', async () => { - const ctx = await setup({ MOCK_TEXT: 'hello from acp child', MOCK_STOP: 'end_turn' }) + const ctx = await setup({ MOCK_TEXT: 'hello from acp child', MOCK_STOP: 'end_turn', MOCK_SESSION_ID: 'acp-child-session' }) const run = await ctx.subagents.start('acp', request('do X')) + expect(run.id).toBe('acp-child-session') const result = await run.result expect(result.stopReason).toBe('completed') expect(text(result.output)).toBe('hello from acp child') diff --git a/packages/subagent/subagent/package.json b/packages/subagent/subagent/package.json index eb0dbf8da0..cf1ebf9485 100644 --- a/packages/subagent/subagent/package.json +++ b/packages/subagent/subagent/package.json @@ -25,6 +25,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-scope": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", "cordis": "^4.0.0-rc.6" }, @@ -32,6 +33,7 @@ "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-scope": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.6" } diff --git a/packages/support/subagent-mock/package.json b/packages/support/subagent-mock/package.json index 8980cc35d2..528691daef 100644 --- a/packages/support/subagent-mock/package.json +++ b/packages/support/subagent-mock/package.json @@ -24,6 +24,7 @@ "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "cordis": "^4.0.0-rc.6" }, @@ -33,6 +34,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", "@cordisjs/plugin-loader": "^1.0.0-rc.4", "cordis": "^4.0.0-rc.6" diff --git a/packages/workflow/workflow/package.json b/packages/workflow/workflow/package.json index a6c004d6d0..4d79d672a1 100644 --- a/packages/workflow/workflow/package.json +++ b/packages/workflow/workflow/package.json @@ -25,6 +25,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-brand": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "cordis": "^4.0.0-rc.6" }, "devDependencies": { diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index d02b4a9ca6..6214564eae 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -827,6 +827,9 @@ importers: '@deepseek-ai/dsh-scope': specifier: workspace:^ version: link:../../core/scope + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools @@ -852,6 +855,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session '@deepseek-ai/dsh-subagent': specifier: workspace:^ version: link:../subagent @@ -1085,6 +1091,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session '@deepseek-ai/dsh-subagent': specifier: workspace:^ version: link:../../subagent/subagent From 9ebb40b84b404b3568a53cd6fab1b966e2c82c74 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:28:04 +0800 Subject: [PATCH 035/359] fix: keep SDK subagent notifications local --- .../2026-06-20-unify-agent-and-session-id.md | 2 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 8 +++++++- packages/ui/jsonrpc/tests/server.spec.ts | 16 +++++----------- 4 files changed, 14 insertions(+), 14 deletions(-) diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 10521447e0..bb77717e3b 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -28,7 +28,7 @@ The config-driven path keeps `agents[].id` as a stable configuration label, not - Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. - The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id; the ACP bridge verifies exact `Agent` ownership from the forward session map; and JSON-RPC caches only disposable-child parent lineage. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id; the ACP bridge verifies exact `Agent` ownership from the forward session map; and JSON-RPC caches only local disposable-child parent lineage while leaving remote runs outside its local-session notification pair. - The config-driven resume-or-create policy is explicit and covered across a durable restart. - A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. - Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 933023a2d9..2324227ff7 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. Runs from remote providers are not reported through this local-session notification pair because they create no local `session/created`/`subagent.started` edge. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index cfa083c394..3c803a6c8c 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -104,8 +104,14 @@ export class HarnessSdkServer { })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { const agent = this.ctx.agents.get(info.id) - const parentSessionId = this.subagentParents.get(info.id) ?? agent?.session.header.parentSession + const cachedParentSessionId = this.subagentParents.get(info.id) this.subagentParents.delete(info.id) + // This protocol reports LOCAL child sessions, paired with the + // session/created-driven subagent.started notification above. A remote + // provider may use a real remote SessionId for its run, but that session + // does not exist in this harness and therefore has no paired start event. + if (cachedParentSessionId === undefined && agent === undefined) return + const parentSessionId = cachedParentSessionId ?? agent?.session.header.parentSession this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 433119e046..e7f591b88f 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -303,7 +303,7 @@ describe('HarnessSdkServer', () => { } }) - it('falls back to live lineage and treats the shared id as the child session id', async () => { + it('falls back to live lineage and ignores runs without a local child session', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) let parentHandle: AgentHandle | undefined @@ -367,16 +367,10 @@ describe('HarnessSdkServer', () => { stopReason: 'error', }, }) - expect(transport.notifications).toContainEqual({ - method: 'subagent.finished', - params: { - provider: 'fork', - agentId: 'missing-child-agent', - childSessionId: 'missing-child-agent', - status: 'error', - stopReason: 'error', - }, - }) + expect(transport.notifications.some(n => + n.method === 'subagent.finished' + && n.params?.agentId === 'missing-child-agent', + )).toBe(false) await server.shutdown() } finally { From 225796c90dc5a6ea9b4afa2a9f4081f9d48606ae Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:32:35 +0800 Subject: [PATCH 036/359] refactor: hide the concrete agent loop --- docs/architecture.md | 2 +- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 26 ++++----- docs/cordis-catalog/services.md | 8 ++- docs/core-data-structures/core.md | 2 +- docs/event-producer-consumer.md | 26 ++++----- .../2026-06-21-subagent-capability-seam.md | 2 +- examples/coding-agent/tests/code-mode.e2e.ts | 6 +- examples/coding-agent/tests/harness.ts | 6 +- examples/coding-agent/tests/resume.e2e.ts | 5 +- examples/cordis-agent/tests/harness.ts | 6 +- .../bash/tool-bash/tests/integration.spec.ts | 8 +-- .../tests/compact-loop-repro.spec.ts | 6 +- .../cordis/tool-cordis/src/api-catalog.ts | 4 +- .../tool-cordis/tests/integration.spec.ts | 6 +- packages/core/README.md | 2 +- packages/core/agent-loop/README.md | 10 ++-- packages/core/agent-loop/src/index.ts | 7 +-- packages/core/agent-loop/tests/agent.spec.ts | 42 +++++++------- packages/core/agent-loop/tests/cancel.spec.ts | 22 +++++--- .../tests/config-session-id.spec.ts | 16 +++--- .../agent-loop/tests/coverage-edges.spec.ts | 16 ++++-- .../agent-loop/tests/interception.spec.ts | 10 ++-- packages/core/agent-loop/tests/loop.spec.ts | 22 +++++--- .../core/agent-loop/tests/properties.spec.ts | 12 ++-- .../tests/request-reconstruction.spec.ts | 10 ++-- packages/core/agent-loop/tests/resume.spec.ts | 24 ++++---- .../agent-loop/tests/review-fixes.spec.ts | 56 ++++++++++--------- .../agent-loop/tests/scope-lifecycle.spec.ts | 8 +-- .../core/agent-loop/tests/tool-order.spec.ts | 6 +- .../core/agent-loop/tests/turn-stop.spec.ts | 6 +- packages/core/agent/src/types.ts | 5 +- .../tests/repeat-tool-guard.spec.ts | 12 ++-- .../hooks/hooks-claude/tests/bridge.spec.ts | 8 +-- .../hooks/hooks-claude/tests/coverage.spec.ts | 14 ++--- .../hooks/hooks-codex/tests/bridge.spec.ts | 8 +-- .../hooks/hooks-codex/tests/coverage.spec.ts | 10 ++-- .../todo/tool-todo/tests/integration.spec.ts | 6 +- packages/ui/acp/README.md | 2 +- packages/ui/acp/src/index.ts | 2 +- 40 files changed, 234 insertions(+), 217 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index a1f0cae9a8..272191c9c6 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -17,7 +17,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service | `ctx.systemPrompt` | `dsh-system-prompt` | ordered prompt sections, tool schemas, and prompt variables | | `ctx.tools` | `dsh-tools` | tool registry and [execution pipeline](tool-execution-pipeline.md) | | `ctx.agents` | `dsh-agent` | live agent registry, public `Agent` handle, `agent/*` events | -| `ctx.agentLoop` | `dsh-agent-loop` | shipped `ReactLoopAgent` driver | +| `ctx.agentLoop` | `dsh-agent-loop` | shipped concrete `Agent` driver | ### Capability Services diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 4ae020f0be..20d90d1e8b 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -129,7 +129,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:324`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:323`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index a5e018079a..32d697f1eb 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -23,7 +23,7 @@ An agent's fully composed scoped world was published in the AgentRegistry. Its s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:304`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:303`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -35,7 +35,7 @@ An agent was removed from the registry. The concrete AgentLoop lifecycle emits t Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:319`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:318`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:593`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:592`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -61,7 +61,7 @@ Serial (awaited in registration order), not a waterfall: a listener mutates the Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:426`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:425`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -73,7 +73,7 @@ Waterfall: decide what happens to ONE drained queued message before it becomes a Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:444`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:443`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -85,7 +85,7 @@ A message entered the agent's inbox (queued or steering). Content and the resolv Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:348`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:347`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -97,7 +97,7 @@ Waterfall: shape the step's call configuration — model switching, sampling ove Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:473`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:472`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -113,7 +113,7 @@ The seed is a frozen empty list; a contributing listener returns a NEW array — Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:525`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:524`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -125,7 +125,7 @@ The agent's session lifecycle began, fired once before its first turn. `source` Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:369`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:368`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -137,7 +137,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). Drive lifecycle Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:333`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:332`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -149,7 +149,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:540`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:539`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -161,7 +161,7 @@ Waterfall: override the turn-continuation decision via a typed ContinuationDecis Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:558`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:557`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -173,7 +173,7 @@ Serial terminal-stop checkpoint after the ordinary `agent/turn-continuation` wat Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:575`](../../packages/core/agent/src/types.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 4d162a55f5..89a8dc4edb 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -11,15 +11,17 @@ The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary ## `ctx.agentLoop` — `AgentLoop` -Concrete ReactLoopAgent factory and driver service. +Concrete agent factory and driver service. ```ts cordis-catalog -create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent +create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): Agent async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:337`](../../packages/core/agent-loop/src/index.ts) +Types: [Agent](../core-data-structures/core.md) + +Source: [`packages/core/agent-loop/src/index.ts:336`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index c6b74ed3c0..897b04240b 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -248,7 +248,7 @@ The fourteen event variants (`turn/start`, `turn/end`, `step/start`, `step/end`, ## The agent handle -`Agent` is the surface every plugin (UI, hooks, orchestrators) programs against. The concrete implementation is `ReactLoopAgent` in dsh-agent-loop; nothing outside the loop depends on the implementation. +`Agent` is the surface every plugin (UI, hooks, orchestrators) programs against. The concrete implementation is package-internal to dsh-agent-loop; nothing outside the loop depends on it. Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 80389608cc..ba0d9722b2 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,19 +7,19 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:444`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:348`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:473`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:525`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:540`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:558`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:576`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:303`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:318`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:592`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:425`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:443`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:347`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:472`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:524`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:368`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:332`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:539`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:557`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:575`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:70`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:123`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:138`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | diff --git a/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md b/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md index 652eac5522..3c42e83691 100644 --- a/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md @@ -10,7 +10,7 @@ The harness has a long-deferred seam for **subagents** — an agent delegating w The distinctive requirement — the one that shapes the whole design — is that **multiple subagent implementations must coexist at runtime**. A parent may want a cheap in-process child for a scoped subtask AND an isolated out-of-process child (over ACP) in the same session. The transports we foresee: -- **in-process** — a child `ReactLoopAgent` on the same `Context` (the cheapest, and nearly free given the existing agent factory); +- **in-process** — a child concrete `Agent` on the same `Context` (the cheapest, and nearly free given the existing agent factory); - **ACP** — act as an ACP *client* driving another agent process (which can be another instance of ourselves); - later: **A2A**, the **Codex app-server**, and the **Claude Code Agent SDK** — each the same out-of-process "start a child, prompt it, stream updates, cancel" shape as the ACP backend. diff --git a/examples/coding-agent/tests/code-mode.e2e.ts b/examples/coding-agent/tests/code-mode.e2e.ts index 22446f0dc3..176b2898d6 100644 --- a/examples/coding-agent/tests/code-mode.e2e.ts +++ b/examples/coding-agent/tests/code-mode.e2e.ts @@ -8,9 +8,9 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -58,7 +58,7 @@ async function codeModeHarness(cwd: string): Promise { return harness } -function waitForIdle(harness: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(harness: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = harness.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/examples/coding-agent/tests/harness.ts b/examples/coding-agent/tests/harness.ts index dd0bc42a1b..6535e30ac3 100644 --- a/examples/coding-agent/tests/harness.ts +++ b/examples/coding-agent/tests/harness.ts @@ -4,8 +4,8 @@ import SessionStore from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' @@ -70,7 +70,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio return ctx } -export function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +export function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/examples/coding-agent/tests/resume.e2e.ts b/examples/coding-agent/tests/resume.e2e.ts index 48e135ad92..486e32608c 100644 --- a/examples/coding-agent/tests/resume.e2e.ts +++ b/examples/coding-agent/tests/resume.e2e.ts @@ -3,7 +3,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import type { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { SessionId } from '@deepseek-ai/dsh-session' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' @@ -41,7 +40,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses const first = (await ctx.agents.create({ sessionId: SESSION_ID, agentOptions: { model: 'deepseek-v4-flash' }, - })).agent as ReactLoopAgent + })).agent first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }]) await waitForIdle(ctx, first) await ctx.fiber.dispose() @@ -54,7 +53,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses const resumed = (await ctx.agents.resume({ resumeSessionId: SESSION_ID, agentOptions: { model: 'deepseek-v4-flash' }, - })).agent as ReactLoopAgent + })).agent expect(resumed.session.id).toBe(SESSION_ID) // The prior user turn is in the rehydrated log before the model is asked. expect(JSON.stringify(resumed.session.deriveMessages())).toContain(SECRET) diff --git a/examples/cordis-agent/tests/harness.ts b/examples/cordis-agent/tests/harness.ts index 78e5b0bb93..c9ccd59767 100644 --- a/examples/cordis-agent/tests/harness.ts +++ b/examples/cordis-agent/tests/harness.ts @@ -3,8 +3,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import * as ToolCordis from '@deepseek-ai/dsh-tool-cordis' @@ -34,7 +34,7 @@ export async function cordisHarness(): Promise { return ctx } -export function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +export function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index 3ab3ae6628..b8275fedba 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -5,9 +5,9 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import { BashTaskId } from '@deepseek-ai/dsh-bash' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' @@ -32,7 +32,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -43,7 +43,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function events(agent: ReactLoopAgent): SessionEvent[] { +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index 52a2ecd134..c9d9e34b26 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -7,9 +7,9 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import { isToolPairingBalanced } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' import type { SurfaceEvent } from '@deepseek-ai/dsh-session' @@ -105,7 +105,7 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr return { ctx, compact } } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 5721bd97d9..23a8c8e1d0 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -54,9 +54,9 @@ export interface TypeApiEntry { export const SERVICE_API: readonly ServiceApiEntry[] = [ { key: 'agentLoop', - summary: 'Concrete ReactLoopAgent factory and driver service.', + summary: 'Concrete agent factory and driver service.', methods: [ - 'create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent', + 'create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): Agent', 'async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise', 'async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise', ], diff --git a/packages/cordis/tool-cordis/tests/integration.spec.ts b/packages/cordis/tool-cordis/tests/integration.spec.ts index 0d4c6c5c18..25adece9bc 100644 --- a/packages/cordis/tool-cordis/tests/integration.spec.ts +++ b/packages/cordis/tool-cordis/tests/integration.spec.ts @@ -4,9 +4,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as ToolCordis from '../src/index.ts' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' import { REVERSE_TOOL_CODE } from './helpers.ts' @@ -32,7 +32,7 @@ async function harness(adapter: MockAdapter): Promise { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/core/README.md b/packages/core/README.md index b132b04d49..d822627136 100644 --- a/packages/core/README.md +++ b/packages/core/README.md @@ -9,7 +9,7 @@ The session log, system-prompt assembly, tool registry, agent vocabulary, and co | `system-prompt/` | Prompt-section + tool-schema assembly registry | `ctx.systemPrompt` | | `tools/` | Scoped tool registry + pre-policy, guards, around-dispatch, post-policy, and final-result observation | `ctx.tools` | | `agent/` | Agent interface, registry, `agent/*` event vocabulary | `ctx.agents` | -| `agent-loop/` | The concrete loop plugin: `ReactLoopAgent` + the loop driver | `ctx.agentLoop` | +| `agent-loop/` | The concrete `Agent` plugin and loop driver | `ctx.agentLoop` | | `agent-core/` | Bundle plugin: the default executor-less/UI-less spine as code | (loads the spine) | `scope/` is the one non-service package here: a dependency-free library (`createScope`/`scopeOf`/`scopeTarget`) the registries and the loop build per-agent scoping on — it sits below `session/` and `system-prompt/` in the module graph precisely so they can consume it without a cycle. diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index f40577bb95..f5b25c0e25 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -1,6 +1,6 @@ # dsh-agent-loop -THE concrete agent plugin: `ReactLoopAgent` and the loop driver. Implements the `Agent` interface and drives the session/turn/step lifecycle. +THE concrete agent plugin and loop driver. Its package-internal implementation satisfies the `Agent` interface and drives the session/turn/step lifecycle. This is the only package in the harness that contains concrete loop logic. Everything else is an abstract service or a plugin against extension seams — new behavior goes into plugins, not here. @@ -14,7 +14,7 @@ The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createA Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and mints `${label}-session-` before calling this boundary; `resumeSessionId` instead loads and registers the exact persisted id. This keeps fresh restarts collision-free without retaining a second live routing identity. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): Agent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and mints `${label}-session-` before calling this boundary; `resumeSessionId` instead loads and registers the exact persisted id. This keeps fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): @@ -42,11 +42,9 @@ interface Config { Agents listed in config are auto-created at startup. `cwd` applies only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. -### Exported concrete class +### Internal concrete driver -- `ReactLoopAgent` — the concrete `Agent` implementation. Its inbox is a JavaScript native-private field, and one prepared session can be claimed by only one concrete driver. Everything observable happens through session events and the `agent/*` event taxonomy. - -`Inbox`, `runLoop`, and the instance-bound publication/start controls are package-internal. The package root does not export them, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than constructing or starting the driver internals. `ReactLoopAgent.send()` and running `steer()` materialize content plus resolved source once as detached, deeply frozen lossless JSON, then share that accepted record between `agent/queued` and the inbox; malformed data throws before either boundary. +The concrete `Agent` class, its `Inbox`, `runLoop`, and instance-bound publication/start controls are package-internal. The package root exports only the plugin/service/config contract, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than naming, constructing, or starting driver internals. The concrete `send()` and running `steer()` materialize content plus resolved source once as detached, deeply frozen lossless JSON, then share that accepted record between `agent/queued` and the inbox; malformed data throws before either boundary. One prepared session can be claimed by only one concrete driver, and everything observable happens through session events and the `agent/*` event taxonomy. ### Loop lifecycle (`loop.ts`) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 33276c01f8..c9c97fb206 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -12,6 +12,7 @@ import { createScope } from '@deepseek-ai/dsh-scope' import type { Scope } from '@deepseek-ai/dsh-scope' import { agentEvents } from '@deepseek-ai/dsh-agent' import type { + Agent, AgentFactory, AgentHandle, AgentOptions, @@ -32,8 +33,6 @@ import { } from './agent.ts' import type { PreparedReactLoopAgent } from './agent.ts' -export { ReactLoopAgent } from './agent.ts' - /** Fiber states that cannot own or serve a new lifecycle. */ const INACTIVE_STATES: ReadonlySet = new Set([ FiberState.UNLOADING, @@ -333,7 +332,7 @@ export interface Config { })[] } -/** Concrete ReactLoopAgent factory and driver service. */ +/** Concrete agent factory and driver service. */ export class AgentLoop extends Service implements AgentFactory { static inject = ['agents', 'sessions', 'llm', 'tools', 'systemPrompt'] @@ -389,7 +388,7 @@ export class AgentLoop extends Service implements AgentFactory { * @param meta - optional fresh-session workspace metadata. * @returns the published running agent. */ - create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent { + create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): Agent { const loopCtx = this.runtime.ctx const transaction = new AgentCreationTransaction(loopCtx, this.ctx, this.ownership, id) try { diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 56d6489fbe..7969d18200 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -4,11 +4,15 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' -import { bindReactLoopAgentContext, prepareReactLoopAgent } from '../src/agent.ts' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' +import { bindReactLoopAgentContext, prepareReactLoopAgent, type ReactLoopAgent } from '../src/agent.ts' import { MockAdapter, textResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + async function harness(adapter: MockAdapter) { const ctx = new Context() await ctx.plugin(LlmService) @@ -21,7 +25,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -32,7 +36,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function waitForStatus(ctx: Context, agent: ReactLoopAgent, expected: ReactLoopAgent['status']): Promise { +function waitForStatus(ctx: Context, agent: Agent, expected: Agent['status']): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === expected) { @@ -43,11 +47,11 @@ function waitForStatus(ctx: Context, agent: ReactLoopAgent, expected: ReactLoopA }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } -describe('ReactLoopAgent', () => { +describe('Agent', () => { it('rejects access before context binding and a second driver for one session', async () => { const ctx = new Context() await ctx.plugin(SessionStore) @@ -70,7 +74,7 @@ describe('ReactLoopAgent', () => { expect(agent.options).toBe(options) expect(agent.id).toBe('owned-bindings') expect(agent.session.id).toBe(agent.id) - expect(() => { bindReactLoopAgentContext(agent, new Context()) }).toThrow(/context is already bound/) + expect(() => { bindReactLoopAgentContext(agent as ReactLoopAgent, new Context()) }).toThrow(/context is already bound/) await ctx.fiber.dispose() }) @@ -78,14 +82,14 @@ describe('ReactLoopAgent', () => { it('send() throws after disposal', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done + await driverDone(agent) expect(() => { agent.send([{ type: 'text', text: 'too late' }]) }).toThrow('disposed') }) @@ -93,14 +97,14 @@ describe('ReactLoopAgent', () => { it('steer() throws after disposal', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done + await driverDone(agent) expect(() => { agent.steer([{ type: 'text', text: 'too late' }]) }).toThrow('disposed') }) @@ -108,14 +112,14 @@ describe('ReactLoopAgent', () => { it('inject() throws after disposal', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done + await driverDone(agent) expect(() => { agent.inject([{ type: 'text', text: 'too late' }]) }).toThrow('disposed') }) @@ -251,7 +255,7 @@ describe('ReactLoopAgent', () => { }) it('disposer is idempotent (double-stop)', async () => { - // Create a bare ReactLoopAgent and start it through the package-internal + // Create a bare Agent and start it through the package-internal // test seam. Then call its disposer twice — the second call hits the // early-return branch. const ctx = new Context() @@ -367,7 +371,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() subscribed while running resolves via done when the agent is then disposed', async () => { // Covers the waiter's disposed arm: whenIdle() queues an internal waiter // while running (not the fast path), then the disposer settles it and chains - // `done` (loop exit), not an eager resolve. A bare ReactLoopAgent + direct + // `done` (loop exit), not an eager resolve. A bare Agent + direct // internal driver disposer keeps the emit synchronous. const ctx = new Context() await ctx.plugin(LlmService) @@ -401,7 +405,7 @@ describe('ReactLoopAgent', () => { // it. Regression for the round-3 whenIdle finding. const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -422,7 +426,7 @@ describe('ReactLoopAgent', () => { // only after `done` — i.e. the loop has actually exited. const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -430,7 +434,7 @@ describe('ReactLoopAgent', () => { await new Promise(r => setTimeout(r, 30)) let doneResolved = false - void agent.done.then(() => { doneResolved = true }) + void driverDone(agent).then(() => { doneResolved = true }) await fiber.dispose() // sets status disposed, aborts, drains the loop expect(agent.status).toBe('disposed') diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index 82b1f6c58c..d88d58a340 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -16,11 +16,15 @@ import LlmService, { type Message } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + async function harness(adapter: MockAdapter) { const ctx = new Context() await ctx.plugin(LlmService) @@ -33,12 +37,12 @@ async function harness(adapter: MockAdapter) { return ctx } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } /** Resolve on the agent's next idle transition (event-based, not status poll). */ -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } @@ -47,7 +51,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { } /** All user-message texts recorded in the log (to assert what actually ran). */ -function userTexts(agent: ReactLoopAgent): string[] { +function userTexts(agent: Agent): string[] { return agent.session.events .filter(e => e.type === 'user/message') .flatMap(e => e.type === 'user/message' ? e.data.content : []) @@ -207,7 +211,7 @@ describe('Agent.cancel()', () => { sessionId: SessionId('dispose-prefix-session'), agentOptions: { model: 'mock' }, }) - const agent = handle.agent as ReactLoopAgent + const agent = handle.agent let disposalDone: Promise | undefined let streamed = false @@ -220,7 +224,7 @@ describe('Agent.cancel()', () => { send(agent, 'go') await new Promise(resolve => setTimeout(resolve, 0)) await disposalDone - await agent.done + await driverDone(agent) // No step opened, no model call ran, and the turn closed disposed. expect(streamed).toBe(false) @@ -337,7 +341,7 @@ describe('Agent.cancel()', () => { sessionId: SessionId('dispose-step-start-session'), agentOptions: { model: 'mock' }, }) - const agent = handle.agent as ReactLoopAgent + const agent = handle.agent let disposalDone: Promise | undefined let streamed = false @@ -348,7 +352,7 @@ describe('Agent.cancel()', () => { send(agent, 'go') await disposalDone - await agent.done + await driverDone(agent) expect(streamed).toBe(false) expect(adapter.requests).toHaveLength(0) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 134ea68c32..428581bb58 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -7,16 +7,16 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' const dirs: string[] = [] afterEach(async () => { for (const d of dirs.splice(0)) await rm(d, { recursive: true, force: true }) }) -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } @@ -57,7 +57,7 @@ describe('config-driven session id', () => { await ctx1.plugin(AgentLoop, { agents: [{ id: 'cfg', model: 'mock' }] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg')])) - const a1 = ctx1.agents.list()[0] as ReactLoopAgent + const a1 = ctx1.agents.list()[0] as Agent expect(a1.id).toBe(a1.session.id) expect(a1.session.id).toMatch(idPattern) expect(ctx1.agents.get(SessionId('cfg'))).toBeUndefined() @@ -76,7 +76,7 @@ describe('config-driven session id', () => { await ctx2.plugin(AgentLoop, { agents: [{ id: 'cfg', model: 'mock' }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg2')])) - const a2 = ctx2.agents.list()[0] as ReactLoopAgent + const a2 = ctx2.agents.list()[0] as Agent expect(a2.id).toBe(a2.session.id) expect(a2.session.id).toMatch(idPattern) expect(a2.session.id).not.toBe(a1.session.id) @@ -100,7 +100,7 @@ describe('config-driven session id', () => { await ctx1.plugin(AgentLoop, { agents: [] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first')])) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('sticky-1') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('sticky-1') })).agent a1.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -119,10 +119,10 @@ describe('config-driven session id', () => { ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')])) // The deferred resume runs on a microtask after the backend is available. - let resumed: ReactLoopAgent | undefined + let resumed: Agent | undefined for (let i = 0; i < 50 && !resumed; i++) { await new Promise(r => setTimeout(r, 5)) - resumed = ctx2.agents.get(SessionId('sticky-1')) as ReactLoopAgent | undefined + resumed = ctx2.agents.get(SessionId('sticky-1')) } expect(resumed).toBeDefined() // The live session id IS the resumed id (NOT a fresh ${id}-session-), diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index 4e82e398f1..708cff504b 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -5,11 +5,15 @@ import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + async function harness(adapter: MockAdapter) { const ctx = new Context() await ctx.plugin(LlmService) @@ -22,7 +26,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -33,7 +37,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } @@ -213,7 +217,7 @@ describe('disposed vs aborted branching', () => { it('handles dispose during model streaming producing reason "disposed"', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -224,7 +228,7 @@ describe('disposed vs aborted branching', () => { send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() // dispose during hang - await agent.done + await driverDone(agent) // The review-fixes test for 'HIGH: disposed status' already covers // this assertion path. The reason is 'disposed' because isDisposed() is diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index 8c95be0d82..bbae57d7f9 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -4,9 +4,9 @@ import LlmService, { CallId, type Message } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent, type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' /** @@ -30,7 +30,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -41,11 +41,11 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } -function events(agent: ReactLoopAgent): SessionEvent[] { +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index c4e49e0fa5..49a7c6a328 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -4,11 +4,15 @@ import LlmService, { CallId, StreamChunk } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + async function harness(adapter: MockAdapter, persona = '') { const ctx = new Context() await ctx.plugin(LlmService) @@ -26,7 +30,7 @@ async function harness(adapter: MockAdapter, persona = '') { * invoke this right after send(), when the loop hasn't woken yet (status is * still 'idle' synchronously), so polling the current status would lie. */ -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -37,7 +41,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } @@ -175,7 +179,7 @@ describe('agent loop', () => { agentOptions: { model: 'mock' }, }) - const agent = handle.agent as ReactLoopAgent + const agent = handle.agent send(agent, 'hi') await waitForIdle(ctx, agent) @@ -911,7 +915,7 @@ describe('agent loop', () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -922,7 +926,7 @@ describe('agent loop', () => { expect(agent.status).toBe('running') await fiber.dispose() - await agent.done + await driverDone(agent) expect(agent.status).toBe('disposed') expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() @@ -942,7 +946,7 @@ describe('agent loop', () => { }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agents.list()[0]! as ReactLoopAgent + const agent = ctx.agents.list()[0]! expect(agent).toBeDefined() expect(agent.id).toBe(agent.session.id) expect(agent.id).toMatch(/^config-agent-session-/) @@ -965,7 +969,7 @@ describe('agent loop', () => { agents: [{ id: 'config-agent', model: 'mock', cwd: '/work/project' }], }) - const agent = ctx.agents.list()[0]! as ReactLoopAgent + const agent = ctx.agents.list()[0]! expect(agent.session.header.cwd).toBe('/work/project') }) diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index b3653d6540..a4539587d5 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -17,9 +17,9 @@ import { LlmAdapter } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import fc from 'fast-check' /** A never-exhausting adapter: every model call returns the same short reply. */ @@ -48,7 +48,7 @@ async function harness() { } /** Resolve on the agent's next transition to idle (event-based, not polled). */ -function nextIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function nextIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -61,7 +61,7 @@ function nextIdle(ctx: Context, agent: ReactLoopAgent): Promise { /** Record every status transition for the legal-machine assertion. Returns * the seen list plus a disposer for the listener (per the registry convention). */ -function recordStatus(ctx: Context, agent: ReactLoopAgent): { seen: string[]; dispose: () => void } { +function recordStatus(ctx: Context, agent: Agent): { seen: string[]; dispose: () => void } { const seen: string[] = [] const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent) seen.push(status) @@ -69,13 +69,13 @@ function recordStatus(ctx: Context, agent: ReactLoopAgent): { seen: string[]; di return { seen, dispose } } -function userMessageTexts(agent: ReactLoopAgent): string[] { +function userMessageTexts(agent: Agent): string[] { return agent.session.events .filter(e => e.type === 'user/message') .map(e => (e.data as { content: { type: string; text?: string }[] }).content.map(b => b.text ?? '').join('')) } -function turnNumbers(agent: ReactLoopAgent): number[] { +function turnNumbers(agent: Agent): number[] { return agent.session.events .filter(e => e.type === 'turn/start') .map(e => (e.data as { turn: number }).turn) diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index 202a8f6795..03b9a058ea 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -15,9 +15,9 @@ import type { GenerateOptions } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' async function harness(adapter: MockAdapter, persona = 'stable base') { @@ -32,7 +32,7 @@ async function harness(adapter: MockAdapter, persona = 'stable base') { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -43,7 +43,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } @@ -229,7 +229,7 @@ describe('request stability across the loop', () => { seed: [...agent.session.events], agentOptions: { model: 'mock' }, }) - const agent2 = handle.agent as ReactLoopAgent + const agent2 = handle.agent send(agent2, 'second') await waitForIdle(ctx2, agent2) diff --git a/packages/core/agent-loop/tests/resume.spec.ts b/packages/core/agent-loop/tests/resume.spec.ts index f5809575ab..630331c39c 100644 --- a/packages/core/agent-loop/tests/resume.spec.ts +++ b/packages/core/agent-loop/tests/resume.spec.ts @@ -8,10 +8,10 @@ import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' const dirs: string[] = [] @@ -51,7 +51,7 @@ async function persistSession(sessionId: SessionId): Promise { return root } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } @@ -124,7 +124,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // Lifecycle 1: create a no-cwd session and run a turn. const adapter1 = new MockAdapter([textResponse('a')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('nocwd-sess') })).agent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -140,7 +140,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('nocwd-sess') })).agent expect(a2.session.header.cwd).toBeUndefined() await ctx2.fiber.dispose() }) @@ -151,7 +151,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { const { ctx: ctx1, root } = await persistentHarness(adapter1) const sources1: string[] = [] ctx1.on('agent/session-start', (_agent, source) => void sources1.push(source)) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('start-sess') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('start-sess') })).agent expect(sources1).toEqual(['startup']) a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) @@ -443,7 +443,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('forked-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('forked-sess') })).agent expect(a2.session.header.parentSession).toBe('parent-sess') expect(a2.session.header.cwd).toBe('/w') expect(a2.session.header.seedLength).toBe(seed.length) @@ -457,7 +457,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // disk, since a crash before the next turn would otherwise lose it. const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) @@ -482,7 +482,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // drop it on reload (the bug this guards). const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) @@ -500,7 +500,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('inject-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('inject-sess') })).agent const flat = JSON.stringify(a2.session.deriveMessages()) expect(flat).toContain('background task 42 finished') await ctx2.fiber.dispose() @@ -510,7 +510,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // Lifecycle 1: run one full turn, persisting it. const adapter1 = new MockAdapter([textResponse('first answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent a1.send([{ type: 'text', text: 'first question' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) const events1 = [...a1.session.events] @@ -530,7 +530,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('sess-resume') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('sess-resume') })).agent // The resumed session carries the prior history… expect(a2.session.id).toBe('sess-resume') expect(a2.session.events.length).toBe(events1.length) diff --git a/packages/core/agent-loop/tests/review-fixes.spec.ts b/packages/core/agent-loop/tests/review-fixes.spec.ts index 942199e9eb..2664e38c04 100644 --- a/packages/core/agent-loop/tests/review-fixes.spec.ts +++ b/packages/core/agent-loop/tests/review-fixes.spec.ts @@ -4,13 +4,17 @@ import LlmService, { CallId, ContentBlock, MessageSource, StreamChunk } from '@d import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { type ContinuationDecision } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent, type ContinuationDecision } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { prepareReactLoopAgent } from '../src/agent.ts' import * as Invariants from '@deepseek-ai/dsh-invariants' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + /** Regression tests for agent-loop boundary, identity, and lifecycle contracts. */ async function harness(adapter: MockAdapter) { @@ -25,7 +29,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -36,7 +40,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } @@ -324,7 +328,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -337,7 +341,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done + await driverDone(agent) expect(statuses).toEqual(['running', 'disposed']) expect(reasons).toEqual([{ kind: 'disposed' }]) @@ -347,7 +351,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -359,7 +363,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done // must not hang + await driverDone(agent) // must not hang expect(agent.status).toBe('disposed') expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() // unregistered despite the throw @@ -697,7 +701,7 @@ describe('turn and step boundary recovery', () => { } /** Count turn/step boundary events for balance assertions. */ - function boundaryCounts(agent: ReactLoopAgent) { + function boundaryCounts(agent: Agent) { const e = [...agent.session.events] return { turnStart: e.filter(x => x.type === 'turn/start').length, @@ -871,7 +875,7 @@ describe('turn and step boundary recovery', () => { // balanced with reason disposed (no error event for a disposal). const adapter = new MockAdapter(['hang']) const ctx = await balancedHarness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-dispose'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -882,7 +886,7 @@ describe('turn and step boundary recovery', () => { send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() // dispose during the hanging step - await agent.done + await driverDone(agent) const e = [...agent.session.events] const turnStarts = e.filter(x => x.type === 'turn/start').length @@ -900,7 +904,7 @@ describe('turn and step boundary recovery', () => { // and must preserve reason=disposed rather than rewrite it as a plugin error. const adapter = new MockAdapter([textResponse('never reached')]) const ctx = await balancedHarness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-prestep-dispose-throw'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -919,7 +923,7 @@ describe('turn and step boundary recovery', () => { ctx.on('agent/error', (_a, _t, _s, error) => void errorEmits.push(error)) send(agent, 'go') - await agent.done + await driverDone(agent) const e = [...agent.session.events] // Balanced: one turn/start, one turn/end carrying disposed (NOT error). @@ -1148,7 +1152,7 @@ describe('disposal and cancellation during pre-step assembly', () => { // calls stop() synchronously, setting status=disposed), then release the // block. The loop must check isDisposed() after assembly and end the turn // `disposed` — no LLM call. Don't await fiber.dispose() before releasing - // the blocker: the dispose chain awaits agent.done, which hangs until the + // the blocker: the dispose chain awaits driverDone(agent), which hangs until the // loop unblocks. const adapter = new MockAdapter(['hang']) let releaseAssemble!: () => void @@ -1170,7 +1174,7 @@ describe('disposal and cancellation during pre-step assembly', () => { return next() }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-dispose-assemble'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1183,15 +1187,15 @@ describe('disposal and cancellation during pre-step assembly', () => { await new Promise(r => setTimeout(r, 50)) // Start disposal — stop() sets status=disposed synchronously, then the - // disposer's await agent.done hangs because the loop is blocked in the + // disposer's await driverDone(agent) hangs because the loop is blocked in the // waterfall. Do NOT await yet; release the blocker first. const disposalDone = fiber.dispose() // Now release the blocked waterfall — the loop unblocks, checks - // isDisposed(), and exits, which resolves agent.done and disposalDone. + // isDisposed(), and exits, which resolves driverDone(agent) and disposalDone. releaseAssemble() await disposalDone - await agent.done + await driverDone(agent) unlisten() const e = [...agent.session.events] @@ -1226,7 +1230,7 @@ describe('disposal and cancellation during pre-step assembly', () => { return next() }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-cancel-assemble'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1241,7 +1245,7 @@ describe('disposal and cancellation during pre-step assembly', () => { releaseAssemble() await waitForIdle(ctx, agent) await fiber.dispose() - await agent.done + await driverDone(agent) unlisten() const e = [...agent.session.events] @@ -1281,7 +1285,7 @@ describe('disposal and cancellation during pre-step assembly', () => { await blocker }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-dispose-prestep'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1296,7 +1300,7 @@ describe('disposal and cancellation during pre-step assembly', () => { const disposalDone = fiber.dispose() releasePreStep() await disposalDone - await agent.done + await driverDone(agent) // After the pre-step seam finishes, the post-seam cancel/dispose check // catches disposal. The step was never opened, no LLM call was made. @@ -1333,7 +1337,7 @@ describe('disposal and cancellation during pre-step assembly', () => { await blocker }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-cancel-prestep'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1348,7 +1352,7 @@ describe('disposal and cancellation during pre-step assembly', () => { releasePreStep() await waitForIdle(ctx, agent) await fiber.dispose() - await agent.done + await driverDone(agent) const e = [...agent.session.events] expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1) @@ -1383,7 +1387,7 @@ describe('disposal and cancellation during pre-step assembly', () => { return next() }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-dispose-no-leak'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1394,7 +1398,7 @@ describe('disposal and cancellation during pre-step assembly', () => { const disposalDone = fiber.dispose() releaseAssemble() await disposalDone - await agent.done + await driverDone(agent) const e = [...agent.session.events] expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1) diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index c68d96e525..57dae254c8 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -8,7 +8,7 @@ import AgentRegistry, { agentEvents, assembleContextFor } from '@deepseek-ai/dsh import type { Agent } from '@deepseek-ai/dsh-agent' import { scopeOf } from '@deepseek-ai/dsh-scope' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -28,7 +28,7 @@ async function harness(adapter: MockAdapter = new MockAdapter([textResponse('ok' return (await harnessWithLoop(adapter)).ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -718,7 +718,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let ownerCtx!: Context let creating!: ReturnType - let announced!: ReactLoopAgent + let announced!: Agent const statuses: string[] = [] let scopeDisposed = false let observerSawLive = false @@ -727,7 +727,7 @@ describe('agent scope lifecycle', () => { }) ctx.on('agent/session-start', (agent) => { if (agent.id !== SessionId('session-start-dispose-s')) return - announced = agent as ReactLoopAgent + announced = agent disposeCurrentLifecycle(ownerCtx) }) ctx.on('agent/session-start', (agent) => { diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index 1085f01a4c..3b7df63965 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -14,9 +14,9 @@ import SessionStore, { SessionId, foldRequestHeader } from '@deepseek-ai/dsh-ses import SystemPrompt, { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['toolOrder']) { @@ -31,7 +31,7 @@ async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['too return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/core/agent-loop/tests/turn-stop.spec.ts b/packages/core/agent-loop/tests/turn-stop.spec.ts index c7823a2aa5..90bc0f9558 100644 --- a/packages/core/agent-loop/tests/turn-stop.spec.ts +++ b/packages/core/agent-loop/tests/turn-stop.spec.ts @@ -4,9 +4,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { type ContinuationStop } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent, type ContinuationStop } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -23,7 +23,7 @@ async function harness(adapter: MockAdapter): Promise { return ctx } -function send(agent: ReactLoopAgent, text = 'go'): Promise { +function send(agent: Agent, text = 'go'): Promise { agent.send([{ type: 'text', text }]) return agent.whenIdle() } diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index b0fb78ad66..edd38e31b6 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -168,9 +168,8 @@ export type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact' /** * The agent handle — the surface every plugin (UI, hooks, orchestrators) - * programs against. The concrete implementation lives in - * `@deepseek-ai/dsh-agent-loop` (class `ReactLoopAgent`); nothing outside the loop - * package should depend on the implementation. + * programs against. The concrete implementation is package-internal to + * `@deepseek-ai/dsh-agent-loop`; nothing outside that package depends on it. */ export interface Agent { /** The single identity shared with {@link session}. */ diff --git a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts index 9538166fc4..4f7015d8c4 100644 --- a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts +++ b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts @@ -4,9 +4,9 @@ import LlmService, { CallId } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as RepeatToolGuard from '@deepseek-ai/dsh-repeat-tool-guard' import type { Config } from '@deepseek-ai/dsh-repeat-tool-guard' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -34,12 +34,12 @@ async function harness(config: Config = {}): Promise { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) }) } /** Every `context/message` in the agent's log, flattened to joined text + source for terse assertions. */ -function reminders(agent: ReactLoopAgent): { text: string; source: unknown }[] { +function reminders(agent: Agent): { text: string; source: unknown }[] { return [...agent.session.events] .filter((e): e is SessionEvent<'context/message'> => e.type === 'context/message') .map(e => ({ @@ -255,14 +255,14 @@ describe('chain semantics', () => { ])) // Loop agents are torn down by disposing the scope that created them // (the loop.spec pattern): a child plugin fiber owns `first`. - let first!: ReactLoopAgent + let first!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { first = inner.agentLoop.create(SessionId('reused'), { model: 'mock' }) }, { inject: ['agentLoop'] })) first.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, first) await fiber.dispose() - await first.done + await first.whenIdle() const second = ctx.agentLoop.create(SessionId('reused'), { model: 'mock' }) second.send([{ type: 'text', text: 'go' }]) diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 2f0a2666c9..2c26d64f5a 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -8,9 +8,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -58,7 +58,7 @@ async function harnessWithFiber(configDir: string, adapter: MockAdapter): Promis return { ctx, hooks } } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } @@ -66,7 +66,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function events(agent: ReactLoopAgent): SessionEvent[] { +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index 16c48aa149..7997e0fd87 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -7,9 +7,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -42,10 +42,10 @@ async function harness(configPath: string, adapter: MockAdapter, opts: HarnessOp ctx.llm.registerAdapter(['mock'], adapter) return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) }) } -function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] } +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } /** Poll until `predicate` holds or the deadline passes — robust to detached * emit-listener hooks firing on a `.then` (a fixed sleep flakes under load). */ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise { @@ -451,8 +451,8 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const { SessionId } = await import('@deepseek-ai/dsh-session') const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, handle.agent as ReactLoopAgent) - expect(events(handle.agent as ReactLoopAgent).some(e => e.type === 'context/message' + await waitForIdle(ctx, handle.agent) + expect(events(handle.agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes(`dir=${workspace}`)))).toBe(true) await handle.dispose() }) @@ -616,7 +616,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server const { SessionId } = await import('@deepseek-ai/dsh-session') const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, handle.agent as ReactLoopAgent) + await waitForIdle(ctx, handle.agent) expect(existsSync(marker)).toBe(true) // the marker landed in the SESSION dir const { readFileSync } = await import('node:fs') diff --git a/packages/hooks/hooks-codex/tests/bridge.spec.ts b/packages/hooks/hooks-codex/tests/bridge.spec.ts index 4aa678c36e..84e877af97 100644 --- a/packages/hooks/hooks-codex/tests/bridge.spec.ts +++ b/packages/hooks/hooks-codex/tests/bridge.spec.ts @@ -8,9 +8,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -54,14 +54,14 @@ async function harness(dir: string, adapter: MockAdapter): Promise { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } }) }) } -function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] } +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } /** Poll `predicate` until true or the deadline passes (detached hook effects can't be awaited directly). */ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise { diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index 75b04d4c57..018f109a83 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -7,9 +7,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -33,10 +33,10 @@ async function harness(configPath: string, adapter: MockAdapter, opts: { stderrS ctx.llm.registerAdapter(['mock'], adapter) return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) }) } -function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] } +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } /** Poll until `predicate` holds or the deadline passes — robust to detached * emit-listener hooks firing on a `.then` (a fixed sleep flakes under load). */ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise { @@ -556,7 +556,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const { SessionId } = await import('@deepseek-ai/dsh-session') const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, handle.agent as ReactLoopAgent) + await waitForIdle(ctx, handle.agent) expect(existsSync(marker)).toBe(true) expect(readFileSync(marker, 'utf8').trim().endsWith(sessionDir.split('/').pop()!)).toBe(true) await handle.dispose() diff --git a/packages/todo/tool-todo/tests/integration.spec.ts b/packages/todo/tool-todo/tests/integration.spec.ts index 8376a70425..ba2df4f6ea 100644 --- a/packages/todo/tool-todo/tests/integration.spec.ts +++ b/packages/todo/tool-todo/tests/integration.spec.ts @@ -5,9 +5,9 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -30,7 +30,7 @@ async function harness(adapter: MockAdapter): Promise { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 31a865c068..9f4e8b7c0b 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-acp -The **Agent Client Protocol (ACP)** bridge: exposes DeepSeek Harness SDK agents as an ACP server over JSON-RPC stdio, so editors (Zed and other ACP clients) can drive them — streaming render, tool-call display, and resumable sessions. Zed is the current target client: baseline ACP behavior should remain reasonable for other clients, but bridge capabilities and compatibility decisions are evaluated against Zed first. **N concurrent sessions per connection** (see [ACP multi-session](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md)): each maps to its own `ReactLoopAgent`, and every event is demuxed strictly by session id so two sessions streaming at once never interleave. +The **Agent Client Protocol (ACP)** bridge: exposes DeepSeek Harness SDK agents as an ACP server over JSON-RPC stdio, so editors (Zed and other ACP clients) can drive them — streaming render, tool-call display, and resumable sessions. Zed is the current target client: baseline ACP behavior should remain reasonable for other clients, but bridge capabilities and compatibility decisions are evaluated against Zed first. **N concurrent sessions per connection** (see [ACP multi-session](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md)): each maps to its own concrete `Agent`, and every event is demuxed strictly by session id so two sessions streaming at once never interleave. It is a **client-driver / UI plugin**, the structured analogue of the readline `stdio-chat` plugin — NOT a loop change and NOT a [capability seam](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md). It consumes the existing `agent/*` event taxonomy, the `dsh-agent` create/resume factory, and `dsh-session-persistence`. diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 369c8ae166..7c97ad715c 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -18,7 +18,7 @@ * turn about to start) + settle the in-flight prompt * * Multi-session (RFC 011): N concurrent sessions per connection, each mapped to - * its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id; + * its own concrete `Agent`. Sessions are keyed by their shared agent/session id; * every `session/event` and `agent/*` event is routed strictly to its owning * session record, so two sessions streaming at once never interleave their * `session/update` notifications. Permission prompts use the same identity: the From f85b831bd2cd0d37ca814473abc17ccfb2a6c287 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:41:23 +0800 Subject: [PATCH 037/359] refactor: hide subagent implementation helpers --- ...claude-code-and-codex-subagent-backends.md | 2 +- .../subagent-acp/tests/subagent-acp.spec.ts | 3 +- .../subagent/subagent-inprocess/README.md | 2 +- .../subagent/subagent-inprocess/src/index.ts | 4 +- .../tests/subagent-inprocess.spec.ts | 24 ++---- .../tests/subagent-spawn.spec.ts | 8 +- .../subagent/subagent-subprocess/README.md | 8 +- .../subagent/subagent-subprocess/src/index.ts | 6 +- .../tests/subagent-subprocess.spec.ts | 84 +++++++------------ 9 files changed, 54 insertions(+), 87 deletions(-) diff --git a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md b/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md index 911d28cf1f..c05ae8d67f 100644 --- a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md +++ b/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md @@ -12,7 +12,7 @@ Two sibling provider packages, structural variants of the ACP backend, plus one - `@deepseek-ai/dsh-subagent-claude-code` — drives a Claude Code child through `@anthropic-ai/claude-agent-sdk`'s `query()` (the SDK runs in the parent process and spawns its bundled `claude` CLI as the subprocess). Provider name `claude-code`: the child is the Claude Code *product*, not an Anthropic model adapter — "claude" stays reserved for a future `dsh-llm` adapter. - `@deepseek-ai/dsh-subagent-codex` — spawns `codex app-server` and drives one thread/turn over its JSON-RPC-over-stdio protocol with a hand-rolled newline-JSON client (~200–300 lines) in the package. -- `@deepseek-ai/dsh-subagent-process` — a pure library (the `subagent-inprocess` precedent) extracting what `dsh-subagent-acp` already carries and both new backends need: the credential env scrub (`SENSITIVE_ENV_PATTERN`/`buildChildEnv`), the EOF → SIGTERM → SIGKILL dispose ladder, and new isolated-config-dir helpers (`mkdtemp` create, best-effort remove). The ACP backend migrates onto it; `bash-local`'s sibling copy is left alone to bound the change. +- `@deepseek-ai/dsh-subagent-process` — a pure library (the `subagent-inprocess` precedent) extracting what `dsh-subagent-acp` already carries and both new backends need: the credential env scrub (`buildChildEnv`), the EOF → SIGTERM → SIGKILL dispose ladder, and new isolated-config-dir helpers (`mkdtemp` create, best-effort remove). The ACP backend migrates onto it; `bash-local`'s sibling copy is left alone to bound the change. Both providers copy the ACP backend's seam posture verbatim: fresh child per `start`, exactly one prompt round-trip, capabilities all `false`, `inheritsParentContext: false`, `request.parent`/`request.agentOptions` ignored, `id = SessionId(randomUUID())`, `result` never rejects — child-level failure flattens to a stop reason and the original error goes to `ctx.logger` via an `onError` spec callback. Model exposure is zero new code: `dsh-tool-subagent` is loaded once per provider with a distinct `toolName` (`subagent_claude_code`, `subagent_codex`). No new session events are needed — the only model-visible artifact is the tool result, so reconstructability holds exactly as it did for ACP. To be explicit about the boundary: the session log reconstructs the model-visible transcript, not workspace mutation history — a child granted write access mutates files as an ambient side effect outside the log, exactly as the bash tools and the ACP backend already do; replay reproduces requests, not the disk. diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index 115d5c3e97..cc4d8307f8 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -6,7 +6,7 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' import SubagentService from '@deepseek-ai/dsh-subagent' -import { buildChildEnv, SENSITIVE_ENV_PATTERN } from '@deepseek-ai/dsh-subagent-subprocess' +import { buildChildEnv } from '@deepseek-ai/dsh-subagent-subprocess' import type { Agent } from '@deepseek-ai/dsh-agent' import * as acp from '../src/index.ts' import { acpStopReason, acpContentText, DEFAULT_DISPOSE_EOF_GRACE_MS, DEFAULT_DISPOSE_GRACE_MS, startAcpRun, toAcpPrompt, type AcpRunSpec } from '../src/run.ts' @@ -112,7 +112,6 @@ describe('buildChildEnv', () => { // The explicitly-supplied key survives (an opt-in for the child's creds). expect(env.DEEPSEEK_API_KEY).toBe('explicit') // A normal ambient var is forwarded. - expect(SENSITIVE_ENV_PATTERN.test('PATH')).toBe(false) expect(env.PATH).toBe(process.env.PATH) } finally { delete process.env.DSH_ACP_TEST_SECRET_TOKEN diff --git a/packages/subagent/subagent-inprocess/README.md b/packages/subagent/subagent-inprocess/README.md index 48fd0a201d..83c2ba3500 100644 --- a/packages/subagent/subagent-inprocess/README.md +++ b/packages/subagent/subagent-inprocess/README.md @@ -26,7 +26,7 @@ After fulfillment, the caller owns the run. Provider-plugin unload does not revo `InProcessRunOptions` is `{ seed?: SessionEvent[] }`. Spawn omits it. Fork supplies a balanced completed-turn prefix and records its length so the result reader never mistakes a seeded parent message for child output. -`depthOf(agent)` reads `AgentOptions.subagentDepth`, treating absence as top-level depth zero and rejecting malformed stored values. `SubagentDepthError` reports an attempted child depth above `maxDepth`; an unrepresentable depth above the safe-integer domain is a `RangeError`. +Depth enforcement is internal to `startInProcessRun`: it reads `AgentOptions.subagentDepth`, treats absence as top-level depth zero, rejects malformed stored values, and reports an attempted child depth above `maxDepth`. An unrepresentable depth above the safe-integer domain is a `RangeError`. ## Structured output diff --git a/packages/subagent/subagent-inprocess/src/index.ts b/packages/subagent/subagent-inprocess/src/index.ts index 965d9c8e78..9676c74b5b 100644 --- a/packages/subagent/subagent-inprocess/src/index.ts +++ b/packages/subagent/subagent-inprocess/src/index.ts @@ -36,7 +36,7 @@ declare module '@deepseek-ai/dsh-agent' { * @param agent - the agent whose options carry the depth. * @returns its non-negative safe-integer depth. */ -export function depthOf(agent: Agent): number { +function depthOf(agent: Agent): number { const depth = agent.options.subagentDepth if (depth === undefined) return 0 if (!Number.isSafeInteger(depth) || depth < 0 || Object.is(depth, -0)) { @@ -46,7 +46,7 @@ export function depthOf(agent: Agent): number { } /** Thrown when starting a child would exceed the requested depth cap. */ -export class SubagentDepthError extends Error { +class SubagentDepthError extends Error { constructor(public readonly attemptedDepth: number, public readonly maxDepth: number) { super(`subagent depth ${attemptedDepth} exceeds maxDepth ${maxDepth}`) this.name = 'SubagentDepthError' diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index aa0f946c89..c594e27fa8 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -10,7 +10,7 @@ import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' import { MockAdapter, textResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' -import { depthOf, SubagentDepthError, startInProcessRun } from '../src/index.ts' +import { startInProcessRun } from '../src/index.ts' type Script = ConstructorParameters[0] @@ -37,19 +37,6 @@ function text(blocks: readonly { type: string; text?: string }[]): string { return blocks.filter(block => block.type === 'text').map(block => block.text).join('') } -describe('depthOf', () => { - it('reads zero for a top-level agent and an explicit child depth', async () => { - const { parent } = await setup([]) - expect(depthOf(parent)).toBe(0) - expect(depthOf({ options: { subagentDepth: 3 } } as unknown as Agent)).toBe(3) - }) - - it.each([Number.NaN, 1.5, -1, -0, Number.MAX_SAFE_INTEGER + 1])('rejects malformed depth %s', (value) => { - expect(() => depthOf({ options: { subagentDepth: value } } as unknown as Agent)) - .toThrow('non-negative safe integer') - }) -}) - describe('startInProcessRun', () => { it('returns only after publication, drives a fresh child, and disposes it', async () => { const { ctx, parent } = await setup([textResponse('driver answer')]) @@ -58,7 +45,7 @@ describe('startInProcessRun', () => { const result = await run.result expect(result.stopReason).toBe('completed') expect(text(result.output)).toBe('driver answer') - expect(depthOf(ctx.agents.get(run.id)!)).toBe(1) + expect(ctx.agents.get(run.id)!.options.subagentDepth).toBe(1) await run.dispose() await run.dispose() expect(ctx.agents.get(run.id)).toBeUndefined() @@ -83,7 +70,12 @@ describe('startInProcessRun', () => { await expect(startInProcessRun({ ...request(parent), maxDepth: -1 }, {})) .rejects.toThrow('non-negative safe integer') await expect(startInProcessRun({ ...request(parent), maxDepth: 0 }, {})) - .rejects.toBeInstanceOf(SubagentDepthError) + .rejects.toMatchObject({ name: 'SubagentDepthError' }) + for (const value of [Number.NaN, 1.5, -1, -0, Number.MAX_SAFE_INTEGER + 1]) { + const malformed = { options: { subagentDepth: value } } as unknown as Agent + await expect(startInProcessRun(request(malformed), {})) + .rejects.toThrow('agent subagentDepth must be a non-negative safe integer') + } const maxParent = { options: { subagentDepth: Number.MAX_SAFE_INTEGER } } as unknown as Agent await expect(startInProcessRun(request(maxParent), {})).rejects.toBeInstanceOf(RangeError) }) diff --git a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts index 06aa40ca9f..9b9e2a8fd2 100644 --- a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts +++ b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts @@ -13,7 +13,7 @@ import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' import * as spawn from '../src/index.ts' -import { depthOf, STRUCTURED_OUTPUT_TOOL, SubagentDepthError } from '@deepseek-ai/dsh-subagent-inprocess' +import { STRUCTURED_OUTPUT_TOOL } from '@deepseek-ai/dsh-subagent-inprocess' type Script = ConstructorParameters[0] @@ -118,11 +118,11 @@ describe('dsh-subagent-spawn', () => { it('stamps child depth = parent depth + 1 (via the merged AgentOptions field)', async () => { const { ctx, parent } = await setup([textResponse('x')]) - expect(depthOf(parent)).toBe(0) + expect(parent.options.subagentDepth).toBeUndefined() const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'p' }], parent }) await run.result const child = ctx.agents.get(run.id)! - expect(depthOf(child)).toBe(1) + expect(child.options.subagentDepth).toBe(1) await run.dispose() }) @@ -130,7 +130,7 @@ describe('dsh-subagent-spawn', () => { const { ctx, parent } = await setup([]) // parent is depth 0, child would be depth 1 — cap at 0 forbids any child. await expect(start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'p' }], parent, maxDepth: 0 })) - .rejects.toThrow(SubagentDepthError) + .rejects.toThrow('subagent depth 1 exceeds maxDepth 0') }) it('maps a child that hit its token ceiling to stopReason "max-tokens"', async () => { diff --git a/packages/subagent/subagent-subprocess/README.md b/packages/subagent/subagent-subprocess/README.md index ccc68bf31b..c8b8a06437 100644 --- a/packages/subagent/subagent-subprocess/README.md +++ b/packages/subagent/subagent-subprocess/README.md @@ -6,7 +6,7 @@ Every tunable is a **parameter**: the dispose ladder takes its grace periods per ## What it exports -### `SENSITIVE_ENV_PATTERN` / `buildChildEnv(extra)` +### `buildChildEnv(extra)` The credential env scrub (same pattern as the [bash executor](../../bash/bash-local/README.md)): the child env is the ambient env minus credential-shaped vars (`/KEY|SECRET|TOKEN/i`), with `extra` layered on top AFTER the scrub. `PATH`, `HOME`, `TMPDIR`, locale, and proxy vars survive, so the child CLI runs normally; the parent's own secrets never leak implicitly, while an explicitly supplied credential (the child's OWN key in a backend's `env` config) still reaches the child. @@ -14,10 +14,6 @@ The credential env scrub (same pattern as the [bash executor](../../bash/bash-lo Spawn-failure capture: a promise that resolves (never rejects) with the child's first `error` event. A spawn failure such as `ENOENT` is an event, not a thrown exception — without a listener Node crashes the parent process — so call this in the same tick as `spawn()` and race it in the run's result path; a bad command then settles as an ordinary child-level failure. For a child that spawns cleanly the promise never settles. -### `waitForExit(child)` / `exitsWithin(child, ms)` - -Exit waits over a `ChildProcess`: resolve once the child exits by any code or signal (immediately if it is already gone), or race that against a timer (`true` = exited in time). The race cleans up after itself on both outcomes — the pending timer is `unref()`ed and cleared on exit, the exit listener removed on timeout — so repeated calls (the dispose ladder's tiers, a poll loop) never accumulate listeners on the child. - ### `disposeChildProcess(child, graces)` The three-tier dispose ladder. Resolves only once the child has ACTUALLY exited — quiescence reached, not merely requested (see [defensive patterns](../../../docs/defensive-patterns.md)): @@ -28,6 +24,8 @@ The three-tier dispose ladder. Resolves only once the child has ACTUALLY exited The two graces (`DisposeLadderGraces`) come from the consuming plugin's `disposeEofGraceMs`/`disposeGraceMs` Config fields; the EOF window is deliberately a separate — usually wider — grace than the signal tier, since a cooperative child's EOF teardown may itself await a signal-trapping grandchild plus a final flush. +The exit waits are internal to this ladder. They clean up their timer and listener on either outcome, so escalation never accumulates listeners on the child. + ### `createIsolatedConfigDir(prefix, pinnedPath?)` A per-run isolated config directory for an external CLI child (the target of `CLAUDE_CONFIG_DIR` / `CODEX_HOME`-style redirection), so child behavior is a function of deployment config alone — never of whatever `~/.claude` / `~/.codex`-style state exists on the host. Returns an `IsolatedConfigDir` handle: `path` goes into the child env, `remove()` runs on dispose. diff --git a/packages/subagent/subagent-subprocess/src/index.ts b/packages/subagent/subagent-subprocess/src/index.ts index 35d7383456..2ee2745985 100644 --- a/packages/subagent/subagent-subprocess/src/index.ts +++ b/packages/subagent/subagent-subprocess/src/index.ts @@ -32,7 +32,7 @@ import { join } from 'node:path' * the scrub, so an intended `DEEPSEEK_API_KEY` survives while an incidental * `AWS_SECRET_ACCESS_KEY` does not. */ -export const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i +const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i /** * The ambient env minus credential-shaped vars, plus the caller's explicit @@ -72,7 +72,7 @@ export function spawnFailure(child: ChildProcess): Promise { * already gone. * @param child - the child process to await. */ -export function waitForExit(child: ChildProcess): Promise { +function waitForExit(child: ChildProcess): Promise { if (child.exitCode !== null || child.signalCode !== null) return Promise.resolve() return new Promise(resolve => child.once('exit', () => { resolve() })) } @@ -87,7 +87,7 @@ export function waitForExit(child: ChildProcess): Promise { * @returns `true` if the child exits within `ms` (immediately if it is * already gone), `false` on timeout. */ -export function exitsWithin(child: ChildProcess, ms: number): Promise { +function exitsWithin(child: ChildProcess, ms: number): Promise { if (child.exitCode !== null || child.signalCode !== null) return Promise.resolve(true) return new Promise((resolve) => { const onExit = (): void => { diff --git a/packages/subagent/subagent-subprocess/tests/subagent-subprocess.spec.ts b/packages/subagent/subagent-subprocess/tests/subagent-subprocess.spec.ts index 2766ed0a41..8e19a8a4a1 100644 --- a/packages/subagent/subagent-subprocess/tests/subagent-subprocess.spec.ts +++ b/packages/subagent/subagent-subprocess/tests/subagent-subprocess.spec.ts @@ -9,10 +9,7 @@ import { buildChildEnv, createIsolatedConfigDir, disposeChildProcess, - exitsWithin, - SENSITIVE_ENV_PATTERN, spawnFailure, - waitForExit, } from '../src/index.ts' // `rm` is wrapped (real-passthrough by default) so ONE test can inject a @@ -47,6 +44,8 @@ interface FakeChildScript { diesOn?: LethalTrigger /** Delay (ms) between the lethal trigger and the exit event. */ delayMs?: number + /** Complete the scripted exit inside the triggering call. */ + synchronousExit?: boolean /** `false` models a child spawned without a stdin pipe. */ stdin?: boolean } @@ -80,11 +79,13 @@ class FakeChild extends EventEmitter { // SIGKILL is uncatchable — it always fells the child; any other trigger // only when the scenario scripts it as the lethal one. if (trigger !== 'SIGKILL' && this.script.diesOn !== trigger) return - setTimeout(() => { + const exit = (): void => { if (trigger === 'eof') this.exitCode = 0 else this.signalCode = trigger this.emit('exit', this.exitCode, this.signalCode) - }, this.script.delayMs ?? 0) + } + if (this.script.synchronousExit === true) exit() + else setTimeout(exit, this.script.delayMs ?? 0) } } @@ -93,7 +94,7 @@ function asChild(fake: FakeChild): ChildProcess { return fake as unknown as ChildProcess } -describe('buildChildEnv / SENSITIVE_ENV_PATTERN', () => { +describe('buildChildEnv', () => { it('drops credential-shaped ambient vars (KEY/SECRET/TOKEN, case-insensitive)', () => { process.env.DSH_PROC_TEST_API_KEY = 'leak' process.env.dsh_proc_test_secret = 'leak' @@ -111,7 +112,6 @@ describe('buildChildEnv / SENSITIVE_ENV_PATTERN', () => { }) it('forwards normal ambient vars', () => { - expect(SENSITIVE_ENV_PATTERN.test('PATH')).toBe(false) expect(buildChildEnv({}).PATH).toBe(process.env.PATH) }) @@ -149,7 +149,7 @@ describe('spawnFailure', () => { const fake = new FakeChild({ diesOn: 'SIGTERM' }) const failure = spawnFailure(asChild(fake)) fake.kill('SIGTERM') - await waitForExit(asChild(fake)) + await new Promise(resolve => fake.once('exit', () => { resolve() })) // A clean lifecycle emits `exit`, never `error` — the capture stays // pending forever, so a race against it is decided by the other arms. const settled = await Promise.race([ @@ -160,51 +160,6 @@ describe('spawnFailure', () => { }) }) -describe('waitForExit / exitsWithin', () => { - it('resolves immediately for a child that already exited by code', async () => { - const fake = new FakeChild() - fake.exitCode = 0 - await expect(waitForExit(asChild(fake))).resolves.toBeUndefined() - }) - - it('resolves immediately for a child that already died by signal', async () => { - const fake = new FakeChild() - fake.signalCode = 'SIGTERM' - await expect(waitForExit(asChild(fake))).resolves.toBeUndefined() - }) - - it('resolves on the exit event of a live child', async () => { - const fake = new FakeChild({ diesOn: 'SIGTERM', delayMs: 5 }) - const exited = waitForExit(asChild(fake)) - fake.kill('SIGTERM') - await expect(exited).resolves.toBeUndefined() - expect(fake.signalCode).toBe('SIGTERM') - }) - - it('exitsWithin resolves true immediately for an already-exited child (no listener attached)', async () => { - const fake = new FakeChild() - fake.exitCode = 0 - await expect(exitsWithin(asChild(fake), 1000)).resolves.toBe(true) - expect(fake.listenerCount('exit')).toBe(0) - }) - - it('exitsWithin resolves true when the child exits inside the window', async () => { - const fake = new FakeChild({ diesOn: 'SIGTERM', delayMs: 5 }) - fake.kill('SIGTERM') - await expect(exitsWithin(asChild(fake), 1000)).resolves.toBe(true) - // The once-listener fired and the grace timer was cleared — nothing lingers. - expect(fake.listenerCount('exit')).toBe(0) - }) - - it('exitsWithin resolves false on timeout for a child that never exits', async () => { - const fake = new FakeChild() // nothing short of SIGKILL fells it; no signal sent - await expect(exitsWithin(asChild(fake), 20)).resolves.toBe(false) - // The timeout arm removed its exit listener: repeated waits (a poll loop, - // the ladder's tiers) never accumulate listeners on the same child. - expect(fake.listenerCount('exit')).toBe(0) - }) -}) - describe('disposeChildProcess', () => { it('returns immediately for an already-exited child (no EOF, no signals)', async () => { const fake = new FakeChild() @@ -230,12 +185,28 @@ describe('disposeChildProcess', () => { expect(fake.exitCode).toBe(0) }) + it('recognizes a child that exits synchronously on stdin EOF', async () => { + const fake = new FakeChild({ diesOn: 'eof', synchronousExit: true }) + await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 1000, disposeGraceMs: 1000 }) + expect(fake.exitCode).toBe(0) + expect(fake.listenerCount('exit')).toBe(0) + }) + it('tier 2: a child that ignores EOF but honors SIGTERM dies on the middle rung', async () => { const fake = new FakeChild({ diesOn: 'SIGTERM', delayMs: 5 }) await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 1000 }) expect(fake.stdinEnded).toBe(true) expect(fake.kills).toEqual(['SIGTERM']) expect(fake.signalCode).toBe('SIGTERM') + expect(fake.listenerCount('exit')).toBe(0) + }) + + it('recognizes a child that exits synchronously on SIGTERM', async () => { + const fake = new FakeChild({ diesOn: 'SIGTERM', synchronousExit: true }) + await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 1000 }) + expect(fake.kills).toEqual(['SIGTERM']) + expect(fake.signalCode).toBe('SIGTERM') + expect(fake.listenerCount('exit')).toBe(0) }) it('tier 3: a SIGTERM-trapping child is SIGKILLed, and dispose resolves only after the exit', async () => { @@ -247,6 +218,13 @@ describe('disposeChildProcess', () => { expect(fake.signalCode).toBe('SIGKILL') }) + it('recognizes a child already gone when the final exit wait begins', async () => { + const fake = new FakeChild({ synchronousExit: true }) + await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 20 }) + expect(fake.kills).toEqual(['SIGTERM', 'SIGKILL']) + expect(fake.signalCode).toBe('SIGKILL') + }) + it('walks the ladder for a child spawned without a stdin pipe', async () => { const fake = new FakeChild({ stdin: false, diesOn: 'SIGTERM', delayMs: 5 }) await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 1000 }) From 65521b589f3ffa1a912bb3d8db05a6e2ce204a85 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:45:34 +0800 Subject: [PATCH 038/359] refactor: hide remaining subagent helpers --- ...t-variables-and-tool-guidance-ownership.md | 2 +- ...7-05-subagent-provider-lifecycle-events.md | 2 +- .../2026-06-22-fork-snapshot-scenarios.md | 2 +- packages/subagent/subagent-fork/README.md | 2 +- packages/subagent/subagent-fork/src/index.ts | 2 +- .../subagent-fork/tests/subagent-fork.spec.ts | 42 ++++++++----------- packages/subagent/tool-subagent/src/index.ts | 4 +- 7 files changed, 25 insertions(+), 31 deletions(-) diff --git a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md index 0961830c1a..aae4564513 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md +++ b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md @@ -38,7 +38,7 @@ Per-tool semantics and when-to-use live in tool DESCRIPTIONS, which already ship ### The subagent conversation-history descriptor -`SubagentProvider` gains `readonly inheritsParentContext: boolean` — a DESCRIPTIVE conversation-history fact beside `capabilities`, not in it (capabilities are start-time validation; nothing validates against this flag). Spawn and ACP declare `false`, fork declares `true`. The name refers only to conversation seeding, not Cordis scope, services, tools, or authority. `dsh-tool-subagent` derives both the tool description and the `prompt` parameter description from the flag (`providerWording`): the fork instance now tells the model the child is seeded with the conversation's completed turns (not the in-flight turn) and that its prompt should state only what is new. Deriving the description from a provider that arrives on its own fiber is what forced the provider-lifecycle events and the tool's reactive registration — that mechanism, its Loader-concurrency rationale, and its rejected alternatives are recorded in [the provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md). +`SubagentProvider` gains `readonly inheritsParentContext: boolean` — a DESCRIPTIVE conversation-history fact beside `capabilities`, not in it (capabilities are start-time validation; nothing validates against this flag). Spawn and ACP declare `false`, fork declares `true`. The name refers only to conversation seeding, not Cordis scope, services, tools, or authority. `dsh-tool-subagent` derives both the tool description and the `prompt` parameter description from the flag: the fork instance now tells the model the child is seeded with the conversation's completed turns (not the in-flight turn) and that its prompt should state only what is new. Deriving the description from a provider that arrives on its own fiber is what forced the provider-lifecycle events and the tool's reactive registration — that mechanism, its Loader-concurrency rationale, and its rejected alternatives are recorded in [the provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md). ## Alternatives considered diff --git a/docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md b/docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md index 46e7ea4e71..4a96ef7419 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md +++ b/docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md @@ -4,7 +4,7 @@ Status: implemented ## Problem -[The prompt-variables RFC](2026-07-05-prompt-variables-and-tool-guidance-ownership.md) makes `dsh-tool-subagent` DERIVE its model-facing wording from its provider: `SubagentProvider.inheritsParentContext` (spawn/ACP `false`, fork `true`) drives both the tool description and the `prompt` parameter description (`providerWording`), so the fork tool stops lying about context inheritance. That fix created a cross-fiber data dependency: a tool's description is fixed at TOOL REGISTRATION (deliberately — the description is where tool-choice guidance lives), but the provider arrives on its own plugin fiber, on no particular schedule. +[The prompt-variables RFC](2026-07-05-prompt-variables-and-tool-guidance-ownership.md) makes `dsh-tool-subagent` DERIVE its model-facing wording from its provider: `SubagentProvider.inheritsParentContext` (spawn/ACP `false`, fork `true`) drives both the tool description and the `prompt` parameter description, so the fork tool stops lying about context inheritance. That fix created a cross-fiber data dependency: a tool's description is fixed at TOOL REGISTRATION (deliberately — the description is where tool-choice guidance lives), but the provider arrives on its own plugin fiber, on no particular schedule. The first implementation resolved the provider at the tool plugin's `apply` time and threw when it was absent — an implicit load-order requirement ("list the backend before the tool in cordis.yml"). Review reproduced the failure that requirement hides: the cordis Loader starts sibling entries CONCURRENTLY (`Promise.all` over the group) and `Entry.init()` does not await activation, so a backend whose activation is delayed leaves the tool's fiber permanently failed even when "listed first". The ordering the requirement leaned on is not a contract the Loader offers — "async state is not synchronous state" ([defensive patterns](../../../defensive-patterns.md)). diff --git a/docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md b/docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md index b2c39047b9..34bebd1194 100644 --- a/docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md +++ b/docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md @@ -17,7 +17,7 @@ Record two scenarios against the real API, both replayed keyless in the default ### Why a completed turn-1 is required -The fork backend seeds the child with the parent's **balanced completed-turn prefix** ([`completedTurnPrefix`](../../../../packages/subagent/subagent-fork)). A parent that forks on its very first turn has no completed turn to inherit, so the seed is empty (≡ a fresh spawn, `seedLength` 0) — which would NOT exercise the slice. Both scenarios therefore use a two-prompt input: the first prompt completes a turn (establishing a codeword the child is later asked to recall), the second delegates the fork. The recalled codeword in the child's transcript is incidental to the model's behavior; the load-bearing artifact is the child fixture's recorded `seedLength`, which the replay slice consumes. +The fork backend seeds the child with the parent's **balanced completed-turn prefix**. A parent that forks on its very first turn has no completed turn to inherit, so the seed is empty (≡ a fresh spawn, `seedLength` 0) — which would NOT exercise the slice. Both scenarios therefore use a two-prompt input: the first prompt completes a turn (establishing a codeword the child is later asked to recall), the second delegates the fork. The recalled codeword in the child's transcript is incidental to the model's behavior; the load-bearing artifact is the child fixture's recorded `seedLength`, which the replay slice consumes. ## Consequences diff --git a/packages/subagent/subagent-fork/README.md b/packages/subagent/subagent-fork/README.md index bf90ecdf52..0909dc0bf1 100644 --- a/packages/subagent/subagent-fork/README.md +++ b/packages/subagent/subagent-fork/README.md @@ -6,7 +6,7 @@ The fork provider creates an in-process child seeded with the parent's completed The parent's current tool-calling turn is still open when a subagent starts: its log contains the assistant tool call but not the matching tool result or `turn/end`. Copying that raw log would give the child an invalid, unbalanced session. -Fork therefore uses `completedTurnPrefix(parent.session.events)`: the contiguous prefix ending at the last `turn/end`. The child sees all completed parent turns and none of the in-flight turn. If the parent has not completed a turn yet, the seed is empty and the child behaves like a fresh spawn. +Fork therefore computes the contiguous prefix ending at the last `turn/end`. The child sees all completed parent turns and none of the in-flight turn. If the parent has not completed a turn yet, the seed is empty and the child behaves like a fresh spawn. The seed transfers conversation history only. The child still receives a fresh flat registration scope; it does not inherit the parent's tool restrictions or authority. diff --git a/packages/subagent/subagent-fork/src/index.ts b/packages/subagent/subagent-fork/src/index.ts index ebf64e7b70..22be47cc56 100644 --- a/packages/subagent/subagent-fork/src/index.ts +++ b/packages/subagent/subagent-fork/src/index.ts @@ -54,7 +54,7 @@ export const Config: z = z.object({ * @param parent - the agent whose session log to slice. * @returns the seed events, contiguous from seq 0; empty when no turn has completed. */ -export function completedTurnPrefix(parent: Agent): SessionEvent[] { +function completedTurnPrefix(parent: Agent): SessionEvent[] { const events = parent.session.events const lastEnd = events.findLast(e => e.type === 'turn/end') if (lastEnd === undefined) return [] diff --git a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts index 360098e369..bfb0bedac7 100644 --- a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts +++ b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts @@ -14,7 +14,6 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent import type { StreamChunk } from '@deepseek-ai/dsh-llm' import * as fork from '../src/index.ts' import { STRUCTURED_OUTPUT_TOOL } from '@deepseek-ai/dsh-subagent-inprocess' -import { completedTurnPrefix } from '../src/index.ts' type Script = ConstructorParameters[0] @@ -52,28 +51,6 @@ function text(blocks: { type: string; text?: string }[]): string { return blocks.filter(b => b.type === 'text').map(b => b.text).join('') } -describe('completedTurnPrefix', () => { - it('returns an empty prefix for a parent that has never completed a turn', async () => { - const { parent } = await setup([]) - expect(completedTurnPrefix(parent)).toEqual([]) - }) - - it('returns the balanced prefix up to and including the last turn/end', async () => { - const { parent } = await setup([textResponse('first'), textResponse('second')]) - parent.send([{ type: 'text', text: 'q1' }]) - await parent.whenIdle() - parent.send([{ type: 'text', text: 'q2' }]) - await parent.whenIdle() - - const prefix = completedTurnPrefix(parent) - // Ends exactly at the last turn/end; seq is contiguous from 0. - expect(prefix.at(-1)?.type).toBe('turn/end') - expect(prefix.map(e => e.seq)).toEqual(prefix.map((_, i) => i)) - // Both completed turns are present. - expect(prefix.filter(e => e.type === 'turn/end')).toHaveLength(2) - }) -}) - describe('dsh-subagent-fork', () => { it('emits subagent/start only after the seeded child is published', async () => { const { ctx, parent } = await setup([textResponse('child answer')]) @@ -96,7 +73,6 @@ describe('dsh-subagent-fork', () => { // The parent has never completed a turn → empty prefix → the provider omits // the seed → the child runs fresh. Exercises the `seed.length > 0` false arm. const { ctx, parent } = await setup([textResponse('fresh child')]) - expect(completedTurnPrefix(parent)).toEqual([]) const run = await start(ctx, 'fork', { prompt: [{ type: 'text', text: 'child q' }], parent }) const result = await run.result expect(result.stopReason).toBe('completed') @@ -104,6 +80,24 @@ describe('dsh-subagent-fork', () => { const child = ctx.agents.get(run.id)! // Only the child's own turn — no seeded parent turns. expect(child.session.events.filter(e => e.type === 'turn/end')).toHaveLength(1) + expect(child.session.header.seedLength).toBeUndefined() + await run.dispose() + }) + + it('seeds every completed parent turn through the last turn/end', async () => { + const { ctx, parent } = await setup([textResponse('first'), textResponse('second'), textResponse('child')]) + parent.send([{ type: 'text', text: 'q1' }]) + await parent.whenIdle() + parent.send([{ type: 'text', text: 'q2' }]) + await parent.whenIdle() + const parentPrefixLen = parent.session.events.length + + const run = await start(ctx, 'fork', { prompt: [{ type: 'text', text: 'child q' }], parent }) + await run.result + const child = ctx.agents.get(run.id)! + expect(child.session.header.seedLength).toBe(parentPrefixLen) + expect(child.session.events.slice(0, parentPrefixLen).at(-1)?.type).toBe('turn/end') + expect(child.session.events.slice(0, parentPrefixLen).filter(e => e.type === 'turn/end')).toHaveLength(2) await run.dispose() }) diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index d07e6726dd..426753dbb9 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -161,13 +161,13 @@ function stopReasonError(result: SubagentResult): string | undefined { * A fresh child needs a standalone prompt; a forked child already sees the * conversation's completed turns — telling the model to restate everything * (or, worse, that the child "does not see this conversation") would be false - * for a fork. Exported for tests. + * for a fork. * @param inheritsConversation - whether the child's conversation is seeded * with the parent's completed turns; this says nothing about tool, service, * scope, or authority inheritance. * @returns the tool `description` and the `prompt` parameter description. */ -export function providerWording(inheritsConversation: boolean): { description: string; promptDescription: string } { +function providerWording(inheritsConversation: boolean): { description: string; promptDescription: string } { if (inheritsConversation) { return { description: From 5c82310f47a57f5031e3301042a53a0768a53b30 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 03:58:34 +0800 Subject: [PATCH 039/359] refactor: prune unused llm contract fields --- docs/cordis-catalog/services.md | 2 +- .../testing/2026-06-19-acp-snapshot-tests.md | 2 +- ...0-remove-redundant-snapshot-log-goldens.md | 2 +- .../error-finish/replay.override.json | 2 +- packages/llm/llm-deepseek/src/adapter.ts | 8 ++-- .../llm/llm-deepseek/tests/adapter.spec.ts | 7 +-- packages/llm/llm/README.md | 2 +- packages/llm/llm/src/assembler.ts | 8 ++-- packages/llm/llm/src/index.ts | 6 +-- packages/llm/llm/tests/assembler.spec.ts | 43 ++++++------------- packages/llm/llm/tests/service.spec.ts | 5 ++- packages/support/llm-replay/src/index.ts | 4 +- .../llm-replay/tests/llm-replay.spec.ts | 10 ++--- 13 files changed, 37 insertions(+), 64 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 0aea3f1589..95df09d45e 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -159,7 +159,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:88`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:86`](../../packages/llm/llm/src/index.ts) ## `ctx.sandbox` — `SandboxProvider` (abstract seam) diff --git a/docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md b/docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md index b424a253bd..4bfa3660bf 100644 --- a/docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md +++ b/docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md @@ -30,7 +30,7 @@ The replay seam is the provider-agnostic `llm/stream` waterfall ([packages/llm/l ``` { kind: 'chunks', chunks: StreamChunk[] } -| { kind: 'throw', chunks: StreamChunk[], message: string, code: string, status?: number } +| { kind: 'throw', chunks: StreamChunk[], message: string, code: string } | { kind: 'hang' } ``` diff --git a/docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-goldens.md b/docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-goldens.md index 2a6f8b7ae3..a7c56af2bd 100644 --- a/docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-goldens.md +++ b/docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-goldens.md @@ -6,7 +6,7 @@ Status: implemented Model-driving ACP snapshot scenarios ship both `session.jsonl` and `session.golden.jsonl`. For normal recorded scenarios, `session.jsonl` is the replay fixture harvested from a real run, and the replay test normalizes the newly persisted log and compares it to `session.golden.jsonl`. In the current fixtures, the normalized recorded log and normalized golden are identical for the ordinary recorded scenarios. -Authored override scenarios (`error-finish`, `cancel`) currently use `replay.override.json` to drive model behavior and keep `session.jsonl` as a minimal dummy fixture, while `session.golden.jsonl` holds the expected persisted log. The override file is a JSON array of `ReplayEntry` objects: `{ "kind": "chunks", "chunks": StreamChunk[] }`, `{ "kind": "throw", "chunks": StreamChunk[], "message": string, "code": string, "status"?: number }`, or `{ "kind": "hang" }`. That split is also unnecessary: when an override sidecar exists, `llm-replay` replaces the derived script and does not need `session.jsonl` for model chunks, so `session.jsonl` can still be the expected session-log artifact for the scenario. +Authored override scenarios (`error-finish`, `cancel`) currently use `replay.override.json` to drive model behavior and keep `session.jsonl` as a minimal dummy fixture, while `session.golden.jsonl` holds the expected persisted log. The override file is a JSON array of `ReplayEntry` objects: `{ "kind": "chunks", "chunks": StreamChunk[] }`, `{ "kind": "throw", "chunks": StreamChunk[], "message": string, "code": string }`, or `{ "kind": "hang" }`. That split is also unnecessary: when an override sidecar exists, `llm-replay` replaces the derived script and does not need `session.jsonl` for model chunks, so `session.jsonl` can still be the expected session-log artifact for the scenario. ## Decision diff --git a/examples/acp-agent/tests/snapshots/error-finish/replay.override.json b/examples/acp-agent/tests/snapshots/error-finish/replay.override.json index eea32f25ca..cfa0d84227 100644 --- a/examples/acp-agent/tests/snapshots/error-finish/replay.override.json +++ b/examples/acp-agent/tests/snapshots/error-finish/replay.override.json @@ -1,3 +1,3 @@ [ - { "kind": "throw", "chunks": [], "message": "simulated provider error (HTTP 401)", "code": "AUTH", "status": 401 } + { "kind": "throw", "chunks": [], "message": "simulated provider error (HTTP 401)", "code": "AUTH" } ] diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index e0627c5695..c90404720b 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -79,9 +79,9 @@ export class DeepSeekAdapter extends LlmAdapter { const parsed = await response.json() as WireError if (parsed.error?.message) message = parsed.error.message } catch { - // Paranoid by design: `code` and the HTTP status are ALREADY captured - // above (and passed to LlmError below), so the only thing this `try` - // can add is a richer provider-supplied message. A malformed, empty, + // Paranoid by design: the stable `code` and status-line message are + // already captured above, so the only thing this `try` can add is a + // richer provider-supplied message. A malformed, empty, // or non-JSON error body is a normal thing for gateways/proxies to // return on a 5xx/429 — swallowing the parse failure keeps the usable // status-line message instead of letting a JSON.parse throw mask the @@ -89,7 +89,7 @@ export class DeepSeekAdapter extends LlmAdapter { // is the sole statement, and any non-parse failure (e.g. body already // consumed) is equally non-actionable here. } - throw new LlmError(message, code, response.status) + throw new LlmError(message, code) } if (!response.body) { throw new LlmError('DeepSeek API returned no response body', 'EMPTY_RESPONSE') diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 46f123a1c7..1f1aef3f05 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -158,7 +158,7 @@ describe('DeepSeekAdapter against a mock server', () => { status, body: JSON.stringify({ error: { message: `failed with ${status}`, type: 't', code: 'c' } }), } - const server = await mockServer([behavior, behavior, behavior]) + const server = await mockServer([behavior, behavior]) const ctx = await harness(server.url) await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })) .rejects.toThrow(`failed with ${status}`) @@ -166,11 +166,6 @@ describe('DeepSeekAdapter against a mock server', () => { assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) .catch((error: unknown) => (error as LlmError).code), ).resolves.toBe(code) - // The numeric HTTP status is carried on the error for explicit handling. - await expect( - assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - .catch((error: unknown) => (error as LlmError).status), - ).resolves.toBe(status) }) it('keeps the status-line message for JSON error bodies without a message', async () => { diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 42694ba5ea..7c847447b8 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -42,7 +42,7 @@ Every product adapter must identify the application on every provider HTTP reque - `LlmAdapter` — abstract base class for provider adapters. The only required method is `stream()`. - `BlockAssembler` — incrementally assembles raw chunks into complete content blocks and an assistant message. The agent loop feeds it raw chunks (logging them for replay) while reading the assembled blocks/message for history. - `HarnessError` — base class for the harness error taxonomy: a stable `code` string (distinct from the human `message`) plus `cause` chaining. Lives here, in the leaf package every other imports, so a single base is shared without a new dependency edge. Per-package errors (`LlmError`, `ToolArgsError`, `InvariantError`, …) extend it. `isHarnessError(value)` narrows at seams. -- `LlmError` — extends `HarnessError`; `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) plus an optional numeric `status` when the failure came from a non-2xx provider response. +- `LlmError` — extends `HarnessError`; its stable `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) is the programmatic failure contract. ### Real adapters diff --git a/packages/llm/llm/src/assembler.ts b/packages/llm/llm/src/assembler.ts index 1b8ba6e60c..fb34afe0b9 100644 --- a/packages/llm/llm/src/assembler.ts +++ b/packages/llm/llm/src/assembler.ts @@ -38,12 +38,10 @@ export class BlockAssembler { private _finish: FinishReason | undefined /** - * Feed one chunk. Returns the completed block when the chunk closes one - * (an explicit `block-end`), otherwise undefined. + * Feed one chunk into the assembly state. * @param chunk - the next raw chunk, in stream order. - * @returns the authoritative block from the first `block-end` at its index; undefined for every other chunk. */ - push(chunk: StreamChunk): ContentBlock | undefined { + push(chunk: StreamChunk): void { switch (chunk.type) { case 'block-start': { if (!this.partials.has(chunk.index)) { @@ -79,7 +77,7 @@ export class BlockAssembler { // re-close could rewrite a block already flushed downstream. if (partial.block) return partial.block = chunk.block - return chunk.block + return } case 'usage': { this._usage = chunk.usage diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 667e9bca78..e32894efdd 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -42,12 +42,10 @@ declare module 'cordis' { /** * Typed error for LLM-related failures. Extends {@link HarnessError}, so the - * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy; - * `status` carries the HTTP status when the error originated from a non-2xx - * provider response (absent for protocol/usage errors that have no HTTP status). + * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy. */ export class LlmError extends HarnessError { - constructor(message: string, code: string, public status?: number, options?: ErrorOptions) { + constructor(message: string, code: string, options?: ErrorOptions) { super(message, code, options) this.name = 'LlmError' } diff --git a/packages/llm/llm/tests/assembler.spec.ts b/packages/llm/llm/tests/assembler.spec.ts index d9a4fe33f3..0674c55fb8 100644 --- a/packages/llm/llm/tests/assembler.spec.ts +++ b/packages/llm/llm/tests/assembler.spec.ts @@ -29,12 +29,12 @@ describe('BlockAssembler', () => { expect(assembler.message().role).toBe('assistant') }) - it('returns the completed block from push() on block-end', () => { + it('records the completed block from block-end', () => { const assembler = new BlockAssembler() - expect(assembler.push({ type: 'block-start', index: 0, blockType: 'text' })).toBeUndefined() - expect(assembler.push({ type: 'text-delta', index: 0, text: 'hi' })).toBeUndefined() - const block = assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } }) - expect(block).toEqual({ type: 'text', text: 'hi' }) + assembler.push({ type: 'block-start', index: 0, blockType: 'text' }) + assembler.push({ type: 'text-delta', index: 0, text: 'hi' }) + assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } }) + expect(assembler.blocks()).toEqual([{ type: 'text', text: 'hi' }]) }) it('tolerates deltas without explicit block-start/end', () => { @@ -57,8 +57,8 @@ describe('BlockAssembler', () => { // push a delta first to guarantee the partial exists assembler.push({ type: 'text-delta', index: 0, text: 'hi' }) // block-end's ensure() must find the existing partial (the second branch path) - const block = assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } }) - expect(block).toEqual({ type: 'text', text: 'hi' }) + assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } }) + expect(assembler.blocks()).toEqual([{ type: 'text', text: 'hi' }]) }) it('throws from assemble() when a partial has an unhandled blockType', () => { @@ -130,7 +130,7 @@ describe('assertNever', () => { it('BlockAssembler.push rejects chunks outside the closed StreamChunk union', () => { const assembler = new BlockAssembler() - expect(() => assembler.push({ type: 'rogue-chunk' } as unknown as StreamChunk)) + expect(() => { assembler.push({ type: 'rogue-chunk' } as unknown as StreamChunk) }) .toThrow('unreachable variant in BlockAssembler.push') }) }) @@ -140,32 +140,13 @@ describe('BlockAssembler regressions (property-test findings)', () => { // Found by fast-check (the property-testing RFC): two block-ends at the same index made the // streamed prefix (first block) disagree with final blocks() (second // block). The first close must win — same straggler rule as post-close - // deltas — so the prefix returned incrementally by push() and the final - // blocks() stay identical. + // deltas — so later chunks cannot rewrite the completed block. const chunks: StreamChunk[] = [ { type: 'block-end', index: 0, block: { type: 'reasoning', text: 'first' } }, { type: 'block-end', index: 0, block: { type: 'text', text: 'second' } }, ] - const streaming = new BlockAssembler() - const closed = [] - for (const chunk of chunks) { - const block = streaming.push(chunk) - if (block) closed.push(block) - } - - const oneShot = new BlockAssembler() - for (const chunk of chunks) oneShot.push(chunk) - - expect(closed).toEqual([{ type: 'reasoning', text: 'first' }]) - expect(oneShot.blocks()).toEqual([{ type: 'reasoning', text: 'first' }]) - expect(closed).toEqual(oneShot.blocks()) - }) - - it('push returns undefined for a duplicate block-end (it closed nothing)', () => { - const a = new BlockAssembler() - expect(a.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'x' } })) - .toEqual({ type: 'text', text: 'x' }) - expect(a.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'y' } })) - .toBeUndefined() + const assembler = new BlockAssembler() + for (const chunk of chunks) assembler.push(chunk) + expect(assembler.blocks()).toEqual([{ type: 'reasoning', text: 'first' }]) }) }) diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index f669069c44..125a810261 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -79,11 +79,12 @@ describe('LlmService', () => { it('LlmError extends the shared HarnessError base', async () => { const { HarnessError, isHarnessError } = await import('@deepseek-ai/dsh-llm') - const err = new LlmError('boom', 'AUTH', 401) + const cause = new Error('root cause') + const err = new LlmError('boom', 'AUTH', { cause }) expect(err).toBeInstanceOf(HarnessError) expect(isHarnessError(err)).toBe(true) expect(err.code).toBe('AUTH') - expect(err.status).toBe(401) + expect(err.cause).toBe(cause) }) it('HarnessError carries a code, names itself by subclass, and chains cause', async () => { diff --git a/packages/support/llm-replay/src/index.ts b/packages/support/llm-replay/src/index.ts index 94bd0cdd7e..b919c21176 100644 --- a/packages/support/llm-replay/src/index.ts +++ b/packages/support/llm-replay/src/index.ts @@ -74,7 +74,7 @@ import { LlmError, assertNever } from '@deepseek-ai/dsh-llm' */ export type ReplayEntry = | { kind: 'chunks'; chunks: StreamChunk[] } - | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string; status?: number } + | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string } | { kind: 'hang' } /** Resolved plugin configuration. */ @@ -324,7 +324,7 @@ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined) if (signal?.aborted) throw new Error('aborted') yield chunk } - throw new LlmError(entry.message, entry.code, entry.status) + throw new LlmError(entry.message, entry.code) case 'hang': // Replay a stream that stalls until cancelled (mirrors MockAdapter): one // chunk, then wait for abort and surface it as the consumer expects. diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index 3b4e8c5fee..f7e85a74bf 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -175,7 +175,7 @@ describe('loadReplayScript', () => { it('uses the sidecar override when present, ignoring the JSONL', () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') - const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH', status: 401 }] + const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH' }] writeFileSync(overrideFile, JSON.stringify(override), 'utf8') expect(loadReplayScript({ file, overrideFile })).toEqual(override) }) @@ -231,12 +231,12 @@ describe('installLlmReplay (through the real waterfall)', () => { expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(second) }) - it('replays a sidecar throw-entry as an LlmError with code/status, after its prefix chunks', async () => { + it('replays a sidecar throw-entry as an LlmError with its stable code, after its prefix chunks', async () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) @@ -245,7 +245,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const seen: StreamChunk[] = [] await expect((async () => { for await (const c of ctx.llm.stream({ model: 'm', messages: [] })) seen.push(c) - })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH', status: 401 }) + })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH' }) expect(seen).toEqual(partial) }) @@ -350,7 +350,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) From 91075e010ab641a3cc236881d0713f68b27e8191 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 04:03:44 +0800 Subject: [PATCH 040/359] refactor: hide llm adapter helpers --- docs/config-catalog.md | 4 ++-- packages/llm/llm-deepseek/README.md | 2 ++ packages/llm/llm-deepseek/src/index.ts | 5 +---- packages/llm/llm-deepseek/tests/adapter.spec.ts | 16 +++++++++++++++- .../llm/llm-deepseek/tests/serialize.spec.ts | 2 +- packages/llm/llm-deepseek/tests/sse.spec.ts | 2 +- .../llm/llm-deepseek/tests/translate.spec.ts | 3 ++- packages/llm/llm-pi-ai/README.md | 2 ++ packages/llm/llm-pi-ai/src/index.ts | 3 +-- packages/llm/llm-pi-ai/tests/adapter.spec.ts | 9 ++++++++- packages/llm/llm-pi-ai/tests/convert.spec.ts | 2 +- 11 files changed, 36 insertions(+), 14 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 9d4b8038b5..9db148cbae 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -389,7 +389,7 @@ export interface Config { } ``` -Source: [`packages/llm/llm-deepseek/src/index.ts:43`](../packages/llm/llm-deepseek/src/index.ts) +Source: [`packages/llm/llm-deepseek/src/index.ts:40`](../packages/llm/llm-deepseek/src/index.ts) ## `@deepseek-ai/dsh-llm-pi-ai` @@ -420,7 +420,7 @@ export interface Config { export type PiAiReasoning = 'off' | 'high' | 'xhigh' ``` -Source: [`packages/llm/llm-pi-ai/src/index.ts:37`](../packages/llm/llm-pi-ai/src/index.ts) +Source: [`packages/llm/llm-pi-ai/src/index.ts:36`](../packages/llm/llm-pi-ai/src/index.ts) ## `@deepseek-ai/dsh-llm-replay` diff --git a/packages/llm/llm-deepseek/README.md b/packages/llm/llm-deepseek/README.md index 15fad9f881..4d9ff8fcae 100644 --- a/packages/llm/llm-deepseek/README.md +++ b/packages/llm/llm-deepseek/README.md @@ -4,6 +4,8 @@ DeepSeek chat-completions adapter for the harness LLM seam: hand-rolled `fetch` A second, independent implementation of the same seam exists in `@deepseek-ai/dsh-llm-pi-ai` (library-backed). Same Config shape — pick one per context (registering both for the same model names throws by design). +The package root exposes the Cordis plugin contract and `DeepSeekAdapter`; wire serialization, SSE parsing, and chunk translation helpers are not part of that root contract. + ## Config ```yaml diff --git a/packages/llm/llm-deepseek/src/index.ts b/packages/llm/llm-deepseek/src/index.ts index 3a3d7bb4a1..3b8013de5c 100644 --- a/packages/llm/llm-deepseek/src/index.ts +++ b/packages/llm/llm-deepseek/src/index.ts @@ -23,12 +23,9 @@ import z from 'schemastery' import type {} from '@deepseek-ai/dsh-llm' import { DeepSeekAdapter } from './adapter.ts' -export { DeepSeekAdapter, httpErrorCode } from './adapter.ts' +export { DeepSeekAdapter } from './adapter.ts' export type { DeepSeekAdapterOptions } from './adapter.ts' -export { serializeMessages, serializeRequest } from './serialize.ts' export type { RequestDefaults } from './serialize.ts' -export { DONE, parseSse } from './sse.ts' -export { mapFinishReason, mapUsage, translate } from './translate.ts' export type * from './types.ts' export const name = 'llm-deepseek' diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 1f1aef3f05..ca9c6b7097 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -4,7 +4,8 @@ import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import LlmService, { LlmError, userAgent } from '@deepseek-ai/dsh-llm' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' -import { DeepSeekAdapter, httpErrorCode } from '@deepseek-ai/dsh-llm-deepseek' +import { DeepSeekAdapter } from '@deepseek-ai/dsh-llm-deepseek' +import { httpErrorCode } from '../src/adapter.ts' import { assemble } from './assemble.ts' /** One scripted behavior for the next request the mock server receives. */ @@ -234,6 +235,19 @@ describe('DeepSeekAdapter against a mock server', () => { }) describe('plugin registration and config', () => { + it('keeps wire helpers off the package root', () => { + for (const helper of [ + 'httpErrorCode', + 'serializeMessages', + 'serializeRequest', + 'DONE', + 'parseSse', + 'mapFinishReason', + 'mapUsage', + 'translate', + ]) expect(LlmDeepSeek).not.toHaveProperty(helper) + }) + it('registers the configured models and unregisters on dispose (HMR safety)', async () => { const server = await mockServer([]) const ctx = new Context() diff --git a/packages/llm/llm-deepseek/tests/serialize.spec.ts b/packages/llm/llm-deepseek/tests/serialize.spec.ts index 3e533f8e7c..a1d7d8b4a7 100644 --- a/packages/llm/llm-deepseek/tests/serialize.spec.ts +++ b/packages/llm/llm-deepseek/tests/serialize.spec.ts @@ -1,7 +1,7 @@ import { describe, expect, it } from 'vitest' import { CallId } from '@deepseek-ai/dsh-llm' import type { ContentBlock, GenerateOptions, Message } from '@deepseek-ai/dsh-llm' -import { serializeMessages, serializeRequest } from '@deepseek-ai/dsh-llm-deepseek' +import { serializeMessages, serializeRequest } from '../src/serialize.ts' function request(overrides: Partial = {}): GenerateOptions { return { model: 'deepseek-v4-flash', messages: [], ...overrides } diff --git a/packages/llm/llm-deepseek/tests/sse.spec.ts b/packages/llm/llm-deepseek/tests/sse.spec.ts index 2fc297bbec..b18862e4f3 100644 --- a/packages/llm/llm-deepseek/tests/sse.spec.ts +++ b/packages/llm/llm-deepseek/tests/sse.spec.ts @@ -1,6 +1,6 @@ import { describe, expect, it } from 'vitest' import { LlmError } from '@deepseek-ai/dsh-llm' -import { DONE, parseSse } from '@deepseek-ai/dsh-llm-deepseek' +import { DONE, parseSse } from '../src/sse.ts' /** Build a byte stream from string fragments (fragments = network reads). */ async function* bytes(...fragments: (string | Uint8Array)[]): AsyncGenerator { diff --git a/packages/llm/llm-deepseek/tests/translate.spec.ts b/packages/llm/llm-deepseek/tests/translate.spec.ts index d6968faed5..e62cebc4af 100644 --- a/packages/llm/llm-deepseek/tests/translate.spec.ts +++ b/packages/llm/llm-deepseek/tests/translate.spec.ts @@ -1,7 +1,8 @@ import { describe, expect, it } from 'vitest' import { BlockAssembler, LlmError } from '@deepseek-ai/dsh-llm' import type { StreamChunk } from '@deepseek-ai/dsh-llm' -import { DONE, mapFinishReason, mapUsage, translate } from '@deepseek-ai/dsh-llm-deepseek' +import { DONE } from '../src/sse.ts' +import { mapFinishReason, mapUsage, translate } from '../src/translate.ts' async function* feed(...payloads: (string | object)[]): AsyncGenerator { for (const payload of payloads) { diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index f74ccd2246..adb22c585c 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -2,6 +2,8 @@ DeepSeek adapter for the harness LLM seam backed by [`@earendil-works/pi-ai`](https://www.npmjs.com/package/@earendil-works/pi-ai) (the LLM library behind the pi agent). +The package root exposes the Cordis plugin contract and `PiAiAdapter`; model construction and event-conversion helpers are not part of that root contract. + ## Why a second adapter exists `@deepseek-ai/dsh-llm-deepseek` already talks to the same endpoint. This package is its **design-verification twin**: same models, same wire protocol, completely different internals — a unified LLM library with its own event vocabulary versus hand-rolled fetch/SSE. Anything the harness `StreamChunk` protocol cannot express for BOTH implementations is a core-vocabulary bug. The differences it exercised on purpose: diff --git a/packages/llm/llm-pi-ai/src/index.ts b/packages/llm/llm-pi-ai/src/index.ts index 43468ba507..fd81b77b56 100644 --- a/packages/llm/llm-pi-ai/src/index.ts +++ b/packages/llm/llm-pi-ai/src/index.ts @@ -22,9 +22,8 @@ import type {} from '@deepseek-ai/dsh-llm' import { PiAiAdapter } from './adapter.ts' import type { PiAiReasoning } from './adapter.ts' -export { buildModel, PiAiAdapter } from './adapter.ts' +export { PiAiAdapter } from './adapter.ts' export type { PiAiAdapterOptions, PiAiReasoning } from './adapter.ts' -export { mapStopReason, mapUsage, toPiContext, toStreamChunks } from './convert.ts' export const name = 'llm-pi-ai' export const inject = ['llm'] diff --git a/packages/llm/llm-pi-ai/tests/adapter.spec.ts b/packages/llm/llm-pi-ai/tests/adapter.spec.ts index cefaa9f745..cc4f129b72 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.spec.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.spec.ts @@ -4,7 +4,8 @@ import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, userAgent } from '@deepseek-ai/dsh-llm' import * as LlmPiAi from '@deepseek-ai/dsh-llm-pi-ai' -import { buildModel, PiAiAdapter } from '@deepseek-ai/dsh-llm-pi-ai' +import { PiAiAdapter } from '@deepseek-ai/dsh-llm-pi-ai' +import { buildModel } from '../src/adapter.ts' import { assemble } from './assemble.ts' /** Scripted SSE responses, one per request (OpenAI chat-completions shape). */ @@ -245,6 +246,12 @@ describe('PiAiAdapter against a mock server', () => { }) describe('option spreads and env fallbacks', () => { + it('keeps adapter conversion helpers off the package root', () => { + for (const helper of ['buildModel', 'mapStopReason', 'mapUsage', 'toPiContext', 'toStreamChunks']) { + expect(LlmPiAi).not.toHaveProperty(helper) + } + }) + it('forwards temperature, maxTokens, and signal', async () => { const server = await mockServer([{ events: textEvents }]) const ctx = await harness(server.url) diff --git a/packages/llm/llm-pi-ai/tests/convert.spec.ts b/packages/llm/llm-pi-ai/tests/convert.spec.ts index 078d2a4d3b..3dc4709603 100644 --- a/packages/llm/llm-pi-ai/tests/convert.spec.ts +++ b/packages/llm/llm-pi-ai/tests/convert.spec.ts @@ -2,7 +2,7 @@ import { describe, expect, it } from 'vitest' import { CallId } from '@deepseek-ai/dsh-llm' import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm' import type { AssistantMessage, AssistantMessageEvent, Usage } from '@earendil-works/pi-ai' -import { mapStopReason, mapUsage, toPiContext, toStreamChunks } from '@deepseek-ai/dsh-llm-pi-ai' +import { mapStopReason, mapUsage, toPiContext, toStreamChunks } from '../src/convert.ts' function usage(input = 0, output = 0, cacheRead = 0, cacheWrite = 0): Usage { return { From f1373cd7abc479ae89a219e6a3fad6023f66aa64 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:15:17 +0800 Subject: [PATCH 041/359] refactor: drop unused tool schema defaults --- docs/core-data-structures/tools.md | 2 -- packages/core/tools/README.md | 2 +- packages/core/tools/src/schema.ts | 10 ------- packages/core/tools/tests/tools.spec.ts | 37 ++----------------------- 4 files changed, 3 insertions(+), 48 deletions(-) diff --git a/docs/core-data-structures/tools.md b/docs/core-data-structures/tools.md index 36c59aea17..1d59542404 100644 --- a/docs/core-data-structures/tools.md +++ b/docs/core-data-structures/tools.md @@ -57,8 +57,6 @@ interface SchemaProp { description?: string /** Enum of allowed values (strings only). */ enum?: string[] - /** Default value. */ - default?: unknown /** Nested properties for type: 'object'. */ properties?: SchemaSpec /** Items schema for type: 'array'. */ diff --git a/packages/core/tools/README.md b/packages/core/tools/README.md index d57aeba10b..5f06154ec4 100644 --- a/packages/core/tools/README.md +++ b/packages/core/tools/README.md @@ -77,7 +77,7 @@ ctx.tools.register(defineTool({ The helper converts the author-facing `SchemaSpec` (with `required: true` as a per-property boolean) to standard JSON Schema for the wire format and uses the same typed spec for execute/presentation validation. Raw JSON-Schema tool definitions (from MCP servers) are still accepted by the registry directly. -A `defineTool` tool also **validates the model-generated arguments against its `SchemaSpec` before `execute` runs** (`validateArgs`). The model's JSON is untrusted — `InferArgs` is a compile-time claim, not a runtime guarantee — so on a mismatch (missing required key, wrong primitive, bad enum member, nested violation) the tool throws a `ToolArgsError` (`code: 'INVALID_ARGS'`); the registry turns it into an `isError` result whose text lists the violations, which the model sees and self-corrects from. Validation mirrors the JSON Schema conversion exactly: extra keys are allowed, `default` is not applied, and an `object`/`array` prop without `properties`/`items` only type-checks. Raw-registered tools (MCP) are **not** validated by the harness — they validate their own input. +A `defineTool` tool also **validates the model-generated arguments against its `SchemaSpec` before `execute` runs** (`validateArgs`). The model's JSON is untrusted — `InferArgs` is a compile-time claim, not a runtime guarantee — so on a mismatch (missing required key, wrong primitive, bad enum member, nested violation) the tool throws a `ToolArgsError` (`code: 'INVALID_ARGS'`); the registry turns it into an `isError` result whose text lists the violations, which the model sees and self-corrects from. Validation mirrors the JSON Schema conversion exactly: extra keys are allowed, and an `object`/`array` prop without `properties`/`items` only type-checks. Raw-registered tools (MCP) are **not** validated by the harness — they validate their own input. See `defineTool`, `validateArgs`, `ToolArgsError`, `SchemaSpec`, `InferArgs`, and `schemaSpecToJsonSchema` in the public API for details. diff --git a/packages/core/tools/src/schema.ts b/packages/core/tools/src/schema.ts index d3a2d32e18..ad7c28760e 100644 --- a/packages/core/tools/src/schema.ts +++ b/packages/core/tools/src/schema.ts @@ -39,15 +39,6 @@ export interface SchemaProp { description?: string /** Enum of allowed values (strings only). */ enum?: string[] - /** - * Default value, emitted into the JSON Schema only (validation never applies - * it — see the validator note below). - * - * XXX(unused-default): no tool definition in the repo sets `default`; it rides - * into the wire schema for a model that no tool surfaces it to. Drop the field - * and its converter line unless a real tool needs a model-visible default. - */ - default?: unknown /** Nested properties for type: 'object'. */ properties?: SchemaSpec /** Items schema for type: 'array'. */ @@ -123,7 +114,6 @@ function propToJsonSchema(prop: SchemaProp): { schema: Record; const result: Record = { type: prop.type } if (prop.description) result.description = prop.description if (prop.enum) result.enum = prop.enum - if (prop.default !== undefined) result.default = prop.default const required = prop.required === true diff --git a/packages/core/tools/tests/tools.spec.ts b/packages/core/tools/tests/tools.spec.ts index a2dff84287..2bca8e05fc 100644 --- a/packages/core/tools/tests/tools.spec.ts +++ b/packages/core/tools/tests/tools.spec.ts @@ -904,17 +904,6 @@ describe('schema DSL edge cases', () => { }) }) - it('emits default value in JSON Schema property', () => { - const spec = { - limit: { type: 'number', default: 25 }, - } satisfies SchemaSpec - const jsonSchema = schemaSpecToJsonSchema(spec) - expect(jsonSchema.properties['limit']).toMatchObject({ - type: 'number', - default: 25, - }) - }) - it('handles array items without nested properties (plain type array)', () => { const spec = { tags: { type: 'array', items: { type: 'string' } }, @@ -926,28 +915,12 @@ describe('schema DSL edge cases', () => { }) }) - it('handles enum and default together in one property', () => { - const spec = { - level: { type: 'string', enum: ['low', 'high'], default: 'low' }, - } satisfies SchemaSpec - const jsonSchema = schemaSpecToJsonSchema(spec) - expect(jsonSchema.properties['level']).toMatchObject({ - type: 'string', - enum: ['low', 'high'], - default: 'low', - }) - }) - - it('omits description, enum, default keys when not specified', () => { + it('emits only the type when optional fields are omitted', () => { const spec = { bare: { type: 'string' }, } satisfies SchemaSpec const jsonSchema = schemaSpecToJsonSchema(spec) - const prop = jsonSchema.properties['bare'] as Record - expect(prop).toEqual({ type: 'string' }) - expect('description' in prop).toBe(false) - expect('enum' in prop).toBe(false) - expect('default' in prop).toBe(false) + expect(jsonSchema.properties['bare']).toEqual({ type: 'string' }) }) it('handles array with no items (items omitted)', () => { @@ -1137,12 +1110,6 @@ describe('validateArgs (the runtime-validation RFC, part 1)', () => { expect(validateArgs(spec, { path: '/tmp', extra: 1 })).toEqual([]) }) - it('does not apply defaults (validation only)', () => { - const spec = { limit: { type: 'number', default: 25 } } satisfies SchemaSpec - // absent optional is valid, and validation does not synthesize the default - expect(validateArgs(spec, {})).toEqual([]) - }) - it('type-checks primitives', () => { const spec = { s: { type: 'string' }, From 863116daaf406d3fc6485be819bcba0fc3d275f1 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:23:17 +0800 Subject: [PATCH 042/359] fix: retain dynamic tool schema defaults --- docs/core-data-structures/tools.md | 2 + .../cordis/tool-cordis/tests/mount.spec.ts | 6 ++- packages/core/tools/README.md | 2 +- packages/core/tools/src/schema.ts | 6 +++ packages/core/tools/tests/tools.spec.ts | 37 ++++++++++++++++++- 5 files changed, 49 insertions(+), 4 deletions(-) diff --git a/docs/core-data-structures/tools.md b/docs/core-data-structures/tools.md index 1d59542404..36c59aea17 100644 --- a/docs/core-data-structures/tools.md +++ b/docs/core-data-structures/tools.md @@ -57,6 +57,8 @@ interface SchemaProp { description?: string /** Enum of allowed values (strings only). */ enum?: string[] + /** Default value. */ + default?: unknown /** Nested properties for type: 'object'. */ properties?: SchemaSpec /** Items schema for type: 'array'. */ diff --git a/packages/cordis/tool-cordis/tests/mount.spec.ts b/packages/cordis/tool-cordis/tests/mount.spec.ts index fc29eeb2a0..bf2e57c13e 100644 --- a/packages/cordis/tool-cordis/tests/mount.spec.ts +++ b/packages/cordis/tool-cordis/tests/mount.spec.ts @@ -185,9 +185,13 @@ describe('cordis_mount', () => { // The registered schema is canonical JSON Schema derived from the DSL: // the required array survived, integer became number, extra is optional. const schema = ctx.tools.schemas().find(s => s.name === 'json_schema_tool')! - const parameters = schema.parameters as { properties: Record; required?: string[] } + const parameters = schema.parameters as { + properties: Record + required?: string[] + } expect(parameters.required).toEqual(['text']) expect(parameters.properties.count!.type).toBe('number') + expect(parameters.properties.count!.default).toBe(1) expect(parameters.properties.mode!.enum).toEqual(['fast', 'slow']) // Arg validation enforces the normalized spec: text required, extra not. expect((await call(ctx, 'json_schema_tool', { count: 2 })).isError).toBe(true) diff --git a/packages/core/tools/README.md b/packages/core/tools/README.md index 5f06154ec4..d57aeba10b 100644 --- a/packages/core/tools/README.md +++ b/packages/core/tools/README.md @@ -77,7 +77,7 @@ ctx.tools.register(defineTool({ The helper converts the author-facing `SchemaSpec` (with `required: true` as a per-property boolean) to standard JSON Schema for the wire format and uses the same typed spec for execute/presentation validation. Raw JSON-Schema tool definitions (from MCP servers) are still accepted by the registry directly. -A `defineTool` tool also **validates the model-generated arguments against its `SchemaSpec` before `execute` runs** (`validateArgs`). The model's JSON is untrusted — `InferArgs` is a compile-time claim, not a runtime guarantee — so on a mismatch (missing required key, wrong primitive, bad enum member, nested violation) the tool throws a `ToolArgsError` (`code: 'INVALID_ARGS'`); the registry turns it into an `isError` result whose text lists the violations, which the model sees and self-corrects from. Validation mirrors the JSON Schema conversion exactly: extra keys are allowed, and an `object`/`array` prop without `properties`/`items` only type-checks. Raw-registered tools (MCP) are **not** validated by the harness — they validate their own input. +A `defineTool` tool also **validates the model-generated arguments against its `SchemaSpec` before `execute` runs** (`validateArgs`). The model's JSON is untrusted — `InferArgs` is a compile-time claim, not a runtime guarantee — so on a mismatch (missing required key, wrong primitive, bad enum member, nested violation) the tool throws a `ToolArgsError` (`code: 'INVALID_ARGS'`); the registry turns it into an `isError` result whose text lists the violations, which the model sees and self-corrects from. Validation mirrors the JSON Schema conversion exactly: extra keys are allowed, `default` is not applied, and an `object`/`array` prop without `properties`/`items` only type-checks. Raw-registered tools (MCP) are **not** validated by the harness — they validate their own input. See `defineTool`, `validateArgs`, `ToolArgsError`, `SchemaSpec`, `InferArgs`, and `schemaSpecToJsonSchema` in the public API for details. diff --git a/packages/core/tools/src/schema.ts b/packages/core/tools/src/schema.ts index ad7c28760e..e912252b18 100644 --- a/packages/core/tools/src/schema.ts +++ b/packages/core/tools/src/schema.ts @@ -39,6 +39,11 @@ export interface SchemaProp { description?: string /** Enum of allowed values (strings only). */ enum?: string[] + /** + * Model-visible JSON Schema default annotation. Validation does not apply it; + * dynamic tool mounts may supply it even though first-party definitions do not. + */ + default?: unknown /** Nested properties for type: 'object'. */ properties?: SchemaSpec /** Items schema for type: 'array'. */ @@ -114,6 +119,7 @@ function propToJsonSchema(prop: SchemaProp): { schema: Record; const result: Record = { type: prop.type } if (prop.description) result.description = prop.description if (prop.enum) result.enum = prop.enum + if (prop.default !== undefined) result.default = prop.default const required = prop.required === true diff --git a/packages/core/tools/tests/tools.spec.ts b/packages/core/tools/tests/tools.spec.ts index 2bca8e05fc..a2dff84287 100644 --- a/packages/core/tools/tests/tools.spec.ts +++ b/packages/core/tools/tests/tools.spec.ts @@ -904,6 +904,17 @@ describe('schema DSL edge cases', () => { }) }) + it('emits default value in JSON Schema property', () => { + const spec = { + limit: { type: 'number', default: 25 }, + } satisfies SchemaSpec + const jsonSchema = schemaSpecToJsonSchema(spec) + expect(jsonSchema.properties['limit']).toMatchObject({ + type: 'number', + default: 25, + }) + }) + it('handles array items without nested properties (plain type array)', () => { const spec = { tags: { type: 'array', items: { type: 'string' } }, @@ -915,12 +926,28 @@ describe('schema DSL edge cases', () => { }) }) - it('emits only the type when optional fields are omitted', () => { + it('handles enum and default together in one property', () => { + const spec = { + level: { type: 'string', enum: ['low', 'high'], default: 'low' }, + } satisfies SchemaSpec + const jsonSchema = schemaSpecToJsonSchema(spec) + expect(jsonSchema.properties['level']).toMatchObject({ + type: 'string', + enum: ['low', 'high'], + default: 'low', + }) + }) + + it('omits description, enum, default keys when not specified', () => { const spec = { bare: { type: 'string' }, } satisfies SchemaSpec const jsonSchema = schemaSpecToJsonSchema(spec) - expect(jsonSchema.properties['bare']).toEqual({ type: 'string' }) + const prop = jsonSchema.properties['bare'] as Record + expect(prop).toEqual({ type: 'string' }) + expect('description' in prop).toBe(false) + expect('enum' in prop).toBe(false) + expect('default' in prop).toBe(false) }) it('handles array with no items (items omitted)', () => { @@ -1110,6 +1137,12 @@ describe('validateArgs (the runtime-validation RFC, part 1)', () => { expect(validateArgs(spec, { path: '/tmp', extra: 1 })).toEqual([]) }) + it('does not apply defaults (validation only)', () => { + const spec = { limit: { type: 'number', default: 25 } } satisfies SchemaSpec + // absent optional is valid, and validation does not synthesize the default + expect(validateArgs(spec, {})).toEqual([]) + }) + it('type-checks primitives', () => { const spec = { s: { type: 'string' }, From 9028c9b63b6c3ed1737c168ae5e1548bab064668 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:35:34 +0800 Subject: [PATCH 043/359] fix: contain ACP update predicate failures --- packages/support/acp-snapshot/src/launcher.ts | 13 +++++++++++-- packages/support/acp-snapshot/tests/harness.spec.ts | 4 ++++ 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 635a02ca35..975b1bb852 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -107,6 +107,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe const updateWaiters: { match: (update: SessionNotification['update']) => boolean resolve: (update: SessionNotification['update']) => void + reject: (reason: unknown) => void }[] = [] const stream = ndJsonStream( Writable.toWeb(child.stdin) as WritableStream, @@ -119,7 +120,15 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe const waiter = updateWaiters[index] /* v8 ignore next 1 -- index is bounded by the array length */ if (waiter === undefined) continue - if (!waiter.match(params.update)) continue + let matches: boolean + try { + matches = waiter.match(params.update) + } catch (error: unknown) { + updateWaiters.splice(index, 1) + waiter.reject(error) + continue + } + if (!matches) continue updateWaiters.splice(index, 1) waiter.resolve(params.update) } @@ -136,7 +145,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe updates, rawStdout: () => Buffer.concat(rawBuffers).toString('utf8'), stderr: () => stderrChunks.join(''), - waitForUpdate: match => new Promise(resolve => updateWaiters.push({ match, resolve })), + waitForUpdate: match => new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })), async close(signal?: NodeJS.Signals): Promise { if (child.exitCode !== null || child.signalCode !== null) return if (signal === undefined) child.stdin.end() diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index ec1ed5cf6f..db715db90c 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -57,7 +57,11 @@ describe('runScenario', () => { await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await launched.client.newSession({ cwd: dir, mcpServers: [] }) const nextChunk = launched.waitForUpdate(update => update.sessionUpdate === 'agent_message_chunk') + const predicateFailure = new Error('predicate failed') + const failedPredicate = launched.waitForUpdate(() => { throw predicateFailure }) + .catch((error: unknown): unknown => error) await launched.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) + expect(await failedPredicate).toBe(predicateFailure) expect((await nextChunk).sessionUpdate).toBe('agent_message_chunk') expect(launched.updates.some(update => update.sessionUpdate === 'agent_message_chunk')).toBe(true) expect(launched.rawStdout()).toContain('permission:{\\"outcome\\":\\"cancelled\\"}') From 7d711c44a8a6202680f2801ba16b391858715163 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:41:01 +0800 Subject: [PATCH 044/359] fix: keep remote subagent ids parent-scoped --- .../2026-06-20-unify-agent-and-session-id.md | 4 ++-- .../core/agent-loop/tests/scope-lifecycle.spec.ts | 2 +- packages/subagent/subagent-acp/README.md | 2 ++ packages/subagent/subagent-acp/src/run.ts | 15 ++++++++++----- .../subagent-acp/tests/subagent-acp.spec.ts | 10 ++++++++-- packages/subagent/subagent/src/types.ts | 2 +- 6 files changed, 24 insertions(+), 11 deletions(-) diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index be1052830a..032eae4f7d 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -14,7 +14,7 @@ Session itself repeated the same fact as `Session.id` and `Session.header.id`. C ## Decision -An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process and ACP subagent creation use the child session id; and `Session.id` derives from `header.id`. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between the ids are gone. +An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process subagent creation uses the child session id; and `Session.id` derives from `header.id`. A remote ACP run has no local agent/session pair: it keeps one parent-minted lifecycle id while the child server's wire-local session id remains private to ACP calls. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between local ids are gone. The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. @@ -28,7 +28,7 @@ The config-driven path keeps `agents[].id` as a stable configuration label, not - Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. - The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend mints its lifecycle id in the parent namespace because a child server's returned session id is only server-local. - The config-driven resume-or-create policy is explicit and covered across a durable restart. - A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. - Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index c68d96e525..e29e73c393 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -249,7 +249,7 @@ describe('agent scope lifecycle', () => { }) await setupStarted.promise expect(ctx.agents.get(SessionId('atomic'))).toBeUndefined() - expect(ctx.sessions.get(SessionId('atomic-s'))).toBeUndefined() + expect(ctx.sessions.get(SessionId('atomic'))).toBeUndefined() expect(order).toEqual(['setup:start']) gate.resolve(undefined) const handle = await creating diff --git a/packages/subagent/subagent-acp/README.md b/packages/subagent/subagent-acp/README.md index c949685fcc..03b1a856ed 100644 --- a/packages/subagent/subagent-acp/README.md +++ b/packages/subagent/subagent-acp/README.md @@ -6,6 +6,8 @@ The ACP provider runs each subagent in a fresh subprocess and drives it as an Ag `start(request)` performs `spawn` → ACP `initialize` → `newSession` before it fulfills. Fulfillment therefore means a remote session is ready and ownership has transferred to the caller. A spawn, initialization, new-session, or pre-publication cancellation failure rejects only after the subprocess has been reaped. +The returned run id is minted in the parent namespace. The child server's session id remains private to ACP wire calls because ACP guarantees it only within that fresh child process; using it as the parent lifecycle id could collide with another remote run or a local agent. + After publication, the provider sends the prompt and collects streamed `agent_message_chunk` text into `SubagentResult.output`. A prompt/transport failure resolves with `stopReason: 'error'`, or `aborted` when the required request signal or disposal requested cancellation. `dispose()` is idempotent. It removes the signal listener, requests ACP cancellation when possible, closes stdin, waits `disposeEofGraceMs`, escalates to SIGTERM, waits `disposeGraceMs`, and finally uses SIGKILL if necessary. Every run uses a fresh process; process pooling is not implemented. diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 1cc220204f..7d0c11cbe1 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -23,6 +23,7 @@ */ import { spawn } from 'node:child_process' +import { randomUUID } from 'node:crypto' import { Readable, Writable } from 'node:stream' import { ClientSideConnection, @@ -190,6 +191,10 @@ function toError(value: unknown): Error { */ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpec): Promise { if (request.signal.aborted) throw new Error('subagent request was aborted before the ACP child started') + // ACP session ids are unique only within the child server. The lifecycle id + // is minted in the parent namespace so fresh processes cannot collide with + // each other or with a local agent that happens to use the same session id. + const id = SessionId(randomUUID()) // Spawn the child ACP agent. stdin = ACP request channel, stdout = ACP // response channel, stderr = INHERIT so the child's diagnostics surface on the @@ -257,7 +262,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe ), ) - let sessionId: SessionId | undefined + let sessionId: string | undefined // Resolves when a cancel is requested, so `result` can settle `aborted` even // if the child never cooperates with `session/cancel` (it ignores the notify, // or the prompt wedges). The result path races this against the ACP drive: the @@ -306,7 +311,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe clientCapabilities: {}, }) const session = await conn.newSession({ cwd: spec.cwd, mcpServers: [] }) - sessionId = SessionId(session.sessionId) + sessionId = session.sessionId if (flags.cancelled) throw new Error('subagent cancelled before the ACP session started') })(), spawnFailed.then((err): never => { throw err }), @@ -322,7 +327,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe // guard keeps that cross-closure invariant explicit for TypeScript. /* v8 ignore next */ if (sessionId === undefined) throw new Error('ACP child published without a session id') - const runId = sessionId + const remoteSessionId = sessionId const result: Promise = (async (): Promise => { try { @@ -334,7 +339,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe // succeeds, transport/process failure rejects the in-flight prompt RPC. const prompt = async (): Promise => { // The startup phase cannot fulfill without assigning the session id. - const promptResult = await conn.prompt({ sessionId: runId, prompt: toAcpPrompt(request.prompt) }) + const promptResult = await conn.prompt({ sessionId: remoteSessionId, prompt: toAcpPrompt(request.prompt) }) return { output: collectOutput(), stopReason: acpStopReason(promptResult.stopReason) } } return await Promise.race([ @@ -368,7 +373,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe let disposal: Promise | undefined return { - id: runId, + id, result, dispose(): Promise { if (disposal !== undefined) return disposal diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index 115d5c3e97..e5fe05384e 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -121,16 +121,22 @@ describe('buildChildEnv', () => { }) describe('dsh-subagent-acp', () => { - it('drives a child process to completion and returns its streamed output', async () => { + it('drives child processes with parent-unique run ids and returns streamed output', async () => { const ctx = await setup({ MOCK_TEXT: 'hello from acp child', MOCK_STOP: 'end_turn', MOCK_SESSION_ID: 'acp-child-session' }) const run = await ctx.subagents.start('acp', request('do X')) - expect(run.id).toBe('acp-child-session') + expect(run.id).not.toBe('acp-child-session') const result = await run.result expect(result.stopReason).toBe('completed') expect(text(result.output)).toBe('hello from acp child') const disposal = run.dispose() expect(run.dispose()).toBe(disposal) await disposal + + const nextRun = await ctx.subagents.start('acp', request('do X again')) + expect(nextRun.id).not.toBe(run.id) + expect(nextRun.id).not.toBe('acp-child-session') + await nextRun.result + await nextRun.dispose() }) it('maps a max_tokens stop reason', async () => { diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 8d360b1182..827c2db7a7 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -147,7 +147,7 @@ export interface SubagentResult { * presence of the method IS the capability — narrow before calling. */ export interface SubagentRun { - /** The child agent's id (local in-process runs are already published in `ctx.agents`; remote transports need not publish locally). */ + /** Parent-scoped run id. Local runs use the published child session id; remote providers mint an id unique in the parent namespace. */ readonly id: SessionId /** * Resolves with the child's terminal {@link SubagentResult} when the run From a415d8fdb1b3de4425495b6c87707b58f5c3f65f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:43:10 +0800 Subject: [PATCH 045/359] docs: remove stale streamed-prefix rationale --- .../implemented/testing/2026-06-11-property-based-testing.md | 2 +- packages/llm/llm/src/assembler.ts | 5 ++--- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/docs/rfc/implemented/testing/2026-06-11-property-based-testing.md b/docs/rfc/implemented/testing/2026-06-11-property-based-testing.md index 67404ab49a..db7a9c8a79 100644 --- a/docs/rfc/implemented/testing/2026-06-11-property-based-testing.md +++ b/docs/rfc/implemented/testing/2026-06-11-property-based-testing.md @@ -20,7 +20,7 @@ Adopt `fast-check` (a root devDependency) with one `tests/properties.spec.ts` pe ## Consequences - Generator quality is the value lever — the generators bias toward small index pools and short strings so collisions and interleavings are common. -- **It already paid off:** the BlockAssembler stream found a real bug — a duplicate `block-end` at the same index overwrote an already-flushed block, so the streamed prefix disagreed with final `blocks()`. Fixed (first close wins, matching the existing straggler rule) with a dedicated regression test. +- **It already paid off:** the BlockAssembler stream found a real bug — a duplicate `block-end` at the same index rewrote a completed block. Fixed (first close wins, matching the existing straggler rule) with a dedicated regression test. - A property flake from a timeout is a finding, not something to retry away. The loop properties are deterministic by construction (settle on `agent/status`), so a hang is a real defect. - Property tests supplement, not replace, the example tests that pin specific branches for the 100%-coverage gate. diff --git a/packages/llm/llm/src/assembler.ts b/packages/llm/llm/src/assembler.ts index fb34afe0b9..1dd023d177 100644 --- a/packages/llm/llm/src/assembler.ts +++ b/packages/llm/llm/src/assembler.ts @@ -72,9 +72,8 @@ export class BlockAssembler { case 'block-end': { const partial = this.ensure(chunk.index, chunk.block.type) // First close wins: a second block-end for an already-closed index is - // a straggler (same rule as post-close deltas). Ignoring it keeps the - // streamed prefix and the final blocks() in agreement — otherwise a - // re-close could rewrite a block already flushed downstream. + // a straggler (same rule as post-close deltas). Ignoring it prevents a + // later chunk from rewriting a completed block. if (partial.block) return partial.block = chunk.block return From 60ce23d77c52b6f4c183c320d2a1b54c4aedea7f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:07:37 +0800 Subject: [PATCH 046/359] fix: surface ACP launcher spawn failures --- packages/support/acp-snapshot/README.md | 2 +- packages/support/acp-snapshot/src/harness.ts | 1 + packages/support/acp-snapshot/src/launcher.ts | 22 ++++++++++++++++++- .../acp-snapshot/tests/harness.spec.ts | 13 ++++++++++- 4 files changed, 35 insertions(+), 3 deletions(-) diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 4a43d0eef9..0058e9116f 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -4,7 +4,7 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tie Four layers, importable separately: -- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. +- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index 93bb556ba6..d04b0bc2b5 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -214,6 +214,7 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise }, }) const active = launched + await active.spawned const { client } = active for (const step of input.steps) { diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 975b1bb852..3508b02ec5 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -53,6 +53,8 @@ export interface AcpTestLaunchOptions { export interface LaunchedAcpTestAgent { /** The child process, exposed for process-level assertions. */ child: ChildProcessWithoutNullStreams + /** Resolve when the OS spawns the child; reject with its asynchronous spawn failure. */ + spawned: Promise /** The SDK connection backed by the child's stdio. */ client: ClientSideConnection /** Session updates in receive order. */ @@ -90,6 +92,18 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe stdio: ['pipe', 'pipe', 'pipe'], }, ) + // A spawn-level failure is an asynchronous `error` event. Observe it in the + // same tick as spawn so a missing cwd or OS rejection cannot crash the test + // runner, then make startup and shutdown surface the original error. + const childFailure = new Promise(resolve => child.once('error', resolve)) + const spawned = Promise.race([ + new Promise(resolve => child.once('spawn', resolve)), + childFailure.then((error): never => { throw error }), + ]) + // `spawned` is public and close() also awaits it, but a caller may ignore both. + // Keep that misuse from turning the already-observed child error into an + // unhandled promise rejection. + void spawned.catch(() => undefined) const stderrChunks: string[] = [] child.stderr.setEncoding('utf8') @@ -141,16 +155,22 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe return { child, + spawned, client, updates, rawStdout: () => Buffer.concat(rawBuffers).toString('utf8'), stderr: () => stderrChunks.join(''), waitForUpdate: match => new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })), async close(signal?: NodeJS.Signals): Promise { + await spawned if (child.exitCode !== null || child.signalCode !== null) return if (signal === undefined) child.stdin.end() else child.kill(signal) - await waitForExit(child) + const failure = await Promise.race([ + waitForExit(child).then((): undefined => undefined), + childFailure, + ]) + if (failure !== undefined) throw failure }, } } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index db715db90c..69c02a407f 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -40,6 +40,13 @@ async function scenario(behavior: object): Promise<{ dir: string; fixtureFile: s const boot: InputStep[] = [{ op: 'initialize' }, { op: 'newSession' }] describe('runScenario', () => { + it('surfaces an asynchronous child spawn failure through startup and close', async () => { + const { dir } = await scenario({}) + const launched = launchAcpTestAgent({ agent: AGENT, cwd: join(dir, 'missing') }) + await expect(launched.spawned).rejects.toMatchObject({ code: 'ENOENT' }) + await expect(launched.close()).rejects.toMatchObject({ code: 'ENOENT' }) + }) + it('centralizes ACP boot, captures, updates, fail-closed permissions, and shutdown', { timeout: 20_000 }, async () => { const { dir, fixtureFile } = await scenario({ permissionProbe: true, echoEnv: true, stderrNote: 'launcher stderr' }) const sessionsRoot = await mkdtemp(join(tmpdir(), 'acp-launcher-sessions-')) @@ -72,7 +79,11 @@ describe('runScenario', () => { // The minimal shape needs no environment or config override. const minimal = launchAcpTestAgent({ agent: AGENT, cwd: dir }) await minimal.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) - await minimal.close() + const childFailure = new Error('child process failed') + const exited = new Promise(resolve => minimal.child.once('exit', () => { resolve() })) + minimal.child.emit('error', childFailure) + await expect(minimal.close('SIGKILL')).rejects.toBe(childFailure) + await exited }) it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { From e9d1e1cdda70eedb49a12f9adce2afb18caa4c00 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:19:24 +0800 Subject: [PATCH 047/359] docs: update ACP ownership routing --- .../rfc/implemented/feature/2026-06-14-acp-multi-session.md | 4 ++-- .../rfc/implemented/feature/2026-06-25-ask-user-question.md | 2 +- docs/rfc/implemented/feature/2026-07-06-approval-seam.md | 6 +++--- packages/ui/acp/README.md | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md b/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md index 77fa2b4669..64961bee89 100644 --- a/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md +++ b/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md @@ -8,11 +8,11 @@ An ACP editor can keep several conversations alive over one agent subprocess. A ## Decision -The ACP bridge stores live sessions in `Map` and keeps a `WeakMap` reverse index for agent-scoped callbacks. A record owns its agent handle, in-flight prompt, live tool-call presentation state, pending idle config switches, session cwd, and client capability snapshot. A separate loading-id set reserves each id before asynchronous resume so two pipelined loads cannot construct duplicate agents; distinct ids may load concurrently. +The ACP bridge stores live sessions in `Map`. Agent-scoped callbacks use `ownedRecord`: look up `agent.session.id` in that forward map and accept the record only when it owns the exact agent object, so a foreign same-id object cannot claim the session. A record owns its agent handle, in-flight prompt, live tool-call presentation state, pending idle config switches, session cwd, and client capability snapshot. A separate loading-id set reserves each id before asynchronous resume so two pipelined loads cannot construct duplicate agents; distinct ids may load concurrently. Every `session/event` and `agent/status` callback resolves the owning record before sending or settling anything. Each session permits one in-flight prompt independently. The prompt records a log watermark, captures its own `turn/start`, and settles only on the matching `turn/end`; a late end from a cancelled prior turn cannot resolve a newer prompt. `session/cancel` addresses one record and calls only that agent's queue-aware cancel path. -Permission ownership uses the same reverse index. The ACP `approval/request` answerer prompts only the editor session that owns the requesting agent and delegates foreign requests. User-interaction elicitations likewise route by agent ownership. Per-session sandbox and approval config values fold only that session's events, with pending idle switches stored on that record until the next turn anchors them. +Permission ownership uses the same exact-agent check against the forward map. The ACP `approval/request` answerer prompts only the editor session that owns the requesting agent and delegates foreign requests. User-interaction elicitations likewise route by agent ownership. Per-session sandbox and approval config values fold only that session's events, with pending idle switches stored on that record until the next turn anchors them. Background bash tasks carry an opaque owner token equal to the owning session id. `bash_output` and `bash_kill` compare the caller's token with the executor's task ownership before reading or killing; a predictable task id alone grants no access. Ownership is stored with the executor task, so a tool plugin reload does not erase it. diff --git a/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md b/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md index 9320189de1..42e5d9a7ab 100644 --- a/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md +++ b/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md @@ -22,7 +22,7 @@ Providers return `{ answers: [{ id, selected, custom? }] }`. `selected` is alway `dsh-stdio-agent`'s in-package readline module renders each question, shows each option's `description` on the next line, supports comma/space-separated numeric choices for `multi_select`, accepts free-form custom answers, and rejects pending questions on abort, provider disposal, or stdin EOF. A batched request is asked in order and resolved as one answer object. The stdio provider serializes simultaneous requests with an internal queue so only one prompt owns stdin at a time. -`dsh-acp` provides the same seam for ACP sessions. It routes an ask request from the calling `Agent` through the bridge's `agent→sessionId` reverse map and calls ACP `unstable_createElicitation` with a session-scoped form for each question. Single-select options become a `choice` string enum; `multi_select` options become a `choice` array enum; optionless questions use a required `custom` text field. If the client returns both `choice` and non-empty `custom`, the custom answer wins. ACP `decline`/`cancel`, a missing answer, a missing session, and a client without elicitation support all become structured `UserInteractionError`s. +`dsh-acp` provides the same seam for ACP sessions. It resolves the calling `Agent` through `ownedRecord`, requiring the forward session-map record at `agent.session.id` to own that exact agent object, and calls ACP `unstable_createElicitation` with a session-scoped form for each question. Single-select options become a `choice` string enum; `multi_select` options become a `choice` array enum; optionless questions use a required `custom` text field. If the client returns both `choice` and non-empty `custom`, the custom answer wins. ACP `decline`/`cancel`, a missing answer, a missing session, and a client without elicitation support all become structured `UserInteractionError`s. The ACP mapping deliberately uses elicitation, not `session/request_permission`. `request_permission` is still reserved for the separate permission gate: it is a yes/no-or-policy authorization protocol around tool execution. `ask_user_question` is a general information-gathering tool with optional free-form answers, so ACP form elicitation is the closer protocol fit. The bridge's session routing is shared with the future permission gate, but the user intent is different. diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 5d82226a96..c5d61b0edb 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -65,9 +65,9 @@ The seam also owns the session-scoped approval policy — the approval knob of t #### The ACP answerer -The bridge registers the first real answerer: it resolves the owning session through its existing `WeakMap` reverse map, issues `session/request_permission` with the request's `callId` as the `toolCall` reference and the one-shot options `allow_once`/`reject_once`, and maps the response — selected `allow-once` → `allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled` → `cancelled`. A request for a foreign agent — or one without a `callId`, since the protocol prompt must attach to a tool call — delegates via `next()`. A rejected RPC (client gone mid-prompt) propagates to the service, which contains it as `unavailable`. Whether a call ASKS at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment. +The bridge registers the first real answerer: it resolves the owning session through `ownedRecord`, requiring the forward session-map record at `agent.session.id` to own that exact agent object, issues `session/request_permission` with the request's `callId` as the `toolCall` reference and the one-shot options `allow_once`/`reject_once`, and maps the response — selected `allow-once` → `allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled` → `cancelled`. A request for a foreign agent — or one without a `callId`, since the protocol prompt must attach to a tool call — delegates via `next()`. A rejected RPC (client gone mid-prompt) propagates to the service, which contains it as `unavailable`. Whether a call ASKS at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment. -The answerer routes through the bridge's reverse-map ownership seam described by [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md). +The answerer routes through the bridge's exact-agent ownership check described by [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md). #### Audit, and what the model sees @@ -137,5 +137,5 @@ In-repo precedents this design copies or contrasts with: - The `fs/write-intent` gate (`packages/fs/fs/`) — the documented single-occupancy decision-slot waterfall semantics (first answer wins, delegate via `next()`) the answerer contract reuses. - `hook/invoked`/`hook/result` — the log-only audit-pair precedent `approval/asked`/`approval/decided` follows; [the hook-bridges RFC](2026-06-30-hook-bridges.md) ships `permissionDecision: ask`, the first producer. - [The interception-seams RFC](2026-06-30-interception-seams.md) — the `tools/pre-execute` `allow`/`deny`/`ask` vocabulary whose `ask` this seam services. -- [The ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) — the `WeakMap` ownership seam the answerer routes through; [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md) — the per-session permission-ownership blocker this implements. +- [The ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) — the exact-agent ownership check against the forward session map that the answerer routes through; [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md) — the per-session permission-ownership blocker this implements. - The opportunistic `ctx.get()` consumption pattern (`tool-bash`'s owner-token lookup, the loop's persistence probe) — how `dsh-tools` consumes the seam without gating its fiber on it. diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 31a865c068..4b9a278707 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -75,7 +75,7 @@ A `session/prompt` resolves or rejects exactly once from the canonical `session/ ## Permission prompts -The bridge registers an `approval/request` waterfall listener — the ACP answerer of the [user-approval seam](../user-approval/README.md). When `ctx.approval` routes an `ask` for an agent the bridge owns, the listener resolves the owning session through the reverse map and issues `session/request_permission` with the request's `callId` as the `toolCall` reference (the editor attaches the prompt to the already-streamed call) and the one-shot options `allow_once`/`reject_once` (`allow_always` is deferred to the approval RFC's grant-storage question). Outcomes map `allow-once → allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled → cancelled`. A request for an agent the bridge does NOT own — or one without a `callId` to attach to — delegates via `next()` so another answerer or the seam's fail-closed `unavailable` default takes it. A rejected `requestPermission` RPC (client gone mid-prompt) propagates to the ApprovalService, which contains it as `unavailable`. Whether a call asks at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment; without such policy, tools keep the executor's full authority. +The bridge registers an `approval/request` waterfall listener — the ACP answerer of the [user-approval seam](../user-approval/README.md). When `ctx.approval` routes an `ask` for an agent the bridge owns, the listener resolves the owning `SessionRecord` through `ownedRecord`, which looks up `agent.session.id` in the forward session map and requires the record to own that exact agent object. It then issues `session/request_permission` with the request's `callId` as the `toolCall` reference (the editor attaches the prompt to the already-streamed call) and the one-shot options `allow_once`/`reject_once` (`allow_always` is deferred to the approval RFC's grant-storage question). Outcomes map `allow-once → allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled → cancelled`. A request for an agent the bridge does NOT own — or one without a `callId` to attach to — delegates via `next()` so another answerer or the seam's fail-closed `unavailable` default takes it. A rejected `requestPermission` RPC (client gone mid-prompt) propagates to the ApprovalService, which contains it as `unavailable`. Whether a call asks at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment; without such policy, tools keep the executor's full authority. ## Disposal & disconnect From 140d32681ef2fc4b35dbae710044c7b7c4e693b7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:33:22 +0800 Subject: [PATCH 048/359] fix: make ACP test teardown failure-safe --- examples/acp-agent/tests/acp.e2e.ts | 14 ++++-- examples/acp-agent/tests/hooks.e2e.ts | 14 ++++-- .../sandbox-acp-agent/tests/escalation.e2e.ts | 14 ++++-- packages/support/acp-snapshot/README.md | 2 +- packages/support/acp-snapshot/src/harness.ts | 44 ++++++++++++------- packages/support/acp-snapshot/src/launcher.ts | 25 +++++++++-- .../acp-snapshot/tests/harness.spec.ts | 8 ++-- 7 files changed, 86 insertions(+), 35 deletions(-) diff --git a/examples/acp-agent/tests/acp.e2e.ts b/examples/acp-agent/tests/acp.e2e.ts index 4b6c675208..871006dfb4 100644 --- a/examples/acp-agent/tests/acp.e2e.ts +++ b/examples/acp-agent/tests/acp.e2e.ts @@ -30,10 +30,16 @@ let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - await spawned?.close('SIGKILL') - spawned = undefined - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - workdir = undefined + try { + await spawned?.close('SIGKILL') + } finally { + spawned = undefined + try { + if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) + } finally { + workdir = undefined + } + } }) describe('acp-agent over real stdio (no key required)', () => { diff --git a/examples/acp-agent/tests/hooks.e2e.ts b/examples/acp-agent/tests/hooks.e2e.ts index a553addc96..8dc169f437 100644 --- a/examples/acp-agent/tests/hooks.e2e.ts +++ b/examples/acp-agent/tests/hooks.e2e.ts @@ -38,10 +38,16 @@ let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - await spawned?.close('SIGKILL') - spawned = undefined - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - workdir = undefined + try { + await spawned?.close('SIGKILL') + } finally { + spawned = undefined + try { + if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) + } finally { + workdir = undefined + } + } }) describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: a PreToolUse hook blocks bash (real model)', () => { diff --git a/examples/sandbox-acp-agent/tests/escalation.e2e.ts b/examples/sandbox-acp-agent/tests/escalation.e2e.ts index a7e8787e36..0ddaa6426e 100644 --- a/examples/sandbox-acp-agent/tests/escalation.e2e.ts +++ b/examples/sandbox-acp-agent/tests/escalation.e2e.ts @@ -81,10 +81,16 @@ let spawned: Spawned | undefined let workdir: string | undefined afterEach(async () => { - await spawned?.close('SIGKILL') - spawned = undefined - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - workdir = undefined + try { + await spawned?.close('SIGKILL') + } finally { + spawned = undefined + try { + if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) + } finally { + workdir = undefined + } + } }) describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () => { diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 0058e9116f..26192f1cac 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -4,7 +4,7 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tie Four layers, importable separately: -- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. +- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Shutdown waits for process exit before resolving or propagating a child error, so callers can remove owned paths after either outcome. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index d04b0bc2b5..3db1355b0f 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -163,7 +163,7 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise let launched: LaunchedAcpTestAgent | undefined let sessionId: string | undefined let sessionLogs: HarvestedLog[] = [] - try { + const outcome = await (async (): Promise => { // Seed the workspace if the scenario ships one (a file the agent reads/edits). // Copied into the temp cwd so the agent's bash tools see it; the goldens // normalize the cwd, so the seeded paths stay stable across runs. @@ -231,22 +231,36 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise // Harvest EVERY persisted log (parent + any subagent children) while the // temp dirs still exist, ordered primary-first. sessionLogs = await harvestSessionLogs(sessionsRoot) - } finally { - // Failure-safe teardown: kill a still-running child and drop the temp dirs - // even if seeding/spawn/a step/harvest threw, so a flaky run never leaks a - // process or dir. `launched` is undefined only if launch itself threw. - await launched?.close('SIGKILL') - await rm(cwd, { recursive: true, force: true }) - await rm(sessionsRoot, { recursive: true, force: true }) - } + return { + rawStdout: launched.rawStdout(), + stderr: launched.stderr(), + cwd, + ...sessionId !== undefined ? { sessionId } : {}, + sessionLogs, + } + })().then( + value => ({ status: 'fulfilled', value } as const), + (error: unknown) => ({ status: 'rejected', error } as const), + ) - return { - rawStdout: launched.rawStdout(), - stderr: launched.stderr(), - cwd, - ...sessionId !== undefined ? { sessionId } : {}, - sessionLogs, + // Failure-safe teardown: wait for a still-running child, then attempt BOTH + // directory removals even when an earlier cleanup rejects. The main outcome + // wins over teardown noise so a step/harvest failure is never replaced; on a + // successful run, the first cleanup failure remains visible to the caller. + const cleanupResults: PromiseSettledResult[] = [] + const cleanup = async (action: () => Promise): Promise => { + cleanupResults.push(...await Promise.allSettled([action()])) } + /* v8 ignore next 1 -- launch itself can only throw on a defensive synchronous spawn API failure */ + await cleanup(() => launched?.close('SIGKILL') ?? Promise.resolve()) + await cleanup(() => rm(cwd, { recursive: true, force: true })) + await cleanup(() => rm(sessionsRoot, { recursive: true, force: true })) + + if (outcome.status === 'rejected') throw outcome.error + const cleanupFailure = cleanupResults.find((result): result is PromiseRejectedResult => result.status === 'rejected') + /* v8 ignore next 1 -- defensive OS cleanup failure after an otherwise successful real subprocess run */ + if (cleanupFailure !== undefined) throw cleanupFailure.reason + return outcome.value } /** Drive one input step over the client connection. */ diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 3508b02ec5..7f2ec9b0a7 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -95,7 +95,10 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // A spawn-level failure is an asynchronous `error` event. Observe it in the // same tick as spawn so a missing cwd or OS rejection cannot crash the test // runner, then make startup and shutdown surface the original error. - const childFailure = new Promise(resolve => child.once('error', resolve)) + // Keep observing after the first error: a fallback kill attempted during + // shutdown may itself report another process error, which must not become an + // unhandled EventEmitter error after the promise has already settled. + const childFailure = new Promise(resolve => child.on('error', resolve)) const spawned = Promise.race([ new Promise(resolve => child.once('spawn', resolve)), childFailure.then((error): never => { throw error }), @@ -163,14 +166,23 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe waitForUpdate: match => new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })), async close(signal?: NodeJS.Signals): Promise { await spawned - if (child.exitCode !== null || child.signalCode !== null) return + if (!isRunning(child)) return + const exited = waitForExit(child) if (signal === undefined) child.stdin.end() else child.kill(signal) const failure = await Promise.race([ - waitForExit(child).then((): undefined => undefined), + exited.then((): undefined => undefined), childFailure, ]) - if (failure !== undefined) throw failure + if (failure === undefined) return + + // An `error` after spawn is not an exit edge: in particular, a failed + // signal can leave the subprocess live. Force termination, await the + // already-observed exit edge, and only then propagate the child error so + // callers may safely remove cwd/session resources after close rejects. + child.kill('SIGKILL') + await exited + throw failure }, } } @@ -179,3 +191,8 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe function waitForExit(child: ChildProcessWithoutNullStreams): Promise { return new Promise(resolve => child.once('exit', () => { resolve() })) } + +/** Whether the child still lacks either OS termination marker. */ +function isRunning(child: ChildProcessWithoutNullStreams): boolean { + return child.exitCode === null && child.signalCode === null +} diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 69c02a407f..3c1bb0d44a 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -80,10 +80,12 @@ describe('runScenario', () => { const minimal = launchAcpTestAgent({ agent: AGENT, cwd: dir }) await minimal.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const childFailure = new Error('child process failed') - const exited = new Promise(resolve => minimal.child.once('exit', () => { resolve() })) + let exited = false + minimal.child.once('exit', () => { exited = true }) minimal.child.emit('error', childFailure) - await expect(minimal.close('SIGKILL')).rejects.toBe(childFailure) - await exited + await expect(minimal.close('SIGTERM')).rejects.toBe(childFailure) + // close rejects only after the fallback SIGKILL has produced an exit edge. + expect(exited).toBe(true) }) it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { From 58e61ae20ba28101be0bed01505b03ec20cd6a7e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:37:58 +0800 Subject: [PATCH 049/359] fix: retain stdio target across agent replacement --- packages/ui/stdio-agent/src/stdio-chat.ts | 19 +++++++++++------ .../ui/stdio-agent/tests/stdio-chat.spec.ts | 21 +++++++++++++++++++ 2 files changed, 34 insertions(+), 6 deletions(-) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index cb9ce0bc10..bfb58e3a57 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -95,13 +95,20 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns exactly one pre-created agent. Hold the live object directly: - // its per-run id is intentionally fresh, while `main` remains only the - // terminal's fixed display label. - let target: Agent | undefined = ctx.agents.list()[0] - ctx.on('agent/created', (agent) => { target ??= agent }) + // This app owns one root agent. Hold the live object directly: its per-run id + // is intentionally fresh, while `main` remains only the terminal's fixed + // display label. HMR may publish the replacement before old teardown emits + // disposed, so a target disposal reselects the surviving root from the live + // registry instead of leaving the terminal detached. Fork children carry + // parentSession lineage and must never become the terminal target. + const rootAgent = (): Agent | undefined => + ctx.agents.list().find(agent => agent.session.header.parentSession === undefined) + let target: Agent | undefined = rootAgent() + ctx.on('agent/created', (agent) => { + if (target === undefined && agent.session.header.parentSession === undefined) target = agent + }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = undefined + if (target === agent) target = rootAgent() }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 69ca5f8837..2b1df53921 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -230,6 +230,27 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 1] ') }) + it('retargets a surviving root when HMR publishes it before disposing the old root', async () => { + const { ctx, input } = await setup() + const oldRoot = makeAgent('old-root') + const child = makeAgent('child') + ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id + const replacement = makeAgent('replacement') + const disposeOld = ctx.agents.register(oldRoot) + ctx.agents.register(child) + ctx.agents.register(replacement) + + // The replacement's created edge arrived while oldRoot was still targeted. + // Once oldRoot is removed, registry order is child then replacement; the + // UI must skip the surviving child and route input to the replacement root. + disposeOld() + input.feed('after hmr') + await new Promise(resolve => setImmediate(resolve)) + + expect(child.sent).toEqual([]) + expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) + }) + it('renders tool/call and tool/result session events', async () => { const { ctx, out } = await setup() const session = {} as Session From 3bd2052d7251b9500e8afca02aaee64ca8b2ad40 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:52:46 +0800 Subject: [PATCH 050/359] fix: allow lineage-bearing stdio targets --- packages/ui/stdio-agent/src/stdio-chat.ts | 24 +++++++++---------- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 17 ++++++++++++- 2 files changed, 27 insertions(+), 14 deletions(-) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index bfb58e3a57..2a4d620494 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -95,20 +95,18 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns one root agent. Hold the live object directly: its per-run id - // is intentionally fresh, while `main` remains only the terminal's fixed - // display label. HMR may publish the replacement before old teardown emits - // disposed, so a target disposal reselects the surviving root from the live - // registry instead of leaving the terminal detached. Fork children carry - // parentSession lineage and must never become the terminal target. - const rootAgent = (): Agent | undefined => - ctx.agents.list().find(agent => agent.session.header.parentSession === undefined) - let target: Agent | undefined = rootAgent() - ctx.on('agent/created', (agent) => { - if (target === undefined && agent.session.header.parentSession === undefined) target = agent - }) + // This app owns one configured agent. Hold the live object directly: its + // per-run id is intentionally fresh, while `main` remains only the + // terminal's fixed display label. At install the configured agent is the + // earliest registry entry (it creates any subagents later). During HMR the + // replacement is published after the old tree, so when old teardown finally + // emits disposed, the newest survivor is the replacement. Persisted + // parentSession lineage is deliberately irrelevant: a resumed child session + // can itself be this process's configured top-level agent. + let target: Agent | undefined = ctx.agents.list()[0] + ctx.on('agent/created', (agent) => { target ??= agent }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = rootAgent() + if (target === agent) target = ctx.agents.list().at(-1) }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2b1df53921..2654a05680 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -185,6 +185,9 @@ describe('createStdioChat rendering', () => { await ctx.plugin(AgentRegistry) await ctx.plugin(UserInteractionService) const agent = makeAgent('main') + // Durable lineage does not imply runtime child ownership: the stdio app + // may explicitly resume a persisted fork as its one configured agent. + ;(agent.session.header as { parentSession?: string }).parentSession = 'persisted-parent' ctx.agents.register(agent) // registered BEFORE the UI plugin below const { runtime, out } = makeRuntime() await ctx.plugin(Object.assign((inner: Context) => { @@ -196,6 +199,18 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 5] ') }) + it('accepts a lineage-bearing configured agent created after the UI installs', async () => { + const { ctx, input } = await setup() + const resumed = makeAgent('resumed') + ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' + ctx.emit('agent/created', resumed) + + input.feed('continue') + await new Promise(resolve => setImmediate(resolve)) + + expect(resumed.sent).toEqual([[{ type: 'text', text: 'continue' }]]) + }) + it('resets dim styling at turn/end if a turn ends mid-reasoning', async () => { const { ctx, out } = await setup() const session = makeSession('main') @@ -242,7 +257,7 @@ describe('createStdioChat rendering', () => { // The replacement's created edge arrived while oldRoot was still targeted. // Once oldRoot is removed, registry order is child then replacement; the - // UI must skip the surviving child and route input to the replacement root. + // most recently published survivor is the HMR replacement. disposeOld() input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) From e2a5a160d3763ee7faaa9b4235ae7284144f05ee Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:00:10 +0800 Subject: [PATCH 051/359] fix: settle ACP update waiters on shutdown --- packages/support/acp-snapshot/src/launcher.ts | 43 ++++++++++++++----- .../acp-snapshot/tests/harness.spec.ts | 3 ++ 2 files changed, 36 insertions(+), 10 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 7f2ec9b0a7..253e67fd5a 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -114,18 +114,26 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe const rawBuffers: Buffer[] = [] const passthrough = new Readable({ read() {} }) - child.stdout.on('data', (buffer: Buffer) => { - rawBuffers.push(buffer) - passthrough.push(buffer) - }) - child.stdout.on('end', () => passthrough.push(null)) - const updates: SessionNotification['update'][] = [] const updateWaiters: { match: (update: SessionNotification['update']) => boolean resolve: (update: SessionNotification['update']) => void reject: (reason: unknown) => void }[] = [] + let updateStreamFailure: Error | undefined + const closeUpdateStream = (): void => { + if (updateStreamFailure !== undefined) return + updateStreamFailure = new Error('ACP test agent update stream closed before a matching session update arrived') + for (const waiter of updateWaiters.splice(0)) waiter.reject(updateStreamFailure) + } + child.stdout.on('data', (buffer: Buffer) => { + rawBuffers.push(buffer) + passthrough.push(buffer) + }) + child.stdout.on('end', () => { + passthrough.push(null) + closeUpdateStream() + }) const stream = ndJsonStream( Writable.toWeb(child.stdin) as WritableStream, Readable.toWeb(passthrough) as ReadableStream, @@ -163,10 +171,21 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe updates, rawStdout: () => Buffer.concat(rawBuffers).toString('utf8'), stderr: () => stderrChunks.join(''), - waitForUpdate: match => new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })), + waitForUpdate(match): Promise { + if (updateStreamFailure !== undefined) return Promise.reject(updateStreamFailure) + return new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })) + }, async close(signal?: NodeJS.Signals): Promise { - await spawned - if (!isRunning(child)) return + try { + await spawned + } catch (error: unknown) { + closeUpdateStream() + throw error + } + if (!isRunning(child)) { + closeUpdateStream() + return + } const exited = waitForExit(child) if (signal === undefined) child.stdin.end() else child.kill(signal) @@ -174,7 +193,10 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe exited.then((): undefined => undefined), childFailure, ]) - if (failure === undefined) return + if (failure === undefined) { + closeUpdateStream() + return + } // An `error` after spawn is not an exit edge: in particular, a failed // signal can leave the subprocess live. Force termination, await the @@ -182,6 +204,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // callers may safely remove cwd/session resources after close rejects. child.kill('SIGKILL') await exited + closeUpdateStream() throw failure }, } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 3c1bb0d44a..192d36dc6c 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -73,7 +73,10 @@ describe('runScenario', () => { expect(launched.updates.some(update => update.sessionUpdate === 'agent_message_chunk')).toBe(true) expect(launched.rawStdout()).toContain('permission:{\\"outcome\\":\\"cancelled\\"}') expect(launched.stderr()).toContain('launcher stderr') + const unmatched = expect(launched.waitForUpdate(() => false)).rejects.toThrow(/update stream closed/) await launched.close() + await unmatched + await expect(launched.waitForUpdate(() => true)).rejects.toThrow(/update stream closed/) await launched.close('SIGKILL') // The minimal shape needs no environment or config override. From c2979322c8b938b1c2e91920740688788867e6d7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:13:42 +0800 Subject: [PATCH 052/359] fix: keep stdio targeting on runtime roots --- docs/cordis-catalog/services.md | 5 ++-- packages/core/agent-loop/src/index.ts | 2 +- .../agent-loop/tests/scope-lifecycle.spec.ts | 18 +++++++++++++ packages/core/agent/README.md | 3 ++- packages/core/agent/src/index.ts | 22 ++++++++++++++-- packages/core/agent/tests/agent.spec.ts | 24 +++++++++++++++--- packages/ui/stdio-agent/src/stdio-chat.ts | 20 +++++++-------- .../ui/stdio-agent/tests/readline.spec.ts | 4 +-- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 25 ++++++++++++------- 9 files changed, 92 insertions(+), 31 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 4d162a55f5..1366fcf6f6 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -30,15 +30,16 @@ setFactory(factory: AgentFactory): () => void async create(options: CreateAgentOptions): Promise async resume(options: ResumeAgentOptions): Promise register(agent: Agent): () => void -enter(agent: Agent): () => void +enter(agent: Agent, owner: Agent | undefined): () => void announce(agent: Agent): void get(id: SessionId): Agent | undefined list(): Agent[] +roots(): Agent[] ``` Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/index.ts:199`](../../packages/core/agent/src/index.ts) +Source: [`packages/core/agent/src/index.ts:201`](../../packages/core/agent/src/index.ts) ## `ctx.approval` — `ApprovalService` diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 33276c01f8..dbe503ff6a 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -229,7 +229,7 @@ class AgentCreationTransaction { this.publishing = true try { this.detachSession = agent.ctx.sessions.enter(session) - this.detachAgent = this.loopCtx.agents.enter(agent) + this.detachAgent = this.loopCtx.agents.enter(agent, this.ownerAgent) agent.ctx.sessions.announce(session) this.assertActive() diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index e29e73c393..610e077a67 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -149,6 +149,24 @@ describe('agent scope lifecycle', () => { await ctx.agents.get(SessionId('a1'))?.whenIdle() }) + it('records agents created through an agent context as non-root runtime children', async () => { + const ctx = await harness() + const root = await ctx.agents.create({ + sessionId: SessionId('runtime-root'), + agentOptions: { model: 'mock' }, + }) + const child = await root.agent.ctx.agents.create({ + sessionId: SessionId('runtime-child'), + agentOptions: { model: 'mock' }, + }) + + expect(ctx.agents.list()).toEqual([root.agent, child.agent]) + expect(ctx.agents.roots()).toEqual([root.agent]) + + await child.dispose() + await root.dispose() + }) + it('scoped registrations live in the agent world and die with the agent', async () => { const ctx = await harness() const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 4eddb050d5..643c15002b 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -11,9 +11,10 @@ Tracks live agents so UI, hook, and orchestrator plugins can find them without i The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh-scope`, key = the agent) — register tools/sections/variables/listeners through it for that agent alone, all unwound on disposal. `agentEvents(ctx, agent)` is the fused dispatcher for ordinary agent-subject operations (carrier + injected subject in one move); its notification mode invokes every listener and contains both synchronous throws and returned-promise rejections. The registry lifecycle pair reuses one stable routing carrier. `assembleContextFor(agent)` builds the per-agent assembly context (`agent` + `scope` together). `CreateAgentOptions.setup(agentCtx)` and `ResumeAgentOptions.setup(agentCtx)` compose a fresh or resumed agent's scoped world while both objects remain unpublished. Setup is trusted, composition-only same-process code: drive the agent only after creation resolves. - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. -- Advanced ordered lifecycle: `enter(agent): () => void` performs the authoritative ID collision check and inserts without announcing; `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. +- Advanced ordered lifecycle: `enter(agent, owner): () => void` performs the authoritative ID collision check and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. - `ctx.agents.get(id: SessionId): Agent | undefined` - `ctx.agents.list(): Agent[]` +- `ctx.agents.roots(): Agent[]` — live agents created without an owning agent context; a resumed lineage-bearing session can still be a runtime root. #### Factory seam (creation) diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index 1306e8004d..b25d1e3cac 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -178,6 +178,8 @@ const NO_FACTORY_MESSAGE = 'no agent factory registered (load an agent-loop plug interface AgentEntry { readonly id: SessionId readonly agent: Agent + /** Runtime creator-agent ownership; independent of durable session lineage. */ + readonly owner: Agent | undefined readonly carrier: Scoped announced: boolean announcing: boolean @@ -303,7 +305,7 @@ export class AgentRegistry extends Service { */ register(agent: Agent): () => void { const dispose = this.ctx.effect(function* (this: AgentRegistry) { - yield this.enter(agent) + yield this.enter(agent, this.ctx.agent) this.announce(agent) }.bind(this), 'agents.register()') // eslint-disable-next-line @typescript-eslint/no-misused-promises -- synchronous cleanup; direct return preserves disposer identity @@ -317,12 +319,15 @@ export class AgentRegistry extends Service { * returned detach closure into its pre-installed composite teardown before * calling {@link announce}. Ordinary callers use {@link register}. * @param agent - the prepared, unpublished agent. + * @param owner - live agent whose scoped context created this agent, or + * undefined for a top-level runtime root. This is runtime ownership, not + * the resumed session's durable parent lineage. * @returns an idempotent closure that removes this exact entry and emits * `agent/disposed` with listener failures contained. When called from a * synchronous `agent/created` listener, removal and disposal wait until * that creation dispatch unwinds. */ - enter(agent: Agent): () => void { + enter(agent: Agent, owner: Agent | undefined): () => void { const id = agent.id const carrier = scopeTarget(agent, agent) // This is the authoritative collision boundary. Concurrent create/resume @@ -331,6 +336,7 @@ export class AgentRegistry extends Service { const entry: AgentEntry = { id, agent, + owner, carrier, announced: false, announcing: false, @@ -438,6 +444,18 @@ export class AgentRegistry extends Service { list(): Agent[] { return [...this.store.values()].map(entry => entry.agent) } + + /** + * All live top-level agents in registration order. A top-level agent was + * created without an owning agent context; durable session lineage does not + * affect this runtime relation, so a resumed fork may still be a root. + * @returns a fresh array; mutating it does not affect the registry. + */ + roots(): Agent[] { + return [...this.store.values()] + .filter(entry => entry.owner === undefined) + .map(entry => entry.agent) + } } export default AgentRegistry diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index cba833b212..5563d01cad 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -42,6 +42,7 @@ describe('AgentRegistry', () => { const dispose = ctx.agents.register(agent) expect(ctx.agents.get(agent.id)).toBe(agent) expect(ctx.agents.list()).toEqual([agent]) + expect(ctx.agents.roots()).toEqual([agent]) expect(() => ctx.agents.register(stubAgent('a1'))).toThrow(/already registered/) dispose() @@ -49,6 +50,23 @@ describe('AgentRegistry', () => { expect(lifecycle).toEqual(['created:a1', 'disposed:a1']) }) + it('tracks runtime creator ownership separately from registry order', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + const root = stubAgent('root') + const child = stubAgent('child') + const detachRoot = ctx.agents.enter(root, undefined) + ctx.agents.announce(root) + const detachChild = ctx.agents.enter(child, root) + ctx.agents.announce(child) + + expect(ctx.agents.list()).toEqual([root, child]) + expect(ctx.agents.roots()).toEqual([root]) + + detachChild() + detachRoot() + }) + it('rolls an entry back and pairs a partially delivered creation when a listener throws', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) @@ -94,7 +112,7 @@ describe('AgentRegistry', () => { ctx.on('agent/disposed', agent => void lifecycle.push(`disposed:${agent.id}`)) const first = stubAgent('split') - const detachFirst = ctx.agents.enter(first) + const detachFirst = ctx.agents.enter(first, undefined) expect(lifecycle).toEqual([]) ctx.agents.announce(first) expect(() => { ctx.agents.announce(first) }).toThrow(/already announced/) @@ -102,7 +120,7 @@ describe('AgentRegistry', () => { detachFirst() const replacement = stubAgent('split') - const detachReplacement = ctx.agents.enter(replacement) + const detachReplacement = ctx.agents.enter(replacement, undefined) detachFirst() expect(ctx.agents.get(replacement.id)).toBe(replacement) expect(() => { ctx.agents.announce(first) }).toThrow(/not live/) @@ -122,7 +140,7 @@ describe('AgentRegistry', () => { }) ctx.on('agent/created', () => void order.push(`second:${ctx.agents.get(agent.id) === agent}`)) ctx.on('agent/disposed', () => void order.push('disposed')) - const detach = ctx.agents.enter(agent) + const detach = ctx.agents.enter(agent, undefined) ctx.agents.announce(agent) expect(order).toEqual(['first:true', 'after-detach:true', 'second:true', 'disposed']) expect(ctx.agents.get(agent.id)).toBeUndefined() diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 2a4d620494..a295274786 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -95,18 +95,16 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns one configured agent. Hold the live object directly: its - // per-run id is intentionally fresh, while `main` remains only the - // terminal's fixed display label. At install the configured agent is the - // earliest registry entry (it creates any subagents later). During HMR the - // replacement is published after the old tree, so when old teardown finally - // emits disposed, the newest survivor is the replacement. Persisted - // parentSession lineage is deliberately irrelevant: a resumed child session - // can itself be this process's configured top-level agent. - let target: Agent | undefined = ctx.agents.list()[0] - ctx.on('agent/created', (agent) => { target ??= agent }) + // This app owns one configured top-level agent. Hold the live object + // directly: its per-run id is intentionally fresh, while `main` remains only + // the terminal's fixed display label. Runtime creator ownership distinguishes + // that root from its subagents even if a child is registered after an HMR + // replacement. Persisted parentSession lineage is deliberately irrelevant: + // a resumed child session can itself be this process's configured root. + let target: Agent | undefined = ctx.agents.roots()[0] + ctx.on('agent/created', () => { target ??= ctx.agents.roots()[0] }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = ctx.agents.list().at(-1) + if (target === agent) target = ctx.agents.roots().at(-1) }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/readline.spec.ts b/packages/ui/stdio-agent/tests/readline.spec.ts index 6116aa356f..fa82db4d96 100644 --- a/packages/ui/stdio-agent/tests/readline.spec.ts +++ b/packages/ui/stdio-agent/tests/readline.spec.ts @@ -16,9 +16,9 @@ function fakeContext(): Context { return { on: vi.fn(() => vi.fn()), effect: vi.fn((callback: () => () => void) => callback()), - // The UI seeds its target object from the registry at install; this suite only + // The UI seeds its root target from the registry at install; this suite only // exercises readline terminal-mode selection, so an empty roster suffices. - agents: { list: vi.fn(() => []) }, + agents: { roots: vi.fn(() => []) }, userInteraction: { registerProvider: vi.fn(() => vi.fn()) }, } as unknown as Context } diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2654a05680..2600fdb24f 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -154,8 +154,7 @@ describe('createStdioChat rendering', () => { it('renders turn/start and turn/end markers from the session feed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') - // agent/created supplies the app-owned target object. - ctx.emit('agent/created', agent) + ctx.agents.register(agent) const session = agent.session ctx.emit('session/event', session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 3, trigger: { kind: 'message' } }, @@ -203,7 +202,7 @@ describe('createStdioChat rendering', () => { const { ctx, input } = await setup() const resumed = makeAgent('resumed') ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' - ctx.emit('agent/created', resumed) + ctx.agents.register(resumed) input.feed('continue') await new Promise(resolve => setImmediate(resolve)) @@ -224,8 +223,8 @@ describe('createStdioChat rendering', () => { it('drops the target object on agent/disposed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') - ctx.emit('agent/created', agent) - ctx.emit('agent/disposed', agent) + const dispose = ctx.agents.register(agent) + dispose() // After disposal the event belongs to a non-target session, so its durable // identity is rendered directly. ctx.emit('session/event', agent.session, { @@ -237,7 +236,7 @@ describe('createStdioChat rendering', () => { it('keeps the target when a different agent is disposed', async () => { const { ctx, out } = await setup() const target = makeAgent('target') - ctx.emit('agent/created', target) + ctx.agents.register(target) ctx.emit('agent/disposed', makeAgent('other')) ctx.emit('session/event', target.session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, @@ -251,19 +250,27 @@ describe('createStdioChat rendering', () => { const child = makeAgent('child') ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id const replacement = makeAgent('replacement') + const lateChild = makeAgent('late-child') const disposeOld = ctx.agents.register(oldRoot) - ctx.agents.register(child) + const disposeChild = ctx.agents.enter(child, oldRoot) + ctx.agents.announce(child) ctx.agents.register(replacement) + const disposeLateChild = ctx.agents.enter(lateChild, replacement) + ctx.agents.announce(lateChild) // The replacement's created edge arrived while oldRoot was still targeted. - // Once oldRoot is removed, registry order is child then replacement; the - // most recently published survivor is the HMR replacement. + // A replacement-owned child then arrived even later. Once oldRoot is + // removed, runtime ownership still identifies replacement as the only + // surviving root instead of selecting either newer child by insertion order. disposeOld() input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) expect(child.sent).toEqual([]) + expect(lateChild.sent).toEqual([]) expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) + disposeLateChild() + disposeChild() }) it('renders tool/call and tool/result session events', async () => { From 0b492e6e62be53abb8560d16f806a4078f56c651 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:22:22 +0800 Subject: [PATCH 053/359] fix: drain ACP test launcher streams --- packages/support/acp-snapshot/README.md | 2 +- packages/support/acp-snapshot/src/launcher.ts | 17 +++++++++++++-- .../tests/fixtures/fake-acp-agent.ts | 21 +++++++++++++++++++ .../acp-snapshot/tests/harness.spec.ts | 21 +++++++++++++++++++ 4 files changed, 58 insertions(+), 3 deletions(-) diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 26192f1cac..b95615abea 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -4,7 +4,7 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tie Four layers, importable separately: -- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Shutdown waits for process exit before resolving or propagating a child error, so callers can remove owned paths after either outcome. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. +- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Shutdown waits for process exit, inherited stdio closure, and ACP parser exhaustion before resolving or propagating a child error, so captures are complete and callers can remove owned paths after either outcome. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 253e67fd5a..815753ae5f 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -65,7 +65,7 @@ export interface LaunchedAcpTestAgent { stderr(): string /** Resolve when a future session update matches the predicate. */ waitForUpdate(match: (update: SessionNotification['update']) => boolean): Promise - /** Gracefully close stdin, or send a signal, and wait for process exit. */ + /** Gracefully close stdin, or send a signal, then wait for process exit, inherited stdio closure, and ACP parser drain. */ close(signal?: NodeJS.Signals): Promise } @@ -132,7 +132,6 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe }) child.stdout.on('end', () => { passthrough.push(null) - closeUpdateStream() }) const stream = ndJsonStream( Writable.toWeb(child.stdin) as WritableStream, @@ -163,6 +162,17 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe ?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' } })), }) const client = new ClientSideConnection(makeClient, stream) + // `exit` only reports the parent process's status. Descendants may retain + // inherited stdout/stderr handles and buffered ACP frames may still be + // crossing the SDK parser. Node's `close` follows stdio closure; the SDK's + // `closed` follows parser exhaustion. Capture both eagerly so a caller that + // invokes close after process exit still joins the complete drain boundary. + const stdioClosed = new Promise(resolve => child.once('close', () => { resolve() })) + const drained = Promise.all([stdioClosed, client.closed]).then(() => undefined) + // A caller may await a pending update without calling close(). Make natural + // stream exhaustion terminal for those waiters too, but only after the + // parser has dispatched every buffered frame. + void client.closed.then(closeUpdateStream) return { child, @@ -183,6 +193,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe throw error } if (!isRunning(child)) { + await drained closeUpdateStream() return } @@ -194,6 +205,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe childFailure, ]) if (failure === undefined) { + await drained closeUpdateStream() return } @@ -204,6 +216,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // callers may safely remove cwd/session resources after close rejects. child.kill('SIGKILL') await exited + await drained closeUpdateStream() throw failure }, diff --git a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts index 861c9d2b04..9b0760213c 100644 --- a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts +++ b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts @@ -18,6 +18,7 @@ import { mkdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs' import { readdirSync } from 'node:fs' +import { spawn } from 'node:child_process' import { dirname, join } from 'node:path' import { randomUUID } from 'node:crypto' import { createInterface } from 'node:readline' @@ -50,6 +51,8 @@ interface Behavior { echoWorkspace?: boolean /** Write a line to stderr on boot (spec-side stderr-capture assertions). */ stderrNote?: string + /** Let a short-lived descendant retain stdio and emit one final ACP update plus stderr line after this parent exits. */ + lateInheritedOutput?: boolean /** Session logs to persist on stdin EOF. */ logs?: ScriptedLog[] /** Leave a stray FILE directly under the sessions root (harvest must skip it). */ @@ -256,6 +259,24 @@ function flushLogsAndExit(): void { writeFileSync(join(sessionsRoot, 'bucket-noise', 'notes.txt'), 'not a session log\n') } if (behavior.deleteSessionsRoot === true) rmSync(sessionsRoot, { recursive: true, force: true }) + if (behavior.lateInheritedOutput === true) { + const frame = JSON.stringify({ + jsonrpc: '2.0', + method: 'session/update', + params: { + sessionId, + update: { + sessionUpdate: 'agent_message_chunk', + content: { type: 'text', text: 'late inherited stdout' }, + }, + }, + }) + const code = [ + `setTimeout(() => process.stdout.write(${JSON.stringify(`${frame}\n`)}), 50)`, + `setTimeout(() => process.stderr.write(${JSON.stringify('late inherited stderr\n')}), 75)`, + ].join(';') + spawn(process.execPath, ['-e', code], { stdio: ['ignore', 1, 2] }).unref() + } process.exit(0) } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 192d36dc6c..051db6a0ba 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -91,6 +91,27 @@ describe('runScenario', () => { expect(exited).toBe(true) }) + it('waits for inherited stdio and buffered ACP parsing after the parent exits', { timeout: 20_000 }, async () => { + const { dir, fixtureFile } = await scenario({ lateInheritedOutput: true }) + const launched = launchAcpTestAgent({ + agent: AGENT, + cwd: dir, + env: { DSH_SNAPSHOT_FILE: fixtureFile }, + }) + await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + await launched.client.newSession({ cwd: dir, mcpServers: [] }) + const lateUpdate = launched.waitForUpdate(update => + update.sessionUpdate === 'agent_message_chunk' + && update.content.type === 'text' + && update.content.text === 'late inherited stdout') + + await launched.close() + + await expect(lateUpdate).resolves.toMatchObject({ sessionUpdate: 'agent_message_chunk' }) + expect(launched.rawStdout()).toContain('late inherited stdout') + expect(launched.stderr()).toContain('late inherited stderr') + }) + it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ permissionProbe: true, From 99b5f04c9bb5ff2ac78d9cc30ce22d65a181c097 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:26:46 +0800 Subject: [PATCH 054/359] fix: use unified identity for bash ownership --- docs/core-data-structures/bash.md | 2 +- ...-18-agent-lifecycle-and-ownership-seams.md | 4 +- .../architecture/2026-06-20-branded-ids.md | 4 +- packages/bash/bash/src/types.ts | 2 +- packages/bash/tool-bash/README.md | 4 +- packages/bash/tool-bash/src/index.ts | 22 ++++----- packages/bash/tool-bash/tests/tools.spec.ts | 46 +++++++++---------- .../cordis/tool-cordis/src/api-catalog.ts | 3 +- 8 files changed, 40 insertions(+), 47 deletions(-) diff --git a/docs/core-data-structures/bash.md b/docs/core-data-structures/bash.md index df6c5ab16b..0cc82e5165 100644 --- a/docs/core-data-structures/bash.md +++ b/docs/core-data-structures/bash.md @@ -37,7 +37,7 @@ interface BashExecRequest { env?: Record | undefined /** * Opaque OWNER token for a background task — the consumer's isolation key - * (the tool layer passes the owning agent's `session.header.id`). The + * (the tool layer passes the owning agent's shared `id`). The * executor stores it on the task and exposes it via {@link BashExecutor.ownerOf}; * the executor itself NEVER interprets it (no access policy lives in the * seam — that is the consumer's job). Absent for foreground runs and for an diff --git a/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md b/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md index d64329262e..d75ec379fc 100644 --- a/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md +++ b/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md @@ -22,7 +22,7 @@ A new `cancel()` verb on the `Agent` interface — the single public stop primit ### 3. Bash owner token in the seam -Background-task ownership moved from a `tool-bash` plugin-local `Map` into the executor. `BashExecRequest` gains an optional `owner?: string`; the resolved `BashExecSpec` carries it as required-but-nullable `owner: string | undefined` (a forgotten owner is a visible `undefined`, never a silently-absent property). The executor stores the token on its task and exposes it via a new `BashExecutor.ownerOf(id): string | undefined` seam (NOT on the public `BashTask` — one read path, no redundant API). `tool-bash` deletes its `Map` entirely: it stamps `exec.agent?.session.header.id` as the owner at `start`, and `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token with `!== undefined` semantics (an empty-string token is still a real owner). The completion notice finds the live agent by scanning `ctx.get('agents')?.list()` for `agent.session.header.id === ownerToken` (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, where the `ctx.agents` proxy would throw). Because ownership now lives on the task in the executor (disposed with the `dsh-bash` fiber), it SURVIVES a `tool-bash` HMR reload — closing the old `XXX(tool-bash-owner-hmr)` gap. (The `onTaskDone` listener is still effect-scoped to `tool-bash`'s `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) +Background-task ownership moved from a `tool-bash` plugin-local `Map` into the executor. `BashExecRequest` gains an optional `owner?: string`; the resolved `BashExecSpec` carries it as required-but-nullable `owner: string | undefined` (a forgotten owner is a visible `undefined`, never a silently-absent property). The executor stores the token on its task and exposes it via a new `BashExecutor.ownerOf(id): string | undefined` seam (NOT on the public `BashTask` — one read path, no redundant API). `tool-bash` deletes its `Map` entirely: it stamps `exec.agent?.id` (the shared registry/session id) as the owner at `start`, and `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token with `!== undefined` semantics (an empty-string token is still a real owner). The completion notice finds the live agent by scanning `ctx.get('agents')?.list()` for `agent.id === ownerToken` (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, where the `ctx.agents` proxy would throw). Because ownership now lives on the task in the executor (disposed with the `dsh-bash` fiber), it SURVIVES a `tool-bash` HMR reload — closing the old `XXX(tool-bash-owner-hmr)` gap. (The `onTaskDone` listener is still effect-scoped to `tool-bash`'s `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) ## Verification @@ -35,7 +35,7 @@ These invariants hold and are pinned by tests: ## Session owner tokens are unique among live agents -The bash owner-token comparison relies on `session.header.id` being unique among live agents. Concurrent same-ID operations may both prepare privately, but publication enters the session and agent in order; `SessionStore.enter()` rejects a duplicate live session id, and every losing transaction rolls its private state back. A programmatic caller therefore cannot publish two live agents with one session token. The access *policy* (token comparison) stays in `tool-bash` (the consumer); the bash seam stores only an opaque `owner` string and never interprets it — the correct interface/implementation/consumer split. +The bash owner-token comparison relies on the shared `Agent.id`/`SessionId` being unique among live agents. Concurrent same-ID operations may both prepare privately, but publication enters the session and agent in order; `SessionStore.enter()` rejects a duplicate live session id, and every losing transaction rolls its private state back. A programmatic caller therefore cannot publish two live agents with one session token. The access *policy* (token comparison) stays in `tool-bash` (the consumer); the bash seam stores only an opaque `owner` string and never interprets it — the correct interface/implementation/consumer split. ## Alternatives considered diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 4fe7f58168..fd5c5bf953 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -8,7 +8,7 @@ The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared age **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. -The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). +The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's shared `Agent.id`/`SessionId` (`callerToken = (exec) => exec.agent?.id` in `packages/bash/tool-bash/src/index.ts`) wearing a different seam-local name. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the shared id alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). **Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. @@ -18,7 +18,7 @@ A type-only change. Brands are zero-cost casts; nothing about runtime behavior, - **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-brand` exactly as `SessionId` does. The brand primitive lives in the dependency-free `dsh-brand` utility package precisely so `dsh-bash` can brand its ids by depending on it alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). -- **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's `session.header.id` (a `SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash seam never imports `dsh-session`. (Rationale in the next section.) +- **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's shared `id` (`SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash seam never imports `dsh-session`. (Rationale in the next section.) - **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `Map`, `get(id: SessionId)`, `Map`, ACP's `SessionId` surface, and the coordinator's `Map`. This is the larger mechanical share of the diff and the part that makes the *existing* brands actually load-bearing on lookups, not just on struct fields. diff --git a/packages/bash/bash/src/types.ts b/packages/bash/bash/src/types.ts index 39dbc162c6..c4c48645e1 100644 --- a/packages/bash/bash/src/types.ts +++ b/packages/bash/bash/src/types.ts @@ -117,7 +117,7 @@ export interface BashExecRequest { env?: Record | undefined /** * Opaque OWNER token for a background task — the consumer's isolation key - * (the tool layer passes the owning agent's `session.header.id`). The + * (the tool layer passes the owning agent's shared `id`). The * executor stores it on the task and exposes it via {@link BashExecutor.ownerOf}; * the executor itself NEVER interprets it (no access policy lives in the * seam — that is the consumer's job). Absent for foreground runs and for an diff --git a/packages/bash/tool-bash/README.md b/packages/bash/tool-bash/README.md index 800de0132c..c4ea498e07 100644 --- a/packages/bash/tool-bash/README.md +++ b/packages/bash/tool-bash/README.md @@ -34,7 +34,7 @@ Result text: stdout, then a `[stderr]` section, then status markers — `[sandbo ### Task ownership (cross-session isolation) -The owning agent's session token (`session.header.id`) is stamped onto the task at spawn — passed to the executor via `resolve({ …, owner })` and stored ON THE TASK inside the executor (the `dsh-bash` `ownerOf(id)` seam), **not** in a plugin-local map. `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token (`session.header.id`) with `!== undefined` semantics and reject a task owned by a *different* session with `task belongs to another session` (a task started with no agent — a non-loop caller — has no owner token and is open to anyone; a call with no `exec.agent` cannot access an owned task). Task ids are global and predictable, so under multi-session ACP this token check is the fence that stops one session's agent from reading or killing another session's background task. Because ownership lives on the task in the executor (disposed with the `dsh-bash` fiber), it **survives an independent `tool-bash` HMR reload** — closing the old plugin-local-map gap where a reload orphaned pre-reload tasks. (The `onTaskDone` listener is still effect-scoped to this plugin's `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) +The owning agent's shared registry/session id (`agent.id`) is stamped onto the task at spawn — passed to the executor via `resolve({ …, owner })` and stored ON THE TASK inside the executor (the `dsh-bash` `ownerOf(id)` seam), **not** in a plugin-local map. `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's shared id with `!== undefined` semantics and reject a task owned by a *different* session with `task belongs to another session` (a task started with no agent — a non-loop caller — has no owner token and is open to anyone; a call with no `exec.agent` cannot access an owned task). Task ids are global and predictable, so under multi-session ACP this token check is the fence that stops one session's agent from reading or killing another session's background task. Because ownership lives on the task in the executor (disposed with the `dsh-bash` fiber), it **survives an independent `tool-bash` HMR reload** — closing the old plugin-local-map gap where a reload orphaned pre-reload tasks. (The `onTaskDone` listener is still effect-scoped to this plugin's `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) ## UI presentation @@ -42,7 +42,7 @@ These tools own how their calls render in a UI (an editor's tool-call card) via ## Background completion notices -When a background task finishes, a short notice is injected into the owning agent's session (`agent.inject()`, source `{kind: 'plugin', plugin: 'tool-bash'}`). The owning agent is found by its session token: the listener reads `ctx.bash.ownerOf(task.id)` and scans `ctx.get('agents')?.list()` for an agent whose `session.header.id` matches (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, so the `ctx.agents` proxy would throw). If no live agent carries that token — e.g. the owning session disconnected and its agent was disposed while the task ran on — the notice is dropped cleanly. Injection is **durable context for the next model request, not a wake-up** — an idle agent stays idle until something sends a message. That's why the tool descriptions tell the model to poll with `bash_output`. +When a background task finishes, a short notice is injected into the owning agent's session (`agent.inject()`, source `{kind: 'plugin', plugin: 'tool-bash'}`). The listener reads `ctx.bash.ownerOf(task.id)` and scans `ctx.get('agents')?.list()` for that shared agent/session id (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, so the `ctx.agents` proxy would throw). If no live agent carries that token — e.g. the owning session disconnected and its agent was disposed while the task ran on — the notice is dropped cleanly. Injection is **durable context for the next model request, not a wake-up** — an idle agent stays idle until something sends a message. That's why the tool descriptions tell the model to poll with `bash_output`. ## The tool builds its request from named args only diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index 31e6512ae0..fe07b80989 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -12,7 +12,7 @@ * `bash_output`. * * Task ownership: a background task's OWNER is an opaque token — the owning - * agent's `session.header.id` — passed to the executor at spawn + * agent's shared `id` — passed to the executor at spawn * (`resolve({ …, owner })`) and stored ON THE TASK inside the executor * (`@deepseek-ai/dsh-bash`'s `ownerOf(id)` seam), NOT in a plugin-local map. * `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token @@ -414,16 +414,12 @@ export function apply(ctx: Context): void { }) /** - * The caller's owner TOKEN — the owning agent's `session.header.id`, or - * `undefined` for a non-agent caller. Read `session.header.id` (NOT - * `session.id`): every other subsystem keys off the header id (the ACP bridge, - * both persistence backends), and the sibling `resolveWorkdir` already reads - * `session.header.cwd`, so using `session.id` here would be the asymmetry smell - * the conventions flag. The two are equal in production, but the header is the - * canonical identity. + * The caller's owner TOKEN — the owning agent's shared registry/session id, + * or `undefined` for a non-agent caller. Agent and Session deliberately have + * one live identity; workdir remains separate session metadata. */ const callerToken = (exec: { agent?: Agent }): OwnerToken | undefined => - exec.agent ? OwnerToken(exec.agent.session.header.id) : undefined + exec.agent ? OwnerToken(exec.agent.id) : undefined /** * Authorize a `bash_output`/`bash_kill` call against the task's stored owner @@ -443,18 +439,16 @@ export function apply(ctx: Context): void { } // Background completion → inject a notice into the owning agent's session. - // Find the live agent by its session id token via the agent registry, read + // Find the live agent by its shared registry/session token, read // opportunistically with `ctx.get('agents')` (NOT `ctx.agents`/static inject): // this listener runs from `task.done.then` on the bash fiber — a foreign // fiber — where the `ctx.agents` property proxy would throw through the // traceable shadow; `ctx.get(name)` is the topology-independent lookup. No - // registry mounted (`undefined`) → drop the notice. Match on - // `agent.session.header.id`, NOT the registry key: a config agent's id differs - // from its session id, and the owner token IS the session id. + // registry mounted (`undefined`) → drop the notice. ctx.bash.onTaskDone((task) => { const ownerToken = ctx.bash.ownerOf(task.id) if (ownerToken === undefined) return - const agent = ctx.get('agents')?.list().find(a => OwnerToken(a.session.header.id) === ownerToken) + const agent = ctx.get('agents')?.list().find(a => OwnerToken(a.id) === ownerToken) if (!agent) return try { agent.inject( diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index c68c445f0a..639dd8631a 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -47,22 +47,16 @@ async function setup() { } /** - * Build a fake {@link Agent} whose session token is `sessionId`, REGISTER it in - * `ctx.agents` (the completion-notice path finds the owning agent by scanning - * the registry for a matching `session.header.id`), and return it. The returned + * Build a fake {@link Agent} with the shared registry/session `sessionId`, + * REGISTER it in `ctx.agents`, and return it. The returned * agent is also passed to `execute` as `exec.agent` so it owns the spawned task. * The registration disposer is tracked so {@link unregisterFakeAgents} can drop * it (simulating the owning session disconnecting before a task completes). */ const fakeAgentDisposers = new Map Promise | void)[]>() function registerFakeAgent(ctx: Context, sessionId: string, inject: (...args: unknown[]) => void): Agent { - // The registry KEY (agent.id) is deliberately DIFFERENT from the session - // token (session.header.id), which is also the agent's durable id. The - // owner token IS the session id, so the notice path must find the agent by - // `session.header.id`, NOT the registry key. Using distinct values here makes - // the test fail if a regression matched on the wrong field (a same-value fake - // would pass either way — the "hits the line but not the scenario" trap). - const agent = { id: `agent-${sessionId}`, inject, session: { header: { version: 0, id: sessionId, createdAt: 0 } } } as unknown as Agent + const id = SessionId(sessionId) + const agent = { id, inject, session: new Session(id) } as unknown as Agent const dispose = ctx.agents.register(agent) const list = fakeAgentDisposers.get(ctx) ?? [] list.push(dispose) @@ -418,9 +412,9 @@ describe('background tools', () => { it('injects a completion notice into the owning agent (found via the registry by session token)', async () => { const ctx = await setup() const inject = vi.fn() - // The notice path looks the agent up in ctx.agents by its session token, so + // The notice path looks the agent up in ctx.agents by its shared id, so // the agent must be REGISTERED (not merely passed to execute). Mount a - // registry and register a fake whose session.header.id IS the owner token. + // registry and register a fake whose agent/session id IS the owner token. const agent = registerFakeAgent(ctx, 'bg', inject) const started = await ctx.tools.execute({ @@ -517,13 +511,14 @@ describe('background task ownership (cross-session isolation)', () => { function callAs(ctx: Context, agent: import('@deepseek-ai/dsh-agent').Agent | undefined, name: string, args: unknown) { return ctx.tools.execute({ callId: CallId(`own-${++callCounter}`), name, arguments: args, ...agent ? { agent } : {} }) } - // Ownership is by TOKEN (session.header.id), NOT agent object identity — so - // each agent needs a DISTINCT session id, else every fake yields the same + // Ownership is by the shared agent/session TOKEN, NOT agent object identity — + // so each agent needs a DISTINCT id, else every fake yields the same // token and the isolation tests pass for the wrong reason (all tasks owned by - // the same token). The impl reads `session.header.id`, so the fakes MUST carry - // it. - const fakeAgent = (sessionId: string) => - ({ inject: () => undefined, session: { header: { version: 0, id: sessionId, createdAt: 0 } } }) as unknown as import('@deepseek-ai/dsh-agent').Agent + // the same token). + const fakeAgent = (sessionId: string) => { + const id = SessionId(sessionId) + return { id, inject: () => undefined, session: new Session(id) } as unknown as import('@deepseek-ai/dsh-agent').Agent + } it('rejects bash_output/bash_kill for a task owned by a DIFFERENT session token', async () => { const ctx = await setup() @@ -548,7 +543,7 @@ describe('background task ownership (cross-session isolation)', () => { }) it('a DIFFERENT Agent object with the SAME session token may access the task (ownership is by token, not object identity)', async () => { - // Ownership fences by session.header.id, NOT Agent object identity. Two + // Ownership fences by the shared id, NOT Agent object identity. Two // distinct Agent objects sharing one session token (e.g. an agent re-created // on the same session) are the SAME owner. const ctx = await setup() @@ -638,8 +633,10 @@ describe('session-cwd routing (per-session workdir)', () => { return ctx.tools.execute({ callId: CallId(`cwd-${++callCounter}`), name: 'bash', arguments: args, ...agent ? { agent } : {} }) } // An agent whose session header carries a cwd (what session/new records). - const agentInCwd = (cwd: string) => - ({ inject: () => undefined, session: { header: { version: 0, id: 'c', createdAt: 0, cwd } } }) as unknown as import('@deepseek-ai/dsh-agent').Agent + const agentInCwd = (cwd: string) => { + const id = SessionId('c') + return { id, inject: () => undefined, session: { header: { version: 0, id, createdAt: 0, cwd } } } as unknown as import('@deepseek-ai/dsh-agent').Agent + } it('defaults bash to the agent\'s session cwd (not the server launch dir)', async () => { const ctx = await setup() @@ -1188,10 +1185,11 @@ describe('sandbox escalation (sandbox_permissions / justification)', () => { * enforces the enclosure. */ function escalationAgent(events: Array<{ type: string; data: Record }>): Agent { + const id = SessionId('sess-esc') return { - id: 'agent-esc', + id, session: { - header: { version: 0, id: 'sess-esc', createdAt: 0 }, + header: { version: 0, id, createdAt: 0 }, events: [{ type: 'turn/start' }], append: (type: string, data: Record) => { events.push({ type, data }) }, }, @@ -1406,7 +1404,7 @@ describe('per-session sandbox mode (the bash/sandbox-mode fold)', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) const injected: string[] = [] const agent = { - id, + id: SessionId(id), session, inject: (content: { type: string; text: string }[]) => { injected.push(content[0]?.text ?? '') }, } as unknown as Agent diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 5721bd97d9..ff27f51067 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -69,10 +69,11 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'async create(options: CreateAgentOptions): Promise', 'async resume(options: ResumeAgentOptions): Promise', 'register(agent: Agent): () => void', - 'enter(agent: Agent): () => void', + 'enter(agent: Agent, owner: Agent | undefined): () => void', 'announce(agent: Agent): void', 'get(id: SessionId): Agent | undefined', 'list(): Agent[]', + 'roots(): Agent[]', ], }, { From 03f91a547183919422aeb1d699af58d678a8984d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:29:40 +0800 Subject: [PATCH 055/359] fix: retain local subagent completion identity --- .../cordis/tool-cordis/src/api-catalog.ts | 3 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 34 +++++++++++-------- packages/ui/jsonrpc/tests/server.spec.ts | 23 ++++++++++++- 4 files changed, 45 insertions(+), 17 deletions(-) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 5721bd97d9..ff27f51067 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -69,10 +69,11 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'async create(options: CreateAgentOptions): Promise', 'async resume(options: ResumeAgentOptions): Promise', 'register(agent: Agent): () => void', - 'enter(agent: Agent): () => void', + 'enter(agent: Agent, owner: Agent | undefined): () => void', 'announce(agent: Agent): void', 'get(id: SessionId): Agent | undefined', 'list(): Agent[]', + 'roots(): Agent[]', ], }, { diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 2324227ff7..735cfead0a 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. Runs from remote providers are not reported through this local-session notification pair because they create no local `session/created`/`subagent.started` edge. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage because the child may be disposed before `subagent/end`, and the provider contract does not require lineage. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 3c803a6c8c..bf21f7fc2d 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -58,6 +58,11 @@ interface SessionRecord { activePrompt: boolean } +/** Runtime-local agent identity plus optional durable fork lineage. */ +interface LocalAgentRecord { + parentSessionId?: SessionId +} + /** * The SDK server over a booted harness context. Constructing it subscribes to * the context's `session/event`, `session/created`, `agent/created`, and @@ -71,7 +76,7 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly subagentParents = new Map() + private readonly localAgents = new Map() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -95,23 +100,24 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache parent lineage on creation: by the time `subagent/end` fires the - // child agent may already be disposed and gone from the registry. The child - // session id needs no cache because it is the shared agent/session id. + // Cache runtime-local identity and optional lineage on creation: by the + // time `subagent/end` fires the child agent may already be disposed and + // gone from the registry. Parent lineage is not required by the provider + // contract, so an empty record remains a load-bearing locality marker. this.disposers.push(ctx.on('agent/created', (agent) => { const parentSessionId = agent.session.header.parentSession - if (parentSessionId !== undefined) this.subagentParents.set(agent.id, parentSessionId) + this.localAgents.set(agent.id, parentSessionId === undefined ? {} : { parentSessionId }) })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { const agent = this.ctx.agents.get(info.id) - const cachedParentSessionId = this.subagentParents.get(info.id) - this.subagentParents.delete(info.id) - // This protocol reports LOCAL child sessions, paired with the - // session/created-driven subagent.started notification above. A remote - // provider may use a real remote SessionId for its run, but that session - // does not exist in this harness and therefore has no paired start event. - if (cachedParentSessionId === undefined && agent === undefined) return - const parentSessionId = cachedParentSessionId ?? agent?.session.header.parentSession + const cachedLocalAgent = this.localAgents.get(info.id) + this.localAgents.delete(info.id) + // This protocol reports LOCAL child sessions. A lineage-bearing child + // has the session/created-driven start notification above; a parentless + // local provider still gets its terminal notification. A remote provider + // has neither a cached creation nor a live local agent and is ignored. + if (cachedLocalAgent === undefined && agent === undefined) return + const parentSessionId = cachedLocalAgent?.parentSessionId ?? agent?.session.header.parentSession this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), @@ -189,7 +195,7 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.subagentParents.clear() + this.localAgents.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index e7f591b88f..163aee4c0c 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -272,15 +272,26 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) + const parentlessHandle = await ctx.agents.create({ + sessionId: SessionId('parentless-child-session'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) // The backend may dispose the child before publishing its run outcome; - // only the cached parent lineage should be needed at this point. + // cached locality must survive with or without optional parent lineage. await handle.dispose() + await parentlessHandle.dispose() await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], }) + await settleSubagent(ctx, parentHandle.agent, { + provider: 'spawn', + id: SessionId('parentless-child-session'), + stopReason: 'error', + }) expect(transport.notifications).toContainEqual({ method: 'subagent.finished', @@ -294,6 +305,16 @@ describe('HarnessSdkServer', () => { lastAssistantMessage: [{ type: 'text', text: 'child done' }], }, }) + expect(transport.notifications).toContainEqual({ + method: 'subagent.finished', + params: { + provider: 'spawn', + agentId: 'parentless-child-session', + childSessionId: 'parentless-child-session', + status: 'error', + stopReason: 'error', + }, + }) await parentHandle.dispose() await server.shutdown() From f02005c832b450d65d372c935c612c7d83eec54d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:39:28 +0800 Subject: [PATCH 056/359] fix: enforce unified agent startup invariants --- packages/core/agent/README.md | 2 +- packages/core/agent/src/index.ts | 3 +++ packages/core/agent/tests/agent.spec.ts | 12 ++++++++- .../hooks/hooks-claude/tests/coverage.spec.ts | 8 +++--- packages/subagent/subagent-acp/src/run.ts | 11 ++++---- .../subagent-acp/tests/mock-acp-server.ts | 3 +++ .../subagent-acp/tests/subagent-acp.spec.ts | 26 +++++++++++++++++++ 7 files changed, 55 insertions(+), 10 deletions(-) diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 643c15002b..a45603f191 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -11,7 +11,7 @@ Tracks live agents so UI, hook, and orchestrator plugins can find them without i The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh-scope`, key = the agent) — register tools/sections/variables/listeners through it for that agent alone, all unwound on disposal. `agentEvents(ctx, agent)` is the fused dispatcher for ordinary agent-subject operations (carrier + injected subject in one move); its notification mode invokes every listener and contains both synchronous throws and returned-promise rejections. The registry lifecycle pair reuses one stable routing carrier. `assembleContextFor(agent)` builds the per-agent assembly context (`agent` + `scope` together). `CreateAgentOptions.setup(agentCtx)` and `ResumeAgentOptions.setup(agentCtx)` compose a fresh or resumed agent's scoped world while both objects remain unpublished. Setup is trusted, composition-only same-process code: drive the agent only after creation resolves. - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. -- Advanced ordered lifecycle: `enter(agent, owner): () => void` performs the authoritative ID collision check and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. +- Advanced ordered lifecycle: `enter(agent, owner): () => void` enforces `agent.id === agent.session.id`, performs the authoritative ID collision check, and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. - `ctx.agents.get(id: SessionId): Agent | undefined` - `ctx.agents.list(): Agent[]` - `ctx.agents.roots(): Agent[]` — live agents created without an owning agent context; a resumed lineage-bearing session can still be a runtime root. diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index b25d1e3cac..abafa38e45 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -329,6 +329,9 @@ export class AgentRegistry extends Service { */ enter(agent: Agent, owner: Agent | undefined): () => void { const id = agent.id + if (id !== agent.session.id) { + throw new Error(`agent id "${id}" does not match session id "${agent.session.id}"`) + } const carrier = scopeTarget(agent, agent) // This is the authoritative collision boundary. Concurrent create/resume // operations may both prepare, but only one exact entry can publish. diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index 5563d01cad..d2866cacb3 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -11,7 +11,7 @@ function stubAgent(rawId: string): Agent { return { id, options: {}, - session: new Session(SessionId(`${id}-session`)), + session: new Session(id), status: 'idle', ctx: new Context(), send() {}, @@ -50,6 +50,16 @@ describe('AgentRegistry', () => { expect(lifecycle).toEqual(['created:a1', 'disposed:a1']) }) + it('rejects an agent whose registry and session identities differ', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + const agent = { ...stubAgent('agent-id'), session: new Session(SessionId('session-id')) } + + expect(() => ctx.agents.enter(agent, undefined)) + .toThrow('agent id "agent-id" does not match session id "session-id"') + expect(ctx.agents.list()).toEqual([]) + }) + it('tracks runtime creator ownership separately from registry order', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index 16c48aa149..0b41fd0d10 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -4,7 +4,7 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { Session, SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' @@ -209,7 +209,8 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const ctx = await harness(path, new MockAdapter([])) // Register a fake child agent under the id the event carries. const injected: string[] = [] - const child = { id: SessionId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters[0] + const childId = SessionId('child-x') + const child = { id: childId, inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: new Session(childId) } as unknown as Parameters[0] ctx.agents.register(child) ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-x') }) await waitFor(() => injected.includes('child guidance')) @@ -225,7 +226,8 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { SubagentStart: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) const warn = vi.fn(); ctx.logger.warn = warn as never - const child = { id: SessionId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters[0] + const childId = SessionId('child-y') + const child = { id: childId, inject: () => { throw new Error('inject boom') }, session: new Session(childId) } as unknown as Parameters[0] ctx.agents.register(child) ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-y') }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SubagentStart hook failed'))) diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 7d0c11cbe1..8ef49f0f7d 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -311,7 +311,9 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe clientCapabilities: {}, }) const session = await conn.newSession({ cwd: spec.cwd, mcpServers: [] }) - sessionId = session.sessionId + const returnedSessionId: unknown = Reflect.get(session, 'sessionId') + if (typeof returnedSessionId !== 'string') throw new Error('ACP child published without a session id') + sessionId = returnedSessionId if (flags.cancelled) throw new Error('subagent cancelled before the ACP session started') })(), spawnFailed.then((err): never => { throw err }), @@ -323,10 +325,9 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe if (flags.cancelled) throw new Error('subagent request was aborted before the ACP child started') throw toError(error) } - // The startup race can fulfill only after newSession assigned the id; this - // guard keeps that cross-closure invariant explicit for TypeScript. - /* v8 ignore next */ - if (sessionId === undefined) throw new Error('ACP child published without a session id') + // The startup transaction validates the returned id before it can fulfill. + // This assertion carries that cross-closure invariant into TypeScript. + if (sessionId === undefined) throw new Error('unreachable: ACP startup fulfilled without a session id') const remoteSessionId = sessionId const result: Promise = (async (): Promise => { diff --git a/packages/subagent/subagent-acp/tests/mock-acp-server.ts b/packages/subagent/subagent-acp/tests/mock-acp-server.ts index 5145941526..f56404834b 100644 --- a/packages/subagent/subagent-acp/tests/mock-acp-server.ts +++ b/packages/subagent/subagent-acp/tests/mock-acp-server.ts @@ -19,6 +19,8 @@ * handler is in flight (it has streamed its chunk). A test * polls for this file to cancel on a CONDITION rather than * an arbitrary timeout (subprocess cold-start is variable). + * - `MOCK_MISSING_SESSION_ID` — if `1`, return a malformed empty `session/new` + * response to exercise startup rollback. * - `MOCK_FLUSH_ON_EOF` — if set, on stdin EOF the agent takes an async beat * (MOCK_FLUSH_DELAY_MS, default 150) simulating the real * acp-agent's EOF-driven quiesce+flush, then touches this @@ -99,6 +101,7 @@ function makeAgent(conn: AgentSideConnection): Agent { writeFileSync(NEWSESSION_GATE.ready, 'at-newSession') while (!existsSync(NEWSESSION_GATE.go)) await new Promise(r => setTimeout(r, 10)) } + if (process.env.MOCK_MISSING_SESSION_ID === '1') return {} as NewSessionResponse return { sessionId: process.env.MOCK_SESSION_ID ?? randomUUID() } }, authenticate(_params: AuthenticateRequest): Promise { diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index e5fe05384e..daa037ca20 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -195,6 +195,32 @@ describe('dsh-subagent-acp', () => { } }) + it('reaps a child whose session/new response omits the session id', async () => { + const tmp = mkdtempSync(join(tmpdir(), 'acp-malformed-session-')) + const flushed = join(tmp, 'flushed') + try { + await expect(startAcpRun(request(), { + command: process.execPath, + args: ['--import', tsxLoader, mockServer], + cwd: process.cwd(), + permission: 'reject', + env: { + MOCK_MISSING_SESSION_ID: '1', + MOCK_FLUSH_ON_EOF: flushed, + MOCK_FLUSH_DELAY_MS: '20', + TSX_TSCONFIG_PATH: repoTsconfig, + }, + disposeEofGraceMs: 1000, + disposeGraceMs: 100, + })).rejects.toThrow('ACP child published without a session id') + // Startup rejects only after its private child reaches quiescence. The + // marker proves rollback closed stdin and allowed the child's EOF flush. + expect(existsSync(flushed)).toBe(true) + } finally { + rmSync(tmp, { recursive: true, force: true }) + } + }) + it('dispose escalates SIGTERM → SIGKILL for a child that traps SIGTERM (bounded quiescence)', async () => { // The child traps SIGTERM and keeps its event loop alive, so a graceful // term alone would hang dispose forever. With a short grace, dispose must From a9c4fe2c4ba9f92a85117d60ad01ce1ee5930c69 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:43:01 +0800 Subject: [PATCH 057/359] test: exclude validated ACP assertion --- packages/subagent/subagent-acp/src/run.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 8ef49f0f7d..e135beb210 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -327,6 +327,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe } // The startup transaction validates the returned id before it can fulfill. // This assertion carries that cross-closure invariant into TypeScript. + /* v8 ignore next */ if (sessionId === undefined) throw new Error('unreachable: ACP startup fulfilled without a session id') const remoteSessionId = sessionId From 47812b45db85a9824530e800b12de1c82fdd6972 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:57:45 +0800 Subject: [PATCH 058/359] test: re-record Codex hook snapshot --- .../hook-codex-posttool-block/session.jsonl | 340 ++++++------------ .../stdout.golden.jsonl | 153 ++------ 2 files changed, 142 insertions(+), 351 deletions(-) diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl index ae105f6679..94bbbc5a08 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl @@ -1,222 +1,118 @@ -{"type":"session","version":0,"id":"7a5183c0-ec3a-46a8-a382-475eaa0c205b","createdAt":1783352220743,"cwd":"/tmp/acp-snap-cwd-vGnYqn"} -{"type":"turn/start","seq":0,"time":1783352220747,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783352220748,"data":{"content":[{"type":"text","text":"Call the bash tool exactly once to run: echo HELLO. Whatever tool result comes back, quote it verbatim and stop without calling another tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783352220749,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352220750,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783352221451,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783352221451,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783352221651,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783352221685,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783352221685,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783352221686,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783352221686,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} -{"type":"assistant/chunk","seq":11,"time":1783352221686,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":12,"time":1783352221686,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} -{"type":"assistant/chunk","seq":13,"time":1783352221709,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":14,"time":1783352221710,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"echo"}}} -{"type":"assistant/chunk","seq":15,"time":1783352221711,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" HE"}}} -{"type":"assistant/chunk","seq":16,"time":1783352221711,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"LL"}}} -{"type":"assistant/chunk","seq":17,"time":1783352221711,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"O"}}} -{"type":"assistant/chunk","seq":18,"time":1783352221711,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":19,"time":1783352221738,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" using"}}} -{"type":"assistant/chunk","seq":20,"time":1783352221738,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":21,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" bash"}}} -{"type":"assistant/chunk","seq":22,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":23,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":24,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" report"}}} -{"type":"assistant/chunk","seq":25,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":26,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} -{"type":"assistant/chunk","seq":27,"time":1783352221794,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} -{"type":"assistant/chunk","seq":28,"time":1783352221795,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} -{"type":"assistant/chunk","seq":29,"time":1783352221795,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":30,"time":1783352221884,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":31,"time":1783352221885,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":32,"time":1783352221885,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":33,"time":1783352221885,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":34,"time":1783352221915,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"command"}}} -{"type":"assistant/chunk","seq":35,"time":1783352221915,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":36,"time":1783352221915,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":37,"time":1783352221915,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":38,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"echo"}}} -{"type":"assistant/chunk","seq":39,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":" HE"}}} -{"type":"assistant/chunk","seq":40,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"LL"}}} -{"type":"assistant/chunk","seq":41,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"O"}}} -{"type":"assistant/chunk","seq":42,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":43,"time":1783352222000,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":44,"time":1783352222000,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":45,"time":1783352222001,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"description"}}} -{"type":"assistant/chunk","seq":46,"time":1783352222001,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":47,"time":1783352222001,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":48,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":49,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"Print"}}} -{"type":"assistant/chunk","seq":50,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":" HE"}}} -{"type":"assistant/chunk","seq":51,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"LL"}}} -{"type":"assistant/chunk","seq":52,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"O"}}} -{"type":"assistant/chunk","seq":53,"time":1783352222058,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":" to"}}} -{"type":"assistant/chunk","seq":54,"time":1783352222059,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":" stdout"}}} -{"type":"assistant/chunk","seq":55,"time":1783352222059,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":56,"time":1783352222088,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":57,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to run the command \"echo HELLO\" using the bash tool and report the result verbatim."}}}} -{"type":"assistant/chunk","seq":58,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}}}} -{"type":"assistant/chunk","seq":59,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":25}}}} -{"type":"assistant/chunk","seq":60,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":61,"time":1783352222124,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run the command \"echo HELLO\" using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}],"usage":{"inputTokens":2878,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":25}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} -{"type":"tool/call","seq":62,"time":1783352222124,"data":{"turn":1,"step":1,"callId":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}} -{"type":"hook/invoked","seq":63,"time":1783352222138,"data":{"turn":1,"point":"PostToolUse","dialect":"codex","handlerId":"codex:PostToolUse:1","matcher":"bash"}} -{"type":"hook/result","seq":64,"time":1783352222148,"data":{"turn":1,"point":"PostToolUse","handlerId":"codex:PostToolUse:1","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by codex policy: summarize instead","durationMs":9.571565000000192}} -{"type":"tool/result","seq":65,"time":1783352222148,"data":{"turn":1,"step":1,"callId":"call_00_wNJIQDMLdssZp45zIXvz2684","content":[{"type":"text","text":"tool output rejected by codex policy: summarize instead"}],"isError":true},"sourceEventSeqs":[62],"surfaceOp":"append"} -{"type":"step/end","seq":66,"time":1783352222149,"data":{"turn":1,"step":1}} -{"type":"step/start","seq":67,"time":1783352222149,"data":{"turn":1,"step":2}} -{"type":"assistant/chunk","seq":68,"time":1783352223151,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":69,"time":1783352223151,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":70,"time":1783352223301,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} -{"type":"assistant/chunk","seq":71,"time":1783352223315,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" was"}}} -{"type":"assistant/chunk","seq":72,"time":1783352223316,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" rejected"}}} -{"type":"assistant/chunk","seq":73,"time":1783352223316,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" by"}}} -{"type":"assistant/chunk","seq":74,"time":1783352223343,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":75,"time":1783352223344,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" code"}}} -{"type":"assistant/chunk","seq":76,"time":1783352223344,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"x"}}} -{"type":"assistant/chunk","seq":77,"time":1783352223344,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" policy"}}} -{"type":"assistant/chunk","seq":78,"time":1783352223372,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":79,"time":1783352223406,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":80,"time":1783352223407,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" instruction"}}} -{"type":"assistant/chunk","seq":81,"time":1783352223407,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":82,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":83,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"sum"}}} -{"type":"assistant/chunk","seq":84,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"mar"}}} -{"type":"assistant/chunk","seq":85,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ize"}}} -{"type":"assistant/chunk","seq":86,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" instead"}}} -{"type":"assistant/chunk","seq":87,"time":1783352223458,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":88,"time":1783352223487,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" This"}}} -{"type":"assistant/chunk","seq":89,"time":1783352223487,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" means"}}} -{"type":"assistant/chunk","seq":90,"time":1783352223488,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":91,"time":1783352223519,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" cannot"}}} -{"type":"assistant/chunk","seq":92,"time":1783352223520,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" show"}}} -{"type":"assistant/chunk","seq":93,"time":1783352223548,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":94,"time":1783352223548,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" raw"}}} -{"type":"assistant/chunk","seq":95,"time":1783352223548,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} -{"type":"assistant/chunk","seq":96,"time":1783352223548,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} -{"type":"assistant/chunk","seq":97,"time":1783352223576,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} -{"type":"assistant/chunk","seq":98,"time":1783352223576,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" as"}}} -{"type":"assistant/chunk","seq":99,"time":1783352223605,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":100,"time":1783352223640,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":101,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" requested"}}} -{"type":"assistant/chunk","seq":102,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":103,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} -{"type":"assistant/chunk","seq":104,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":105,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" try"}}} -{"type":"assistant/chunk","seq":106,"time":1783352223663,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":107,"time":1783352223664,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" comply"}}} -{"type":"assistant/chunk","seq":108,"time":1783352223691,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" but"}}} -{"type":"assistant/chunk","seq":109,"time":1783352223692,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" report"}}} -{"type":"assistant/chunk","seq":110,"time":1783352223721,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" what"}}} -{"type":"assistant/chunk","seq":111,"time":1783352223721,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" happened"}}} -{"type":"assistant/chunk","seq":112,"time":1783352223749,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":".\n\n"}}} -{"type":"assistant/chunk","seq":113,"time":1783352223749,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"Actually"}}} -{"type":"assistant/chunk","seq":114,"time":1783352223750,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":115,"time":1783352223750,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":116,"time":1783352223750,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":117,"time":1783352223750,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}} -{"type":"assistant/chunk","seq":118,"time":1783352223778,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":119,"time":1783352223779,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":120,"time":1783352223779,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" report"}}} -{"type":"assistant/chunk","seq":121,"time":1783352223813,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":122,"time":1783352223813,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":123,"time":1783352223837,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} -{"type":"assistant/chunk","seq":124,"time":1783352223837,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} -{"type":"assistant/chunk","seq":125,"time":1783352223837,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} -{"type":"assistant/chunk","seq":126,"time":1783352223837,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":127,"time":1783352223865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" The"}}} -{"type":"assistant/chunk","seq":128,"time":1783352223866,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":129,"time":1783352223866,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} -{"type":"assistant/chunk","seq":130,"time":1783352223896,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":131,"time":1783352223897,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" got"}}} -{"type":"assistant/chunk","seq":132,"time":1783352223923,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" back"}}} -{"type":"assistant/chunk","seq":133,"time":1783352223923,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}} -{"type":"assistant/chunk","seq":134,"time":1783352223952,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":":\n\n"}}} -{"type":"assistant/chunk","seq":135,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":136,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"tool"}}} -{"type":"assistant/chunk","seq":137,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} -{"type":"assistant/chunk","seq":138,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" rejected"}}} -{"type":"assistant/chunk","seq":139,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" by"}}} -{"type":"assistant/chunk","seq":140,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" code"}}} -{"type":"assistant/chunk","seq":141,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"x"}}} -{"type":"assistant/chunk","seq":142,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" policy"}}} -{"type":"assistant/chunk","seq":143,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":":"}}} -{"type":"assistant/chunk","seq":144,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" summarize"}}} -{"type":"assistant/chunk","seq":145,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" instead"}}} -{"type":"assistant/chunk","seq":146,"time":1783352224017,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"\n\n"}}} -{"type":"assistant/chunk","seq":147,"time":1783352224017,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"So"}}} -{"type":"assistant/chunk","seq":148,"time":1783352224017,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":149,"time":1783352224018,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" should"}}} -{"type":"assistant/chunk","seq":150,"time":1783352224039,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" report"}}} -{"type":"assistant/chunk","seq":151,"time":1783352224039,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} -{"type":"assistant/chunk","seq":152,"time":1783352224039,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} -{"type":"assistant/chunk","seq":153,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} -{"type":"assistant/chunk","seq":154,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":155,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":156,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"The"}}} -{"type":"assistant/chunk","seq":157,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" tool"}}} -{"type":"assistant/chunk","seq":158,"time":1783352224105,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" result"}}} -{"type":"assistant/chunk","seq":159,"time":1783352224105,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" I"}}} -{"type":"assistant/chunk","seq":160,"time":1783352224105,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" got"}}} -{"type":"assistant/chunk","seq":161,"time":1783352224105,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" back"}}} -{"type":"assistant/chunk","seq":162,"time":1783352224129,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" is"}}} -{"type":"assistant/chunk","seq":163,"time":1783352224159,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":":\n\n"}}} -{"type":"assistant/chunk","seq":164,"time":1783352224159,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":">"}}} -{"type":"assistant/chunk","seq":165,"time":1783352224186,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" `"}}} -{"type":"assistant/chunk","seq":166,"time":1783352224186,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"tool"}}} -{"type":"assistant/chunk","seq":167,"time":1783352224187,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" output"}}} -{"type":"assistant/chunk","seq":168,"time":1783352224215,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" rejected"}}} -{"type":"assistant/chunk","seq":169,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" by"}}} -{"type":"assistant/chunk","seq":170,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" code"}}} -{"type":"assistant/chunk","seq":171,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"x"}}} -{"type":"assistant/chunk","seq":172,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" policy"}}} -{"type":"assistant/chunk","seq":173,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":":"}}} -{"type":"assistant/chunk","seq":174,"time":1783352224244,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" summarize"}}} -{"type":"assistant/chunk","seq":175,"time":1783352224244,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" instead"}}} -{"type":"assistant/chunk","seq":176,"time":1783352224244,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"`\n\n"}}} -{"type":"assistant/chunk","seq":177,"time":1783352224245,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"This"}}} -{"type":"assistant/chunk","seq":178,"time":1783352224245,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" is"}}} -{"type":"assistant/chunk","seq":179,"time":1783352224297,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} -{"type":"assistant/chunk","seq":180,"time":1783352224297,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" verb"}}} -{"type":"assistant/chunk","seq":181,"time":1783352224305,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"atim"}}} -{"type":"assistant/chunk","seq":182,"time":1783352224305,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" result"}}} -{"type":"assistant/chunk","seq":183,"time":1783352224305,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" from"}}} -{"type":"assistant/chunk","seq":184,"time":1783352224305,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} -{"type":"assistant/chunk","seq":185,"time":1783352224331,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" tool"}}} -{"type":"assistant/chunk","seq":186,"time":1783352224360,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" —"}}} -{"type":"assistant/chunk","seq":187,"time":1783352224361,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" it"}}} -{"type":"assistant/chunk","seq":188,"time":1783352224361,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" was"}}} -{"type":"assistant/chunk","seq":189,"time":1783352224392,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" not"}}} -{"type":"assistant/chunk","seq":190,"time":1783352224418,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} -{"type":"assistant/chunk","seq":191,"time":1783352224446,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" expected"}}} -{"type":"assistant/chunk","seq":192,"time":1783352224476,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" `"}}} -{"type":"assistant/chunk","seq":193,"time":1783352224476,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"\""}}} -{"type":"assistant/chunk","seq":194,"time":1783352224476,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"HE"}}} -{"type":"assistant/chunk","seq":195,"time":1783352224505,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"LL"}}} -{"type":"assistant/chunk","seq":196,"time":1783352224505,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"O"}}} -{"type":"assistant/chunk","seq":197,"time":1783352224506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"\""}}} -{"type":"assistant/chunk","seq":198,"time":1783352224506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"`"}}} -{"type":"assistant/chunk","seq":199,"time":1783352224506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" output"}}} -{"type":"assistant/chunk","seq":200,"time":1783352224506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" because"}}} -{"type":"assistant/chunk","seq":201,"time":1783352224533,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} -{"type":"assistant/chunk","seq":202,"time":1783352224534,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" code"}}} -{"type":"assistant/chunk","seq":203,"time":1783352224534,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"x"}}} -{"type":"assistant/chunk","seq":204,"time":1783352224563,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" policy"}}} -{"type":"assistant/chunk","seq":205,"time":1783352224563,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" blocked"}}} -{"type":"assistant/chunk","seq":206,"time":1783352224563,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" it"}}} -{"type":"assistant/chunk","seq":207,"time":1783352224592,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" and"}}} -{"type":"assistant/chunk","seq":208,"time":1783352224621,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" instructed"}}} -{"type":"assistant/chunk","seq":209,"time":1783352224621,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" me"}}} -{"type":"assistant/chunk","seq":210,"time":1783352224653,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" to"}}} -{"type":"assistant/chunk","seq":211,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" summarize"}}} -{"type":"assistant/chunk","seq":212,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" instead"}}} -{"type":"assistant/chunk","seq":213,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"."}}} -{"type":"assistant/chunk","seq":214,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The output was rejected by the codex policy with the instruction to \"summarize instead\". This means I cannot show the raw output verbatim as the user requested. Let me try to comply but report what happened.\n\nActually, the user asked me to report the tool result verbatim. The tool result I got back is:\n\n\"tool output rejected by codex policy: summarize instead\"\n\nSo I should report that verbatim."}}}} -{"type":"assistant/chunk","seq":215,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result I got back is:\n\n> `tool output rejected by codex policy: summarize instead`\n\nThis is the verbatim result from the tool — it was not the expected `\"HELLO\"` output because the codex policy blocked it and instructed me to summarize instead."}}}} -{"type":"assistant/chunk","seq":216,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":176,"outputTokens":145,"cacheReadTokens":2816,"reasoningTokens":86}}}} -{"type":"assistant/chunk","seq":217,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":218,"time":1783352224655,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output was rejected by the codex policy with the instruction to \"summarize instead\". This means I cannot show the raw output verbatim as the user requested. Let me try to comply but report what happened.\n\nActually, the user asked me to report the tool result verbatim. The tool result I got back is:\n\n\"tool output rejected by codex policy: summarize instead\"\n\nSo I should report that verbatim."},{"type":"text","text":"The tool result I got back is:\n\n> `tool output rejected by codex policy: summarize instead`\n\nThis is the verbatim result from the tool — it was not the expected `\"HELLO\"` output because the codex policy blocked it and instructed me to summarize instead."}],"usage":{"inputTokens":176,"outputTokens":145,"cacheReadTokens":2816,"reasoningTokens":86}},"sourceEventSeqs":[68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217],"surfaceOp":"append"} -{"type":"step/end","seq":219,"time":1783352224655,"data":{"turn":1,"step":2}} -{"type":"turn/end","seq":220,"time":1783352224655,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"01aa6a36-e9c2-42ba-934b-30bec80a1658","createdAt":1783986962232,"cwd":"/var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-x67BsP"} +{"type":"turn/start","seq":0,"time":1783986962235,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783986962235,"data":{"content":[{"type":"text","text":"Call the bash tool exactly once to run: echo HELLO. Whatever tool result comes back, quote it verbatim and stop without calling another tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783986962240,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783986962240,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783986962953,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1783986962953,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" call"}}} +{"type":"assistant/chunk","seq":11,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":12,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" bash"}}} +{"type":"assistant/chunk","seq":13,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":14,"time":1783986963135,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" once"}}} +{"type":"assistant/chunk","seq":15,"time":1783986963135,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":16,"time":1783986963135,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}} +{"type":"assistant/chunk","seq":17,"time":1783986963160,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"echo"}}} +{"type":"assistant/chunk","seq":18,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" HE"}}} +{"type":"assistant/chunk","seq":19,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"LL"}}} +{"type":"assistant/chunk","seq":20,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"O"}}} +{"type":"assistant/chunk","seq":21,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"`,"}}} +{"type":"assistant/chunk","seq":22,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} +{"type":"assistant/chunk","seq":23,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" quote"}}} +{"type":"assistant/chunk","seq":24,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":25,"time":1783986963221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} +{"type":"assistant/chunk","seq":26,"time":1783986963221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} +{"type":"assistant/chunk","seq":27,"time":1783986963221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} +{"type":"assistant/chunk","seq":28,"time":1783986963221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":29,"time":1783986963252,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} +{"type":"assistant/chunk","seq":30,"time":1783986963252,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":31,"time":1783986963314,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":32,"time":1783986963315,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":33,"time":1783986963345,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":34,"time":1783986963345,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":35,"time":1783986963345,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"command"}}} +{"type":"assistant/chunk","seq":36,"time":1783986963369,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":37,"time":1783986963369,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":38,"time":1783986963369,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":39,"time":1783986963369,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"echo"}}} +{"type":"assistant/chunk","seq":40,"time":1783986963397,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":" HE"}}} +{"type":"assistant/chunk","seq":41,"time":1783986963397,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"LL"}}} +{"type":"assistant/chunk","seq":42,"time":1783986963397,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"O"}}} +{"type":"assistant/chunk","seq":43,"time":1783986963397,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":44,"time":1783986963428,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":45,"time":1783986963429,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":46,"time":1783986963457,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":47,"time":1783986963457,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":48,"time":1783986963457,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":49,"time":1783986963457,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":50,"time":1783986963489,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"E"}}} +{"type":"assistant/chunk","seq":51,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"cho"}}} +{"type":"assistant/chunk","seq":52,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":" HE"}}} +{"type":"assistant/chunk","seq":53,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"LL"}}} +{"type":"assistant/chunk","seq":54,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"O"}}} +{"type":"assistant/chunk","seq":55,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":" to"}}} +{"type":"assistant/chunk","seq":56,"time":1783986963544,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":" stdout"}}} +{"type":"assistant/chunk","seq":57,"time":1783986963544,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":58,"time":1783986963658,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":59,"time":1783986963659,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to call the bash tool once with `echo HELLO`, then quote the result verbatim and stop."}}}} +{"type":"assistant/chunk","seq":60,"time":1783986963660,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}}}} +{"type":"assistant/chunk","seq":61,"time":1783986963660,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3256,"outputTokens":94,"cacheReadTokens":0,"reasoningTokens":26}}}} +{"type":"assistant/chunk","seq":62,"time":1783986963660,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":63,"time":1783986963663,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to call the bash tool once with `echo HELLO`, then quote the result verbatim and stop."},{"type":"tool-call","id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}],"usage":{"inputTokens":3256,"outputTokens":94,"cacheReadTokens":0,"reasoningTokens":26}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62],"surfaceOp":"append"} +{"type":"tool/call","seq":64,"time":1783986963664,"data":{"turn":1,"step":1,"callId":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}} +{"type":"hook/invoked","seq":65,"time":1783986963673,"data":{"turn":1,"point":"PostToolUse","dialect":"codex","handlerId":"codex:PostToolUse:1","matcher":"bash"}} +{"type":"hook/result","seq":66,"time":1783986963677,"data":{"turn":1,"point":"PostToolUse","handlerId":"codex:PostToolUse:1","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by codex policy: summarize instead","durationMs":4.42941699999983}} +{"type":"tool/result","seq":67,"time":1783986963678,"data":{"turn":1,"step":1,"callId":"call_00_1rmSWHhVchVg7PDTmegT0421","content":[{"type":"text","text":"tool output rejected by codex policy: summarize instead"}],"isError":true},"sourceEventSeqs":[64],"surfaceOp":"append"} +{"type":"step/end","seq":68,"time":1783986963678,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":69,"time":1783986963679,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":70,"time":1783986964555,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":71,"time":1783986964555,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":72,"time":1783986964809,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":73,"time":1783986964835,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} +{"type":"assistant/chunk","seq":74,"time":1783986964835,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" was"}}} +{"type":"assistant/chunk","seq":75,"time":1783986964836,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" rejected"}}} +{"type":"assistant/chunk","seq":76,"time":1783986964864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" by"}}} +{"type":"assistant/chunk","seq":77,"time":1783986964865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" code"}}} +{"type":"assistant/chunk","seq":78,"time":1783986964865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"x"}}} +{"type":"assistant/chunk","seq":79,"time":1783986964893,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" policy"}}} +{"type":"assistant/chunk","seq":80,"time":1783986964899,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":81,"time":1783986964900,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} +{"type":"assistant/chunk","seq":82,"time":1783986964924,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":83,"time":1783986964924,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" quote"}}} +{"type":"assistant/chunk","seq":84,"time":1783986964955,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" what"}}} +{"type":"assistant/chunk","seq":85,"time":1783986964985,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":86,"time":1783986965013,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" got"}}} +{"type":"assistant/chunk","seq":87,"time":1783986965014,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" back"}}} +{"type":"assistant/chunk","seq":88,"time":1783986965045,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":89,"time":1783986965132,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":90,"time":1783986965132,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"```\n"}}} +{"type":"assistant/chunk","seq":91,"time":1783986965133,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"<"}}} +{"type":"assistant/chunk","seq":92,"time":1783986965133,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"tool"}}} +{"type":"assistant/chunk","seq":93,"time":1783986965133,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_result"}}} +{"type":"assistant/chunk","seq":94,"time":1783986965133,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":">"}}} +{"type":"assistant/chunk","seq":95,"time":1783986965233,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"tool"}}} +{"type":"assistant/chunk","seq":96,"time":1783986965234,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" output"}}} +{"type":"assistant/chunk","seq":97,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" rejected"}}} +{"type":"assistant/chunk","seq":98,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" by"}}} +{"type":"assistant/chunk","seq":99,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" code"}}} +{"type":"assistant/chunk","seq":100,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"x"}}} +{"type":"assistant/chunk","seq":101,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" policy"}}} +{"type":"assistant/chunk","seq":102,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":":"}}} +{"type":"assistant/chunk","seq":103,"time":1783986965236,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" summarize"}}} +{"type":"assistant/chunk","seq":104,"time":1783986965236,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" instead"}}} +{"type":"assistant/chunk","seq":105,"time":1783986965236,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"\n"}}} +{"type":"assistant/chunk","seq":109,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"```"}}} +{"type":"assistant/chunk","seq":110,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The tool output was rejected by codex policy. Let me quote what I got back."}}}} +{"type":"assistant/chunk","seq":111,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"```\ntool output rejected by codex policy: summarize instead\n```"}}}} +{"type":"assistant/chunk","seq":112,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":44,"outputTokens":39,"cacheReadTokens":3328,"reasoningTokens":18}}}} +{"type":"assistant/chunk","seq":113,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":114,"time":1783986965238,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The tool output was rejected by codex policy. Let me quote what I got back."},{"type":"text","text":"```\ntool output rejected by codex policy: summarize instead\n```"}],"usage":{"inputTokens":44,"outputTokens":39,"cacheReadTokens":3328,"reasoningTokens":18}},"sourceEventSeqs":[70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113],"surfaceOp":"append"} +{"type":"step/end","seq":115,"time":1783986965238,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":116,"time":1783986965238,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl index fddecc08c6..1c99b178a3 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl @@ -5,124 +5,52 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" run"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" call"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" command"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" bash"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" once"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" `"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"echo"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" HE"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"LL"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"O"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" using"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" bash"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" report"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"`,"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" then"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" quote"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" result"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" verb"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"atim"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" stop"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_wNJIQDMLdssZp45zIXvz2684","title":"echo HELLO","kind":"execute","status":"in_progress","rawInput":"echo HELLO","content":[{"type":"content","content":{"type":"text","text":"Print HELLO to stdout"}}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_wNJIQDMLdssZp45zIXvz2684","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\ntool output rejected by codex policy: summarize instead\n```"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_1rmSWHhVchVg7PDTmegT0421","title":"echo HELLO","kind":"execute","status":"in_progress","rawInput":"echo HELLO","content":[{"type":"content","content":{"type":"text","text":"Echo HELLO to stdout"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_1rmSWHhVchVg7PDTmegT0421","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\ntool output rejected by codex policy: summarize instead\n```"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" output"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" was"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" rejected"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" by"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" code"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"x"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" policy"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instruction"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"sum"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"mar"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ize"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instead"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" This"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" means"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" cannot"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" show"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" raw"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" output"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" verb"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"atim"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" as"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" requested"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Let"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" try"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" comply"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" but"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" report"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" quote"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" what"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" happened"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Actually"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" report"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" result"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" verb"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"atim"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" result"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" got"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" back"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" is"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" output"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" rejected"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" by"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" code"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"x"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" policy"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" summarize"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instead"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"So"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" should"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" report"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" that"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" verb"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"atim"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"The"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" result"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" got"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" back"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" is"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":":\n\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"```\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"<"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"tool"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"_result"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":">"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" `"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"tool"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" output"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" rejected"}}}} @@ -133,42 +61,9 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":":"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" summarize"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" instead"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"`\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"This"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" is"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" verb"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"atim"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" result"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" from"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" —"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" it"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" was"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" not"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" expected"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" `"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"HE"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"LL"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"O"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"`"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" output"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" because"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" code"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"x"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" policy"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" blocked"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" it"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" and"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" instructed"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" me"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" summarize"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" instead"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"```"}}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} From 8ada835396a021a7dce8f72d6b025dcd3a264c15 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:03:33 +0800 Subject: [PATCH 059/359] docs: remove links to private subagent helpers --- packages/subagent/subagent-subprocess/src/index.ts | 12 +++++------- packages/subagent/tool-subagent/src/index.ts | 10 +++++----- 2 files changed, 10 insertions(+), 12 deletions(-) diff --git a/packages/subagent/subagent-subprocess/src/index.ts b/packages/subagent/subagent-subprocess/src/index.ts index 2ee2745985..bd792e7f23 100644 --- a/packages/subagent/subagent-subprocess/src/index.ts +++ b/packages/subagent/subagent-subprocess/src/index.ts @@ -2,11 +2,10 @@ * Shared machinery for OUT-OF-PROCESS subagent backends — providers that spawn * an external agent as a child process and must keep the parent deployment's * credentials out of it, tear it down to quiescence, and isolate it from the - * host user's on-disk CLI state. The pieces: the credential env scrub - * ({@link SENSITIVE_ENV_PATTERN} / {@link buildChildEnv}), the spawn-failure - * capture ({@link spawnFailure}), the child-exit waits ({@link waitForExit} / - * {@link exitsWithin}), the stdin-EOF → SIGTERM → SIGKILL dispose ladder - * ({@link disposeChildProcess}), and the per-run isolated config dir + * host user's on-disk CLI state. The pieces: credential-shaped env scrubbing + * ({@link buildChildEnv}), spawn-failure capture ({@link spawnFailure}), + * bounded child-exit waits inside the stdin-EOF → SIGTERM → SIGKILL dispose + * ladder ({@link disposeChildProcess}), and the per-run isolated config dir * ({@link createIsolatedConfigDir}). * * This package owns no provider and registers nothing; it is a pure library @@ -37,8 +36,7 @@ const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i /** * The ambient env minus credential-shaped vars, plus the caller's explicit * env. `PATH`, `HOME`, `TMPDIR`, locale, and proxy vars survive the scrub, so - * a child CLI runs normally; only {@link SENSITIVE_ENV_PATTERN}-shaped names - * are dropped. + * a child CLI runs normally; only credential-shaped names are dropped. * @param extra - explicit vars layered on top AFTER the scrub, so a * credential-shaped name supplied deliberately still reaches the child. * @returns the environment to spawn the child with. diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index 426753dbb9..ff54bc109a 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -12,11 +12,11 @@ * sees only `{ description, prompt }`. * * The tool DESCRIPTION is derived from the bound provider's conversation-history - * descriptor ({@link providerWording}): a fresh-conversation provider (spawn, - * ACP) gets the standalone-prompt wording, while a seeded-conversation provider - * (fork) tells the model the child already sees the conversation's completed - * turns. This descriptor says nothing about Cordis scope, services, tools, or - * authority. The tool MIRRORS the + * descriptor ({@link SubagentProvider.inheritsParentContext}): a + * fresh-conversation provider (spawn, ACP) gets the standalone-prompt wording, + * while a seeded-conversation provider (fork) tells the model the child already + * sees the conversation's completed turns. This descriptor says nothing about + * Cordis scope, services, tools, or authority. The tool MIRRORS the * provider's lifecycle via `subagent/provider-added`/`-removed` — it registers * when the provider is (or becomes) available and unregisters when the * provider goes away — so no load-order requirement exists and an HMR reload From cb80277e60c17ac5238dc7ee740ae315ee3521ff Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:11:13 +0800 Subject: [PATCH 060/359] fix: retain JSON-RPC subagent locality per run --- docs/event-producer-consumer.md | 4 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 45 +++++++++++---- packages/ui/jsonrpc/tests/server.spec.ts | 73 ++++++++++++++++++++---- 4 files changed, 98 insertions(+), 26 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 80389608cc..04aff464a9 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -8,7 +8,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | | `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:444`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | @@ -34,7 +34,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:91`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:67`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | | `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:73`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | +| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:49`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:59`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:173`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 735cfead0a..95d7d7c7d7 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage because the child may be disposed before `subagent/end`, and the provider contract does not require lineage. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and snapshots it per run, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index bf21f7fc2d..12bf82de3c 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -17,7 +17,7 @@ import { resolve } from 'node:path' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { AgentHandle } from '@deepseek-ai/dsh-agent' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' -import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' +import type { SubagentRunEndInfo, SubagentRunInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import type { JsonRpcTransportPeer } from './transport.ts' @@ -65,10 +65,11 @@ interface LocalAgentRecord { /** * The SDK server over a booted harness context. Constructing it subscribes to - * the context's `session/event`, `session/created`, `agent/created`, and - * `subagent/end` events and forwards them to the host as notifications; the - * subscriptions live until {@link shutdown}. One instance serves one transport - * peer for the process lifetime — there is no re-`initialize`. + * session, agent, and subagent lifecycle events, forwarding durable session + * events and SDK-facing completion notifications while retaining local-run + * identity across child disposal. The subscriptions live until + * {@link shutdown}. One instance serves one transport peer for the process + * lifetime — there is no re-`initialize`. */ export class HarnessSdkServer { private cwd = process.cwd() @@ -77,6 +78,7 @@ export class HarnessSdkServer { private readonly sessions = new Map() private readonly sessionCreations = new Map>() private readonly localAgents = new Map() + private readonly localRuns = new Map() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -100,18 +102,38 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache runtime-local identity and optional lineage on creation: by the - // time `subagent/end` fires the child agent may already be disposed and - // gone from the registry. Parent lineage is not required by the provider - // contract, so an empty record remains a load-bearing locality marker. + // Cache runtime-local identity and optional lineage for each agent lifetime. + // Parent lineage is not required by the provider contract, so an empty + // record remains a load-bearing locality marker. this.disposers.push(ctx.on('agent/created', (agent) => { const parentSessionId = agent.session.header.parentSession this.localAgents.set(agent.id, parentSessionId === undefined ? {} : { parentSessionId }) })) - this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { + this.disposers.push(ctx.on('agent/disposed', (agent) => { + this.localAgents.delete(agent.id) + })) + // Snapshot locality per run. A provider may settle one run, continue the + // same live child in another run, and dispose that child before the later + // result settles. Consuming an agent-lifetime marker at the first end would + // lose the later notification; this queue pairs each start with one end. + this.disposers.push(ctx.on('subagent/start', (info: SubagentRunInfo) => { const agent = this.ctx.agents.get(info.id) const cachedLocalAgent = this.localAgents.get(info.id) - this.localAgents.delete(info.id) + const localAgent = cachedLocalAgent ?? (agent === undefined + ? undefined + : agent.session.header.parentSession === undefined + ? {} + : { parentSessionId: agent.session.header.parentSession }) + if (localAgent === undefined) return + const runs = this.localRuns.get(info.id) ?? [] + runs.push(localAgent) + this.localRuns.set(info.id, runs) + })) + this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { + const agent = this.ctx.agents.get(info.id) + const runs = this.localRuns.get(info.id) + const cachedLocalAgent = runs?.shift() + if (runs?.length === 0) this.localRuns.delete(info.id) // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above; a parentless // local provider still gets its terminal notification. A remote provider @@ -196,6 +218,7 @@ export class HarnessSdkServer { const records = [...this.sessions.values()] this.sessions.clear() this.localAgents.clear() + this.localRuns.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 163aee4c0c..d56f3000f6 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -11,7 +11,7 @@ import { SessionId } from '@deepseek-ai/dsh-session' import * as agentCore from '@deepseek-ai/dsh-agent-core' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' -import SubagentService, { type SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' +import SubagentService, { type SubagentResult, type SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' import { HarnessSdkServer, type JsonRpcTransportPeer } from '../src/index.ts' class FakeTransport implements JsonRpcTransportPeer { @@ -67,7 +67,13 @@ async function makeHarness(storageDir: string) { } /** Drive the owning service so test lifecycle events carry the real parent scope. */ -async function settleSubagent(ctx: Context, parent: Agent, info: SubagentRunEndInfo): Promise { +async function settleSubagent( + ctx: Context, + parent: Agent, + info: SubagentRunEndInfo, + beforeSettle?: () => Promise, +): Promise { + const result = Promise.withResolvers() const disposeProvider = ctx.subagents.registerProvider({ name: info.provider, capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, @@ -75,9 +81,7 @@ async function settleSubagent(ctx: Context, parent: Agent, info: SubagentRunEndI async start() { return { id: info.id, - result: info.lastAssistantMessage === undefined - ? Promise.reject(new Error('synthetic infrastructure failure')) - : Promise.resolve({ output: info.lastAssistantMessage, stopReason: info.stopReason }), + result: result.promise, dispose: () => Promise.resolve(), } }, @@ -88,6 +92,12 @@ async function settleSubagent(ctx: Context, parent: Agent, info: SubagentRunEndI prompt: [], signal: new AbortController().signal, }) + await beforeSettle?.() + if (info.lastAssistantMessage === undefined) { + result.reject(new Error('synthetic infrastructure failure')) + } else { + result.resolve({ output: info.lastAssistantMessage, stopReason: info.stopReason }) + } await run.result.then(() => undefined, () => undefined) await run.dispose() } finally { @@ -277,21 +287,17 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - // The backend may dispose the child before publishing its run outcome; - // cached locality must survive with or without optional parent lineage. - await handle.dispose() - await parentlessHandle.dispose() await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], - }) + }, () => handle.dispose()) await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('parentless-child-session'), stopReason: 'error', - }) + }, () => parentlessHandle.dispose()) expect(transport.notifications).toContainEqual({ method: 'subagent.finished', @@ -324,6 +330,49 @@ describe('HarnessSdkServer', () => { } }) + it('retains locality across continuation runs on one live child', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-continuation-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const parentHandle = await ctx.agents.create({ + sessionId: SessionId('continuation-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const childHandle = await ctx.agents.create({ + sessionId: SessionId('continuation-child'), + meta: { cwd: storageDir, parentSession: SessionId('continuation-parent') }, + agentOptions: { model: 'deepseek' }, + }) + + await settleSubagent(ctx, parentHandle.agent, { + provider: 'continuation', + id: SessionId('continuation-child'), + stopReason: 'completed', + lastAssistantMessage: [{ type: 'text', text: 'first' }], + }) + await settleSubagent(ctx, parentHandle.agent, { + provider: 'continuation', + id: SessionId('continuation-child'), + stopReason: 'completed', + lastAssistantMessage: [{ type: 'text', text: 'second' }], + }, () => childHandle.dispose()) + + expect(transport.notifications.filter(notification => + notification.method === 'subagent.finished' + && notification.params?.childSessionId === 'continuation-child', + )).toHaveLength(2) + + await parentHandle.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + it('falls back to live lineage and ignores runs without a local child session', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) @@ -585,6 +634,6 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, new FakeTransport()) await expect(server.shutdown()).rejects.toBe(listenerFailure) - expect(on).toHaveBeenCalledTimes(4) + expect(on).toHaveBeenCalledTimes(6) }) }) From d898d1faf0739e4e4f2edd5b6f7a156f54ed2d25 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:25:52 +0800 Subject: [PATCH 061/359] fix: avoid FIFO subagent lineage attribution --- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 49 ++++++--- packages/ui/jsonrpc/tests/server.spec.ts | 123 ++++++++++++++++++++++- 3 files changed, 158 insertions(+), 16 deletions(-) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 95d7d7c7d7..5ff7eb7f8e 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and snapshots it per run, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and counts pending runs per provider/id, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Settlement order is not assumed: if concurrent ID reuse makes parent lineage ambiguous, the completion remains local but omits the optional `parentSessionId` rather than attributing the wrong parent. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 12bf82de3c..ce0ac9c75a 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -63,6 +63,13 @@ interface LocalAgentRecord { parentSessionId?: SessionId } +/** Pending local runs that share one provider/id correlation key. */ +interface PendingLocalRuns { + count: number + parentSessionId?: SessionId + parentAmbiguous: boolean +} + /** * The SDK server over a booted harness context. Constructing it subscribes to * session, agent, and subagent lifecycle events, forwarding durable session @@ -78,7 +85,7 @@ export class HarnessSdkServer { private readonly sessions = new Map() private readonly sessionCreations = new Map>() private readonly localAgents = new Map() - private readonly localRuns = new Map() + private readonly localRuns = new Map>() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -112,10 +119,12 @@ export class HarnessSdkServer { this.disposers.push(ctx.on('agent/disposed', (agent) => { this.localAgents.delete(agent.id) })) - // Snapshot locality per run. A provider may settle one run, continue the - // same live child in another run, and dispose that child before the later - // result settles. Consuming an agent-lifetime marker at the first end would - // lose the later notification; this queue pairs each start with one end. + // Snapshot locality per provider/id run key. A provider may settle one run, + // continue the same live child in another run, and dispose that child before + // the later result settles. Counts preserve every completion without + // assuming settlement order. If id reuse produces disagreeing lineage, the + // optional parent is omitted until that pending group drains rather than + // attributed to the wrong completion. this.disposers.push(ctx.on('subagent/start', (info: SubagentRunInfo) => { const agent = this.ctx.agents.get(info.id) const cachedLocalAgent = this.localAgents.get(info.id) @@ -125,21 +134,35 @@ export class HarnessSdkServer { ? {} : { parentSessionId: agent.session.header.parentSession }) if (localAgent === undefined) return - const runs = this.localRuns.get(info.id) ?? [] - runs.push(localAgent) - this.localRuns.set(info.id, runs) + const providerRuns = this.localRuns.get(info.provider) ?? new Map() + const pending = providerRuns.get(info.id) + if (pending === undefined) { + providerRuns.set(info.id, localAgent.parentSessionId === undefined + ? { count: 1, parentAmbiguous: false } + : { count: 1, parentSessionId: localAgent.parentSessionId, parentAmbiguous: false }) + } else { + pending.count += 1 + if (pending.parentSessionId !== localAgent.parentSessionId) pending.parentAmbiguous = true + } + this.localRuns.set(info.provider, providerRuns) })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { const agent = this.ctx.agents.get(info.id) - const runs = this.localRuns.get(info.id) - const cachedLocalAgent = runs?.shift() - if (runs?.length === 0) this.localRuns.delete(info.id) + const providerRuns = this.localRuns.get(info.provider) + const pending = providerRuns?.get(info.id) + if (pending !== undefined) { + pending.count -= 1 + if (pending.count === 0) providerRuns?.delete(info.id) + if (providerRuns?.size === 0) this.localRuns.delete(info.provider) + } // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above; a parentless // local provider still gets its terminal notification. A remote provider // has neither a cached creation nor a live local agent and is ignored. - if (cachedLocalAgent === undefined && agent === undefined) return - const parentSessionId = cachedLocalAgent?.parentSessionId ?? agent?.session.header.parentSession + if (pending === undefined && agent === undefined) return + const parentSessionId = pending === undefined + ? agent?.session.header.parentSession + : pending.parentAmbiguous ? undefined : pending.parentSessionId this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index d56f3000f6..48b8c4b1be 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -373,6 +373,100 @@ describe('HarnessSdkServer', () => { } }) + it('omits ambiguous lineage when one local id is reused and runs settle out of order', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-reuse-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const oldParent = await ctx.agents.create({ + sessionId: SessionId('old-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const oldChild = await ctx.agents.create({ + sessionId: SessionId('reused-child'), + meta: { cwd: storageDir, parentSession: SessionId('old-parent') }, + agentOptions: { model: 'deepseek' }, + }) + const first = Promise.withResolvers() + const sameLifetime = Promise.withResolvers() + const replacement = Promise.withResolvers() + const results = [first.promise, sameLifetime.promise, replacement.promise] + let starts = 0 + const disposeProvider = ctx.subagents.registerProvider({ + name: 'reused', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start() { + const result = results[starts] + starts += 1 + if (result === undefined) throw new Error('unexpected fourth reused-id run') + return Promise.resolve({ id: SessionId('reused-child'), result, dispose: () => Promise.resolve() }) + }, + }) + + const firstRun = await ctx.subagents.start('reused', { + parent: oldParent.agent, + prompt: [], + signal: new AbortController().signal, + }) + const sameLifetimeRun = await ctx.subagents.start('reused', { + parent: oldParent.agent, + prompt: [], + signal: new AbortController().signal, + }) + sameLifetime.resolve({ output: [{ type: 'text', text: 'same lifetime' }], stopReason: 'completed' }) + await sameLifetimeRun.result + await oldChild.dispose() + const newParent = await ctx.agents.create({ + sessionId: SessionId('new-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const newChild = await ctx.agents.create({ + sessionId: SessionId('reused-child'), + meta: { cwd: storageDir, parentSession: SessionId('new-parent') }, + agentOptions: { model: 'deepseek' }, + }) + const secondRun = await ctx.subagents.start('reused', { + parent: newParent.agent, + prompt: [], + signal: new AbortController().signal, + }) + + replacement.resolve({ output: [{ type: 'text', text: 'new lifetime' }], stopReason: 'completed' }) + await secondRun.result + first.resolve({ output: [{ type: 'text', text: 'old lifetime' }], stopReason: 'completed' }) + await firstRun.result + await Promise.resolve() + + const finished = transport.notifications.filter(notification => + notification.method === 'subagent.finished' + && notification.params?.childSessionId === 'reused-child', + ) + expect(finished.map(notification => notification.params?.lastAssistantMessage)).toEqual([ + [{ type: 'text', text: 'same lifetime' }], + [{ type: 'text', text: 'new lifetime' }], + [{ type: 'text', text: 'old lifetime' }], + ]) + expect(finished[0]?.params?.parentSessionId).toBe('old-parent') + expect(finished.slice(1).every(notification => !Object.hasOwn(notification.params ?? {}, 'parentSessionId'))).toBe(true) + + await firstRun.dispose() + await sameLifetimeRun.dispose() + await secondRun.dispose() + disposeProvider() + await newChild.dispose() + await oldParent.dispose() + await newParent.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + it('falls back to live lineage and ignores runs without a local child session', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) @@ -395,13 +489,38 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) + const missedStartResult = Promise.withResolvers() + const disposeMissedStartProvider = ctx.subagents.registerProvider({ + name: 'fork', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: true, + start: () => Promise.resolve({ + id: SessionId('fallback-child-session'), + result: missedStartResult.promise, + dispose: () => Promise.resolve(), + }), + }) + // Start before the server subscribes, so the terminal fallback must use + // the still-live registry entry rather than a cached start record. + const missedStartRun = await ctx.subagents.start('fork', { + parent: parentHandle.agent, + prompt: [], + signal: new AbortController().signal, + }) const transport = new FakeTransport() const server = new HarnessSdkServer(ctx, transport) + missedStartResult.resolve({ output: [], stopReason: 'max-tokens' }) + await missedStartRun.result + await Promise.resolve() + await missedStartRun.dispose() + disposeMissedStartProvider() + // The server also missed this agent's creation, but observes the start; + // recover its lineage from the still-live registry entry. await settleSubagent(ctx, parentHandle.agent, { - provider: 'fork', + provider: 'fork-live-fallback', id: SessionId('fallback-child-session'), - stopReason: 'max-tokens', + stopReason: 'completed', lastAssistantMessage: [], }) await settleSubagent(ctx, parentHandle.agent, { From 45e3997efcecf48c57e171a7d77401b1c914ea32 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:41:31 +0800 Subject: [PATCH 062/359] fix: correlate subagent completion by parent scope --- docs/event-producer-consumer.md | 4 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 101 ++++++++--------------- packages/ui/jsonrpc/tests/server.spec.ts | 13 ++- 4 files changed, 47 insertions(+), 73 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 04aff464a9..bc1c0d38d0 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,8 +7,8 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | | `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:444`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 5ff7eb7f8e..ffbd7a1288 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and counts pending runs per provider/id, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Settlement order is not assumed: if concurrent ID reuse makes parent lineage ambiguous, the completion remains local but omits the optional `parentSessionId` rather than attributing the wrong parent. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server counts local starts by provider/id and the exact delegating-parent carrier, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index ce0ac9c75a..352563f7f2 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -15,8 +15,10 @@ import type { Context } from 'cordis' import { resolve } from 'node:path' import type { ContentBlock } from '@deepseek-ai/dsh-llm' -import type { AgentHandle } from '@deepseek-ai/dsh-agent' +import type { Agent, AgentHandle } from '@deepseek-ai/dsh-agent' +import { carrierKeyOf, type Scoped } from '@deepseek-ai/dsh-scope' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' +import type SubagentService from '@deepseek-ai/dsh-subagent' import type { SubagentRunEndInfo, SubagentRunInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import type { JsonRpcTransportPeer } from './transport.ts' @@ -58,21 +60,14 @@ interface SessionRecord { activePrompt: boolean } -/** Runtime-local agent identity plus optional durable fork lineage. */ -interface LocalAgentRecord { - parentSessionId?: SessionId -} - -/** Pending local runs that share one provider/id correlation key. */ -interface PendingLocalRuns { - count: number - parentSessionId?: SessionId - parentAmbiguous: boolean +/** Recover the delegating parent carried by every service-owned subagent lifecycle event. */ +function subagentParentOf(carrier: Scoped): Agent { + return carrierKeyOf(carrier) as Agent } /** * The SDK server over a booted harness context. Constructing it subscribes to - * session, agent, and subagent lifecycle events, forwarding durable session + * session and subagent lifecycle events, forwarding durable session * events and SDK-facing completion notifications while retaining local-run * identity across child disposal. The subscriptions live until * {@link shutdown}. One instance serves one transport peer for the process @@ -84,8 +79,7 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly localAgents = new Map() - private readonly localRuns = new Map>() + private readonly localRuns = new Map>>() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -109,64 +103,40 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache runtime-local identity and optional lineage for each agent lifetime. - // Parent lineage is not required by the provider contract, so an empty - // record remains a load-bearing locality marker. - this.disposers.push(ctx.on('agent/created', (agent) => { - const parentSessionId = agent.session.header.parentSession - this.localAgents.set(agent.id, parentSessionId === undefined ? {} : { parentSessionId }) + // In-process providers publish the child before start. Count those starts by + // the exact delegating-parent carrier so later completions remain local after + // child disposal and reused ids need no settlement-order assumption. + const localRuns = this.localRuns + this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { + if (ctx.agents.get(info.id) === undefined) return + const parent = subagentParentOf(this) + const providerRuns = localRuns.get(info.provider) ?? new Map>() + const parentRuns = providerRuns.get(info.id) ?? new Map() + parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) + providerRuns.set(info.id, parentRuns) + localRuns.set(info.provider, providerRuns) })) - this.disposers.push(ctx.on('agent/disposed', (agent) => { - this.localAgents.delete(agent.id) - })) - // Snapshot locality per provider/id run key. A provider may settle one run, - // continue the same live child in another run, and dispose that child before - // the later result settles. Counts preserve every completion without - // assuming settlement order. If id reuse produces disagreeing lineage, the - // optional parent is omitted until that pending group drains rather than - // attributed to the wrong completion. - this.disposers.push(ctx.on('subagent/start', (info: SubagentRunInfo) => { - const agent = this.ctx.agents.get(info.id) - const cachedLocalAgent = this.localAgents.get(info.id) - const localAgent = cachedLocalAgent ?? (agent === undefined - ? undefined - : agent.session.header.parentSession === undefined - ? {} - : { parentSessionId: agent.session.header.parentSession }) - if (localAgent === undefined) return - const providerRuns = this.localRuns.get(info.provider) ?? new Map() - const pending = providerRuns.get(info.id) - if (pending === undefined) { - providerRuns.set(info.id, localAgent.parentSessionId === undefined - ? { count: 1, parentAmbiguous: false } - : { count: 1, parentSessionId: localAgent.parentSessionId, parentAmbiguous: false }) - } else { - pending.count += 1 - if (pending.parentSessionId !== localAgent.parentSessionId) pending.parentAmbiguous = true - } - this.localRuns.set(info.provider, providerRuns) - })) - this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { - const agent = this.ctx.agents.get(info.id) - const providerRuns = this.localRuns.get(info.provider) - const pending = providerRuns?.get(info.id) - if (pending !== undefined) { - pending.count -= 1 - if (pending.count === 0) providerRuns?.delete(info.id) - if (providerRuns?.size === 0) this.localRuns.delete(info.provider) + this.disposers.push(ctx.on('subagent/end', function (this: Scoped, info: SubagentRunEndInfo) { + const agent = ctx.agents.get(info.id) + const parent = subagentParentOf(this) + const providerRuns = localRuns.get(info.provider) + const parentRuns = providerRuns?.get(info.id) + const pendingCount = parentRuns?.get(parent) + if (pendingCount !== undefined) { + if (pendingCount === 1) parentRuns?.delete(parent) + else parentRuns?.set(parent, pendingCount - 1) + if (parentRuns?.size === 0) providerRuns?.delete(info.id) + if (providerRuns?.size === 0) localRuns.delete(info.provider) } // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above; a parentless // local provider still gets its terminal notification. A remote provider - // has neither a cached creation nor a live local agent and is ignored. - if (pending === undefined && agent === undefined) return - const parentSessionId = pending === undefined - ? agent?.session.header.parentSession - : pending.parentAmbiguous ? undefined : pending.parentSessionId - this.transport.notify('subagent.finished', { + // has neither a pending local start nor a live local agent and is ignored. + if (pendingCount === undefined && agent === undefined) return + transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), - ...(parentSessionId === undefined ? {} : { parentSessionId: String(parentSessionId) }), + parentSessionId: String(parent.session.id), childSessionId: String(info.id), status: info.stopReason === 'completed' ? 'ok' : 'error', stopReason: info.stopReason, @@ -240,7 +210,6 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.localAgents.clear() this.localRuns.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 48b8c4b1be..427a190c36 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -316,6 +316,7 @@ describe('HarnessSdkServer', () => { params: { provider: 'spawn', agentId: 'parentless-child-session', + parentSessionId: 'main', childSessionId: 'parentless-child-session', status: 'error', stopReason: 'error', @@ -373,7 +374,7 @@ describe('HarnessSdkServer', () => { } }) - it('omits ambiguous lineage when one local id is reused and runs settle out of order', async () => { + it('correlates reused local ids by parent scope when runs settle out of order', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-reuse-')) const ctx = await makeHarness(storageDir) try { @@ -450,8 +451,11 @@ describe('HarnessSdkServer', () => { [{ type: 'text', text: 'new lifetime' }], [{ type: 'text', text: 'old lifetime' }], ]) - expect(finished[0]?.params?.parentSessionId).toBe('old-parent') - expect(finished.slice(1).every(notification => !Object.hasOwn(notification.params ?? {}, 'parentSessionId'))).toBe(true) + expect(finished.map(notification => notification.params?.parentSessionId)).toEqual([ + 'old-parent', + 'new-parent', + 'old-parent', + ]) await firstRun.dispose() await sameLifetimeRun.dispose() @@ -551,6 +555,7 @@ describe('HarnessSdkServer', () => { params: { provider: 'fork', agentId: 'failed-child-session', + parentSessionId: 'fallback-parent', childSessionId: 'failed-child-session', status: 'error', stopReason: 'error', @@ -753,6 +758,6 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, new FakeTransport()) await expect(server.shutdown()).rejects.toBe(listenerFailure) - expect(on).toHaveBeenCalledTimes(6) + expect(on).toHaveBeenCalledTimes(4) }) }) From d33a819d15964fac1212f7b716f50106c8bb0ed1 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:55:38 +0800 Subject: [PATCH 063/359] fix: share scope carrier across built JSON-RPC --- AGENTS.md | 2 +- docs/testing.md | 2 +- packages/ui/jsonrpc/package.json | 2 + .../jsonrpc/tests/built-scope-carrier.e2e.ts | 121 ++++++++++++++++++ pnpm-lock.yaml | 3 + scripts/run-gates.ts | 1 + 6 files changed, 129 insertions(+), 2 deletions(-) create mode 100644 packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts diff --git a/AGENTS.md b/AGENTS.md index 4dfbedb97b..1494d3fcf8 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -76,7 +76,7 @@ printf '%s\n' "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})' printf '%s\n' "$out" | grep -q '\[tool result\] ECHO: CI SMOKE' test -n "$(find .sessions -path '.sessions/cwd-*/main-session-*.jsonl' -type f -print -quit)" rm -rf .sessions -pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts +pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts ``` `test:coverage`, not `test`, is the gating run ([why](docs/testing.md)); a sign-off counts only for commands actually run. diff --git a/docs/testing.md b/docs/testing.md index 23cca651fe..a1a841296a 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -25,7 +25,7 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword - A plugin shipped via `cordis.yml` needs at least one test through the REAL Loader path: hand-built `ctx.plugin({...})` mounts bypass `unwrapExports` and cannot catch a broken export shape ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md); export-shape rules in [packages/AGENTS.md](../packages/AGENTS.md)). - A guard only guards if the regression actually fails it. For a plugin without `inject` (bundle/composition plugins), a Loader smoke stays green under a broken export shape — add an explicit `expect('default' in mod).toBe(false)` plus an `unwrapExports` round-trip assertion, and prove it: introduce the regression, watch red, revert. -- "Real entry path" means the published artifact: the package `bin` points at built `lib/bin.js` under plain `node`, which tsx masks (settle races, module resolution, a swallowed load failure exiting 0). The same applies to any non-index runtime entry the built package resolves at run time (the worker-thread runtime's sibling `lib/worker.cjs`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. +- "Real entry path" means the published artifact: a package `bin` runs built `lib/bin.js` under plain `node`, exposing failures tsx masks (settle races, module resolution, swallowed load failures). The same applies to non-index runtime entries (the worker-thread sibling `lib/worker.cjs`) and singleton modules shared across bundles (`packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. - An e2e that spawns an example from a temp cwd sets `TSX_TSCONFIG_PATH` to the repo-root tsconfig, or it silently falls back to stale built `lib/` ([examples/AGENTS.md](../examples/AGENTS.md)). ## When a snapshot test is required diff --git a/packages/ui/jsonrpc/package.json b/packages/ui/jsonrpc/package.json index be19ab7217..bf4fe39118 100644 --- a/packages/ui/jsonrpc/package.json +++ b/packages/ui/jsonrpc/package.json @@ -28,6 +28,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-llm-deepseek": "^0.0.1", + "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -38,6 +39,7 @@ "@deepseek-ai/dsh-agent-core": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", + "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts new file mode 100644 index 0000000000..159600e49c --- /dev/null +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -0,0 +1,121 @@ +/** + * Built-artifact guard for the scope carrier shared by `dsh-subagent` and + * `dsh-jsonrpc`. The carrier registry is module-local, so both bundles must + * externalize `dsh-scope`; source-mode tests cannot expose an accidentally + * inlined second registry. This test runs the real `lib/index.js` bundles in a + * plain Node subprocess, disposes the child before settlement, and requires the + * SDK completion notification to retain the delegating parent. + */ + +import { execFile } from 'node:child_process' +import { existsSync } from 'node:fs' +import { fileURLToPath } from 'node:url' +import { promisify } from 'node:util' +import { describe, expect, it } from 'vitest' + +const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url)) +const jsonrpcBundle = fileURLToPath(new URL('../lib/index.js', import.meta.url)) +const execFileAsync = promisify(execFile) + +const builtRuntimeProbe = String.raw` +import { mkdtemp, rm } from "node:fs/promises"; +import { tmpdir } from "node:os"; +import { join, resolve } from "node:path"; +import { pathToFileURL } from "node:url"; + +const load = (path) => import(pathToFileURL(resolve(path)).href); +const [ + { Context }, + agentCore, + { default: SubagentService }, + { default: SessionPersistenceJsonl }, + { HarnessSdkServer }, + { SessionId }, +] = await Promise.all([ + load("vendor/cordis/lib/index.js"), + load("packages/core/agent-core/lib/index.js"), + load("packages/subagent/subagent/lib/index.js"), + load("packages/session-persistence/session-persistence-jsonl/lib/index.js"), + load("packages/ui/jsonrpc/lib/index.js"), + load("packages/core/session/lib/index.js"), +]); + +const storageRoot = await mkdtemp(join(tmpdir(), "jsonrpc-built-scope-")); +const ctx = new Context(); +try { + await ctx.plugin(agentCore); + await ctx.plugin(SubagentService); + await ctx.plugin(SessionPersistenceJsonl, { root: storageRoot }); + await new Promise((ready) => setTimeout(ready, 50)); + + const notifications = []; + const server = new HarnessSdkServer(ctx, { + request() { return Promise.reject(new Error("unexpected host request")); }, + notify(method, params) { notifications.push({ method, params }); }, + }); + const parent = await ctx.agents.create({ + sessionId: SessionId("built-parent"), + meta: { cwd: storageRoot }, + agentOptions: { model: "test" }, + }); + const child = await ctx.agents.create({ + sessionId: SessionId("built-child"), + meta: { cwd: storageRoot, parentSession: SessionId("built-parent") }, + agentOptions: { model: "test" }, + }); + const result = Promise.withResolvers(); + const unregister = ctx.subagents.registerProvider({ + name: "built-local", + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start() { + return Promise.resolve({ + id: child.agent.id, + result: result.promise, + dispose() { return Promise.resolve(); }, + }); + }, + }); + const run = await ctx.subagents.start("built-local", { + parent: parent.agent, + prompt: [], + signal: new AbortController().signal, + }); + await child.dispose(); + result.resolve({ output: [], stopReason: "completed" }); + await run.result; + await Promise.resolve(); + + console.log(JSON.stringify(notifications.filter(({ method }) => method === "subagent.finished"))); + await run.dispose(); + unregister(); + await parent.dispose(); + await server.shutdown(); +} finally { + await ctx.fiber.dispose(); + await rm(storageRoot, { recursive: true, force: true }); +} +` + +describe.skipIf(!existsSync(jsonrpcBundle))('dsh-jsonrpc BUILT scope carrier', () => { + it('preserves parent-scoped completion after child disposal', async () => { + const { stdout, stderr } = await execFileAsync(process.execPath, ['--input-type=module', '-e', builtRuntimeProbe], { + cwd: repoRoot, + timeout: 15_000, + }) + + expect(stderr).not.toContain('listener threw') + expect(JSON.parse(stdout) as unknown).toEqual([{ + method: 'subagent.finished', + params: { + provider: 'built-local', + agentId: 'built-child', + parentSessionId: 'built-parent', + childSessionId: 'built-child', + status: 'ok', + stopReason: 'completed', + lastAssistantMessage: [], + }, + }]) + }) +}) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 6214564eae..dec8c3024f 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1288,6 +1288,9 @@ importers: '@deepseek-ai/dsh-llm-deepseek': specifier: workspace:^ version: link:../../llm/llm-deepseek + '@deepseek-ai/dsh-scope': + specifier: workspace:^ + version: link:../../core/scope '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index 131501abb0..e1c41149ca 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -332,6 +332,7 @@ function builtBinSmokeGate(): Gate { 'vitest.e2e.config.ts', 'packages/ui/stdio-agent/tests/built-bin.e2e.ts', 'packages/ui/acp-agent/tests/built-bin.e2e.ts', + 'packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts', // The worker-entry packages' built bundles: the only automated proof // that lib/index.js resolves its sibling lib/worker.cjs under plain node // (the e2e lane runs unbuilt, so these files self-skip there). From 39c6c1120abdcc0414325bbdd1624917b0cb8624 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:56:21 +0800 Subject: [PATCH 064/359] Revert "fix: share scope carrier across built JSON-RPC" This reverts commit 835fd3ca4f46e0c6464098e3d0864dc56f31398d. --- AGENTS.md | 2 +- docs/testing.md | 2 +- packages/ui/jsonrpc/package.json | 2 - .../jsonrpc/tests/built-scope-carrier.e2e.ts | 121 ------------------ pnpm-lock.yaml | 3 - scripts/run-gates.ts | 1 - 6 files changed, 2 insertions(+), 129 deletions(-) delete mode 100644 packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts diff --git a/AGENTS.md b/AGENTS.md index 1494d3fcf8..4dfbedb97b 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -76,7 +76,7 @@ printf '%s\n' "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})' printf '%s\n' "$out" | grep -q '\[tool result\] ECHO: CI SMOKE' test -n "$(find .sessions -path '.sessions/cwd-*/main-session-*.jsonl' -type f -print -quit)" rm -rf .sessions -pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts +pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts ``` `test:coverage`, not `test`, is the gating run ([why](docs/testing.md)); a sign-off counts only for commands actually run. diff --git a/docs/testing.md b/docs/testing.md index a1a841296a..23cca651fe 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -25,7 +25,7 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword - A plugin shipped via `cordis.yml` needs at least one test through the REAL Loader path: hand-built `ctx.plugin({...})` mounts bypass `unwrapExports` and cannot catch a broken export shape ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md); export-shape rules in [packages/AGENTS.md](../packages/AGENTS.md)). - A guard only guards if the regression actually fails it. For a plugin without `inject` (bundle/composition plugins), a Loader smoke stays green under a broken export shape — add an explicit `expect('default' in mod).toBe(false)` plus an `unwrapExports` round-trip assertion, and prove it: introduce the regression, watch red, revert. -- "Real entry path" means the published artifact: a package `bin` runs built `lib/bin.js` under plain `node`, exposing failures tsx masks (settle races, module resolution, swallowed load failures). The same applies to non-index runtime entries (the worker-thread sibling `lib/worker.cjs`) and singleton modules shared across bundles (`packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. +- "Real entry path" means the published artifact: the package `bin` points at built `lib/bin.js` under plain `node`, which tsx masks (settle races, module resolution, a swallowed load failure exiting 0). The same applies to any non-index runtime entry the built package resolves at run time (the worker-thread runtime's sibling `lib/worker.cjs`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. - An e2e that spawns an example from a temp cwd sets `TSX_TSCONFIG_PATH` to the repo-root tsconfig, or it silently falls back to stale built `lib/` ([examples/AGENTS.md](../examples/AGENTS.md)). ## When a snapshot test is required diff --git a/packages/ui/jsonrpc/package.json b/packages/ui/jsonrpc/package.json index bf4fe39118..be19ab7217 100644 --- a/packages/ui/jsonrpc/package.json +++ b/packages/ui/jsonrpc/package.json @@ -28,7 +28,6 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-llm-deepseek": "^0.0.1", - "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -39,7 +38,6 @@ "@deepseek-ai/dsh-agent-core": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", - "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts deleted file mode 100644 index 159600e49c..0000000000 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ /dev/null @@ -1,121 +0,0 @@ -/** - * Built-artifact guard for the scope carrier shared by `dsh-subagent` and - * `dsh-jsonrpc`. The carrier registry is module-local, so both bundles must - * externalize `dsh-scope`; source-mode tests cannot expose an accidentally - * inlined second registry. This test runs the real `lib/index.js` bundles in a - * plain Node subprocess, disposes the child before settlement, and requires the - * SDK completion notification to retain the delegating parent. - */ - -import { execFile } from 'node:child_process' -import { existsSync } from 'node:fs' -import { fileURLToPath } from 'node:url' -import { promisify } from 'node:util' -import { describe, expect, it } from 'vitest' - -const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url)) -const jsonrpcBundle = fileURLToPath(new URL('../lib/index.js', import.meta.url)) -const execFileAsync = promisify(execFile) - -const builtRuntimeProbe = String.raw` -import { mkdtemp, rm } from "node:fs/promises"; -import { tmpdir } from "node:os"; -import { join, resolve } from "node:path"; -import { pathToFileURL } from "node:url"; - -const load = (path) => import(pathToFileURL(resolve(path)).href); -const [ - { Context }, - agentCore, - { default: SubagentService }, - { default: SessionPersistenceJsonl }, - { HarnessSdkServer }, - { SessionId }, -] = await Promise.all([ - load("vendor/cordis/lib/index.js"), - load("packages/core/agent-core/lib/index.js"), - load("packages/subagent/subagent/lib/index.js"), - load("packages/session-persistence/session-persistence-jsonl/lib/index.js"), - load("packages/ui/jsonrpc/lib/index.js"), - load("packages/core/session/lib/index.js"), -]); - -const storageRoot = await mkdtemp(join(tmpdir(), "jsonrpc-built-scope-")); -const ctx = new Context(); -try { - await ctx.plugin(agentCore); - await ctx.plugin(SubagentService); - await ctx.plugin(SessionPersistenceJsonl, { root: storageRoot }); - await new Promise((ready) => setTimeout(ready, 50)); - - const notifications = []; - const server = new HarnessSdkServer(ctx, { - request() { return Promise.reject(new Error("unexpected host request")); }, - notify(method, params) { notifications.push({ method, params }); }, - }); - const parent = await ctx.agents.create({ - sessionId: SessionId("built-parent"), - meta: { cwd: storageRoot }, - agentOptions: { model: "test" }, - }); - const child = await ctx.agents.create({ - sessionId: SessionId("built-child"), - meta: { cwd: storageRoot, parentSession: SessionId("built-parent") }, - agentOptions: { model: "test" }, - }); - const result = Promise.withResolvers(); - const unregister = ctx.subagents.registerProvider({ - name: "built-local", - capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, - inheritsParentContext: false, - start() { - return Promise.resolve({ - id: child.agent.id, - result: result.promise, - dispose() { return Promise.resolve(); }, - }); - }, - }); - const run = await ctx.subagents.start("built-local", { - parent: parent.agent, - prompt: [], - signal: new AbortController().signal, - }); - await child.dispose(); - result.resolve({ output: [], stopReason: "completed" }); - await run.result; - await Promise.resolve(); - - console.log(JSON.stringify(notifications.filter(({ method }) => method === "subagent.finished"))); - await run.dispose(); - unregister(); - await parent.dispose(); - await server.shutdown(); -} finally { - await ctx.fiber.dispose(); - await rm(storageRoot, { recursive: true, force: true }); -} -` - -describe.skipIf(!existsSync(jsonrpcBundle))('dsh-jsonrpc BUILT scope carrier', () => { - it('preserves parent-scoped completion after child disposal', async () => { - const { stdout, stderr } = await execFileAsync(process.execPath, ['--input-type=module', '-e', builtRuntimeProbe], { - cwd: repoRoot, - timeout: 15_000, - }) - - expect(stderr).not.toContain('listener threw') - expect(JSON.parse(stdout) as unknown).toEqual([{ - method: 'subagent.finished', - params: { - provider: 'built-local', - agentId: 'built-child', - parentSessionId: 'built-parent', - childSessionId: 'built-child', - status: 'ok', - stopReason: 'completed', - lastAssistantMessage: [], - }, - }]) - }) -}) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index dec8c3024f..6214564eae 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1288,9 +1288,6 @@ importers: '@deepseek-ai/dsh-llm-deepseek': specifier: workspace:^ version: link:../../llm/llm-deepseek - '@deepseek-ai/dsh-scope': - specifier: workspace:^ - version: link:../../core/scope '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index e1c41149ca..131501abb0 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -332,7 +332,6 @@ function builtBinSmokeGate(): Gate { 'vitest.e2e.config.ts', 'packages/ui/stdio-agent/tests/built-bin.e2e.ts', 'packages/ui/acp-agent/tests/built-bin.e2e.ts', - 'packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts', // The worker-entry packages' built bundles: the only automated proof // that lib/index.js resolves its sibling lib/worker.cjs under plain node // (the e2e lane runs unbuilt, so these files self-skip there). From c6cb9f4210d9303c197ac985fca7a4dc3b11cb88 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:55:38 +0800 Subject: [PATCH 065/359] fix: share scope carrier across built JSON-RPC --- AGENTS.md | 2 +- docs/testing.md | 2 +- packages/ui/jsonrpc/package.json | 2 + .../jsonrpc/tests/built-scope-carrier.e2e.ts | 121 ++++++++++++++++++ pnpm-lock.yaml | 3 + scripts/run-gates.ts | 1 + 6 files changed, 129 insertions(+), 2 deletions(-) create mode 100644 packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts diff --git a/AGENTS.md b/AGENTS.md index 4dfbedb97b..1494d3fcf8 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -76,7 +76,7 @@ printf '%s\n' "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})' printf '%s\n' "$out" | grep -q '\[tool result\] ECHO: CI SMOKE' test -n "$(find .sessions -path '.sessions/cwd-*/main-session-*.jsonl' -type f -print -quit)" rm -rf .sessions -pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts +pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts ``` `test:coverage`, not `test`, is the gating run ([why](docs/testing.md)); a sign-off counts only for commands actually run. diff --git a/docs/testing.md b/docs/testing.md index 23cca651fe..a1a841296a 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -25,7 +25,7 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword - A plugin shipped via `cordis.yml` needs at least one test through the REAL Loader path: hand-built `ctx.plugin({...})` mounts bypass `unwrapExports` and cannot catch a broken export shape ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md); export-shape rules in [packages/AGENTS.md](../packages/AGENTS.md)). - A guard only guards if the regression actually fails it. For a plugin without `inject` (bundle/composition plugins), a Loader smoke stays green under a broken export shape — add an explicit `expect('default' in mod).toBe(false)` plus an `unwrapExports` round-trip assertion, and prove it: introduce the regression, watch red, revert. -- "Real entry path" means the published artifact: the package `bin` points at built `lib/bin.js` under plain `node`, which tsx masks (settle races, module resolution, a swallowed load failure exiting 0). The same applies to any non-index runtime entry the built package resolves at run time (the worker-thread runtime's sibling `lib/worker.cjs`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. +- "Real entry path" means the published artifact: a package `bin` runs built `lib/bin.js` under plain `node`, exposing failures tsx masks (settle races, module resolution, swallowed load failures). The same applies to non-index runtime entries (the worker-thread sibling `lib/worker.cjs`) and singleton modules shared across bundles (`packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. - An e2e that spawns an example from a temp cwd sets `TSX_TSCONFIG_PATH` to the repo-root tsconfig, or it silently falls back to stale built `lib/` ([examples/AGENTS.md](../examples/AGENTS.md)). ## When a snapshot test is required diff --git a/packages/ui/jsonrpc/package.json b/packages/ui/jsonrpc/package.json index be19ab7217..bf4fe39118 100644 --- a/packages/ui/jsonrpc/package.json +++ b/packages/ui/jsonrpc/package.json @@ -28,6 +28,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-llm-deepseek": "^0.0.1", + "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -38,6 +39,7 @@ "@deepseek-ai/dsh-agent-core": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", + "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts new file mode 100644 index 0000000000..159600e49c --- /dev/null +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -0,0 +1,121 @@ +/** + * Built-artifact guard for the scope carrier shared by `dsh-subagent` and + * `dsh-jsonrpc`. The carrier registry is module-local, so both bundles must + * externalize `dsh-scope`; source-mode tests cannot expose an accidentally + * inlined second registry. This test runs the real `lib/index.js` bundles in a + * plain Node subprocess, disposes the child before settlement, and requires the + * SDK completion notification to retain the delegating parent. + */ + +import { execFile } from 'node:child_process' +import { existsSync } from 'node:fs' +import { fileURLToPath } from 'node:url' +import { promisify } from 'node:util' +import { describe, expect, it } from 'vitest' + +const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url)) +const jsonrpcBundle = fileURLToPath(new URL('../lib/index.js', import.meta.url)) +const execFileAsync = promisify(execFile) + +const builtRuntimeProbe = String.raw` +import { mkdtemp, rm } from "node:fs/promises"; +import { tmpdir } from "node:os"; +import { join, resolve } from "node:path"; +import { pathToFileURL } from "node:url"; + +const load = (path) => import(pathToFileURL(resolve(path)).href); +const [ + { Context }, + agentCore, + { default: SubagentService }, + { default: SessionPersistenceJsonl }, + { HarnessSdkServer }, + { SessionId }, +] = await Promise.all([ + load("vendor/cordis/lib/index.js"), + load("packages/core/agent-core/lib/index.js"), + load("packages/subagent/subagent/lib/index.js"), + load("packages/session-persistence/session-persistence-jsonl/lib/index.js"), + load("packages/ui/jsonrpc/lib/index.js"), + load("packages/core/session/lib/index.js"), +]); + +const storageRoot = await mkdtemp(join(tmpdir(), "jsonrpc-built-scope-")); +const ctx = new Context(); +try { + await ctx.plugin(agentCore); + await ctx.plugin(SubagentService); + await ctx.plugin(SessionPersistenceJsonl, { root: storageRoot }); + await new Promise((ready) => setTimeout(ready, 50)); + + const notifications = []; + const server = new HarnessSdkServer(ctx, { + request() { return Promise.reject(new Error("unexpected host request")); }, + notify(method, params) { notifications.push({ method, params }); }, + }); + const parent = await ctx.agents.create({ + sessionId: SessionId("built-parent"), + meta: { cwd: storageRoot }, + agentOptions: { model: "test" }, + }); + const child = await ctx.agents.create({ + sessionId: SessionId("built-child"), + meta: { cwd: storageRoot, parentSession: SessionId("built-parent") }, + agentOptions: { model: "test" }, + }); + const result = Promise.withResolvers(); + const unregister = ctx.subagents.registerProvider({ + name: "built-local", + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start() { + return Promise.resolve({ + id: child.agent.id, + result: result.promise, + dispose() { return Promise.resolve(); }, + }); + }, + }); + const run = await ctx.subagents.start("built-local", { + parent: parent.agent, + prompt: [], + signal: new AbortController().signal, + }); + await child.dispose(); + result.resolve({ output: [], stopReason: "completed" }); + await run.result; + await Promise.resolve(); + + console.log(JSON.stringify(notifications.filter(({ method }) => method === "subagent.finished"))); + await run.dispose(); + unregister(); + await parent.dispose(); + await server.shutdown(); +} finally { + await ctx.fiber.dispose(); + await rm(storageRoot, { recursive: true, force: true }); +} +` + +describe.skipIf(!existsSync(jsonrpcBundle))('dsh-jsonrpc BUILT scope carrier', () => { + it('preserves parent-scoped completion after child disposal', async () => { + const { stdout, stderr } = await execFileAsync(process.execPath, ['--input-type=module', '-e', builtRuntimeProbe], { + cwd: repoRoot, + timeout: 15_000, + }) + + expect(stderr).not.toContain('listener threw') + expect(JSON.parse(stdout) as unknown).toEqual([{ + method: 'subagent.finished', + params: { + provider: 'built-local', + agentId: 'built-child', + parentSessionId: 'built-parent', + childSessionId: 'built-child', + status: 'ok', + stopReason: 'completed', + lastAssistantMessage: [], + }, + }]) + }) +}) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 6214564eae..dec8c3024f 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1288,6 +1288,9 @@ importers: '@deepseek-ai/dsh-llm-deepseek': specifier: workspace:^ version: link:../../llm/llm-deepseek + '@deepseek-ai/dsh-scope': + specifier: workspace:^ + version: link:../../core/scope '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index 131501abb0..e1c41149ca 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -332,6 +332,7 @@ function builtBinSmokeGate(): Gate { 'vitest.e2e.config.ts', 'packages/ui/stdio-agent/tests/built-bin.e2e.ts', 'packages/ui/acp-agent/tests/built-bin.e2e.ts', + 'packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts', // The worker-entry packages' built bundles: the only automated proof // that lib/index.js resolves its sibling lib/worker.cjs under plain node // (the e2e lane runs unbuilt, so these files self-skip there). From 151d6387e03b9f41b553e7f079588f76d7317516 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:57:46 +0800 Subject: [PATCH 066/359] docs: refresh module dependency graph --- docs/module-graph.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index 8ac71b11cc..864f39359f 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -293,6 +293,7 @@ flowchart TD pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm pkg_jsonrpc --> pkg_llm_deepseek + pkg_jsonrpc --> pkg_scope pkg_jsonrpc --> pkg_session pkg_jsonrpc --> pkg_subagent pkg_workflow_workerthread --> pkg_agent @@ -389,7 +390,7 @@ flowchart TD | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | -| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | +| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | From 82c0d1fb7cc291196bc3fd5733dfec867d84dac7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:59:33 +0800 Subject: [PATCH 067/359] test: register JSON-RPC artifact smoke --- knip.json | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/knip.json b/knip.json index 825980f205..fe2366e3fa 100644 --- a/knip.json +++ b/knip.json @@ -77,13 +77,17 @@ "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] }, - "packages/ui/stdio-agent": { + "packages/ui/jsonrpc": { "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] }, "packages/ui/jsonrpc-agent": { "project": ["src/**/*.ts"] }, + "packages/ui/stdio-agent": { + "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], + "project": ["src/**/*.ts", "tests/**/*.ts"] + }, "packages/subagent/subagent-spawn": { "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] From e784e4dce5f5178b5e22a3d3376599144d8bea1b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:12:32 +0800 Subject: [PATCH 068/359] fix: await ACP client callbacks during shutdown --- packages/support/acp-snapshot/src/launcher.ts | 59 ++++++++++++------- .../acp-snapshot/tests/harness.spec.ts | 36 +++++++++++ 2 files changed, 75 insertions(+), 20 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 815753ae5f..30702a5888 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -65,7 +65,7 @@ export interface LaunchedAcpTestAgent { stderr(): string /** Resolve when a future session update matches the predicate. */ waitForUpdate(match: (update: SessionNotification['update']) => boolean): Promise - /** Gracefully close stdin, or send a signal, then wait for process exit, inherited stdio closure, and ACP parser drain. */ + /** Gracefully close stdin, or send a signal, then wait for process exit, inherited stdio closure, ACP parsing, and client callbacks. */ close(signal?: NodeJS.Signals): Promise } @@ -137,29 +137,41 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe Writable.toWeb(child.stdin) as WritableStream, Readable.toWeb(passthrough) as ReadableStream, ) + const inFlightClientCallbacks = new Set>() + const trackClientCallback = (callback: () => T | PromiseLike): Promise => { + const pending = Promise.resolve().then(callback) + inFlightClientCallbacks.add(pending) + void pending.then( + () => { inFlightClientCallbacks.delete(pending) }, + () => { inFlightClientCallbacks.delete(pending) }, + ) + return pending + } + const requestPermission = options.requestPermission + ?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' as const } })) const makeClient = (_agent: AcpAgent): Client => ({ sessionUpdate(params: SessionNotification): Promise { - updates.push(params.update) - for (let index = updateWaiters.length - 1; index >= 0; index--) { - const waiter = updateWaiters[index] - /* v8 ignore next 1 -- index is bounded by the array length */ - if (waiter === undefined) continue - let matches: boolean - try { - matches = waiter.match(params.update) - } catch (error: unknown) { + return trackClientCallback(() => { + updates.push(params.update) + for (let index = updateWaiters.length - 1; index >= 0; index--) { + const waiter = updateWaiters[index] + /* v8 ignore next 1 -- index is bounded by the array length */ + if (waiter === undefined) continue + let matches: boolean + try { + matches = waiter.match(params.update) + } catch (error: unknown) { + updateWaiters.splice(index, 1) + waiter.reject(error) + continue + } + if (!matches) continue updateWaiters.splice(index, 1) - waiter.reject(error) - continue + waiter.resolve(params.update) } - if (!matches) continue - updateWaiters.splice(index, 1) - waiter.resolve(params.update) - } - return Promise.resolve() + }) }, - requestPermission: options.requestPermission - ?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' } })), + requestPermission: params => trackClientCallback(() => requestPermission(params)), }) const client = new ClientSideConnection(makeClient, stream) // `exit` only reports the parent process's status. Descendants may retain @@ -168,7 +180,14 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // `closed` follows parser exhaustion. Capture both eagerly so a caller that // invokes close after process exit still joins the complete drain boundary. const stdioClosed = new Promise(resolve => child.once('close', () => { resolve() })) - const drained = Promise.all([stdioClosed, client.closed]).then(() => undefined) + const drained = Promise.all([stdioClosed, client.closed]).then(async () => { + // The ACP SDK's readable loop dispatches client callbacks without awaiting + // them. Once `closed` settles no new callbacks can start, but callbacks + // already in flight still belong to this launch's teardown boundary. + while (inFlightClientCallbacks.size > 0) { + await Promise.allSettled([...inFlightClientCallbacks]) + } + }) // A caller may await a pending update without calling close(). Make natural // stream exhaustion terminal for those waiters too, but only after the // parser has dispatched every buffered frame. diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 051db6a0ba..902f48d2cf 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -1,4 +1,5 @@ import { mkdtemp, rm, writeFile } from 'node:fs/promises' +import { once } from 'node:events' import { tmpdir } from 'node:os' import { delimiter, join } from 'node:path' import { fileURLToPath } from 'node:url' @@ -112,6 +113,41 @@ describe('runScenario', () => { expect(launched.stderr()).toContain('late inherited stderr') }) + it('waits for in-flight client callbacks after the ACP stream closes', { timeout: 20_000 }, async () => { + const { dir, fixtureFile } = await scenario({ permissionProbe: true }) + let releasePermission: (() => void) | undefined + const permissionReleased = new Promise((resolve) => { releasePermission = resolve }) + let markPermissionStarted: (() => void) | undefined + const permissionStarted = new Promise((resolve) => { markPermissionStarted = resolve }) + let permissionFinished = false + const launched = launchAcpTestAgent({ + agent: AGENT, + cwd: dir, + env: { DSH_SNAPSHOT_FILE: fixtureFile }, + async requestPermission() { + markPermissionStarted?.() + await permissionReleased + permissionFinished = true + return { outcome: { outcome: 'cancelled' } } + }, + }) + await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const { sessionId } = await launched.client.newSession({ cwd: dir, mcpServers: [] }) + void launched.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => undefined) + await permissionStarted + + const childClosed = once(launched.child, 'close') + let closeSettled = false + const closing = launched.close('SIGKILL').then(() => { closeSettled = true }) + await childClosed + await launched.client.closed + expect(closeSettled).toBe(false) + + releasePermission?.() + await closing + expect(permissionFinished).toBe(true) + }) + it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ permissionProbe: true, From d4c96deac3802164c430335309f936f3e5ab4f1d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:19:02 +0800 Subject: [PATCH 069/359] refactor: share ACP callback cleanup --- packages/support/acp-snapshot/src/launcher.ts | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 30702a5888..f1271986c0 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -141,10 +141,8 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe const trackClientCallback = (callback: () => T | PromiseLike): Promise => { const pending = Promise.resolve().then(callback) inFlightClientCallbacks.add(pending) - void pending.then( - () => { inFlightClientCallbacks.delete(pending) }, - () => { inFlightClientCallbacks.delete(pending) }, - ) + const untrack = (): void => { inFlightClientCallbacks.delete(pending) } + void pending.then(untrack, untrack) return pending } const requestPermission = options.requestPermission From 2dea4afac0d49976700139a766d40734e3204f4e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:23:02 +0800 Subject: [PATCH 070/359] fix: bind stdio to its configured agent --- packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/src/index.ts | 5 ++- packages/ui/stdio-agent/src/stdio-chat.ts | 30 +++++++++++----- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 35 ++++++++++++++----- 4 files changed, 53 insertions(+), 19 deletions(-) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 82da64cd81..d7d30ee49d 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id. Resumed sessions register under the exact `resumeSessionId` and keep the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id; the UI binds to that fresh-id namespace, or to the exact `resumeSessionId` for a resumed run, and never selects unrelated registry roots. Resumed sessions keep the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index f01c48a615..2eca0cceb3 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -124,5 +124,8 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) ctx.plugin(UserInteractionService) ctx.plugin(toolAskUser) - ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.' }) + ctx.plugin(uiStdio, { + welcome: config.welcome ?? 'ready.', + ...config.resumeSessionId !== undefined ? { resumeSessionId: config.resumeSessionId } : {}, + }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index a295274786..76347c91e4 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -36,10 +36,13 @@ export const inject = ['agents', 'userInteraction'] export interface Config { /** Banner printed once on start, before the first `> ` prompt. */ welcome?: string + /** Exact persisted session id the app configured for resume; absent selects the app's fresh `main-session-*` identity. */ + resumeSessionId?: string } export const Config: z = z.object({ welcome: z.string().default('ready.'), + resumeSessionId: z.string(), }) /** @@ -95,16 +98,25 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns one configured top-level agent. Hold the live object - // directly: its per-run id is intentionally fresh, while `main` remains only - // the terminal's fixed display label. Runtime creator ownership distinguishes - // that root from its subagents even if a child is registered after an HMR - // replacement. Persisted parentSession lineage is deliberately irrelevant: - // a resumed child session can itself be this process's configured root. - let target: Agent | undefined = ctx.agents.roots()[0] - ctx.on('agent/created', () => { target ??= ctx.agents.roots()[0] }) + // Bind only to this app's configured top-level agent. Fresh runs own the + // `main-session-*` namespace; resumed runs own the exact persisted id. The + // registry's runtime-root relation excludes subagents without confusing it + // with durable parentSession lineage. Keeping the matching candidates also + // covers HMR's publish-new-before-dispose-old ordering without ever falling + // through to an unrelated root owned by another app or test fixture. + const matchesConfiguredIdentity = (agent: Agent): boolean => config.resumeSessionId === undefined + ? agent.id.startsWith('main-session-') + : agent.id === config.resumeSessionId + const configuredRoots = new Set(ctx.agents.roots().filter(matchesConfiguredIdentity)) + let target: Agent | undefined = [...configuredRoots].at(-1) + ctx.on('agent/created', (agent) => { + if (!matchesConfiguredIdentity(agent) || !ctx.agents.roots().includes(agent)) return + configuredRoots.add(agent) + target ??= agent + }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = ctx.agents.roots().at(-1) + configuredRoots.delete(agent) + if (target === agent) target = [...configuredRoots].at(-1) }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2600fdb24f..668068a72d 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -74,7 +74,7 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { return { type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 0, chunk } } } -const CONFIG: Config = { welcome: 'hi there' } +const CONFIG: Config = { welcome: 'hi there', resumeSessionId: 'main' } async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() @@ -199,7 +199,9 @@ describe('createStdioChat rendering', () => { }) it('accepts a lineage-bearing configured agent created after the UI installs', async () => { - const { ctx, input } = await setup() + const { ctx, input } = await setup({ welcome: 'hi there', resumeSessionId: 'resumed' }) + const unrelated = makeAgent('unrelated') + ctx.agents.register(unrelated) const resumed = makeAgent('resumed') ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' ctx.agents.register(resumed) @@ -207,6 +209,7 @@ describe('createStdioChat rendering', () => { input.feed('continue') await new Promise(resolve => setImmediate(resolve)) + expect(unrelated.sent).toEqual([]) expect(resumed.sent).toEqual([[{ type: 'text', text: 'continue' }]]) }) @@ -235,7 +238,7 @@ describe('createStdioChat rendering', () => { it('keeps the target when a different agent is disposed', async () => { const { ctx, out } = await setup() - const target = makeAgent('target') + const target = makeAgent('main') ctx.agents.register(target) ctx.emit('agent/disposed', makeAgent('other')) ctx.emit('session/event', target.session, { @@ -245,11 +248,11 @@ describe('createStdioChat rendering', () => { }) it('retargets a surviving root when HMR publishes it before disposing the old root', async () => { - const { ctx, input } = await setup() - const oldRoot = makeAgent('old-root') + const { ctx, input } = await setup({ welcome: 'hi there' }) + const oldRoot = makeAgent('main-session-old') const child = makeAgent('child') ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id - const replacement = makeAgent('replacement') + const replacement = makeAgent('main-session-replacement') const lateChild = makeAgent('late-child') const disposeOld = ctx.agents.register(oldRoot) const disposeChild = ctx.agents.enter(child, oldRoot) @@ -273,6 +276,22 @@ describe('createStdioChat rendering', () => { disposeChild() }) + it('does not retarget stdin to an unrelated root after the configured agent is disposed', async () => { + const { ctx, input } = await setup() + const unrelated = makeAgent('unrelated') + ctx.agents.register(unrelated) + const configured = makeAgent('main') + const disposeConfigured = ctx.agents.register(configured) + const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) + + disposeConfigured() + input.feed('must not leak') + await new Promise(resolve => setImmediate(resolve)) + + expect(unrelated.sent).toEqual([]) + expect(error).toHaveBeenCalledWith('ui-stdio: main agent is not running') + }) + it('renders tool/call and tool/result session events', async () => { const { ctx, out } = await setup() const session = {} as Session @@ -720,8 +739,8 @@ describe('createStdioChat input', () => { expect(spy).toHaveBeenCalledWith('ui-stdio: main agent is not running') }) - it('drives the app-owned agent without a duplicate id config', async () => { - const { ctx, input } = await setup({ welcome: 'w' }) + it('drives the exact app-configured resumed session', async () => { + const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: 'worker' }) const agent = makeAgent('worker') ctx.agents.register(agent) input.feed('hi') From 1bb9995128f75474eeec9933e2bab6fc69a8b60e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:28:41 +0800 Subject: [PATCH 071/359] docs: state subagent carrier invariant --- packages/ui/jsonrpc/src/server.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 352563f7f2..fe605a8536 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -62,6 +62,7 @@ interface SessionRecord { /** Recover the delegating parent carried by every service-owned subagent lifecycle event. */ function subagentParentOf(carrier: Scoped): Agent { + // SubagentService emits this lifecycle pair only through scopeTarget(this, parent). return carrierKeyOf(carrier) as Agent } From ba8a5c89ed4390b4b1679b736f2c44d79bdbaab9 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:29:02 +0800 Subject: [PATCH 072/359] docs: name the public agent injection seam --- packages/bash/tool-bash/src/index.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index fe07b80989..cda683c5b4 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -457,7 +457,7 @@ export function apply(ctx: Context): void { ) } catch (error: unknown) { // The ONE expected failure: the agent was disposed between task - // completion and this injection (ReactLoopAgent.inject throws + // completion and this injection (Agent.inject throws // `agent "" is disposed`). That race is benign — drop the notice. // Anything else is a real bug and must surface, not be swallowed. if (error instanceof Error && error.message.includes('is disposed')) return From ccd810f84d74ce452d858b553eb0cbdb282d715c Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:36:22 +0800 Subject: [PATCH 073/359] fix: normalize empty stdio resume identity --- packages/ui/stdio-agent/src/stdio-chat.ts | 5 +++-- packages/ui/stdio-agent/tests/stdio-chat.spec.ts | 9 +++++++++ 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 76347c91e4..17a11168db 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -104,9 +104,10 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt // with durable parentSession lineage. Keeping the matching candidates also // covers HMR's publish-new-before-dispose-old ordering without ever falling // through to an unrelated root owned by another app or test fixture. - const matchesConfiguredIdentity = (agent: Agent): boolean => config.resumeSessionId === undefined + const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId + const matchesConfiguredIdentity = (agent: Agent): boolean => resumeSessionId === undefined ? agent.id.startsWith('main-session-') - : agent.id === config.resumeSessionId + : agent.id === resumeSessionId const configuredRoots = new Set(ctx.agents.roots().filter(matchesConfiguredIdentity)) let target: Agent | undefined = [...configuredRoots].at(-1) ctx.on('agent/created', (agent) => { diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 668068a72d..2ebc51e14e 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -747,6 +747,15 @@ describe('createStdioChat input', () => { await new Promise(r => setImmediate(r)) expect(agent.sent).toHaveLength(1) }) + + it('treats an empty resume session id as a fresh configured identity', async () => { + const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: '' }) + const agent = makeAgent('main-session-fresh') + ctx.agents.register(agent) + input.feed('hi') + await new Promise(r => setImmediate(r)) + expect(agent.sent).toHaveLength(1) + }) }) describe('createStdioChat EOF exit', () => { From 6b59b6050e379de30bb8f53bbc38172f8ffe896a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:43:12 +0800 Subject: [PATCH 074/359] fix: preserve ACP scenario cleanup failures --- packages/support/acp-snapshot/src/harness.ts | 20 +++++++--- .../acp-snapshot/tests/harness.spec.ts | 38 ++++++++++++++++++- 2 files changed, 51 insertions(+), 7 deletions(-) diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index 3db1355b0f..22b22deacd 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -244,9 +244,9 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise ) // Failure-safe teardown: wait for a still-running child, then attempt BOTH - // directory removals even when an earlier cleanup rejects. The main outcome - // wins over teardown noise so a step/harvest failure is never replaced; on a - // successful run, the first cleanup failure remains visible to the caller. + // directory removals even when an earlier cleanup rejects. Report every + // teardown failure alongside a scenario failure so neither orthogonal + // outcome hides the other. const cleanupResults: PromiseSettledResult[] = [] const cleanup = async (action: () => Promise): Promise => { cleanupResults.push(...await Promise.allSettled([action()])) @@ -256,10 +256,18 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise await cleanup(() => rm(cwd, { recursive: true, force: true })) await cleanup(() => rm(sessionsRoot, { recursive: true, force: true })) + const cleanupFailures = cleanupResults + .filter((result): result is PromiseRejectedResult => result.status === 'rejected') + .map(result => result.reason as unknown) + if (cleanupFailures.length > 0) { + throw new AggregateError( + outcome.status === 'rejected' ? [outcome.error, ...cleanupFailures] : cleanupFailures, + outcome.status === 'rejected' + ? 'snapshot scenario and cleanup failed' + : 'snapshot cleanup failed', + ) + } if (outcome.status === 'rejected') throw outcome.error - const cleanupFailure = cleanupResults.find((result): result is PromiseRejectedResult => result.status === 'rejected') - /* v8 ignore next 1 -- defensive OS cleanup failure after an otherwise successful real subprocess run */ - if (cleanupFailure !== undefined) throw cleanupFailure.reason return outcome.value } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 902f48d2cf..de764cfd8a 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -3,11 +3,29 @@ import { once } from 'node:events' import { tmpdir } from 'node:os' import { delimiter, join } from 'node:path' import { fileURLToPath } from 'node:url' -import { afterAll, describe, expect, it } from 'vitest' +import { afterAll, describe, expect, it, vi } from 'vitest' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { runScenario, type AgentUnderTest, type InputStep } from '../src/harness.ts' import { launchAcpTestAgent } from '../src/launcher.ts' +const fsControl = vi.hoisted(() => ({ cleanupFailure: undefined as Error | undefined })) + +vi.mock('node:fs/promises', async (importOriginal) => { + const actual = await importOriginal() + return { + ...actual, + async rm(...args: Parameters): Promise { + if (String(args[0]).includes('acp-snap-cwd-') && fsControl.cleanupFailure !== undefined) { + const failure = fsControl.cleanupFailure + fsControl.cleanupFailure = undefined + await actual.rm(...args) + throw failure + } + await actual.rm(...args) + }, + } +}) + /** * Unit tests for the subprocess harness, driven through the REAL spawn path * (tsx loader, temp cwd, env plumbing) against the scripted fake ACP bin in @@ -238,6 +256,24 @@ describe('runScenario', () => { )).rejects.toThrow(/expected the prompt to fail/) }) + it('reports scenario and cleanup failures together', { timeout: 20_000 }, async () => { + const { fixtureFile } = await scenario({ prompt: 'respond' }) + const cleanupFailure = new Error('cleanup failed') + fsControl.cleanupFailure = cleanupFailure + + const failure = await runScenario( + { steps: [...boot, { op: 'promptExpectError', text: 'fine' }] }, + { agent: AGENT, mode: 'replay', fixtureFile }, + ).catch((error: unknown): unknown => error) + + expect(failure).toBeInstanceOf(AggregateError) + const failures = (failure as AggregateError).errors as unknown[] + expect(failures).toHaveLength(2) + expect(failures[0]).toBeInstanceOf(Error) + expect((failures[0] as Error).message).toMatch(/expected the prompt to fail/) + expect(failures[1]).toBe(cleanupFailure) + }) + it('newSessionExpectError swallows the rejection, with and without extra dirs', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ rejectExtraDirs: true }) const result = await runScenario( From 2333ab19e3b03bc84cf050b16e897b830b2dfdf2 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:46:05 +0800 Subject: [PATCH 075/359] fix: verify JSON-RPC child ownership --- docs/cordis-catalog/services.md | 1 + packages/core/agent/README.md | 1 + packages/core/agent/src/index.ts | 12 ++++++ packages/core/agent/tests/agent.spec.ts | 4 ++ packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 11 +++-- packages/ui/jsonrpc/tests/server.spec.ts | 51 ++++++++++++++++++++---- 7 files changed, 68 insertions(+), 14 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 1366fcf6f6..6a40f88a23 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -33,6 +33,7 @@ register(agent: Agent): () => void enter(agent: Agent, owner: Agent | undefined): () => void announce(agent: Agent): void get(id: SessionId): Agent | undefined +isOwnedBy(id: SessionId, owner: Agent): boolean list(): Agent[] roots(): Agent[] ``` diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index a45603f191..941f46baf0 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -13,6 +13,7 @@ The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh- - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. - Advanced ordered lifecycle: `enter(agent, owner): () => void` enforces `agent.id === agent.session.id`, performs the authoritative ID collision check, and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. - `ctx.agents.get(id: SessionId): Agent | undefined` +- `ctx.agents.isOwnedBy(id: SessionId, owner: Agent): boolean` — whether the exact live entry was created through that parent agent's scoped context; runtime ownership is independent of durable session lineage. - `ctx.agents.list(): Agent[]` - `ctx.agents.roots(): Agent[]` — live agents created without an owning agent context; a resumed lineage-bearing session can still be a runtime root. diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index abafa38e45..8a9ed68ab6 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -440,6 +440,18 @@ export class AgentRegistry extends Service { return this.store.get(id)?.agent } + /** + * Test whether a live agent was created through one exact parent agent's + * scoped context. Runtime ownership is independent of durable session + * lineage and remains unambiguous when unrelated providers reuse an id. + * @param id - the candidate child agent's shared agent/session id. + * @param owner - the expected runtime creator agent. + * @returns true only while the exact child entry is live under that owner. + */ + isOwnedBy(id: SessionId, owner: Agent): boolean { + return this.store.get(id)?.owner === owner + } + /** * All live agents, in registration order. * @returns a fresh array; mutating it does not affect the registry. diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index d2866cacb3..5d79d1a91f 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -72,8 +72,12 @@ describe('AgentRegistry', () => { expect(ctx.agents.list()).toEqual([root, child]) expect(ctx.agents.roots()).toEqual([root]) + expect(ctx.agents.isOwnedBy(child.id, root)).toBe(true) + expect(ctx.agents.isOwnedBy(root.id, root)).toBe(false) + expect(ctx.agents.isOwnedBy(SessionId('missing'), root)).toBe(false) detachChild() + expect(ctx.agents.isOwnedBy(child.id, root)).toBe(false) detachRoot() }) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index ffbd7a1288..df612ac263 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server counts local starts by provider/id and the exact delegating-parent carrier, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server verifies that the live child is owned by the exact delegating parent, then counts local starts by provider/id and that parent carrier because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported even when their parent-scoped run id collides with an unrelated local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index fe605a8536..d78f24b5ab 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -109,8 +109,8 @@ export class HarnessSdkServer { // child disposal and reused ids need no settlement-order assumption. const localRuns = this.localRuns this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { - if (ctx.agents.get(info.id) === undefined) return const parent = subagentParentOf(this) + if (!ctx.agents.isOwnedBy(info.id, parent)) return const providerRuns = localRuns.get(info.provider) ?? new Map>() const parentRuns = providerRuns.get(info.id) ?? new Map() parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) @@ -118,7 +118,6 @@ export class HarnessSdkServer { localRuns.set(info.provider, providerRuns) })) this.disposers.push(ctx.on('subagent/end', function (this: Scoped, info: SubagentRunEndInfo) { - const agent = ctx.agents.get(info.id) const parent = subagentParentOf(this) const providerRuns = localRuns.get(info.provider) const parentRuns = providerRuns?.get(info.id) @@ -130,10 +129,10 @@ export class HarnessSdkServer { if (providerRuns?.size === 0) localRuns.delete(info.provider) } // This protocol reports LOCAL child sessions. A lineage-bearing child - // has the session/created-driven start notification above; a parentless - // local provider still gets its terminal notification. A remote provider - // has neither a pending local start nor a live local agent and is ignored. - if (pendingCount === undefined && agent === undefined) return + // has the session/created-driven start notification above. A remote run + // has neither a cached owned start nor a live child owned by this exact + // parent; an unrelated local agent with the same id never makes it local. + if (pendingCount === undefined && !ctx.agents.isOwnedBy(info.id, parent)) return transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 427a190c36..c97bd1a6e1 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -277,12 +277,12 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const handle = await ctx.agents.create({ + const handle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) - const parentlessHandle = await ctx.agents.create({ + const parentlessHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('parentless-child-session'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, @@ -331,6 +331,43 @@ describe('HarnessSdkServer', () => { } }) + it('ignores a remote run id that collides with an unrelated local agent', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-remote-collision-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const parentHandle = await ctx.agents.create({ + sessionId: SessionId('collision-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const unrelatedHandle = await ctx.agents.create({ + sessionId: SessionId('remote-run-id'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + + await settleSubagent(ctx, parentHandle.agent, { + provider: 'remote', + id: SessionId('remote-run-id'), + stopReason: 'completed', + lastAssistantMessage: [], + }, () => unrelatedHandle.dispose()) + + expect(transport.notifications.some(notification => + notification.method === 'subagent.finished' + && notification.params?.agentId === 'remote-run-id', + )).toBe(false) + + await parentHandle.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + it('retains locality across continuation runs on one live child', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-continuation-')) const ctx = await makeHarness(storageDir) @@ -342,7 +379,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const childHandle = await ctx.agents.create({ + const childHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('continuation-child'), meta: { cwd: storageDir, parentSession: SessionId('continuation-parent') }, agentOptions: { model: 'deepseek' }, @@ -385,7 +422,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const oldChild = await ctx.agents.create({ + const oldChild = await oldParent.agent.ctx.agents.create({ sessionId: SessionId('reused-child'), meta: { cwd: storageDir, parentSession: SessionId('old-parent') }, agentOptions: { model: 'deepseek' }, @@ -425,7 +462,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const newChild = await ctx.agents.create({ + const newChild = await newParent.agent.ctx.agents.create({ sessionId: SessionId('reused-child'), meta: { cwd: storageDir, parentSession: SessionId('new-parent') }, agentOptions: { model: 'deepseek' }, @@ -483,12 +520,12 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - handle = await ctx.agents.create({ + handle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('fallback-child-session'), meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') }, agentOptions: { model: 'deepseek' }, }) - failedHandle = await ctx.agents.create({ + failedHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('failed-child-session'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, From 415907a1621fbc10a303217637897020eec4ccd1 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Tue, 14 Jul 2026 09:54:00 +0800 Subject: [PATCH 076/359] test(acp): sync advanced snapshot with bash environment hint --- .../tests/snapshots/advanced-toolchain/session.1.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.2.jsonl | 2 +- .../acp-agent/tests/snapshots/advanced-toolchain/session.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/system-prompt.golden.md | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index 1eabba53b3..64b0149dd9 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index 7787ed2ab1..0db778789e 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl index bb74382b22..a4ef64146d 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index e70cfcce44..bcfacf6d99 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -28,7 +28,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */ bash(args: { /** The bash command to execute. */ command: string; From 6b782b018927139ea07e5907488b0b948d90c813 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:54:34 +0800 Subject: [PATCH 077/359] fix: bind stdio to its exact fresh identity --- docs/config-catalog.md | 4 +- .../2026-06-20-unify-agent-and-session-id.md | 2 +- packages/core/agent-loop/README.md | 5 ++- packages/core/agent-loop/src/index.ts | 11 +++-- .../tests/config-session-id.spec.ts | 30 +++++++++++++ packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/src/index.ts | 7 ++- packages/ui/stdio-agent/src/stdio-chat.ts | 32 +++++--------- .../ui/stdio-agent/tests/stdio-agent.spec.ts | 13 ++++++ .../ui/stdio-agent/tests/stdio-chat.spec.ts | 44 +++++-------------- 10 files changed, 88 insertions(+), 62 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 94d613bc4e..66791edb0a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -119,6 +119,8 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string + /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -645,7 +647,7 @@ export interface Config { Depends on: [`agentCore`](../packages/core/agent-core/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/ui/stdio-agent/src/index.ts:64`](../packages/ui/stdio-agent/src/index.ts) +Source: [`packages/ui/stdio-agent/src/index.ts:65`](../packages/ui/stdio-agent/src/index.ts) ## `@deepseek-ai/dsh-subagent-acp` diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 032eae4f7d..404ba83636 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -16,7 +16,7 @@ Session itself repeated the same fact as `Session.id` and `Session.header.id`. C An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process subagent creation uses the child session id; and `Session.id` derives from `header.id`. A remote ACP run has no local agent/session pair: it keeps one parent-minted lifecycle id while the child server's wire-local session id remains private to ACP calls. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between local ids are gone. -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start normally mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; a coupled app may pre-mint and pass the exact fresh `sessionId`, while `resumeSessionId` supplies the exact combined identity to load and register. The two exact-id inputs are mutually exclusive. Stdio uses this narrow escape hatch so its config-created agent and UI share one opaque identity instead of guessing from a prefix. Logs may use the stable label while all live and durable lookups use the one `SessionId`. `agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index f40577bb95..246c9cdc27 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -14,7 +14,7 @@ The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createA Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and mints `${label}-session-` before calling this boundary; `resumeSessionId` instead loads and registers the exact persisted id. This keeps fresh restarts collision-free without retaining a second live routing identity. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and normally mints `${label}-session-` before calling this boundary; an app may instead supply an exact fresh `sessionId` when another coupled component must bind to it. `resumeSessionId` loads and registers the exact persisted id and is mutually exclusive with `sessionId`. This keeps default fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): @@ -33,6 +33,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo interface Config { agents: Array<{ id: string // required stable label; prefixes fresh combined ids + sessionId?: string // optional exact identity for a fresh session model?: string resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session @@ -40,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` applies only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` and optional `sessionId` apply only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index dbe503ff6a..0041b984d1 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -326,6 +326,8 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string + /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -341,6 +343,7 @@ export class AgentLoop extends Service implements AgentFactory { static Config = z.object({ agents: z.array(z.object({ id: z.string().required(), + sessionId: z.string(), model: z.string(), cwd: z.string(), resumeSessionId: z.string(), @@ -360,12 +363,14 @@ export class AgentLoop extends Service implements AgentFactory { ctx.systemPrompt.variable('model', context => context.agent?.options.model) ctx.systemPrompt.variable('cwd', context => context.agent?.session.header.cwd) - for (const { id, cwd, resumeSessionId, ...options } of config.agents) { + for (const { id, sessionId, cwd, resumeSessionId, ...options } of config.agents) { if (resumeSessionId === undefined || resumeSessionId === '') { - const sessionId = SessionId(`${id}-session-${randomUUID()}`) - this.create(sessionId, options, cwd === undefined ? {} : { cwd }) + this.create(sessionId ?? SessionId(`${id}-session-${randomUUID()}`), options, cwd === undefined ? {} : { cwd }) continue } + if (sessionId !== undefined) { + throw new Error(`agent "${id}": sessionId and resumeSessionId are mutually exclusive`) + } ctx.effect(() => { const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => { void this.resumeWith(ctx, childCtx.sessionPersistence, { diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 134ea68c32..543335e5fd 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -24,7 +24,37 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } +async function makeCoreContext(): Promise { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + return ctx +} + describe('config-driven session id', () => { + it('accepts one exact fresh id and rejects it alongside a resume id', async () => { + const exact = await makeCoreContext() + await exact.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact'), model: 'mock' }], + }) + expect(exact.agents.get(SessionId('stdio-exact'))?.session.id).toBe('stdio-exact') + await exact.fiber.dispose() + + const conflicting = await makeCoreContext() + await expect(conflicting.plugin(AgentLoop, { + agents: [{ + id: 'main', + sessionId: SessionId('fresh'), + resumeSessionId: SessionId('persisted'), + model: 'mock', + }], + })).rejects.toThrow('sessionId and resumeSessionId are mutually exclusive') + await conflicting.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index d7d30ee49d..b509e46781 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id; the UI binds to that fresh-id namespace, or to the exact `resumeSessionId` for a resumed run, and never selects unrelated registry roots. Resumed sessions keep the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; the UI's `main` text is only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 2eca0cceb3..03f3d49555 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -39,6 +39,7 @@ */ import type { Context } from 'cordis' +import { randomUUID } from 'node:crypto' import ConsoleExporter from '@cordisjs/plugin-logger-console' import z from 'schemastery' import { SessionId } from '@deepseek-ai/dsh-session' @@ -108,6 +109,8 @@ export const Config: z = z.object({ * a leaf concern (see the module doc), so it is not mounted here. */ export function apply(ctx: Context, config: Config): void { + const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId + const sessionId = SessionId(resumeSessionId ?? `main-session-${randomUUID()}`) ctx.plugin(ConsoleExporter) ctx.plugin(agentCore, { ...config.persona !== undefined ? { persona: config.persona } : {}, @@ -117,7 +120,7 @@ export function apply(ctx: Context, config: Config): void { id: 'main', model: config.model, cwd: process.cwd(), - ...config.resumeSessionId !== undefined ? { resumeSessionId: SessionId(config.resumeSessionId) } : {}, + ...resumeSessionId === undefined ? { sessionId } : { resumeSessionId: sessionId }, }], ...config.skills !== undefined ? { skills: config.skills } : {}, }) @@ -126,6 +129,6 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(toolAskUser) ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.', - ...config.resumeSessionId !== undefined ? { resumeSessionId: config.resumeSessionId } : {}, + sessionId, }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 17a11168db..93c8f9b4f1 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -36,13 +36,13 @@ export const inject = ['agents', 'userInteraction'] export interface Config { /** Banner printed once on start, before the first `> ` prompt. */ welcome?: string - /** Exact persisted session id the app configured for resume; absent selects the app's fresh `main-session-*` identity. */ - resumeSessionId?: string + /** Exact shared agent/session identity this app instance created or resumed. */ + sessionId?: string } export const Config: z = z.object({ welcome: z.string().default('ready.'), - resumeSessionId: z.string(), + sessionId: z.string(), }) /** @@ -98,26 +98,18 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // Bind only to this app's configured top-level agent. Fresh runs own the - // `main-session-*` namespace; resumed runs own the exact persisted id. The - // registry's runtime-root relation excludes subagents without confusing it - // with durable parentSession lineage. Keeping the matching candidates also - // covers HMR's publish-new-before-dispose-old ordering without ever falling - // through to an unrelated root owned by another app or test fixture. - const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId - const matchesConfiguredIdentity = (agent: Agent): boolean => resumeSessionId === undefined - ? agent.id.startsWith('main-session-') - : agent.id === resumeSessionId - const configuredRoots = new Set(ctx.agents.roots().filter(matchesConfiguredIdentity)) - let target: Agent | undefined = [...configuredRoots].at(-1) + // Bind only to the exact identity this app passed to its config-created + // agent. Session ids are opaque: neither a prefix nor registry order can + // identify ownership. The root check rejects a child that somehow preempts + // the configured id; later recreation under the same id supports loop HMR. + const matchesConfiguredIdentity = (agent: Agent): boolean => + agent.id === config.sessionId && ctx.agents.roots().includes(agent) + let target: Agent | undefined = ctx.agents.roots().find(agent => agent.id === config.sessionId) ctx.on('agent/created', (agent) => { - if (!matchesConfiguredIdentity(agent) || !ctx.agents.roots().includes(agent)) return - configuredRoots.add(agent) - target ??= agent + if (matchesConfiguredIdentity(agent)) target = agent }) ctx.on('agent/disposed', (agent) => { - configuredRoots.delete(agent) - if (target === agent) target = [...configuredRoots].at(-1) + if (target === agent) target = undefined }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 5c5c0d2667..9a7bf10bad 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -93,6 +93,19 @@ describe('dsh-stdio-agent app', () => { await ctx.fiber.dispose() }) + it('normalizes an empty resume id to a fresh exact app identity', async () => { + const ctx = await mount({ + model: 'mock', + resumeSessionId: '', + persistenceRoot: '/tmp/dsh-stdio-agent-spec-empty-resume', + skills: await isolatedSkillsConfig(), + }) + const agent = ctx.get('agents')?.list()[0] + expect(agent?.id).toMatch(/^main-session-[0-9a-f-]{36}$/) + expect(agent?.id).toBe(agent?.session.id) + await ctx.fiber.dispose() + }) + it('defaults persistenceRoot and welcome when omitted', async () => { // Direct apply (NOT via ctx.plugin, which validates+defaults the config // first) so the runtime `?? './.sessions'` / `?? 'ready.'` fallbacks on diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2ebc51e14e..f1ca914525 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -74,7 +74,7 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { return { type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 0, chunk } } } -const CONFIG: Config = { welcome: 'hi there', resumeSessionId: 'main' } +const CONFIG: Config = { welcome: 'hi there', sessionId: 'main' } async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() @@ -199,7 +199,7 @@ describe('createStdioChat rendering', () => { }) it('accepts a lineage-bearing configured agent created after the UI installs', async () => { - const { ctx, input } = await setup({ welcome: 'hi there', resumeSessionId: 'resumed' }) + const { ctx, input } = await setup({ welcome: 'hi there', sessionId: 'resumed' }) const unrelated = makeAgent('unrelated') ctx.agents.register(unrelated) const resumed = makeAgent('resumed') @@ -247,33 +247,21 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 1] ') }) - it('retargets a surviving root when HMR publishes it before disposing the old root', async () => { - const { ctx, input } = await setup({ welcome: 'hi there' }) - const oldRoot = makeAgent('main-session-old') - const child = makeAgent('child') - ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id - const replacement = makeAgent('main-session-replacement') - const lateChild = makeAgent('late-child') + it('retargets only the exact identity after loop HMR recreation', async () => { + const { ctx, input } = await setup({ welcome: 'hi there', sessionId: 'main-session-fixed' }) + const oldRoot = makeAgent('main-session-fixed') + const prefixCollision = makeAgent('main-session-unrelated') const disposeOld = ctx.agents.register(oldRoot) - const disposeChild = ctx.agents.enter(child, oldRoot) - ctx.agents.announce(child) - ctx.agents.register(replacement) - const disposeLateChild = ctx.agents.enter(lateChild, replacement) - ctx.agents.announce(lateChild) - - // The replacement's created edge arrived while oldRoot was still targeted. - // A replacement-owned child then arrived even later. Once oldRoot is - // removed, runtime ownership still identifies replacement as the only - // surviving root instead of selecting either newer child by insertion order. + ctx.agents.register(prefixCollision) disposeOld() + const replacement = makeAgent('main-session-fixed') + ctx.agents.register(replacement) + input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) - expect(child.sent).toEqual([]) - expect(lateChild.sent).toEqual([]) + expect(prefixCollision.sent).toEqual([]) expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) - disposeLateChild() - disposeChild() }) it('does not retarget stdin to an unrelated root after the configured agent is disposed', async () => { @@ -740,7 +728,7 @@ describe('createStdioChat input', () => { }) it('drives the exact app-configured resumed session', async () => { - const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: 'worker' }) + const { ctx, input } = await setup({ welcome: 'w', sessionId: 'worker' }) const agent = makeAgent('worker') ctx.agents.register(agent) input.feed('hi') @@ -748,14 +736,6 @@ describe('createStdioChat input', () => { expect(agent.sent).toHaveLength(1) }) - it('treats an empty resume session id as a fresh configured identity', async () => { - const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: '' }) - const agent = makeAgent('main-session-fresh') - ctx.agents.register(agent) - input.feed('hi') - await new Promise(r => setImmediate(r)) - expect(agent.sent).toHaveLength(1) - }) }) describe('createStdioChat EOF exit', () => { From a8c0e8a03c35b1303d7780b8215e482809c32d6f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:55:15 +0800 Subject: [PATCH 078/359] test: cover successful ACP cleanup failure --- .../support/acp-snapshot/tests/harness.spec.ts | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index de764cfd8a..23b4192a4d 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -274,6 +274,21 @@ describe('runScenario', () => { expect(failures[1]).toBe(cleanupFailure) }) + it('reports cleanup failure after an otherwise successful scenario', { timeout: 20_000 }, async () => { + const { fixtureFile } = await scenario({}) + const cleanupFailure = new Error('cleanup failed') + fsControl.cleanupFailure = cleanupFailure + + const failure = await runScenario( + { steps: boot }, + { agent: AGENT, mode: 'replay', fixtureFile }, + ).catch((error: unknown): unknown => error) + + expect(failure).toBeInstanceOf(AggregateError) + expect((failure as AggregateError).message).toBe('snapshot cleanup failed') + expect((failure as AggregateError).errors as unknown[]).toEqual([cleanupFailure]) + }) + it('newSessionExpectError swallows the rejection, with and without extra dirs', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ rejectExtraDirs: true }) const result = await runScenario( From 1951eb546386e9002caf6c270ff0e055793fbeab Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Tue, 14 Jul 2026 09:55:31 +0800 Subject: [PATCH 079/359] fix(runtime): include dsh-home in bundled closure --- pnpm-lock.yaml | 3 +++ python/sdk-runtime/package.json | 1 + 2 files changed, 4 insertions(+) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 2a65f7ae73..8f76603a34 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1719,6 +1719,9 @@ importers: '@deepseek-ai/dsh-fs-policy': specifier: workspace:^ version: link:../../packages/fs/fs-policy + '@deepseek-ai/dsh-home': + specifier: workspace:^ + version: link:../../packages/util/home '@deepseek-ai/dsh-hook-protocol': specifier: workspace:^ version: link:../../packages/hooks/hook-protocol diff --git a/python/sdk-runtime/package.json b/python/sdk-runtime/package.json index 76e6bf157f..3f234887c9 100644 --- a/python/sdk-runtime/package.json +++ b/python/sdk-runtime/package.json @@ -23,6 +23,7 @@ "@deepseek-ai/dsh-fs": "workspace:^", "@deepseek-ai/dsh-fs-local": "workspace:^", "@deepseek-ai/dsh-fs-policy": "workspace:^", + "@deepseek-ai/dsh-home": "workspace:^", "@deepseek-ai/dsh-hook-protocol": "workspace:^", "@deepseek-ai/dsh-hooks-claude": "workspace:^", "@deepseek-ai/dsh-hooks-codex": "workspace:^", From 2dca8e2151ef3745f88507fe2aac17cabd630eac Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:58:35 +0800 Subject: [PATCH 080/359] docs: refresh agent loop catalog location --- docs/cordis-catalog/services.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 1366fcf6f6..6b456ef942 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:337`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` From 00462f80a6ff59604e44b71446bb9b2427a212c8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:01:36 +0800 Subject: [PATCH 081/359] docs: expose agent ownership in Cordis catalog --- packages/cordis/tool-cordis/src/api-catalog.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index ff27f51067..ede7935f8e 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -72,6 +72,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'enter(agent: Agent, owner: Agent | undefined): () => void', 'announce(agent: Agent): void', 'get(id: SessionId): Agent | undefined', + 'isOwnedBy(id: SessionId, owner: Agent): boolean', 'list(): Agent[]', 'roots(): Agent[]', ], From db3e97fc17a0f96fda7a2ecee94af86e7fad2102 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:05:19 +0800 Subject: [PATCH 082/359] test: create built probe child in parent scope --- packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts index 159600e49c..bc6642263e 100644 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -58,7 +58,7 @@ try { meta: { cwd: storageRoot }, agentOptions: { model: "test" }, }); - const child = await ctx.agents.create({ + const child = await parent.agent.ctx.agents.create({ sessionId: SessionId("built-child"), meta: { cwd: storageRoot, parentSession: SessionId("built-parent") }, agentOptions: { model: "test" }, From 3e2ba3f5574b43dc5af5d03e146769be241f96a3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:13:05 +0800 Subject: [PATCH 083/359] fix: stop ACP teardown when fallback kill fails --- packages/support/acp-snapshot/src/launcher.ts | 27 ++++++++- .../acp-snapshot/tests/harness.spec.ts | 59 +++++++++++++++++++ 2 files changed, 83 insertions(+), 3 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index f1271986c0..8d25a6f56c 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -65,7 +65,7 @@ export interface LaunchedAcpTestAgent { stderr(): string /** Resolve when a future session update matches the predicate. */ waitForUpdate(match: (update: SessionNotification['update']) => boolean): Promise - /** Gracefully close stdin, or send a signal, then wait for process exit, inherited stdio closure, ACP parsing, and client callbacks. */ + /** Close the process and drain its streams and callbacks; rejects promptly if fallback termination is refused. */ close(signal?: NodeJS.Signals): Promise } @@ -231,8 +231,29 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // signal can leave the subprocess live. Force termination, await the // already-observed exit edge, and only then propagate the child error so // callers may safely remove cwd/session resources after close rejects. - child.kill('SIGKILL') - await exited + const fallbackError = Promise.withResolvers() + const observeFallbackError = (error: Error): void => { fallbackError.resolve(error) } + child.once('error', observeFallbackError) + if (!child.kill('SIGKILL')) { + child.off('error', observeFallbackError) + closeUpdateStream() + throw new AggregateError( + [failure, new Error('Fallback SIGKILL was not accepted by the child process')], + 'ACP test agent failed and fallback termination was refused', + ) + } + const fallbackFailure = await Promise.race([ + exited.then((): undefined => undefined), + fallbackError.promise, + ]) + child.off('error', observeFallbackError) + if (fallbackFailure !== undefined) { + closeUpdateStream() + throw new AggregateError( + [failure, fallbackFailure], + 'ACP test agent failed and fallback termination was refused', + ) + } await drained closeUpdateStream() throw failure diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 23b4192a4d..ff7c304121 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -131,6 +131,65 @@ describe('runScenario', () => { expect(launched.stderr()).toContain('late inherited stderr') }) + it('rejects promptly when fallback termination is refused', async () => { + const { dir } = await scenario({}) + const launched = launchAcpTestAgent({ agent: AGENT, cwd: dir }) + await launched.spawned + + const childFailure = Object.assign(new Error('signal refused'), { code: 'EPERM' }) + const originalKill = launched.child.kill.bind(launched.child) + const kill = vi.spyOn(launched.child, 'kill').mockReturnValue(false) + const closed = new Promise(resolve => launched.child.once('close', () => { resolve() })) + try { + launched.child.emit('error', childFailure) + const rejection = await launched.close('SIGTERM').catch((error: unknown): unknown => error) + expect(rejection).toBeInstanceOf(AggregateError) + expect(rejection).toMatchObject({ + message: 'ACP test agent failed and fallback termination was refused', + errors: [ + childFailure, + expect.objectContaining({ message: 'Fallback SIGKILL was not accepted by the child process' }), + ], + }) + expect(kill).toHaveBeenNthCalledWith(1, 'SIGTERM') + expect(kill).toHaveBeenNthCalledWith(2, 'SIGKILL') + } finally { + kill.mockRestore() + originalKill('SIGKILL') + await closed + } + }) + + it('rejects promptly when fallback termination emits an error', async () => { + const { dir } = await scenario({}) + const launched = launchAcpTestAgent({ agent: AGENT, cwd: dir }) + await launched.spawned + + const childFailure = Object.assign(new Error('signal refused'), { code: 'EPERM' }) + const fallbackFailure = Object.assign(new Error('fallback signal refused'), { code: 'EPERM' }) + const originalKill = launched.child.kill.bind(launched.child) + const kill = vi.spyOn(launched.child, 'kill').mockImplementation((signal) => { + if (signal === 'SIGKILL') queueMicrotask(() => launched.child.emit('error', fallbackFailure)) + return signal === 'SIGKILL' + }) + const closed = new Promise(resolve => launched.child.once('close', () => { resolve() })) + try { + launched.child.emit('error', childFailure) + const rejection = await launched.close('SIGTERM').catch((error: unknown): unknown => error) + expect(rejection).toBeInstanceOf(AggregateError) + expect(rejection).toMatchObject({ + message: 'ACP test agent failed and fallback termination was refused', + errors: [childFailure, fallbackFailure], + }) + expect(kill).toHaveBeenNthCalledWith(1, 'SIGTERM') + expect(kill).toHaveBeenNthCalledWith(2, 'SIGKILL') + } finally { + kill.mockRestore() + originalKill('SIGKILL') + await closed + } + }) + it('waits for in-flight client callbacks after the ACP stream closes', { timeout: 20_000 }, async () => { const { dir, fixtureFile } = await scenario({ permissionProbe: true }) let releasePermission: (() => void) | undefined From 816b6e4c68e26c38c4ac0aab1cad3ee14714a510 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:25:49 +0800 Subject: [PATCH 084/359] fix: restore exact config sessions on loop reload --- docs/config-catalog.md | 2 +- .../2026-06-20-unify-agent-and-session-id.md | 10 ++--- .../2026-07-02-remove-stream-chunk-mirror.md | 2 +- packages/core/agent-loop/README.md | 6 +-- packages/core/agent-loop/src/index.ts | 29 ++++++++++++++- .../tests/config-session-id.spec.ts | 37 +++++++++++++++++++ packages/ui/stdio-agent/README.md | 2 +- 7 files changed, 75 insertions(+), 13 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 66791edb0a..024d3b766b 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -119,7 +119,7 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string - /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + /** Optional stable identity; remounts resume its materialized history, while first use creates it fresh. */ sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 404ba83636..20ba40c196 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -4,19 +4,19 @@ Status: implemented ## Problem -The agent factory previously carried two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` took both; `ResumeAgentOptions` took `agentId` plus `resumeSessionId`; in-process subagents minted two independent UUIDs despite recording lineage separately. +A live agent/session pair needs one identity for registry routing, event sourcing, and persistence. Giving the factory independent `agentId` and `sessionId` inputs would permit pairings no production path can use, while forcing every consumer to choose or translate between two names for the same lifecycle. -ACP already used the same value for both identities. Where they diverged, stdio kept `labelBySession` solely to recover an agent label from session events, and hooks exposed both values for authors to reconcile. No production path reattached one live agent object to several sessions or drove one session through several agent ids. +ACP uses the same value for both identities. Stdio and hooks also operate on the session event stream and need the corresponding live agent directly; no production path reattaches one live agent object to several sessions or drives one session through several agent ids. -The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) had no reservation side tables: create and resume used one `AgentCreationTransaction`, and agent/session entries used the same final-entry collision rule. Separate ids therefore did not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification was only an API and representation simplification: it deleted one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. +The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) uses one `AgentCreationTransaction` for create and resume, and agent/session entries share the same final-entry collision rule. A second identity would not represent separate liveness, rollback, or quiescence; it would only add API and translation state around the same transaction. -Session itself repeated the same fact as `Session.id` and `Session.header.id`. Construction rejected a header whose id differed, so the aliases were constrained equal; the durable boundary nevertheless had to validate the duplicate, and production consumers chose between its two homes. +Session identity likewise has one home in `Session.header.id`; `Session.id` is a derived accessor rather than independent state that needs duplicate validation. ## Decision An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process subagent creation uses the child session id; and `Session.id` derives from `header.id`. A remote ACP run has no local agent/session pair: it keeps one parent-minted lifecycle id while the child server's wire-local session id remains private to ACP calls. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between local ids are gone. -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start normally mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; a coupled app may pre-mint and pass the exact fresh `sessionId`, while `resumeSessionId` supplies the exact combined identity to load and register. The two exact-id inputs are mutually exclusive. Stdio uses this narrow escape hatch so its config-created agent and UI share one opaque identity instead of guessing from a prefix. Logs may use the stable label while all live and durable lookups use the one `SessionId`. +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. An ordinary fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide. A coupled app may pre-mint and pass an exact `sessionId`: first use creates it, while an AgentLoop remount with an already-present persistence service resumes materialized history under that same identity. `resumeSessionId` instead requires an existing persisted identity. The two exact-id inputs are mutually exclusive. Stdio uses the resume-or-create form so its config-created agent and UI share one opaque identity across loop reloads instead of guessing from a prefix. Logs may use the stable label while all live and durable lookups use the one `SessionId`. `agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. diff --git a/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md b/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md index a272dfe0b2..6ca85b3d16 100644 --- a/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md +++ b/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md @@ -42,4 +42,4 @@ Not touched: ## Consequences -A plugin can no longer observe token deltas from an `Agent`-first event. It subscribes to `session/event` and filters `assistant/chunk` (the `Agent` handle, if needed, is recovered from a session-id→agent map built from `agent/created`/`agent/disposed`, exactly as boundary consumers already do). No production consumer needed the live `Agent` at chunk time; this is the same acceptable trade the boundary-mirror removal made. +A plugin can no longer observe token deltas from an `Agent`-first event. It subscribes to `session/event`, filters `assistant/chunk`, and looks up the corresponding live handle directly with `ctx.agents.get(session.id)` when needed. No production consumer needed the live `Agent` at chunk time; this is the same acceptable trade the boundary-mirror removal made. diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 246c9cdc27..2db1a6c079 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -14,7 +14,7 @@ The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createA Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and normally mints `${label}-session-` before calling this boundary; an app may instead supply an exact fresh `sessionId` when another coupled component must bind to it. `resumeSessionId` loads and registers the exact persisted id and is mutually exclusive with `sessionId`. This keeps default fresh restarts collision-free without retaining a second live routing identity. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and normally mints `${label}-session-` before calling this boundary. An app may instead supply a stable exact `sessionId`: first use creates it, while a remount with persistence already present resumes its materialized history. `resumeSessionId` requires and loads an existing persisted id and is mutually exclusive with `sessionId`. This keeps default fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): @@ -33,7 +33,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo interface Config { agents: Array<{ id: string // required stable label; prefixes fresh combined ids - sessionId?: string // optional exact identity for a fresh session + sessionId?: string // optional exact resume-or-create identity model?: string resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` and optional `sessionId` apply only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 0041b984d1..33e8c3c443 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -326,7 +326,7 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string - /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + /** Optional stable identity; remounts resume its materialized history, while first use creates it fresh. */ sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string @@ -364,8 +364,17 @@ export class AgentLoop extends Service implements AgentFactory { ctx.systemPrompt.variable('cwd', context => context.agent?.session.header.cwd) for (const { id, sessionId, cwd, resumeSessionId, ...options } of config.agents) { + const meta = cwd === undefined ? {} : { cwd } if (resumeSessionId === undefined || resumeSessionId === '') { - this.create(sessionId ?? SessionId(`${id}-session-${randomUUID()}`), options, cwd === undefined ? {} : { cwd }) + const configuredId = sessionId ?? SessionId(`${id}-session-${randomUUID()}`) + const persistence = sessionId === undefined ? undefined : ctx.get('sessionPersistence') + if (persistence === undefined) { + this.create(configuredId, options, meta) + } else { + void this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { + ctx.logger.warn(`agent "${id}": config-driven restore of "${configuredId}" failed: ${String(error)}`) + }) + } continue } if (sessionId !== undefined) { @@ -385,6 +394,22 @@ export class AgentLoop extends Service implements AgentFactory { } } + /** Restore a materialized exact config identity on remount, or create it on first use. */ + private async restoreOrCreateConfigured( + ownerCtx: Context, + persistence: SessionPersistence, + sessionId: SessionId, + agentOptions: AgentOptions, + meta: Pick, + ): Promise { + const exists = (await persistence.list()).some(header => header.id === sessionId) + if (exists) { + await this.resumeWith(ownerCtx, persistence, { resumeSessionId: sessionId, agentOptions }) + return + } + this.create(sessionId, agentOptions, meta) + } + /** * Create an agent and session under one caller-supplied identity, owned by * the accessing fiber. Constructor-driven config calls mint a fresh combined diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 543335e5fd..9382804527 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -55,6 +55,43 @@ describe('config-driven session id', () => { await conflicting.fiber.dispose() }) + it('restores a materialized exact id across an AgentLoop-only reload', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-reload-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first'), textResponse('second')])) + const config = { agents: [{ id: 'main', sessionId: SessionId('stdio-exact-reload'), model: 'mock' }] } + + const firstLoop = await ctx.plugin(AgentLoop, config) + let first: ReactLoopAgent | undefined + for (let i = 0; i < 50 && first === undefined; i++) { + await new Promise(resolve => setTimeout(resolve, 5)) + first = ctx.agents.get(SessionId('stdio-exact-reload')) as ReactLoopAgent | undefined + } + expect(first).toBeDefined() + first!.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) + await waitForIdle(ctx, first!) + await firstLoop.dispose() + + const secondLoop = await ctx.plugin(AgentLoop, config) + let second: ReactLoopAgent | undefined + for (let i = 0; i < 50 && second === undefined; i++) { + await new Promise(resolve => setTimeout(resolve, 5)) + second = ctx.agents.get(SessionId('stdio-exact-reload')) as ReactLoopAgent | undefined + } + expect(second).toBeDefined() + expect(JSON.stringify(second!.session.deriveMessages())).toContain('remember me') + second!.send([{ type: 'text', text: 'continue' }], { source: { kind: 'user' } }) + await waitForIdle(ctx, second!) + await ctx.sessions.flush(second!.session) + const loaded = await ctx.sessionPersistence.load(SessionId('stdio-exact-reload')) + expect(loaded.events.filter(event => event.type === 'turn/start')).toHaveLength(2) + + await secondLoop.dispose() + await ctx.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index b509e46781..15b1c78f09 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; the UI's `main` text is only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin From 656ae95263cfd9f832bdeefbf9da6a91b8ce72bb Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:28:04 +0800 Subject: [PATCH 085/359] test: await exact stdio startup condition --- packages/ui/stdio-agent/tests/stdio-agent.spec.ts | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 9a7bf10bad..a14848a549 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -114,9 +114,8 @@ describe('dsh-stdio-agent app', () => { const ctx = new Context() // No persona: covers the omitted-persona forwarding branch too. stdioAgent.apply(ctx, { model: 'mock', skills: await isolatedSkillsConfig() }) - await new Promise(resolve => setTimeout(resolve, 80)) - expect(ctx.get('sessionPersistence')).toBeDefined() - expect(ctx.get('agents')?.list()).toHaveLength(1) + await expect.poll(() => ctx.get('sessionPersistence')).toBeDefined() + await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) await ctx.fiber.dispose() }) From cf21e252fa8fd7e66c4b0c6a5acface4821d4712 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:32:02 +0800 Subject: [PATCH 086/359] fix: recognize provider-owned local subagents --- packages/subagent/subagent/README.md | 2 ++ packages/subagent/subagent/src/types.ts | 6 +++++- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 22 ++++++++++++++++------ packages/ui/jsonrpc/tests/server.spec.ts | 5 ++++- 5 files changed, 28 insertions(+), 9 deletions(-) diff --git a/packages/subagent/subagent/README.md b/packages/subagent/subagent/README.md index 413bbbdafc..016d363d78 100644 --- a/packages/subagent/subagent/README.md +++ b/packages/subagent/subagent/README.md @@ -50,6 +50,8 @@ Runtime features are optional methods on `SubagentRun`: `sendMessage?` steers a `SubagentRun.result` resolves to `{ output, structured?, stopReason }`. Child-level failures resolve with a non-`completed` reason; only an infrastructure fault that the seam cannot represent may reject. `dispose()` is idempotent, cancels remaining work, and waits for the child resources to quiesce. +A local run publishes an ordinary child agent/session before `start()` fulfills, returns that shared session id as `SubagentRun.id`, and records `request.parent.session.id` in the child's `parentSession` header. The child may be owned by the parent scope or by a provider/root scope; durable lineage is the transport-neutral local-child relation. Remote providers instead mint a parent-scoped lifecycle id without publishing a local child. + The service emits `subagent/start` only after `start()` has fulfilled. It attaches the result observer before that synchronous notification, so even an already-settled child still produces `subagent/start` before `subagent/end`. In-process start observers can resolve the published child through `ctx.agents.get(info.id)`; remote providers need not publish a local agent. Run events are scoped to the delegating parent. Every listener is independently contained: a synchronous throw or rejected returned promise is logged without starving peer listeners or changing the run. diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 827c2db7a7..37e0b28323 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -147,7 +147,11 @@ export interface SubagentResult { * presence of the method IS the capability — narrow before calling. */ export interface SubagentRun { - /** Parent-scoped run id. Local runs use the published child session id; remote providers mint an id unique in the parent namespace. */ + /** + * Parent-scoped run id. A local run publishes a child session whose + * `parentSession` records `request.parent`; a remote provider mints an id + * unique in the parent namespace. + */ readonly id: SessionId /** * Resolves with the child's terminal {@link SubagentResult} when the run diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index df612ac263..4ef9e86ffc 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server verifies that the live child is owned by the exact delegating parent, then counts local starts by provider/id and that parent carrier because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported even when their parent-scoped run id collides with an unrelated local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server recognizes a live child through either exact delegating-parent runtime ownership or matching durable `parentSession` lineage, then counts local starts by provider/id and that parent carrier because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported even when their parent-scoped run id collides with an unrelated local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index d78f24b5ab..723f2eb4eb 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -66,6 +66,15 @@ function subagentParentOf(carrier: Scoped): Agent { return carrierKeyOf(carrier) as Agent } +/** Whether the live id names a local child related to this exact delegating parent. */ +function isLocalChild(ctx: Context, id: SessionId, parent: Agent): boolean { + const child = ctx.agents.get(id) + return child !== undefined && ( + ctx.agents.isOwnedBy(id, parent) + || child.session.header.parentSession === parent.session.id + ) +} + /** * The SDK server over a booted harness context. Constructing it subscribes to * session and subagent lifecycle events, forwarding durable session @@ -104,13 +113,14 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // In-process providers publish the child before start. Count those starts by - // the exact delegating-parent carrier so later completions remain local after - // child disposal and reused ids need no settlement-order assumption. + // In-process providers publish the child before start. Count starts related + // by exact runtime ownership or durable parent lineage so provider-owned + // roots remain local, completions survive child disposal, and reused ids + // need no settlement-order assumption. const localRuns = this.localRuns this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { const parent = subagentParentOf(this) - if (!ctx.agents.isOwnedBy(info.id, parent)) return + if (!isLocalChild(ctx, info.id, parent)) return const providerRuns = localRuns.get(info.provider) ?? new Map>() const parentRuns = providerRuns.get(info.id) ?? new Map() parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) @@ -130,9 +140,9 @@ export class HarnessSdkServer { } // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above. A remote run - // has neither a cached owned start nor a live child owned by this exact + // has neither a cached local start nor a live child related to this // parent; an unrelated local agent with the same id never makes it local. - if (pendingCount === undefined && !ctx.agents.isOwnedBy(info.id, parent)) return + if (pendingCount === undefined && !isLocalChild(ctx, info.id, parent)) return transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index c97bd1a6e1..3861a6729d 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -277,11 +277,14 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const handle = await parentHandle.agent.ctx.agents.create({ + // A custom in-process provider may own its child at the provider/root + // scope while preserving durable parent lineage. + const handle = await ctx.agents.create({ sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) + expect(ctx.agents.roots()).toContain(handle.agent) const parentlessHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('parentless-child-session'), meta: { cwd: storageDir }, From 949ee03377719aea96a26fd96ba0bc284cf740ec Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:38:53 +0800 Subject: [PATCH 087/359] test: cover exact session restore failure --- .../tests/config-session-id.spec.ts | 21 +++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 9382804527..dcde82efe2 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -92,6 +92,27 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('contains an exact-id persistence lookup failure', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const failure = new Error('persistence index failed') + vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(failure) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + + await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-failure'), model: 'mock' }], + }) + + await expect.poll(() => warn).toHaveBeenCalledWith(expect.stringContaining( + 'config-driven restore of "stdio-exact-failure" failed: Error: persistence index failed', + )) + expect(ctx.agents.get(SessionId('stdio-exact-failure'))).toBeUndefined() + warn.mockRestore() + await ctx.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) From 46b8bce03acebd579cdcb4daf91c02e51eddf78e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:47:47 +0800 Subject: [PATCH 088/359] fix: join exact session startup on teardown --- docs/config-catalog.md | 2 +- docs/cordis-catalog/services.md | 2 +- packages/core/agent-loop/src/index.ts | 19 +++++++++++--- .../tests/config-session-id.spec.ts | 25 +++++++++++++++++++ 4 files changed, 42 insertions(+), 6 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 024d3b766b..d22bcca6f7 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:324`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:333`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 6b456ef942..e79422b94f 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 33e8c3c443..d2d8648595 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -45,6 +45,7 @@ const INACTIVE_STATES: ReadonlySet = new Set([ class FactoryOwnership { private accepting = true private transactions = new Set() + private startupTasks = new Set>() constructor(private readonly fiber: Context['fiber']) {} @@ -57,12 +58,20 @@ class FactoryOwnership { return () => { this.transactions.delete(transaction) } } + /** Join config startup work that begins before an agent transaction exists. */ + trackStartup(task: Promise): void { + this.startupTasks.add(task) + const forget = () => { this.startupTasks.delete(task) } + void task.then(forget, forget) + } + async dispose(): Promise { this.accepting = false const reason = new Error('agent loop is not active') - await Promise.all( - [...this.transactions].map(transaction => transaction.disposeForFactory(reason)), - ) + await Promise.all([ + ...[...this.transactions].map(transaction => transaction.disposeForFactory(reason)), + ...this.startupTasks, + ]) } } @@ -371,9 +380,10 @@ export class AgentLoop extends Service implements AgentFactory { if (persistence === undefined) { this.create(configuredId, options, meta) } else { - void this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { + const startup = this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { ctx.logger.warn(`agent "${id}": config-driven restore of "${configuredId}" failed: ${String(error)}`) }) + this.ownership.trackStartup(startup) } continue } @@ -403,6 +413,7 @@ export class AgentLoop extends Service implements AgentFactory { meta: Pick, ): Promise { const exists = (await persistence.list()).some(header => header.id === sessionId) + if (!this.ownership.isActive()) return if (exists) { await this.resumeWith(ownerCtx, persistence, { resumeSessionId: sessionId, agentOptions }) return diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index dcde82efe2..c1a04fadd0 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -113,6 +113,31 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('joins an exact-id persistence lookup before AgentLoop disposal completes', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const listing = Promise.withResolvers>>() + vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + + const loop = await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], + }) + let disposed = false + const disposal = loop.dispose().then(() => { disposed = true }) + await Promise.resolve() + expect(disposed).toBe(false) + + listing.resolve([]) + await disposal + expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() + expect(warn).not.toHaveBeenCalled() + warn.mockRestore() + await ctx.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) From 288023dac182c407c296571f3730ff3a89a0696a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:51:36 +0800 Subject: [PATCH 089/359] docs: define local subagent lineage --- docs/core-data-structures/subagent.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 883c33020a..7b57789a7c 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -76,6 +76,8 @@ interface SubagentRun { } ``` +A local run MUST publish an ordinary child agent/session before `start()` fulfills, return that child session id as `SubagentRun.id`, and record `request.parent.session.id` in the child's `parentSession` header. Runtime ownership may place the child under the parent, provider, or root scope; `parentSession` is the durable transport-neutral lineage. A remote provider instead returns a parent-scoped lifecycle id and does not publish a local child. + ## The provider seam: `SubagentProvider` One transport for running a child agent. Implementations register under a unique name via `SubagentService.registerProvider`; multiple coexist in one context. The service validates every requested start-time capability before calling `start`, so an implementation may assume e.g. `request.maxDepth` is honorable when present. `inheritsParentContext` is a DESCRIPTIVE fact beside the capabilities (nothing validates against it): whether a child sees the parent conversation (`fork`: true, `spawn`/`acp`: false) — the model-facing consumer derives truthful tool wording from it. It describes conversation history only, not tool registrations, injected services, or authority inheritance. From e8f1bd41f5bd96c529c59ed524cfdeef7d3d1ce3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 11:02:18 +0800 Subject: [PATCH 090/359] fix: buffer stdio until exact session starts --- docs/event-producer-consumer.md | 2 +- packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/src/stdio-chat.ts | 65 ++++++++++++----- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 72 +++++++++++++++---- 4 files changed, 108 insertions(+), 33 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 80389608cc..1439873f69 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -15,7 +15,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:348`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:473`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | | `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:525`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/status` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:540`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | | `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:558`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 15b1c78f09..bbf175d92d 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. Readline buffers nonblank startup input for that identity until `agent/session-start`, so piped stdin cannot outrun asynchronous exact-id restoration or let EOF discard the queued prompt. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 93c8f9b4f1..17d396c042 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -3,9 +3,10 @@ * `steer()`, and renders the durable transcript to stdout. A UI is "just a * plugin" — it consumes the `session/event` feed (the assistant token stream, * turn/step boundaries, tool activity, todos) plus a few `agent/*` control - * events (`agent/status`, `agent/created`/`agent/disposed`) and the `agents` - * service. Dimmed chain-of-thought rendering plus robust piped-stdin EOF→idle - * exit handling, configured via {@link Config}. + * events (`agent/status`, `agent/created`/`agent/disposed`, + * `agent/session-start`) and the `agents` service. Dimmed chain-of-thought + * rendering plus robust piped-stdin EOF→idle exit handling, configured via + * {@link Config}. * * An internal module of the stdio app, not a package of its own: the app's * front-door cluster always includes this UI, and nothing else composes it. @@ -105,12 +106,6 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const matchesConfiguredIdentity = (agent: Agent): boolean => agent.id === config.sessionId && ctx.agents.roots().includes(agent) let target: Agent | undefined = ctx.agents.roots().find(agent => agent.id === config.sessionId) - ctx.on('agent/created', (agent) => { - if (matchesConfiguredIdentity(agent)) target = agent - }) - ctx.on('agent/disposed', (agent) => { - if (target === agent) target = undefined - }) // Transcript rendering off the durable `session/event` feed — the assistant // token stream, turn/step boundaries, tool activity, and todos all come from @@ -158,7 +153,6 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt }) ctx.effect(() => { - const reader = createInterface({ input, output, terminal: isTTYPair(input, output) }) // Piped-input exit, once stdin reaches EOF: // - If no line ever submitted work (empty stdin, blank-only lines), exit // immediately — no turn will ever start, so there is nothing to wait @@ -176,6 +170,36 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt let exitTimer: ReturnType | undefined let activeQuestion: PendingQuestion | undefined const questionQueue: PendingQuestion[] = [] + const queuedInput: string[] = [] + let targetReady = target !== undefined + let hadReadyTarget = targetReady + + const submit = (agent: Agent, text: string): void => { + submittedWork = true + if (agent.status === 'running') { + agent.steer([{ type: 'text', text }]) + } else { + agent.send([{ type: 'text', text }]) + } + } + + const disposeCreatedListener = ctx.on('agent/created', (agent) => { + if (!matchesConfiguredIdentity(agent)) return + target = agent + targetReady = false + }) + const disposeSessionStartListener = ctx.on('agent/session-start', (agent) => { + if (agent !== target) return + targetReady = true + hadReadyTarget = true + for (const text of queuedInput.splice(0)) submit(agent, text) + }) + const disposeDisposedListener = ctx.on('agent/disposed', (agent) => { + if (target !== agent) return + target = undefined + targetReady = false + }) + const reader = createInterface({ input, output, terminal: isTTYPair(input, output) }) const maybeExit = (): void => { if (disposed || !stdinClosed) return @@ -351,16 +375,20 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const text = line.trim() if (!text) return const agent = target - if (!agent) { + if (agent === undefined || !targetReady) { + // Initial exact-id restoration is asynchronous. Preserve input until + // session-start, the first supported point for queueing agent work. + // After a previously ready target disappears, a line in the HMR gap + // still fails loud unless its exact replacement is already publishing. + if (!hadReadyTarget || agent !== undefined) { + submittedWork = true + queuedInput.push(text) + return + } ctx.logger.error('ui-stdio: main agent is not running') return } - submittedWork = true - if (agent.status === 'running') { - agent.steer([{ type: 'text', text }]) - } else { - agent.send([{ type: 'text', text }]) - } + submit(agent, text) }) reader.on('close', () => { // Fires for BOTH stdin EOF and plugin disposal (reader.close() below); @@ -376,6 +404,9 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt disposePendingQuestions() disposeUserInteractionProvider() disposeStatusListener() + disposeCreatedListener() + disposeSessionStartListener() + disposeDisposedListener() reader.close() } }, 'ui-stdio') diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index f1ca914525..943c48ef08 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -64,6 +64,13 @@ function makeAgent(id: string, status: AgentStatus = 'idle'): Agent & { } as never } +/** Register a fake configured agent and cross the supported startup-work boundary. */ +function registerReady(ctx: Context, agent: Agent, source: 'startup' | 'resume' = 'startup'): () => void { + const dispose = ctx.agents.register(agent) + ctx.emit('agent/session-start', agent, source) + return dispose +} + /** A session stub whose `header.id` matches an agent's, for `session/event` emits. */ function makeSession(id: string): Session { return { id, header: { id } } as Session @@ -198,15 +205,21 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 5] ') }) - it('accepts a lineage-bearing configured agent created after the UI installs', async () => { + it('buffers input for a lineage-bearing configured agent until its session starts', async () => { const { ctx, input } = await setup({ welcome: 'hi there', sessionId: 'resumed' }) + input.feed('continue') + await new Promise(resolve => setImmediate(resolve)) + const unrelated = makeAgent('unrelated') ctx.agents.register(unrelated) + ctx.emit('agent/session-start', unrelated, 'startup') const resumed = makeAgent('resumed') ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' ctx.agents.register(resumed) + await new Promise(resolve => setImmediate(resolve)) + expect(resumed.sent).toEqual([]) - input.feed('continue') + ctx.emit('agent/session-start', resumed, 'resume') await new Promise(resolve => setImmediate(resolve)) expect(unrelated.sent).toEqual([]) @@ -256,9 +269,11 @@ describe('createStdioChat rendering', () => { disposeOld() const replacement = makeAgent('main-session-fixed') ctx.agents.register(replacement) - input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) + expect(replacement.sent).toEqual([]) + ctx.emit('agent/session-start', replacement, 'resume') + await new Promise(resolve => setImmediate(resolve)) expect(prefixCollision.sent).toEqual([]) expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) @@ -269,7 +284,7 @@ describe('createStdioChat rendering', () => { const unrelated = makeAgent('unrelated') ctx.agents.register(unrelated) const configured = makeAgent('main') - const disposeConfigured = ctx.agents.register(configured) + const disposeConfigured = registerReady(ctx, configured) const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) disposeConfigured() @@ -693,7 +708,7 @@ describe('createStdioChat input', () => { it('sends a typed line to an idle agent', async () => { const { ctx, input } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('do a thing') await new Promise(r => setImmediate(r)) expect(agent.sent).toEqual([[{ type: 'text', text: 'do a thing' }]]) @@ -703,7 +718,7 @@ describe('createStdioChat input', () => { it('steers a typed line into a running agent', async () => { const { ctx, input } = await setup() const agent = makeAgent('main', 'running') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('steer me') await new Promise(r => setImmediate(r)) expect(agent.steered).toEqual([[{ type: 'text', text: 'steer me' }]]) @@ -719,18 +734,26 @@ describe('createStdioChat input', () => { expect(agent.sent).toEqual([]) }) - it('logs and drops a line when the target agent is not running', async () => { + it('buffers a line until the initial target session starts', async () => { const { ctx, input } = await setup() const spy = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) input.feed('nobody home') await new Promise(r => setImmediate(r)) - expect(spy).toHaveBeenCalledWith('ui-stdio: main agent is not running') + expect(spy).not.toHaveBeenCalled() + + const agent = makeAgent('main') + ctx.agents.register(agent) + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([]) + ctx.emit('agent/session-start', agent, 'startup') + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([[{ type: 'text', text: 'nobody home' }]]) }) it('drives the exact app-configured resumed session', async () => { const { ctx, input } = await setup({ welcome: 'w', sessionId: 'worker' }) const agent = makeAgent('worker') - ctx.agents.register(agent) + registerReady(ctx, agent, 'resume') input.feed('hi') await new Promise(r => setImmediate(r)) expect(agent.sent).toHaveLength(1) @@ -749,7 +772,7 @@ describe('createStdioChat EOF exit', () => { it('waits for the agent to settle idle after running before exiting', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) input.finish() @@ -764,10 +787,31 @@ describe('createStdioChat EOF exit', () => { expect(exit).toHaveBeenCalledWith(0) }) + it('keeps piped EOF pending until buffered startup input runs', async () => { + const { ctx, input, exit } = await setup() + input.feed('work') + input.finish() + await flushExit() + expect(exit).not.toHaveBeenCalled() + + const agent = makeAgent('main', 'idle') + ctx.agents.register(agent) + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([]) + ctx.emit('agent/session-start', agent, 'startup') + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([[{ type: 'text', text: 'work' }]]) + ctx.emit('agent/status', agent, 'running') + ;(agent as { status: AgentStatus }).status = 'idle' + ctx.emit('agent/status', agent, 'idle') + await flushExit() + expect(exit).toHaveBeenCalledWith(0) + }) + it('schedules the exit only once when idle fires repeatedly', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'running') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) ctx.emit('agent/status', agent, 'running') // sawRunning = true @@ -785,7 +829,7 @@ describe('createStdioChat EOF exit', () => { it('does not exit on an idle transition for a different agent', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) input.finish() @@ -799,7 +843,7 @@ describe('createStdioChat EOF exit', () => { it('does not exit while a turn is still running at EOF', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) ctx.emit('agent/status', agent, 'running') @@ -848,7 +892,7 @@ describe('createStdioChat disposal (HMR safety)', () => { it('removes the agent/status listener on dispose', async () => { const { ctx, fiber, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) await fiber.dispose() From c1fb97c63a3ac7c3a6d4066ccc7615d292c0dfa7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 11:23:38 +0800 Subject: [PATCH 091/359] fix: surface config startup failures --- docs/architecture.md | 7 ++- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 12 +++++ docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 1 + docs/module-graph.md | 3 +- .../cordis/tool-cordis/src/api-catalog.ts | 6 +++ packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/index.ts | 30 +++++++++++- .../tests/config-session-id.spec.ts | 10 ++++ packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/package.json | 2 + packages/ui/stdio-agent/src/index.ts | 23 ++++----- packages/ui/stdio-agent/src/stdio-chat.ts | 20 ++++++++ .../ui/stdio-agent/tests/stdio-chat.spec.ts | 47 ++++++++++++++++++- pnpm-lock.yaml | 3 ++ 16 files changed, 151 insertions(+), 21 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index a1f0cae9a8..06a3a86fb4 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -51,14 +51,17 @@ Waterfall events behave like around-middleware: a listener delegates by calling ## Default Loop Lifecycle -The shipped loop drains work, assembles requests, streams model answers, executes tools, applies continuation policy, and checkpoints state. Every pause is a service call or event available to plugins. +Default loop processing remains exposed through plugin-visible services and events. A **session** is one agent's append-only event log. A **turn** drains one queued batch and runs until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. +Declarative startup chooses one agent/session identity. No id mints `-session-`; exact `sessionId` resumes when stored and otherwise creates; `resumeSessionId` requires stored history. Failures emit `agent-loop/config-start-failed(sessionId, error)`, letting front doors reject buffered work. + ### Turn Flow ```text -prepare private session + agent.ctx -> await unpublished setup +choose declarative identity and fresh/resume path + -> prepare private session + agent.ctx -> await unpublished setup -> enter session + agent -> session/created -> agent/created -> enable driving -> agent/session-start(source) -> start driver forever: diff --git a/docs/config-catalog.md b/docs/config-catalog.md index d22bcca6f7..839e7967e6 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:333`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:344`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index a5e018079a..3c56882494 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -175,6 +175,18 @@ Types: [Agent](../core-data-structures/core.md) Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/types.ts) +## `agent-loop/*` + +### `agent-loop/config-start-failed` — emit + +A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. + +```ts cordis-catalog +'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void +``` + +Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) + ## `approval/*` ### `approval/request` — waterfall diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index e79422b94f..63375a46bf 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:359`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 1439873f69..0ab96fca31 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,6 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/docs/module-graph.md b/docs/module-graph.md index 8ac71b11cc..cc4cd86c47 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -316,6 +316,7 @@ flowchart TD pkg_acp_agent --> pkg_user_interaction pkg_stdio_agent --> pkg_agent pkg_stdio_agent --> pkg_agent_core + pkg_stdio_agent --> pkg_agent_loop pkg_stdio_agent --> pkg_app_boot pkg_stdio_agent --> pkg_llm pkg_stdio_agent --> pkg_session @@ -394,4 +395,4 @@ flowchart TD | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`acp-agent`](../packages/ui/acp-agent) | `ui` | [`acp`](../packages/ui/acp), [`agent-core`](../packages/core/agent-core), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | -| [`stdio-agent`](../packages/ui/stdio-agent) | `ui` | [`agent`](../packages/core/agent), [`agent-core`](../packages/core/agent-core), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | +| [`stdio-agent`](../packages/ui/stdio-agent) | `ui` | [`agent`](../packages/core/agent), [`agent-core`](../packages/core/agent-core), [`agent-loop`](../packages/core/agent-loop), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index ff27f51067..a9d1d5acaa 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -237,6 +237,12 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ /** Every harness event, sorted by name. */ export const EVENT_API: readonly EventApiEntry[] = [ + { + name: 'agent-loop/config-start-failed', + mode: 'emit', + signature: '\'agent-loop/config-start-failed\'(sessionId: SessionId, error: unknown): void', + summary: 'A declarative agent entry failed before it could publish a live agent.', + }, { name: 'agent/created', mode: 'emit', diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 2db1a6c079..2593da7c47 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. A declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index d2d8648595..62c5d94b06 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -327,6 +327,17 @@ declare module 'cordis' { interface Context { agentLoop: AgentLoop } + interface Events { + /** + * A declarative agent entry failed before it could publish a live agent. + * Consumers that buffer work for the configured identity use this + * transient signal to reject that work instead of waiting forever. + * @param sessionId - exact shared agent/session identity that failed startup. + * @param error - persistence, setup, or publication failure. + * @mode emit + */ + 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void + } } /** Plugin configuration for declarative startup agents. */ @@ -381,7 +392,7 @@ export class AgentLoop extends Service implements AgentFactory { this.create(configuredId, options, meta) } else { const startup = this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { - ctx.logger.warn(`agent "${id}": config-driven restore of "${configuredId}" failed: ${String(error)}`) + this.reportConfiguredStartupFailure(id, 'restore', configuredId, error) }) this.ownership.trackStartup(startup) } @@ -396,7 +407,7 @@ export class AgentLoop extends Service implements AgentFactory { resumeSessionId, agentOptions: options, }).catch((error: unknown) => { - ctx.logger.warn(`agent "${id}": config-driven resume of "${resumeSessionId}" failed: ${String(error)}`) + this.reportConfiguredStartupFailure(id, 'resume', resumeSessionId, error) }) }) return fiber.dispose @@ -404,6 +415,21 @@ export class AgentLoop extends Service implements AgentFactory { } } + /** Report a contained declarative-start failure to identity-bound consumers. */ + private reportConfiguredStartupFailure( + configId: string, + action: 'restore' | 'resume', + sessionId: SessionId, + error: unknown, + ): void { + this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${String(error)}`) + try { + this.ctx.emit('agent-loop/config-start-failed', sessionId, error) + } catch (listenerError) { + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + } + } + /** Restore a materialized exact config identity on remount, or create it on first use. */ private async restoreOrCreateConfigured( ownerCtx: Context, diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index c1a04fadd0..ad9ec6b792 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -98,6 +98,12 @@ describe('config-driven session id', () => { const ctx = await makeCoreContext() await ctx.plugin(SessionPersistenceJsonl, { root }) const failure = new Error('persistence index failed') + const listenerFailure = new Error('failure observer failed') + const failures: { sessionId: SessionId; error: unknown }[] = [] + ctx.on('agent-loop/config-start-failed', (sessionId, error) => { + failures.push({ sessionId, error }) + }) + ctx.on('agent-loop/config-start-failed', () => { throw listenerFailure }) vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(failure) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) @@ -108,6 +114,10 @@ describe('config-driven session id', () => { await expect.poll(() => warn).toHaveBeenCalledWith(expect.stringContaining( 'config-driven restore of "stdio-exact-failure" failed: Error: persistence index failed', )) + expect(failures).toEqual([{ sessionId: SessionId('stdio-exact-failure'), error: failure }]) + expect(warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener threw: Error: failure observer failed', + ) expect(ctx.agents.get(SessionId('stdio-exact-failure'))).toBeUndefined() warn.mockRestore() await ctx.fiber.dispose() diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index bbf175d92d..a91bef85a0 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. Readline buffers nonblank startup input for that identity until `agent/session-start`, so piped stdin cannot outrun asynchronous exact-id restoration or let EOF discard the queued prompt. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. Readline buffers nonblank startup input for that identity until `agent/session-start`, so piped stdin cannot outrun asynchronous exact-id restoration or let EOF discard the queued prompt; `agent-loop/config-start-failed` instead drains and reports buffered input so a missing or corrupt persisted session cannot hang EOF. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/package.json b/packages/ui/stdio-agent/package.json index fcd432a9fd..60a9529d47 100644 --- a/packages/ui/stdio-agent/package.json +++ b/packages/ui/stdio-agent/package.json @@ -35,6 +35,7 @@ "@deepseek-ai/dsh-app-boot": "^0.0.1", "@cordisjs/plugin-logger-console": "^1.0.0", "@deepseek-ai/dsh-agent": "^0.0.1", + "@deepseek-ai/dsh-agent-loop": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-agent-core": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", @@ -51,6 +52,7 @@ "@deepseek-ai/dsh-app-boot": "workspace:^", "@cordisjs/plugin-logger-console": "workspace:^", "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-agent-core": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 03f3d49555..1278ded88a 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -102,16 +102,23 @@ export const Config: z = z.object({ }) /** - * Compose the spine with the stdio front door. The console logger comes first - * (infra), then the agent-core bundle pre-creating one agent from this app's - * `model`/`resumeSessionId` with the deployment `persona`, then the JSONL - * backend, then the readline UI rendering that object as `main`. The `hmr` dev-reload plugin is - * a leaf concern (see the module doc), so it is not mounted here. + * Compose the spine with the stdio front door. Console logging, persistence, + * and user interaction mount first; the readline UI then waits on the agent + * registry and subscribes to config-start failures before agent-core can start + * the configured identity. The ask-user tool waits on the completed spine. + * The `hmr` dev-reload plugin is a leaf concern (see the module doc), so it is + * not mounted here. */ export function apply(ctx: Context, config: Config): void { const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId const sessionId = SessionId(resumeSessionId ?? `main-session-${randomUUID()}`) ctx.plugin(ConsoleExporter) + ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) + ctx.plugin(UserInteractionService) + ctx.plugin(uiStdio, { + welcome: config.welcome ?? 'ready.', + sessionId, + }) ctx.plugin(agentCore, { ...config.persona !== undefined ? { persona: config.persona } : {}, ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {}, @@ -124,11 +131,5 @@ export function apply(ctx: Context, config: Config): void { }], ...config.skills !== undefined ? { skills: config.skills } : {}, }) - ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) - ctx.plugin(UserInteractionService) ctx.plugin(toolAskUser) - ctx.plugin(uiStdio, { - welcome: config.welcome ?? 'ready.', - sessionId, - }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 17d396c042..39d59dfdc0 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -21,6 +21,7 @@ import type { Readable, Writable } from 'node:stream' import type { Context } from 'cordis' import z from 'schemastery' import type { Agent } from '@deepseek-ai/dsh-agent' +import type {} from '@deepseek-ai/dsh-agent-loop' import { UserInteractionError, type AskUserQuestionAnswer, @@ -173,6 +174,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const queuedInput: string[] = [] let targetReady = target !== undefined let hadReadyTarget = targetReady + let failedStartup: { error: unknown } | undefined const submit = (agent: Agent, text: string): void => { submittedWork = true @@ -187,6 +189,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt if (!matchesConfiguredIdentity(agent)) return target = agent targetReady = false + failedStartup = undefined }) const disposeSessionStartListener = ctx.on('agent/session-start', (agent) => { if (agent !== target) return @@ -220,6 +223,18 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt exitTimer = setTimeout(() => { exit(0) }, 200) } + const disposeStartupFailedListener = ctx.on('agent-loop/config-start-failed', (sessionId, error) => { + if (sessionId !== config.sessionId || targetReady) return + failedStartup = { error } + const dropped = queuedInput.length + queuedInput.length = 0 + submittedWork = sawRunning + if (dropped > 0) { + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (${dropped} line(s)): ${String(error)}`) + } + maybeExit() + }) + const disposeStatusListener = ctx.on('agent/status', (subject, status) => { if (subject !== target) return if (status === 'running') sawRunning = true @@ -374,6 +389,10 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt } const text = line.trim() if (!text) return + if (failedStartup !== undefined) { + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ${String(failedStartup.error)}`) + return + } const agent = target if (agent === undefined || !targetReady) { // Initial exact-id restoration is asynchronous. Preserve input until @@ -407,6 +426,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt disposeCreatedListener() disposeSessionStartListener() disposeDisposedListener() + disposeStartupFailedListener() reader.close() } }, 'ui-stdio') diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 943c48ef08..11e64ac19c 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -4,7 +4,7 @@ import { Context } from 'cordis' import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent' import AgentRegistry from '@deepseek-ai/dsh-agent' import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm' -import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' +import { SessionId, type Session, type SessionEvent } from '@deepseek-ai/dsh-session' import UserInteractionService from '@deepseek-ai/dsh-user-interaction' import { createStdioChat, type Config, type StdioRuntime } from '../src/stdio-chat.ts' @@ -750,6 +750,32 @@ describe('createStdioChat input', () => { expect(agent.sent).toEqual([[{ type: 'text', text: 'nobody home' }]]) }) + it('drops later input after the configured startup fails', async () => { + const { ctx, input } = await setup() + const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) + const failure = new Error('persisted session is corrupt') + ctx.emit('agent-loop/config-start-failed', SessionId('main'), failure) + + input.feed('cannot run') + await new Promise(r => setImmediate(r)) + + expect(error).toHaveBeenCalledWith( + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: persisted session is corrupt', + ) + }) + + it('ignores a stale config-start failure after the exact target is ready', async () => { + const { ctx, input } = await setup() + const agent = makeAgent('main') + registerReady(ctx, agent) + ctx.emit('agent-loop/config-start-failed', SessionId('main'), new Error('stale')) + + input.feed('still live') + await new Promise(r => setImmediate(r)) + + expect(agent.sent).toEqual([[{ type: 'text', text: 'still live' }]]) + }) + it('drives the exact app-configured resumed session', async () => { const { ctx, input } = await setup({ welcome: 'w', sessionId: 'worker' }) const agent = makeAgent('worker') @@ -808,6 +834,25 @@ describe('createStdioChat EOF exit', () => { expect(exit).toHaveBeenCalledWith(0) }) + it('drains buffered piped input and exits when configured startup fails', async () => { + const { ctx, input, exit } = await setup() + const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) + input.feed('work') + input.finish() + await new Promise(r => setImmediate(r)) + ctx.emit('agent-loop/config-start-failed', SessionId('other'), new Error('unrelated')) + await flushExit() + expect(exit).not.toHaveBeenCalled() + + ctx.emit('agent-loop/config-start-failed', SessionId('main'), new Error('missing persisted session')) + await flushExit() + + expect(error).toHaveBeenCalledWith( + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: missing persisted session', + ) + expect(exit).toHaveBeenCalledWith(0) + }) + it('schedules the exit only once when idle fires repeatedly', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'running') diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 6214564eae..7a8fe5a6ea 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1328,6 +1328,9 @@ importers: '@deepseek-ai/dsh-agent-core': specifier: workspace:^ version: link:../../core/agent-core + '@deepseek-ai/dsh-agent-loop': + specifier: workspace:^ + version: link:../../core/agent-loop '@deepseek-ai/dsh-app-boot': specifier: workspace:^ version: link:../app-boot From 7d6ef0a47260a096a7594e54c797fde9e1ba8ca0 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 11:33:36 +0800 Subject: [PATCH 092/359] fix: contain config failure observers --- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/src/index.ts | 14 ++++++++++---- .../agent-loop/tests/config-session-id.spec.ts | 7 ++++++- scripts/gen-doc-graphs.ts | 3 +++ 4 files changed, 20 insertions(+), 6 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 0ab96fca31..de89a69f18 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 62c5d94b06..5a7484a378 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -423,10 +423,16 @@ export class AgentLoop extends Service implements AgentFactory { error: unknown, ): void { this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${String(error)}`) - try { - this.ctx.emit('agent-loop/config-start-failed', sessionId, error) - } catch (listenerError) { - this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error] + for (const callback of this.ctx.events.dispatch('emit', args)) { + try { + const returned: unknown = callback(...args) + void Promise.resolve(returned).catch((listenerError: unknown) => { + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener rejected: ${String(listenerError)}`) + }) + } catch (listenerError: unknown) { + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + } } } diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index ad9ec6b792..a7292b2284 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -99,11 +99,13 @@ describe('config-driven session id', () => { await ctx.plugin(SessionPersistenceJsonl, { root }) const failure = new Error('persistence index failed') const listenerFailure = new Error('failure observer failed') + const asyncListenerFailure = new Error('async failure observer failed') const failures: { sessionId: SessionId; error: unknown }[] = [] + ctx.on('agent-loop/config-start-failed', () => { throw listenerFailure }) + ctx.on('agent-loop/config-start-failed', () => Promise.reject(asyncListenerFailure) as never) ctx.on('agent-loop/config-start-failed', (sessionId, error) => { failures.push({ sessionId, error }) }) - ctx.on('agent-loop/config-start-failed', () => { throw listenerFailure }) vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(failure) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) @@ -118,6 +120,9 @@ describe('config-driven session id', () => { expect(warn).toHaveBeenCalledWith( 'agent "main": config-start-failed listener threw: Error: failure observer failed', ) + await expect.poll(() => warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener rejected: Error: async failure observer failed', + ) expect(ctx.agents.get(SessionId('stdio-exact-failure'))).toBeUndefined() warn.mockRestore() await ctx.fiber.dispose() diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 5144e388a2..fa7daed85e 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -245,6 +245,9 @@ const DYNAMIC_EVENT_DISPATCHERS: Array<{ event: string; pkg: string; method: str // Registry disposal reuses the stable carrier captured before entry commit // and contains each listener directly rather than rebuilding via agentEvents. { event: 'agent/disposed', pkg: 'agent', method: 'events.dispatch' }, + // Config startup failures have no live Agent carrier; AgentLoop resolves the + // callbacks directly to contain each synchronous throw and async rejection. + { event: 'agent-loop/config-start-failed', pkg: 'agent-loop', method: 'events.dispatch' }, { event: 'session/created', pkg: 'session', method: 'events.dispatch' }, // Session event callbacks are likewise resolved before the log push, then // invoked individually after commit so observer failures are contained. From eae8b8ce2e9109d1bf827d7c3d2c2804c38d90d4 Mon Sep 17 00:00:00 2001 From: Dudu-0223 Date: Tue, 14 Jul 2026 11:55:39 +0800 Subject: [PATCH 093/359] feat(ui): configure maxParallelToolCalls for factory-created agents MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The acp and stdio-agent plugins only forwarded `model` into their created agents, so every factory/ACP deployment was pinned to the agent-loop default parallel cap with no cordis.yml override. Add a `maxParallelToolCalls` config field (positive-integer validated) to both, threaded through the existing per-agent options path — symmetric with `model`. --- docs/config-catalog.md | 12 ++++++++++++ packages/ui/acp/README.md | 1 + packages/ui/acp/src/index.ts | 16 +++++++++++++--- packages/ui/acp/tests/stream-update.spec.ts | 2 ++ packages/ui/stdio-agent/README.md | 1 + packages/ui/stdio-agent/src/index.ts | 10 ++++++++++ .../ui/stdio-agent/tests/stdio-agent.spec.ts | 11 +++++++++++ 7 files changed, 50 insertions(+), 3 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 3ef3f6fad7..0a242d31b1 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -18,6 +18,12 @@ Requires: `agents` · `sessions` · `sessionPersistence` · `tools` · `userInte export interface AcpConfig { /** Model name for created agents (must have a registered adapter). */ model?: string + /** + * Maximum tool calls each created agent runs concurrently within one assistant + * step (a positive integer; the agent loop defaults it when omitted). `1` + * preserves fully serial execution. + */ + maxParallelToolCalls?: number /** * Transport stream override. Production omits this (the plugin wires * `process.stdin`/`process.stdout` via `ndJsonStream`). Tests inject an @@ -591,6 +597,12 @@ Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-l export interface Config { /** Model name for the `main` agent (must have a registered adapter). */ model: string + /** + * Maximum tool calls the `main` agent runs concurrently within one assistant + * step (a positive integer; the agent loop defaults it when omitted). `1` + * preserves fully serial execution. + */ + maxParallelToolCalls?: number /** Deployment persona (the system-prompt plugin's `persona` config). */ persona?: string /** Explicit model-facing tool order (the system-prompt plugin's `toolOrder` config; see dsh-system-prompt). */ diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index f4947e5d25..1043b13004 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -15,6 +15,7 @@ It is a **client-driver / UI plugin**, the structured analogue of the readline ` | Key | Default | Meaning | |---|---|---| | `model` | — | Model name for created agents (must have a registered adapter). | +| `maxParallelToolCalls` | (agent-loop default) | Positive integer cap on tool calls each created agent runs concurrently within one assistant step; `1` is fully serial. | (No persona key: `dsh-system-prompt`'s own `persona` config supplies the global default section, so ACP-created agents render it without the bridge carrying prompt text. An agent-scoped same-name section may still shadow that default.) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 5a5ce9e51f..ade9e0ccd0 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -248,6 +248,12 @@ function stringArrayContent( export interface AcpConfig { /** Model name for created agents (must have a registered adapter). */ model?: string + /** + * Maximum tool calls each created agent runs concurrently within one assistant + * step (a positive integer; the agent loop defaults it when omitted). `1` + * preserves fully serial execution. + */ + maxParallelToolCalls?: number /** * Transport stream override. Production omits this (the plugin wires * `process.stdin`/`process.stdout` via `ndJsonStream`). Tests inject an @@ -260,6 +266,9 @@ export interface AcpConfig { export const Config: Schema = Schema.object({ model: Schema.string(), + // A positive integer; a bad value (0, negative, fractional) fails config + // validation here rather than being silently dropped from cordis.yml. + maxParallelToolCalls: Schema.number().step(1).min(1), }) /** @@ -1010,12 +1019,13 @@ export function apply(ctx: Context, config: AcpConfig): void { * Build per-agent options from the plugin config, omitting absent fields * (exactOptionalPropertyTypes: never assign `undefined` to an optional key). * Exported for unit coverage of both the present and absent branches. - * @param config - the plugin config carrying the optional model name. - * @returns the per-agent options, with `model` present only when configured. + * @param config - the plugin config carrying the optional model name and parallel cap. + * @returns the per-agent options, with each field present only when configured. */ -export function agentOptions(config: AcpConfig): { model?: string } { +export function agentOptions(config: AcpConfig): { model?: string; maxParallelToolCalls?: number } { return { ...config.model !== undefined ? { model: config.model } : {}, + ...config.maxParallelToolCalls !== undefined ? { maxParallelToolCalls: config.maxParallelToolCalls } : {}, } } diff --git a/packages/ui/acp/tests/stream-update.spec.ts b/packages/ui/acp/tests/stream-update.spec.ts index cb3eab3545..afd3e22686 100644 --- a/packages/ui/acp/tests/stream-update.spec.ts +++ b/packages/ui/acp/tests/stream-update.spec.ts @@ -818,5 +818,7 @@ describe('agentOptions', () => { it('includes only the fields present in config', () => { expect(agentOptions({})).toEqual({}) expect(agentOptions({ model: 'm' })).toEqual({ model: 'm' }) + expect(agentOptions({ maxParallelToolCalls: 3 })).toEqual({ maxParallelToolCalls: 3 }) + expect(agentOptions({ model: 'm', maxParallelToolCalls: 1 })).toEqual({ model: 'm', maxParallelToolCalls: 1 }) }) }) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 27f0d20be7..448089e904 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -26,6 +26,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | Key | Default | Routed to | |---|---|---| | `model` | (required) | the pre-created `main` agent's model | +| `maxParallelToolCalls` | (agent-loop default) | positive integer cap on tool calls the `main` agent runs concurrently within one assistant step (`1` is fully serial), routed to `dsh-agent-loop` | | `persona` | — | the deployment persona template (may reference `{{model}}`), routed to `dsh-system-prompt` | | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 1037c28112..6535c5b054 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -65,6 +65,12 @@ export const name = 'stdio-agent' export interface Config { /** Model name for the `main` agent (must have a registered adapter). */ model: string + /** + * Maximum tool calls the `main` agent runs concurrently within one assistant + * step (a positive integer; the agent loop defaults it when omitted). `1` + * preserves fully serial execution. + */ + maxParallelToolCalls?: number /** Deployment persona (the system-prompt plugin's `persona` config). */ persona?: string /** Explicit model-facing tool order (the system-prompt plugin's `toolOrder` config; see dsh-system-prompt). */ @@ -87,6 +93,9 @@ export interface Config { export const Config: z = z.object({ model: z.string().required(), + // A positive integer; a bad value (0, negative, fractional) fails config + // validation here rather than being silently dropped from cordis.yml. + maxParallelToolCalls: z.number().step(1).min(1), persona: z.string(), // The array default is forced to undefined: ABSENT means "lexicographic // order" (the owning dsh-system-prompt schema does the same), while @@ -116,6 +125,7 @@ export function apply(ctx: Context, config: Config): void { id: AgentId('main'), model: config.model, cwd: process.cwd(), + ...config.maxParallelToolCalls !== undefined ? { maxParallelToolCalls: config.maxParallelToolCalls } : {}, ...config.resumeSessionId !== undefined ? { resumeSessionId: SessionId(config.resumeSessionId) } : {}, }], ...config.skills !== undefined ? { skills: config.skills } : {}, diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 0668d25fb0..c5f9c075f6 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -136,6 +136,17 @@ describe('dsh-stdio-agent app', () => { await ctx.fiber.dispose() }) + it('forwards maxParallelToolCalls onto the pre-created agent when set', async () => { + const ctx = await mount({ + model: 'mock', + maxParallelToolCalls: 3, + persistenceRoot: '/tmp/dsh-stdio-agent-spec-parallel', + skills: await isolatedSkillsConfig(), + }) + expect(ctx.get('agents')?.get(AgentId('main'))?.options.maxParallelToolCalls).toBe(3) + await ctx.fiber.dispose() + }) + it('exposes its name and Config schema', () => { expect(stdioAgent.name).toBe('stdio-agent') expect(stdioAgent.Config).toBeDefined() From 5ab8f2e328f0f9b762b9a4fd1697786c681d868d Mon Sep 17 00:00:00 2001 From: Dudu-0223 Date: Tue, 14 Jul 2026 11:56:27 +0800 Subject: [PATCH 094/359] docs: correct fs/observed concurrency-safety wording The read tool's isConcurrencySafe rationale called the fs/observed recorder "commutative" and said concurrent reads "converge to one observed version", overstating the guarantee: the WeakMap record is last-writer-wins. Safety comes from write/edit re-checking the version in their in-lock CAS (a stale observation only forces a later edit to fail closed with FS_STALE_VERSION), as the RFC already states. Align the read comment, the ToolDefinition JSDoc, both READMEs, and the regenerated catalogs. --- docs/config-catalog.md | 2 +- docs/cordis-catalog/services.md | 2 +- docs/core-data-structures/tools.md | 6 ++++-- packages/core/tools/README.md | 2 +- packages/core/tools/src/index.ts | 6 ++++-- packages/fs/tool-fs/README.md | 2 +- packages/fs/tool-fs/src/read.ts | 10 ++++++---- 7 files changed, 18 insertions(+), 12 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 0a242d31b1..b06942002d 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -975,7 +975,7 @@ export interface Config { export type ToolPresentationMode = 'native' | 'code' | 'both' ``` -Source: [`packages/core/tools/src/index.ts:482`](../packages/core/tools/src/index.ts) +Source: [`packages/core/tools/src/index.ts:484`](../packages/core/tools/src/index.ts) ## `@deepseek-ai/dsh-user-approval` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index e8ab41247f..8b427f9bff 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -277,7 +277,7 @@ async execute(exec: ToolExecutionInput): Promise Types: [ToolDefinition](../core-data-structures/tools.md) · [ToolExecutionInput](../core-data-structures/tools.md) · [ToolExecutionMode](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) -Source: [`packages/core/tools/src/index.ts:574`](../../packages/core/tools/src/index.ts) +Source: [`packages/core/tools/src/index.ts:576`](../../packages/core/tools/src/index.ts) ## `ctx.userInteraction` — `UserInteractionService` diff --git a/docs/core-data-structures/tools.md b/docs/core-data-structures/tools.md index bc231d6b2e..2e4a269537 100644 --- a/docs/core-data-structures/tools.md +++ b/docs/core-data-structures/tools.md @@ -40,8 +40,10 @@ interface ToolDefinition extends ToolSchema { * step outputs are the returned content, `meta`, structured error, and * `additionalContext` carried through the loop's ordered post-execute path. * The narrow exception is a synchronous, side-effect-only recorder whose - * updates are commutative for concurrent calls by the same session (the - * `fs/observed` version recorder is the worked example). + * updates are commutative OR fail closed for concurrent calls by the same + * session (the `fs/observed` version recorder is the worked example: its + * WeakMap record is last-writer-wins, and a stale observation only makes a + * later write/edit fail closed at its in-lock version CAS). */ isConcurrencySafe?(args: unknown): boolean /** diff --git a/packages/core/tools/README.md b/packages/core/tools/README.md index 8866de6d8c..4f29f4b6e1 100644 --- a/packages/core/tools/README.md +++ b/packages/core/tools/README.md @@ -85,7 +85,7 @@ See `defineTool`, `validateArgs`, `ToolArgsError`, `SchemaSpec`, `InferArgs`, an `defineTool` also validates an optional `timeoutMs` at definition time when present: it must be a positive finite number, or the helper throws — the budget is attached to the produced `ToolDefinition` (for `@deepseek-ai/dsh-timeout-policy`) and never reaches the model. -`defineTool` also accepts an optional `isConcurrencySafe(args): boolean` — the per-call concurrency classifier the agent-loop scheduler reads via `executionMode`. `args` is the typed `InferArgs` shape. It is soft-validated exactly like the presenters: an arg mismatch yields `false` (the conservative exclusive default), never the hard `ToolArgsError`. Declaring `true` is a contract — the tool body must not mutate parent-owned async state (`exec.agent.session.append`, `agent.inject`) during `execute`; its only ordered outputs are the returned content, `meta`, error, and `additionalContext`. The one exception is a synchronous, side-effect-only commutative recorder (the `fs/observed` version recorder is the worked example); anything richer stays exclusive. Host-only, never model-visible. +`defineTool` also accepts an optional `isConcurrencySafe(args): boolean` — the per-call concurrency classifier the agent-loop scheduler reads via `executionMode`. `args` is the typed `InferArgs` shape. It is soft-validated exactly like the presenters: an arg mismatch yields `false` (the conservative exclusive default), never the hard `ToolArgsError`. Declaring `true` is a contract — the tool body must not mutate parent-owned async state (`exec.agent.session.append`, `agent.inject`) during `execute`; its only ordered outputs are the returned content, `meta`, error, and `additionalContext`. The one exception is a synchronous, side-effect-only recorder whose updates are commutative or fail closed (the `fs/observed` version recorder is the worked example: its record is last-writer-wins, and a stale observation only makes a later write/edit fail closed at its in-lock version CAS); anything richer stays exclusive. Host-only, never model-visible. ### Structured-output schema subset diff --git a/packages/core/tools/src/index.ts b/packages/core/tools/src/index.ts index f2eac7349b..0a26ff7089 100644 --- a/packages/core/tools/src/index.ts +++ b/packages/core/tools/src/index.ts @@ -217,8 +217,10 @@ export interface ToolDefinition extends ToolSchema { * step outputs are the returned content, `meta`, structured error, and * `additionalContext` carried through the loop's ordered post-execute path. * The narrow exception is a synchronous, side-effect-only recorder whose - * updates are commutative for concurrent calls by the same session (the - * `fs/observed` version recorder is the worked example). + * updates are commutative OR fail closed for concurrent calls by the same + * session (the `fs/observed` version recorder is the worked example: its + * WeakMap record is last-writer-wins, and a stale observation only makes a + * later write/edit fail closed at its in-lock version CAS). */ isConcurrencySafe?(args: unknown): boolean /** diff --git a/packages/fs/tool-fs/README.md b/packages/fs/tool-fs/README.md index 5817c0eb95..7cd9b3d641 100644 --- a/packages/fs/tool-fs/README.md +++ b/packages/fs/tool-fs/README.md @@ -46,6 +46,6 @@ The tool passes `exec` (the tool-execution context) as the opaque `actor` on eve `fs/observed` fires AFTER the read/write/edit already succeeded, via a plain `ctx.emit`. A listener is contractually a synchronous, side-effect-only recorder (`@deepseek-ai/dsh-fs-policy`'s is a `WeakMap.set`); the tool does not guard the emit, so a listener that throws would surface as the tool's `isError` result — async or fallible observation does not belong on this event. -This is exactly why `read` declares `isConcurrencySafe: () => true` while `write`/`edit` do not: `read`'s only side effect is that synchronous commutative recorder (same-target concurrent reads converge to one observed version), so the agent loop may run sibling reads in parallel. `write`/`edit` mutate the filesystem and stay exclusive barriers — the provider re-checks the observed version inside its per-target lock before mutating, so a stale read never corrupts (it only forces a re-read). See the [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md). +This is exactly why `read` declares `isConcurrencySafe: () => true` while `write`/`edit` do not: `read`'s only side effect is that synchronous version recorder (same-target concurrent reads race last-writer-wins on the observed version), so the agent loop may run sibling reads in parallel. `write`/`edit` mutate the filesystem and stay exclusive barriers — the provider re-checks the observed version inside its per-target lock before mutating, so a stale read never corrupts (it only forces a re-read via `FS_STALE_VERSION`). See the [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md). The read rendering (line windowing + output formatting) lives in `src/read-render.ts` (Cordis-free, independently unit-tested); `src/read.ts`/`write.ts`/`edit.ts` are the tool executors and `src/index.ts` composes them. diff --git a/packages/fs/tool-fs/src/read.ts b/packages/fs/tool-fs/src/read.ts index dc43177726..ad60dc7afb 100644 --- a/packages/fs/tool-fs/src/read.ts +++ b/packages/fs/tool-fs/src/read.ts @@ -92,10 +92,12 @@ export function applyReadTool(ctx: Context, caps: ReadToolCaps): void { offset: { type: 'number', description: '1-based first line to return. Defaults to 1.' }, limit: { type: 'number', description: `Maximum number of lines to return. Defaults to ${caps.limit}.` }, }, - // Read-only. Its one side effect is the synchronous, commutative `fs/observed` - // version recorder (a WeakMap write; see below and the fs-policy plugin), so - // concurrent same-target reads converge to one observed version. write/edit - // stay exclusive barriers and re-check versions in-lock before mutating. + // Read-only. Its one side effect is the synchronous `fs/observed` version + // recorder (a WeakMap write; see below and the fs-policy plugin): concurrent + // same-target reads race last-writer-wins on that record, which is safe because + // it is NOT the safety boundary — write/edit stay exclusive barriers and + // re-check the version in-lock, so a stale observation only makes a later edit + // fail closed with FS_STALE_VERSION. isConcurrencySafe: () => true, async execute(args, exec): Promise { const input = parseReadArgs(args, caps.limit) From a25c0f084f035f94a11292b17ec9a31e93349c2e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:25:30 +0800 Subject: [PATCH 095/359] fix: totalize configured startup failures --- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 2 +- docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/src/index.ts | 15 ++++++-- .../tests/config-session-id.spec.ts | 36 +++++++++++++++++++ 6 files changed, 52 insertions(+), 7 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index d7a973fd81..484ba1c632 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:344`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:353`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 088e60450d..e44df3c3b2 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -185,7 +185,7 @@ A declarative agent entry failed before it could publish a live agent. Consumers 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` -Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 8c00bd45ef..699c73fe2c 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:359`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:368`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 825f54b077..78a30bd4e1 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:348`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 5a7484a378..3c09ef2e7f 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -41,6 +41,15 @@ const INACTIVE_STATES: ReadonlySet = new Set([ FiberState.FAILED, ]) +/** Render an arbitrary thrown value without letting coercion escape containment. */ +function renderThrown(value: unknown): string { + try { + return String(value) + } catch { + return '' + } +} + /** Factory-level ownership of every preparing or live transaction. */ class FactoryOwnership { private accepting = true @@ -422,16 +431,16 @@ export class AgentLoop extends Service implements AgentFactory { sessionId: SessionId, error: unknown, ): void { - this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${String(error)}`) + this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${renderThrown(error)}`) const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error] for (const callback of this.ctx.events.dispatch('emit', args)) { try { const returned: unknown = callback(...args) void Promise.resolve(returned).catch((listenerError: unknown) => { - this.ctx.logger.warn(`agent "${configId}": config-start-failed listener rejected: ${String(listenerError)}`) + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener rejected: ${renderThrown(listenerError)}`) }) } catch (listenerError: unknown) { - this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${renderThrown(listenerError)}`) } } } diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index a7292b2284..b35dc71739 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -128,6 +128,42 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('contains startup and observer failures whose string coercion throws', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-unrenderable-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const unrenderable = { + [Symbol.toPrimitive](): never { + throw new Error('coercion escaped') + }, + } + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', () => { throw unrenderable }) + // Deliberately violate the normal Error-only rejection rule to exercise the unknown boundary. + // eslint-disable-next-line @typescript-eslint/prefer-promise-reject-errors + ctx.on('agent-loop/config-start-failed', () => Promise.reject(unrenderable) as never) + ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) + vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(unrenderable) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + + await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-unrenderable'), model: 'mock' }], + }) + + await expect.poll(() => failures).toEqual([unrenderable]) + expect(warn).toHaveBeenCalledWith( + 'agent "main": config-driven restore of "stdio-exact-unrenderable" failed: ', + ) + expect(warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener threw: ', + ) + await expect.poll(() => warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener rejected: ', + ) + await ctx.fiber.dispose() + }) + it('joins an exact-id persistence lookup before AgentLoop disposal completes', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) dirs.push(root) From 49e45ff184dbb1c5a293d83359afd0b8ce333f95 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:32:44 +0800 Subject: [PATCH 096/359] fix: reject legacy fallback headers --- docs/cordis-catalog/services.md | 2 +- docs/core-data-structures/session.md | 2 +- ...-12-simplify-session-log-representation.md | 2 +- packages/core/session/README.md | 2 +- packages/core/session/src/index.ts | 11 ++++++ .../core/session/tests/request-header.spec.ts | 14 ++++++++ .../tests/jsonl.spec.ts | 19 ++++++++++ .../tests/sqlite.spec.ts | 19 ++++++++++ .../session-persistence/src/coordinator.ts | 5 +++ .../tests/persistence.spec.ts | 36 +++++++++++++++++++ 10 files changed, 108 insertions(+), 4 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 05ecf9df56..9501a86c6b 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -245,7 +245,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:593`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:604`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index e4a508e4dd..b7fa0e126f 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -109,7 +109,7 @@ export interface EpochHeader { } ``` -Canonical form: an empty system prompt, an empty tool list, and an empty session prefix are absent fields, matching how requests are built. `messagePrefix` is the durable record of the `agent/session-prefix` waterfall's product (the request is `messagePrefix + derived history`); it is composed once per loop instance and included in every full snapshot that instance records. Legacy v0 logs containing the removed `request/header-delta` format are rejected at seed and persistence-load boundaries rather than replayed incompletely. +Canonical form: an empty system prompt, an empty tool list, and an empty session prefix are absent fields, matching how requests are built. `messagePrefix` is the durable record of the `agent/session-prefix` waterfall's product (the request is `messagePrefix + derived history`); it is composed once per loop instance and included in every full snapshot that instance records. Legacy v0 logs containing the removed `request/header-delta` event or its full-snapshot `fallback` reason are rejected at seed, append, and persistence-load boundaries rather than replayed incompletely. ## `SessionEvent` — one log entry diff --git a/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md b/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md index 4f4bf8d569..a1dfb5eafb 100644 --- a/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md +++ b/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md @@ -18,7 +18,7 @@ This proposal deliberately retains append and replacement `sourceEventSeqs`, cra Request headers use canonical full snapshots only. Initial and resume anchors remain full snapshots even when unchanged; an in-instance change appends another full `request/header` with reason `change`. The delta event, codec types, diff/apply helpers, and codec-only `fallback` reason are removed. Request reconstruction selects the latest snapshot. -`SESSION_FORMAT_VERSION` remains pinned at `0`, so seed and persistence-load validation explicitly reject an old v0 log containing `request/header-delta`. There is no compatibility fold or migration. JSONL and SQLite tests pin this fail-loud boundary, and the ACP snapshot harness represents legitimate mid-session changes as full pinned headers and full readable prompts. +`SESSION_FORMAT_VERSION` remains pinned at `0`, so seed, append, and persistence-load validation explicitly reject old v0 `request/header-delta` events and full snapshots carrying the removed `fallback` reason. There is no compatibility fold or migration. JSONL and SQLite tests pin this fail-loud boundary, and the ACP snapshot harness represents legitimate mid-session changes as full pinned headers and full readable prompts. ## Alternatives considered diff --git a/packages/core/session/README.md b/packages/core/session/README.md index ae168ad3eb..9f196c6d3d 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -53,7 +53,7 @@ Durable values need one accepted representation, not a check followed by a secon ### Request-header reconstruction (`request-header.ts`) -The `request/header` event records a full canonical `EpochHeader` snapshot with reason `initial`, `resume`, or `change`, making the request envelope logged session state and every conversation request a pure function of the log. `foldRequestHeader(events)` selects the latest snapshot from a log or prefix; `canonicalHeader` pins the one representation of absence (empty system/tools/messagePrefix ≡ absent fields), and `headerEquals` compares canonical headers. `EpochHeader.messagePrefix` is the durable record of the `agent/session-prefix` waterfall's product — composed once per loop instance, the request is `messagePrefix + derived history`, and `deriveMessages()` never returns it. Legacy v0 seeds containing the removed `request/header-delta` format are rejected rather than partially replayed. +The `request/header` event records a full canonical `EpochHeader` snapshot with reason `initial`, `resume`, or `change`, making the request envelope logged session state and every conversation request a pure function of the log. `foldRequestHeader(events)` selects the latest snapshot from a log or prefix; `canonicalHeader` pins the one representation of absence (empty system/tools/messagePrefix ≡ absent fields), and `headerEquals` compares canonical headers. `EpochHeader.messagePrefix` is the durable record of the `agent/session-prefix` waterfall's product — composed once per loop instance, the request is `messagePrefix + derived history`, and `deriveMessages()` never returns it. Legacy v0 seeds containing the removed `request/header-delta` event or its full-snapshot `fallback` reason are rejected rather than partially replayed. ### Session event vocabulary (`types.ts`) diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index f4a87e5a2f..11451811c3 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -212,6 +212,15 @@ function assertSessionEventEnvelope(value: Record, index: numbe } } +/** Reject request-header vocabulary removed with the legacy delta codec. */ +function assertSupportedRequestHeader(type: string, data: unknown, location: string): void { + if (type === 'request/header' + && data !== null && typeof data === 'object' && !Array.isArray(data) + && (data as Record)['reason'] === 'fallback') { + throw new Error(`${location} uses unsupported legacy request/header reason "fallback"`) + } +} + type SessionCallback = (...args: unknown[]) => unknown /** Resolve one listener snapshot, including Cordis's internal dispatch checks. */ @@ -306,6 +315,7 @@ export class Session { throw new Error(`seed event at index ${index} is not losslessly JSON-serializable`) } assertSessionEventEnvelope(snapshot, index) + assertSupportedRequestHeader(snapshot.type, snapshot.data, `seed event at index ${index}`) if (snapshot.seq !== index) { throw new Error(`seed event at index ${index} has seq ${snapshot.seq} (expected ${index}); seed must be contiguous from 0`) } @@ -391,6 +401,7 @@ export class Session { if (dataSnapshot === undefined) { throw new Error(`session event "${type}" carries non-JSON-serializable data`) } + assertSupportedRequestHeader(type, dataSnapshot, `session event "${type}"`) const surfaceMetadataSnapshot = snapshotJsonValue(surfaceMetadata) if (surfaceMetadataSnapshot === undefined) { throw new Error(`session event "${type}" carries non-JSON-serializable surface metadata`) diff --git a/packages/core/session/tests/request-header.spec.ts b/packages/core/session/tests/request-header.spec.ts index fa2acdda28..8bc2a4bf6c 100644 --- a/packages/core/session/tests/request-header.spec.ts +++ b/packages/core/session/tests/request-header.spec.ts @@ -68,4 +68,18 @@ describe('legacy request-header format', () => { }] as unknown as SessionEvent[] expect(() => new Session(SessionId('legacy'), legacy)).toThrow(/unsupported legacy request\/header-delta/) }) + + it('rejects the removed fallback reason in seeds and untyped appends', () => { + const legacy = [{ + type: 'request/header', seq: 0, time: 1, data: { header: { config: CONFIG }, reason: 'fallback' }, + }] as unknown as SessionEvent[] + expect(() => new Session(SessionId('legacy-seed-reason'), legacy)) + .toThrow('unsupported legacy request/header reason "fallback"') + + const session = new Session(SessionId('legacy-append-reason')) + const appendLegacy = session.append.bind(session) as (type: string, data: unknown) => SessionEvent + expect(() => appendLegacy('request/header', { header: { config: CONFIG }, reason: 'fallback' })) + .toThrow('unsupported legacy request/header reason "fallback"') + expect(session.events).toHaveLength(0) + }) }) diff --git a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts index b9bc0f8d9a..7c5febb88f 100644 --- a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts +++ b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts @@ -162,6 +162,25 @@ describe('SessionPersistenceJsonl: durability and crash semantics', () => { await expect(ctx.sessionPersistence.load(m.id)).rejects.toThrow(/unsupported legacy request\/header-delta event at seq 1/) }) + it('rejects a stored v0 full header carrying the legacy fallback reason', async () => { + const m = meta('legacy-header-fallback', '/legacy') + const path = logPath(root, m.cwd, m.id) + await mkdir(sessionDir(root, m.cwd), { recursive: true }) + await writeFile(path, [ + JSON.stringify(toHeaderLine(m)), + JSON.stringify({ + type: 'request/header', + seq: 0, + time: 1, + data: { header: { config: { model: 'legacy' } }, reason: 'fallback' }, + }), + '', + ].join('\n')) + + await expect(ctx.sessionPersistence.load(m.id)) + .rejects.toThrow(/unsupported legacy request\/header reason "fallback" at seq 0/) + }) + it('persists a forked child seed through the existing session write path', async () => { const source = ctx.sessions.create(SessionId('persist-parent'), { meta: { cwd: '/workspace' } }) appendClosedTurn(source) diff --git a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts index 12857d2cd8..15d2a44492 100644 --- a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts +++ b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts @@ -161,6 +161,25 @@ describe('SessionPersistenceSqlite: durability and crash semantics', () => { await mounted.dispose() }) + it('rejects a stored v0 full header carrying the legacy fallback reason', async () => { + const path = await freshDbPath() + const m = meta('legacy-header-fallback', '/legacy') + const db = openDatabase(path, 'wal') + db.prepare('INSERT INTO sessions (id, version, created_at, cwd, parent_session, seed_length) VALUES (?, ?, ?, ?, NULL, NULL)') + .run(m.id, m.version, m.createdAt, m.cwd ?? null) + db.prepare('INSERT INTO events (session_id, seq, type, time, data) VALUES (?, ?, ?, ?, ?)') + .run(m.id, 0, 'request/header', 1, JSON.stringify({ + header: { config: { model: 'legacy' } }, + reason: 'fallback', + })) + db.close() + + const mounted = await backend(path) + await expect(mounted.ctx.sessionPersistence.load(m.id)) + .rejects.toThrow(/unsupported legacy request\/header reason "fallback" at seq 0/) + await mounted.dispose() + }) + it('an interrupted turn (rows after the last turn/end) is PRESERVED and closed during load', async () => { const path = await freshDbPath() const m = meta('crash') diff --git a/packages/session-persistence/session-persistence/src/coordinator.ts b/packages/session-persistence/session-persistence/src/coordinator.ts index b80e4c8d23..e35a6e2e41 100644 --- a/packages/session-persistence/session-persistence/src/coordinator.ts +++ b/packages/session-persistence/session-persistence/src/coordinator.ts @@ -158,6 +158,11 @@ function assertSupportedEvents(events: readonly SessionEvent[], id: SessionId): if (legacy !== undefined) { throw new Error(`session "${id}" contains unsupported legacy request/header-delta event at seq ${legacy.seq}`) } + const fallback = events.find(event => event.type === 'request/header' + && (event.data as { reason?: string }).reason === 'fallback') + if (fallback !== undefined) { + throw new Error(`session "${id}" contains unsupported legacy request/header reason "fallback" at seq ${fallback.seq}`) + } } /** diff --git a/packages/session-persistence/session-persistence/tests/persistence.spec.ts b/packages/session-persistence/session-persistence/tests/persistence.spec.ts index a20d850d83..5d0ba2c607 100644 --- a/packages/session-persistence/session-persistence/tests/persistence.spec.ts +++ b/packages/session-persistence/session-persistence/tests/persistence.spec.ts @@ -22,6 +22,16 @@ function legacyHeaderDelta(seq = 0): SessionEvent { } as unknown as SessionEvent } +/** An obsolete full-header reason fixture from the removed delta codec. */ +function legacyFallbackHeader(seq = 0): SessionEvent { + return { + type: 'request/header', + seq, + time: 1, + data: { header: { config: { model: 'legacy' } }, reason: 'fallback' }, + } as unknown as SessionEvent +} + /** Optional plugin config: an EXTERNAL store shared across backend instances. */ interface MemoryConfig { store?: MemoryStore } @@ -190,6 +200,19 @@ describe('SessionPersistence service registration', () => { await fiber.dispose() }) + it('rejects a legacy fallback header buffered by a pre-change live producer', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + const fiber = await ctx.plugin(MemoryPersistence) + const session = ctx.sessions.create(SessionId('legacy-fallback-live'), { meta: { cwd: '/legacy' } }) + const appendLegacy = session.append.bind(session) as (type: string, data: unknown) => SessionEvent + + expect(() => appendLegacy('request/header', legacyFallbackHeader().data)) + .toThrow('unsupported legacy request/header reason "fallback"') + expect(session.events).toHaveLength(0) + await fiber.dispose() + }) + it('rejects a legacy stored prefix during live HMR adoption', async () => { const id = SessionId('legacy-hmr') const m = meta(id, '/legacy') @@ -207,4 +230,17 @@ describe('SessionPersistence service registration', () => { .rejects.toThrow(/unsupported legacy request\/header-delta event at seq 0/) await Promise.allSettled([fiber.dispose()]) }) + + it('rejects a stored legacy fallback header during load', async () => { + const id = SessionId('legacy-fallback-load') + const m = meta(id, '/legacy') + const store: MemoryStore = new Map([[id, { meta: m, events: [legacyFallbackHeader()] }]]) + const ctx = new Context() + await ctx.plugin(SessionStore) + const fiber = await ctx.plugin(MemoryPersistence, { store }) + + await expect(ctx.sessionPersistence.load(id)) + .rejects.toThrow('unsupported legacy request/header reason "fallback" at seq 0') + await fiber.dispose() + }) }) From 287041e39e93b368646f0fe8298b65feab692acc Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:35:25 +0800 Subject: [PATCH 097/359] fix: preserve malformed snapshot fixtures --- packages/support/acp-snapshot/src/suite.ts | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts index 4d87093c8a..906521c42d 100644 --- a/packages/support/acp-snapshot/src/suite.ts +++ b/packages/support/acp-snapshot/src/suite.ts @@ -486,8 +486,10 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { const entries = await readdir(dir, { withFileTypes: true }) await Promise.all(entries .filter(entry => entry.isFile() - && entry.name.startsWith('session.') - && entry.name.endsWith('.jsonl') + // Only valid numbered children are record-owned stale output. + // Malformed session-like names stay for the inventory guard to + // reject instead of being silently deleted during mutation. + && /^session\.[1-9]\d*\.jsonl$/.test(entry.name) && !outputNames.has(entry.name)) .map(entry => rm(join(dir, entry.name)))) fixtureFiles = outputFixtureFiles From 2027c70a17661fe2b8b5aab1685cd443ac2c3b56 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:38:32 +0800 Subject: [PATCH 098/359] fix: drain failed ACP launches --- packages/support/acp-snapshot/src/launcher.ts | 4 +++- packages/support/acp-snapshot/tests/harness.spec.ts | 9 +++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 3f9a21d596..30ca0b42b8 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -178,13 +178,14 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // `closed` follows parser exhaustion. Capture both eagerly so a caller that // invokes close after process exit still joins the complete drain boundary. const stdioClosed = new Promise(resolve => child.once('close', () => { resolve() })) - const drained = Promise.all([stdioClosed, client.closed]).then(async () => { + const drained = Promise.allSettled([stdioClosed, client.closed]).then(async ([, clientResult]) => { // The ACP SDK's readable loop dispatches client callbacks without awaiting // them. Once `closed` settles no new callbacks can start, but callbacks // already in flight still belong to this launch's teardown boundary. while (inFlightClientCallbacks.size > 0) { await Promise.allSettled([...inFlightClientCallbacks]) } + if (clientResult.status === 'rejected') throw clientResult.reason }) // A caller may await a pending update without calling close(). Make natural // stream exhaustion terminal for those waiters too, but only after the @@ -206,6 +207,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe try { await spawned } catch (error: unknown) { + await drained.catch(() => undefined) closeUpdateStream() throw error } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index ff7c304121..6adb0d4268 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -62,8 +62,17 @@ describe('runScenario', () => { it('surfaces an asynchronous child spawn failure through startup and close', async () => { const { dir } = await scenario({}) const launched = launchAcpTestAgent({ agent: AGENT, cwd: join(dir, 'missing') }) + let stdioClosed = false + let clientClosed = false + launched.child.once('close', () => { stdioClosed = true }) + void launched.client.closed.then( + () => { clientClosed = true }, + () => { clientClosed = true }, + ) await expect(launched.spawned).rejects.toMatchObject({ code: 'ENOENT' }) await expect(launched.close()).rejects.toMatchObject({ code: 'ENOENT' }) + expect(stdioClosed).toBe(true) + expect(clientClosed).toBe(true) }) it('centralizes ACP boot, captures, updates, fail-closed permissions, and shutdown', { timeout: 20_000 }, async () => { From 9f9f83c11f0ba190da488156efb015e3f7d921f4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:40:22 +0800 Subject: [PATCH 099/359] docs: align compaction output contract --- packages/compact/compact/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index fafcad76b8..adad9cfdfa 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -10,7 +10,7 @@ This package is the interface tier of the compaction capability, split so each c | `@deepseek-ai/dsh-compact-basic` (deferred) | a backend: chars-per-token estimation (`charsPerToken`, default 4) + token-budget retention + `llm.stream()` summarization | | `@deepseek-ai/dsh-tool-compact` (deferred) | the model-facing `/compact` tool over `ctx.compact` | -Unlike the bash seam, this interface depends on `@deepseek-ai/dsh-session` and `@deepseek-ai/dsh-llm` — the contract's verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so they cannot be expressed without naming those packages. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). +Unlike the bash seam, this interface depends on `@deepseek-ai/dsh-session` and `@deepseek-ai/dsh-llm` — the contract's verbs are defined over a `Session`, and its durable `compact/summary` event uses the `ContentBlock` vocabulary, so they cannot be expressed without naming those packages. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). ## Service API (`ctx.compact`) From b47e4c5276604dd1e5a400f5f60d2c16e195df10 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:45:12 +0800 Subject: [PATCH 100/359] fix: suppress teardown startup failures --- docs/architecture.md | 2 +- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 4 ++-- docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/index.ts | 4 +++- packages/core/agent-loop/tests/config-session-id.spec.ts | 5 ++++- 8 files changed, 14 insertions(+), 9 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index 41ab5c716b..0eb7f1fe55 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -56,7 +56,7 @@ Default loop processing remains exposed through plugin-visible services and even A **session** is an append-only event log. A **turn** drains queued input until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. -Startup resolves one identity. No id mints `-session-`; `sessionId` resumes stored or creates; `resumeSessionId` requires history. Failures emit `agent-loop/config-start-failed(sessionId, error)`, so front doors reject buffered work. +Startup resolves identity. No id mints `-session-`; `sessionId` resumes or creates; `resumeSessionId` requires history. Active failures emit `agent-loop/config-start-failed(sessionId, error)`, so front doors reject work; teardown stays silent. ### Turn Flow diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 484ba1c632..173806572a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:353`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:354`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index e44df3c3b2..df3aec8b12 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -179,13 +179,13 @@ Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/t ### `agent-loop/config-start-failed` — emit -A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. +A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. Normal factory teardown suppresses failures from the cancelled startup attempt. ```ts cordis-catalog 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` -Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:349`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 965a640966..74496739e2 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:368`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:369`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 78a30bd4e1..cc155ebb16 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:348`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:349`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 2593da7c47..e27e8b625a 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. A declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 3c09ef2e7f..06c108d324 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -340,7 +340,8 @@ declare module 'cordis' { /** * A declarative agent entry failed before it could publish a live agent. * Consumers that buffer work for the configured identity use this - * transient signal to reject that work instead of waiting forever. + * transient signal to reject that work instead of waiting forever. Normal + * factory teardown suppresses failures from the cancelled startup attempt. * @param sessionId - exact shared agent/session identity that failed startup. * @param error - persistence, setup, or publication failure. * @mode emit @@ -431,6 +432,7 @@ export class AgentLoop extends Service implements AgentFactory { sessionId: SessionId, error: unknown, ): void { + if (!this.ownership.isActive()) return this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${renderThrown(error)}`) const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error] for (const callback of this.ctx.events.dispatch('emit', args)) { diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index b35dc71739..53782fe03c 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -172,6 +172,8 @@ describe('config-driven session id', () => { const listing = Promise.withResolvers>>() vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) const loop = await ctx.plugin(AgentLoop, { agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], @@ -181,9 +183,10 @@ describe('config-driven session id', () => { await Promise.resolve() expect(disposed).toBe(false) - listing.resolve([]) + listing.reject(new Error('startup cancelled by teardown')) await disposal expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() + expect(failures).toEqual([]) expect(warn).not.toHaveBeenCalled() warn.mockRestore() await ctx.fiber.dispose() From 1f2c85c854985384febdf6829cc3d9eb2181b3ed Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 13:47:44 +0800 Subject: [PATCH 101/359] test: await fresh stdio agent publication --- packages/ui/stdio-agent/tests/stdio-agent.spec.ts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index a14848a549..4d555f5965 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -85,6 +85,7 @@ describe('dsh-stdio-agent app', () => { expect(ctx.get('tools')?.get('ask_user_question')).toBeDefined() // The sole pre-created agent the UI drives. `main` is its stable config // label; each fresh process mints a durable combined agent/session id. + await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) const agent = ctx.get('agents')?.list()[0] expect(agent).toBeDefined() expect(agent?.id).toBe(agent?.session.id) @@ -100,6 +101,7 @@ describe('dsh-stdio-agent app', () => { persistenceRoot: '/tmp/dsh-stdio-agent-spec-empty-resume', skills: await isolatedSkillsConfig(), }) + await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) const agent = ctx.get('agents')?.list()[0] expect(agent?.id).toMatch(/^main-session-[0-9a-f-]{36}$/) expect(agent?.id).toBe(agent?.session.id) From dbe65e1d13fb8c4d482177b60fab7cd552c1facc Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Tue, 14 Jul 2026 13:49:36 +0800 Subject: [PATCH 102/359] Unify session surface validation --- docs/cordis-catalog/services.md | 2 +- docs/core-data-structures/session-query.md | 1 - .../2026-07-13-session-query-tracing.md | 2 +- packages/core/session/README.md | 7 +- packages/core/session/src/index.ts | 57 ++-- packages/core/session/src/surface.ts | 312 +++++++++--------- packages/core/session/tests/session.spec.ts | 27 +- packages/core/session/tests/surface.spec.ts | 125 ++++--- .../core/session/tests/tool-pairing.spec.ts | 3 +- .../session-query/session-query/README.md | 4 +- .../session-query/session-query/src/config.ts | 1 - .../session-query/src/tracing.ts | 34 +- .../session-query/tests/session-query.spec.ts | 14 +- .../session-query/tests/tracing.spec.ts | 12 +- packages/support/invariants/README.md | 3 +- packages/support/invariants/src/index.ts | 91 +---- .../invariants/tests/invariants.spec.ts | 37 +-- 17 files changed, 327 insertions(+), 405 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index e62a96a7bb..b948ea898f 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -247,7 +247,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:557`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:550`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` diff --git a/docs/core-data-structures/session-query.md b/docs/core-data-structures/session-query.md index 71fb956dcb..86d2259f7f 100644 --- a/docs/core-data-structures/session-query.md +++ b/docs/core-data-structures/session-query.md @@ -112,7 +112,6 @@ export type SessionQueryErrorCode = | 'SESSION_QUERY_EVENT_NOT_FOUND' | 'SESSION_QUERY_INVALID_CONFIG' | 'SESSION_QUERY_INVALID_LINEAGE' - | 'SESSION_QUERY_INVALID_PROVENANCE' | 'SESSION_QUERY_INVALID_SURFACE' | 'SESSION_QUERY_INVALID_WINDOW' | 'SESSION_QUERY_PERSISTENCE_FAILED' diff --git a/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md b/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md index ff2e9b7c23..9ebb8ee961 100644 --- a/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md +++ b/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md @@ -16,7 +16,7 @@ Session relationships are encoded across immutable headers, positional surface o ## Validation boundary -Event tracing checks target existence before surface analysis. Before returning a trace it validates the whole loaded log through `dsh-session`'s shared surface-metadata checker: surface markers obey event-type eligibility, provenance belongs only to surface event types, present arrays are nonempty and duplicate-free, every source is a known earlier seq, and every positional replacement names all surface nodes it removed. Surface-marker and positional-fold failures use `SESSION_QUERY_INVALID_SURFACE`; provenance failures use `SESSION_QUERY_INVALID_PROVENANCE`. `listEvents()` remains a surface-classification operation and does not acquire trace-specific provenance rejection. +Event tracing checks target existence before surface analysis. Both event listing and tracing then use `dsh-session`'s one-pass surface fold, which accepts or rejects the loaded log as a whole: surface markers obey event-type eligibility, provenance belongs only to surface event types, present arrays are nonempty and duplicate-free, every source is a known earlier seq, and every positional replacement names and cites all surface nodes it removes. Every contract failure uses `SESSION_QUERY_INVALID_SURFACE`; there is no weaker classification-only surface standard. All returned records and arrays are detached. A known live event trace never consults persistence; persisted event traces preserve the exact-read list/load consistency check. Session lineage is necessarily a cross-corpus operation and therefore preserves cross-corpus persistence failure semantics. diff --git a/packages/core/session/README.md b/packages/core/session/README.md index fc7e6d4300..7632212621 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -32,10 +32,10 @@ The store pairs announced creation with disposal, publishes each append, and pro Plain class (not a Cordis Service). Create via `ctx.sessions.create()`. -- `session.append(type, data, opts?): SessionEvent` — synchronous, never blocks on I/O. At this durable boundary, data and surface metadata are lossless-JSON snapshotted and deep-frozen. For an attached session, a reentrant append during dispatch/observer publication rejects, and detach waits for that publication to unwind. Callbacks resolve before the log push; the push is the commit point, after which each observer failure is contained independently. Runtime surface validation covers widened unions and raw seed/load logs. +- `session.append(type, data, opts?): SessionEvent` — synchronous, never blocks on I/O. At this durable boundary, data and surface metadata are lossless-JSON snapshotted and deep-frozen, then the same atomic surface transition used by replay validates marker shape, provenance, and complete replacement coverage before the log changes. For an attached session, a reentrant append during dispatch/observer publication rejects, and detach waits for that publication to unwind. Callbacks resolve before the log push; the push is the commit point, after which each observer failure is contained independently. - `session.deriveMessages(): Message[]` — the LLM message history, CACHED: each surface node is projected exactly once, when first seen (O(new nodes) per call; a surface rewrite rebuilds via `surface.replaceGeneration`). Returns a fresh array per call over shared, deep-frozen `Message` objects. Each projection reuses the already deep-frozen content in its durable log event, so no second deep clone is needed and a consumer still cannot mutate logged data. The surface is the single source of derived history — there is no raw-log fallback. - `session.deriveEventMessage(event): Message | null` — the per-event projection `deriveMessages()` folds: a fresh message wrapper that reuses the event's already frozen content, or `null` when the event produces none (a non-surface event, or an empty-content `assistant/message` hosting only usage). External reconstructors and the dev invariant fold the same function over a log prefix's surface, so no two paths can disagree about what a request's messages were (the reconstructability RFC). -- `session.surface: SurfaceManager` — the derived surface, lazily rebuilt from `surfaceOp` markers in the log. Processes only new events (delta) on each access — the log is append-only, so prior events never change. `surface.replaceGeneration` is the rewrite signal: bumped by every folded `replace` and by `invalidate()`, never reset, so an incremental consumer comparing generations cannot be fooled. +- `session.surface: SurfaceManager` — the derived surface, lazily rebuilt from `surfaceOp` markers in the log. It processes only new events (delta) on each access; event acceptance uses a separate manager with the same transition so validation does not eagerly mutate this public view. `surface.replaceGeneration` is the rewrite signal: bumped by every folded `replace` and by `invalidate()`, never reset, so an incremental consumer comparing generations cannot be fooled. - `session.events` — a cached, frozen array snapshot over deep-frozen events. Repeated reads without an append return the same array; an append invalidates the cache and the next read returns a new snapshot, while earlier snapshots stay unchanged. Neither a cast nor a retained reference can push into the live log or rewrite an accepted event. - `session.seq`, `session.id` — current sequence and readonly typed identity. - `session.header: SessionHeader` — detached, deep-frozen creation metadata (`version`, `id`, `createdAt`, optional `cwd`/`parentSession`/`seedLength`). Construction validates the durable record and requires its id to match `session.id`. @@ -49,8 +49,7 @@ Durable values need one accepted representation, not a check followed by a secon - `SurfaceOp` — how a surface node entered the linked list: `'append'` (normal tail append) or `{ op: 'replace', start, end }` (replace nodes from `start` through `end` inclusive — both must be valid surface node seqs; `start === end` replaces a single node). Used by compaction to shadow old nodes without deleting them. - `SurfaceIntent` — `{ surfaceOp: SurfaceOp; sourceEventSeqs?: number[] }`, the required third parameter to `session.append()` for surface-eligible types. - `SurfaceNode` — `{ seq: number; prev: number | null; next: number | null }`, one node in the surface linked list. -- `foldSurface(events)` — replay the canonical surface transitions into detached current nodes and actual replacement ranges, rejecting misplaced, missing, malformed, or positionally invalid `surfaceOp` metadata while leaving provenance validation to callers. `SurfaceManager` shares the same transitions while retaining its incremental cache. -- `validateSurfaceMetadata(event, knownSeqs?, shadowedSeqs?)` — canonical structural and provenance check shared by session acceptance, surface folding, incremental invariants, and exact readers. It tags violations as `surface` or `provenance` so callers retain their error taxonomy; omit `knownSeqs` for local shape validation only. +- `foldSurface(events)` — replay the one canonical surface contract into detached current nodes and actual replacement ranges. The same pass rejects misplaced or malformed metadata, empty or duplicate provenance, unknown or non-earlier sources, invalid positional ranges, and replacements that fail to cite every shadowed surface node; `SurfaceManager` shares the atomic transition while retaining its incremental cache. - `isSurfaceEvent(event)` / `isSurfaceEligibleType(type)` — the first narrows a `SessionEvent` to a fully-formed surface node (type is surface-eligible AND `surfaceOp` present); the second is the type-only check (is this one of the five `SurfaceEventType` values?), used to detect a surface-eligible event MISSING its marker — e.g. when validating a seed/load log. ### Request-header reconstruction (`request-header.ts`) diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index 88b3c15aff..fc3a7fcd29 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -15,7 +15,7 @@ import type { ContentBlock, Message, MessageSource } from '@deepseek-ai/dsh-llm' import { SESSION_FORMAT_VERSION, SessionId } from './types.ts' import type { CreateSessionOptions, EpochHeader, SessionEvent, SessionEventMap, SessionEventType, SessionHeader, SurfaceIntent, SurfaceEventType } from './types.ts' import { snapshotJsonValue } from './json.ts' -import { SurfaceManager, validateSurfaceMetadata } from './surface.ts' +import { SurfaceManager } from './surface.ts' import { foldRequestHeader } from './request-header.ts' export * from './types.ts' @@ -23,7 +23,7 @@ export { isJsonValue, snapshotJsonValue } from './json.ts' export type { JsonValue } from './json.ts' export { interruptedTurnClosers } from './repair.ts' export type { SurfaceFoldReplacement, SurfaceFoldResult, SurfaceNode } from './surface.ts' -export { foldSurface, isSurfaceEvent, isSurfaceEligibleType, validateSurfaceMetadata } from './surface.ts' +export { foldSurface, isSurfaceEvent, isSurfaceEligibleType } from './surface.ts' export { isToolPairingBalanced } from './tool-pairing.ts' export { applyHeaderDelta, canonicalHeader, diffHeader, foldRequestHeader, headerEquals } from './request-header.ts' @@ -223,13 +223,15 @@ const attachments = new WeakMap() */ export class Session { private log: SessionEvent[] = [] + /** Incremental acceptance state, kept separate from the public lazy view. */ + private readonly surfaceValidator = new SurfaceManager(this.log) /** * Derived surface — a cached linked list of message-producing events. * Lazily rebuilt from `surfaceOp` markers in the log; processes only new * events (delta) on each access — the log is append-only, so prior events * never change. - * `append`. Undefined until first accessed (including after fork/seed). + * Undefined until first accessed (including after fork/seed). */ private _surface: SurfaceManager | undefined @@ -258,7 +260,7 @@ export class Session { // `seq = log.length` contract the whole system relies on). Without this, // a bad seed would surface only later as a backend rejection or a silent // divergence between the live log and disk. - this.log = Array.from(seed, (source, index) => { + for (const [index, source] of seed.entries()) { // The seed is a persistence/replay boundary: validate and detach the // complete event in one lossless-JSON pass. const snapshot = snapshotJsonValue(source) @@ -269,23 +271,16 @@ export class Session { if (snapshot.seq !== index) { throw new Error(`seed event at index ${index} has seq ${snapshot.seq} (expected ${index}); seed must be contiguous from 0`) } - // Surface-eligible events MUST carry a surfaceOp marker — the surface is - // the sole source of derived history, so a marker-less message event - // would load fine yet vanish from deriveMessages(). `append` enforces - // this at compile time via its typed overload; a seed arrives as raw - // SessionEvent[] (replay/fork/load), bypassing that, so re-check at - // runtime here rather than silently resuming with empty history. - let violation: ReturnType + // A seed is accepted incrementally through the same transition as a + // live append and a full-log fold. The candidate is planned before it + // enters `log`, so a failure cannot partially mutate the surface. try { - violation = validateSurfaceMetadata(snapshot) + this.surfaceValidator.validateNext(snapshot) } catch (error: unknown) { throw new Error(`invalid seed event at index ${index}: ${error instanceof Error ? error.message : 'invalid surface metadata'}`) } - if (violation !== undefined) { - throw new Error(`invalid seed event at index ${index}: ${violation.message}`) - } - return deepFreeze(snapshot) - }) + this.log.push(deepFreeze(snapshot)) + } } this.header = snapshotSessionHeader(id, header) } @@ -332,7 +327,10 @@ export class Session { * @throws if `data` or surface metadata is not losslessly JSON-serializable * (BigInt, function, symbol, undefined, negative zero, non-finite number, * circular reference, sparse array, or an exotic object such as - * Map/Set/Date/class instance). One recursive pass reads, validates, and + * Map/Set/Date/class instance), or when the candidate violates the + * canonical surface contract (marker shape and eligibility, unique known + * earlier provenance, positional replacement validity, and complete + * shadowed-node coverage). One recursive pass reads, validates, and * copies each nested value once, so a stateful getter cannot supply one value * to validation and another to storage. The event log is the durable source * of truth, so a bad event fails at the append site rather than later during @@ -358,26 +356,21 @@ export class Session { if (surfaceMetadataSnapshot === undefined) { throw new Error(`session event "${type}" carries non-JSON-serializable surface metadata`) } - const surfaceViolation = validateSurfaceMetadata({ - type, - seq: this.log.length, - ...(surfaceMetadataSnapshot as { surfaceOp?: unknown; sourceEventSeqs?: unknown }), - }) - if (surfaceViolation !== undefined) throw new Error(surfaceViolation.message) - const entry = attachments.get(this) if (entry?.appending) { throw new Error('session append cannot reenter while another append is being published') } + const event = deepFreeze({ + type, + seq: this.log.length, + time: Date.now(), + data: dataSnapshot, + ...(surfaceMetadataSnapshot as { surfaceOp?: unknown; sourceEventSeqs?: unknown }), + } as unknown as SessionEvent) + this.surfaceValidator.validateNext(event as SessionEvent) + if (entry !== undefined) entry.appending = true try { - const event = deepFreeze({ - type, - seq: this.log.length, - time: Date.now(), - data: dataSnapshot, - ...surfaceMetadataSnapshot, - } as unknown as SessionEvent) let callbacks: SessionCallback[] | undefined const callbackArgs: unknown[] = [this, event] if (entry !== undefined) { diff --git a/packages/core/session/src/surface.ts b/packages/core/session/src/surface.ts index c8642d18fc..7e1da76832 100644 --- a/packages/core/session/src/surface.ts +++ b/packages/core/session/src/surface.ts @@ -81,165 +81,118 @@ export interface SurfaceFoldResult { replacements: SurfaceFoldReplacement[] } -/** - * Validate one event's surface metadata through the canonical structural and - * provenance contract. Structural validation always runs; when `knownSeqs` is - * supplied, provenance must additionally name unique known earlier events and - * cover every shadowed surface node. The tagged result lets callers retain - * their own surface-versus-provenance error taxonomy. - * @param event - event whose `surfaceOp` and `sourceEventSeqs` are being checked. - * @param knownSeqs - seqs preceding `event`, or `undefined` for local shape validation only. - * @param shadowedSeqs - surface nodes directly removed by this event. - * @returns the first tagged contract violation, or `undefined` when valid. - */ -export function validateSurfaceMetadata( - event: Pick & { - surfaceOp?: unknown - sourceEventSeqs?: unknown - }, - knownSeqs?: ReadonlySet, - shadowedSeqs: readonly number[] = [], -): { kind: 'surface' | 'provenance'; message: string } | undefined { - const eligible = isSurfaceEligibleType(event.type) - const surfaceOp = event.surfaceOp - const sources = event.sourceEventSeqs - - if (!eligible && surfaceOp !== undefined) { - return { - kind: 'surface', - message: `session event "${event.type}" is not surface-eligible and cannot carry surfaceOp`, - } - } - if (eligible && surfaceOp === undefined) { - return { - kind: 'surface', - message: `session event "${event.type}" is surface-eligible and requires a surfaceOp marker`, - } - } - if (surfaceOp !== undefined && surfaceOp !== 'append') { - if (surfaceOp === null || typeof surfaceOp !== 'object' || Array.isArray(surfaceOp)) { - return { - kind: 'surface', - message: `session event "${event.type}" carries an invalid surfaceOp`, - } - } - const op = surfaceOp as Record - const keys = Object.keys(op) - if (keys.length !== 3 || !Object.hasOwn(op, 'op') || !Object.hasOwn(op, 'start') || !Object.hasOwn(op, 'end') - || op['op'] !== 'replace' - || typeof op['start'] !== 'number' || !Number.isSafeInteger(op['start']) || op['start'] < 0 - || typeof op['end'] !== 'number' || !Number.isSafeInteger(op['end']) || op['end'] < 0) { - return { - kind: 'surface', - message: `session event "${event.type}" carries an invalid replace surfaceOp`, - } - } - } - - if (sources !== undefined && !eligible) { - return { - kind: 'provenance', - message: `${event.type} cannot carry sourceEventSeqs (non-surface event)`, - } - } - if (sources !== undefined && !Array.isArray(sources)) { - return { - kind: 'provenance', - message: `sourceEventSeqs on event at seq ${event.seq} must be an array when present`, - } - } - if (Array.isArray(sources) - && sources.some(source => typeof source !== 'number' || !Number.isSafeInteger(source) || source < 0)) { - return { - kind: 'provenance', - message: `session event "${event.type}" sourceEventSeqs must contain non-negative safe integers`, - } - } - if (knownSeqs === undefined) return - - const sourceSeqs = sources as number[] | undefined - if (sourceSeqs !== undefined && sourceSeqs.length === 0) { - return { kind: 'provenance', message: 'sourceEventSeqs must not be empty when present' } - } - - const unique = new Set() - for (const source of sourceSeqs ?? []) { - if (unique.has(source)) { - return { kind: 'provenance', message: 'sourceEventSeqs must not contain duplicates' } - } - unique.add(source) - if (source >= event.seq) { - return { - kind: 'provenance', - message: `sourceEventSeqs must reference earlier events: ${source} >= current seq ${event.seq}`, - } - } - if (!knownSeqs.has(source)) { - return { kind: 'provenance', message: `sourceEventSeqs references unknown seq ${source}` } - } - } - - const sourceSet = new Set(sourceSeqs ?? []) - const missing = shadowedSeqs.filter(seq => !sourceSet.has(seq)) - if (missing.length > 0) { - return { - kind: 'provenance', - message: `surface replace: sourceEventSeqs must include every shadowed surface node; missing ${missing.join(', ')}`, - } - } - return undefined -} - /** Mutable state shared by the incremental manager and the full-log fold. */ interface SurfaceFoldState { nodes: SurfaceNode[] nodeBySeq: Map + knownSeqs: Set replaceGeneration: number } +/** A validated replacement transition that has not mutated fold state yet. */ +interface SurfaceReplacePlan extends SurfaceFoldReplacement { + kind: 'replace' + startIdx: number + endIdx: number +} + +/** One validated surface transition that has not mutated fold state yet. */ +type SurfacePlan = + | { kind: 'append'; seq: number } + | SurfaceReplacePlan + /** Create an empty surface fold state. */ function createFoldState(replaceGeneration = 0): SurfaceFoldState { return { nodes: [], nodeBySeq: new Map(), + knownSeqs: new Set(), replaceGeneration, } } -/** Apply one event and return replacement metadata only when one occurred. */ -function applySurfaceEvent( - state: SurfaceFoldState, - event: SessionEvent, -): SurfaceFoldReplacement | undefined { - const violation = validateSurfaceMetadata(event) - if (violation?.kind === 'surface') throw new Error(violation.message) - if (!isSurfaceEligibleType(event.type)) return - // The canonical metadata validation above proves this runtime shape. - const surfaceEvent = event as SurfaceEvent +/** Whether a runtime value is a non-negative safe event sequence. */ +function isEventSeq(value: unknown): value is number { + return typeof value === 'number' && Number.isSafeInteger(value) && value >= 0 +} - if (surfaceEvent.surfaceOp === 'append') { - const tail = state.nodes.length > 0 ? state.nodes[state.nodes.length - 1] : undefined - const node: SurfaceNode = { seq: surfaceEvent.seq, prev: tail?.seq ?? null, next: null } - if (tail) tail.next = surfaceEvent.seq - state.nodes.push(node) - state.nodeBySeq.set(surfaceEvent.seq, node) +/** Whether a runtime value is the exact positional-replacement shape. */ +function isReplaceOp(value: object): value is Extract { + const op = value as Record + return Object.keys(op).length === 3 + && Object.hasOwn(op, 'op') + && Object.hasOwn(op, 'start') + && Object.hasOwn(op, 'end') + && op['op'] === 'replace' + && isEventSeq(op['start']) + && isEventSeq(op['end']) +} + +/** Validate event-local metadata and narrow a surface-eligible event. */ +function surfaceEventOf(event: SessionEvent): SurfaceEvent | undefined { + const raw = event as SessionEvent & { surfaceOp?: unknown; sourceEventSeqs?: unknown } + if (!isSurfaceEligibleType(event.type)) { + if (raw.surfaceOp !== undefined) { + throw new Error(`session event "${event.type}" is not surface-eligible and cannot carry surfaceOp`) + } + if (raw.sourceEventSeqs !== undefined) { + throw new Error(`session event "${event.type}" is not surface-eligible and cannot carry sourceEventSeqs`) + } return } + if (raw.surfaceOp === undefined) { + throw new Error(`session event "${event.type}" is surface-eligible and requires a surfaceOp marker`) + } + if (raw.surfaceOp !== 'append') { + if (raw.surfaceOp === null || typeof raw.surfaceOp !== 'object' || Array.isArray(raw.surfaceOp)) { + throw new Error(`session event "${event.type}" carries an invalid surfaceOp`) + } + if (!isReplaceOp(raw.surfaceOp)) { + throw new Error(`session event "${event.type}" carries an invalid replace surfaceOp`) + } + } + if (raw.sourceEventSeqs !== undefined && !Array.isArray(raw.sourceEventSeqs)) { + throw new Error(`sourceEventSeqs on event at seq ${event.seq} must be an array when present`) + } + if (Array.isArray(raw.sourceEventSeqs) && !raw.sourceEventSeqs.every(isEventSeq)) { + throw new Error(`session event "${event.type}" sourceEventSeqs must contain non-negative safe integers`) + } + return event as SurfaceEvent +} - return { - seq: surfaceEvent.seq, - start: surfaceEvent.surfaceOp.start, - end: surfaceEvent.surfaceOp.end, - shadowedSeqs: replaceSurface(state, surfaceEvent.seq, surfaceEvent.surfaceOp), +/** Validate provenance against prior log entries and the replacement range. */ +function assertProvenance( + event: SurfaceEvent, + knownSeqs: ReadonlySet, + shadowedSeqs: readonly number[], +): void { + const sources = event.sourceEventSeqs + if (sources !== undefined && sources.length === 0) { + throw new Error('sourceEventSeqs must not be empty when present') + } + const sourceSet = new Set(sources ?? []) + if (sources !== undefined && sourceSet.size !== sources.length) { + throw new Error('sourceEventSeqs must not contain duplicates') + } + for (const source of sources ?? []) { + if (source >= event.seq) { + throw new Error(`sourceEventSeqs must reference earlier events: ${source} >= current seq ${event.seq}`) + } + if (!knownSeqs.has(source)) { + throw new Error(`sourceEventSeqs references unknown seq ${source}`) + } + } + const missing = shadowedSeqs.filter(seq => !sourceSet.has(seq)) + if (missing.length > 0) { + throw new Error(`surface replace: sourceEventSeqs must include every shadowed surface node; missing ${missing.join(', ')}`) } } -/** Apply one positional replacement and return the nodes it removed. */ -function replaceSurface( +/** Locate one replacement range without mutating the current fold state. */ +function replacementRange( state: SurfaceFoldState, - newSeq: number, op: Extract, -): number[] { +): Pick { const startNode = state.nodeBySeq.get(op.start) if (!startNode) { throw new Error(`surface replace: start seq ${op.start} not found in surface`) @@ -253,6 +206,35 @@ function replaceSurface( if (startIdx > endIdx) { throw new Error(`surface replace: start seq ${op.start} (index ${startIdx}) is after end seq ${op.end} (index ${endIdx})`) } + return { + startIdx, + endIdx, + shadowedSeqs: state.nodes.slice(startIdx, endIdx + 1).map(node => node.seq), + } +} + +/** Validate one event and prepare its atomic fold transition. */ +function planSurfaceEvent(state: SurfaceFoldState, event: SessionEvent): SurfacePlan | undefined { + const surfaceEvent = surfaceEventOf(event) + if (surfaceEvent === undefined) return + if (surfaceEvent.surfaceOp === 'append') { + assertProvenance(surfaceEvent, state.knownSeqs, []) + return { kind: 'append', seq: event.seq } + } + const range = replacementRange(state, surfaceEvent.surfaceOp) + assertProvenance(surfaceEvent, state.knownSeqs, range.shadowedSeqs) + return { + kind: 'replace', + seq: event.seq, + start: surfaceEvent.surfaceOp.start, + end: surfaceEvent.surfaceOp.end, + ...range, + } +} + +/** Apply one already-validated positional replacement. */ +function replaceSurface(state: SurfaceFoldState, plan: SurfaceReplacePlan): void { + const { startIdx, endIdx } = plan const removed = state.nodes.splice(startIdx, endIdx - startIdx + 1) for (const node of removed) state.nodeBySeq.delete(node.seq) @@ -260,16 +242,40 @@ function replaceSurface( const prevNode = startIdx > 0 ? state.nodes[startIdx - 1] : undefined const nextNode = startIdx < state.nodes.length ? state.nodes[startIdx] : undefined const newNode: SurfaceNode = { - seq: newSeq, + seq: plan.seq, prev: prevNode?.seq ?? null, next: nextNode?.seq ?? null, } - if (prevNode) prevNode.next = newSeq - if (nextNode) nextNode.prev = newSeq + if (prevNode) prevNode.next = plan.seq + if (nextNode) nextNode.prev = plan.seq state.nodes.splice(startIdx, 0, newNode) - state.nodeBySeq.set(newSeq, newNode) + state.nodeBySeq.set(plan.seq, newNode) state.replaceGeneration += 1 - return removed.map(node => node.seq) +} + +/** Apply one event and return replacement metadata only when one occurred. */ +function applySurfaceEvent( + state: SurfaceFoldState, + event: SessionEvent, +): SurfaceFoldReplacement | undefined { + const plan = planSurfaceEvent(state, event) + if (plan?.kind === 'append') { + const tail = state.nodes.at(-1) + const node: SurfaceNode = { seq: plan.seq, prev: tail?.seq ?? null, next: null } + if (tail) tail.next = plan.seq + state.nodes.push(node) + state.nodeBySeq.set(plan.seq, node) + } else if (plan?.kind === 'replace') { + replaceSurface(state, plan) + } + state.knownSeqs.add(event.seq) + if (plan?.kind !== 'replace') return + return { + seq: plan.seq, + start: plan.start, + end: plan.end, + shadowedSeqs: plan.shadowedSeqs, + } } /** @@ -280,8 +286,9 @@ function replaceSurface( * models cannot disagree with `deriveMessages()` about replacement ranges. * @param events - session events in contiguous seq order. * @returns the current surface and every positional replacement. - * @throws when an event violates the `surfaceOp` type/marker contract, or a - * replacement names nodes that are absent or reversed on the current surface. + * @throws when any event violates the unified surface contract: metadata must + * be well shaped and type-eligible, provenance must name unique known earlier + * events, and a positional replacement must name and cite its complete range. */ export function foldSurface(events: readonly SessionEvent[]): SurfaceFoldResult { const state = createFoldState() @@ -297,11 +304,10 @@ export function foldSurface(events: readonly SessionEvent[]): SurfaceFoldResult } /** - * Maintains a cached linked list of surface nodes, rebuilt lazily from - * `surfaceOp` markers in the event log. Because the log is append-only, it - * processes only the delta since the last rebuild — new events are folded - * into the existing surface in O(new events) rather than rescanning the - * whole log. + * Maintains a cached linked list of surface nodes and validates each candidate + * before it enters the event log. Because the log is append-only, it processes + * only committed deltas and plans the candidate without mutation rather than + * rescanning the whole log. */ export class SurfaceManager { /** Incremental state shared with the complete surface fold. */ @@ -311,6 +317,18 @@ export class SurfaceManager { constructor(private log: readonly SessionEvent[]) {} + /** + * Validate one candidate as the next log event without applying it. The + * committed log is folded first, then the candidate's complete surface and + * provenance transition is planned atomically; a failure leaves the current + * surface unchanged. + * @param event - candidate event that has not entered `log` yet. + */ + validateNext(event: SessionEvent): void { + if (this._lastProcessedSeq < this.log.length - 1) this._processDelta() + planSurfaceEvent(this._state, event) + } + /** * Reset to unprocessed state. Call after the log has been replaced * wholesale (e.g. after Session seed). Not needed for normal appends — @@ -353,7 +371,7 @@ export class SurfaceManager { // eslint-disable-next-line @typescript-eslint/no-non-null-assertion const event = this.log[i]! applySurfaceEvent(this._state, event) + this._lastProcessedSeq = i } - this._lastProcessedSeq = this.log.length - 1 } } diff --git a/packages/core/session/tests/session.spec.ts b/packages/core/session/tests/session.spec.ts index fe44de871f..e3e5cc76c2 100644 --- a/packages/core/session/tests/session.spec.ts +++ b/packages/core/session/tests/session.spec.ts @@ -301,12 +301,19 @@ describe('Session', () => { type: 'user/message', seq: 0, time: 1, + data: { content: [{ type: 'text', text: 'source' }], source: { kind: 'user' } }, + surfaceOp: 'append', + }, { + type: 'user/message', + seq: 1, + time: 2, data: { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } }, surfaceOp, + sourceEventSeqs: [0], }] as unknown as SessionEvent[] const session = new Session(SessionId('seed-unstable-metadata'), seed) - const event = session.events[0]! + const event = session.events[1]! if (event.type !== 'user/message') throw new Error('test fixture must remain a user/message') expect(reads).toBe(1) @@ -326,13 +333,20 @@ describe('Session', () => { type: 'user/message', seq: 0, time: 1, + data: { content: [{ type: 'text', text: 'source' }], source: { kind: 'user' } }, + surfaceOp: 'append', + }, { + type: 'user/message', + seq: 1, + time: 2, data: { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } }, surfaceOp: { op: 'replace', start: 0, end: 0 }, + sourceEventSeqs: [0], }] as unknown as SessionEvent[] try { expect(() => new Session(SessionId('seed-non-error-metadata-failure'), seed)) - .toThrow(`invalid seed event at index 0: ${expected}`) + .toThrow(`invalid seed event at index 1: ${expected}`) } finally { hasOwn.mockRestore() } @@ -418,6 +432,11 @@ describe('Session', () => { it('reads a nested append-metadata getter once and stores its first JSON value', () => { const session = new Session(SessionId('append-unstable-metadata')) + const source = session.append( + 'user/message', + { content: [{ type: 'text', text: 'source' }], source: { kind: 'user' } }, + { surfaceOp: 'append' }, + ) let reads = 0 const surfaceOp = Object.defineProperty({ op: 'replace', end: 0 }, 'start', { enumerable: true, @@ -430,12 +449,12 @@ describe('Session', () => { const event = session.append( 'user/message', { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } }, - { surfaceOp } as never, + { surfaceOp, sourceEventSeqs: [0] } as never, ) expect(reads).toBe(1) expect(event.surfaceOp).toEqual({ op: 'replace', start: 0, end: 0 }) - expect(session.events).toEqual([event]) + expect(session.events).toEqual([source, event]) }) it('rejects invalid plain surface metadata shapes at append', () => { diff --git a/packages/core/session/tests/surface.spec.ts b/packages/core/session/tests/surface.spec.ts index fa7b1ff3ce..e1f948f2b1 100644 --- a/packages/core/session/tests/surface.spec.ts +++ b/packages/core/session/tests/surface.spec.ts @@ -6,7 +6,6 @@ import { foldSurface, isSurfaceEligibleType, isSurfaceEvent, - validateSurfaceMetadata, } from '@deepseek-ai/dsh-session' import { CallId } from '@deepseek-ai/dsh-llm' @@ -27,53 +26,52 @@ function provenanceEvent(seq: number, sourceEventSeqs: unknown): SessionEvent { time: seq, data: { content: [], source: { kind: 'user' } }, surfaceOp: 'append', - sourceEventSeqs, + ...sourceEventSeqs === undefined ? {} : { sourceEventSeqs }, } as unknown as SessionEvent } -describe('validateSurfaceMetadata', () => { +describe('foldSurface provenance', () => { it('accepts absent or valid provenance and complete replacement coverage', () => { - expect(validateSurfaceMetadata(provenanceEvent(0, undefined), new Set())) - .toBeUndefined() - expect(validateSurfaceMetadata(provenanceEvent(2, [0, 1]), new Set([0, 1]), [1])) - .toBeUndefined() + const events = [ + provenanceEvent(0, undefined), + provenanceEvent(1, undefined), + { + ...provenanceEvent(2, [0, 1]), + surfaceOp: { op: 'replace', start: 0, end: 1 }, + }, + ] as SessionEvent[] + expect(() => foldSurface(events)).not.toThrow() }) it('rejects provenance on a non-surface event', () => { const event = { type: 'turn/start', - seq: 1, + seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }, sourceEventSeqs: [0], } as unknown as SessionEvent - expect(validateSurfaceMetadata(event, new Set([0]))) - .toEqual({ - kind: 'provenance', - message: 'turn/start cannot carry sourceEventSeqs (non-surface event)', - }) + expect(() => foldSurface([event])).toThrow(/cannot carry sourceEventSeqs/) }) it.each([ - ['a non-array', 1, 'invalid', new Set([0]), [], /must be an array/], - ['an empty array', 1, [], new Set([0]), [], /must not be empty/], - ['duplicates', 1, [0, 0], new Set([0]), [], /must not contain duplicates/], - ['a non-number', 1, ['0'], new Set([0]), [], /non-negative safe integers/], - ['a fractional number', 1, [0.5], new Set([0]), [], /non-negative safe integers/], - ['a negative number', 1, [-1], new Set([0]), [], /non-negative safe integers/], - ['a self reference', 1, [1], new Set([0]), [], /must reference earlier events/], - ['an unknown earlier seq', 2, [1], new Set([0]), [], /references unknown seq 1/], - ['incomplete replacement coverage', 2, [0], new Set([0, 1]), [0, 1], /missing 1/], + ['a non-array', [{ ...provenanceEvent(0, undefined), sourceEventSeqs: 'invalid' }], /must be an array/], + ['an empty array', [provenanceEvent(0, [])], /must not be empty/], + ['duplicates', [provenanceEvent(0, undefined), provenanceEvent(1, [0, 0])], /must not contain duplicates/], + ['a non-number', [{ ...provenanceEvent(0, undefined), sourceEventSeqs: ['0'] }], /non-negative safe integers/], + ['a fractional number', [provenanceEvent(0, [0.5])], /non-negative safe integers/], + ['a negative number', [provenanceEvent(0, [-1])], /non-negative safe integers/], + ['a self reference', [provenanceEvent(0, [0])], /must reference earlier events/], + ['an unknown earlier seq', [provenanceEvent(0, undefined), provenanceEvent(2, [1])], /references unknown seq 1/], + ['incomplete replacement coverage', [ + provenanceEvent(0, undefined), + provenanceEvent(1, undefined), + { ...provenanceEvent(2, [0]), surfaceOp: { op: 'replace', start: 0, end: 1 } }, + ], /missing 1/], ] as const)( - 'returns the first violation for %s', - (_name, seq, sources, knownSeqs, shadowedSeqs, expected) => { - const violation = validateSurfaceMetadata( - provenanceEvent(seq, sources), - knownSeqs, - shadowedSeqs, - ) - expect(violation?.kind).toBe('provenance') - expect(violation?.message).toMatch(expected) + 'rejects %s', + (_name, events, expected) => { + expect(() => foldSurface(events as unknown as SessionEvent[])).toThrow(expected) }, ) }) @@ -101,7 +99,7 @@ describe('SurfaceManager', () => { it('does not retain fold-only replacement history in incremental state', () => { const s = new Session(SessionId('incremental-state')) s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'b' }] }, { surfaceOp: { op: 'replace', start: 0, end: 0 } }) + s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'b' }] }, { surfaceOp: { op: 'replace', start: 0, end: 0 }, sourceEventSeqs: [0] }) expect(s.surface.nodes).toEqual([{ seq: 1, prev: null, next: null }]) const manager = s.surface as unknown as { _state: object } @@ -112,12 +110,29 @@ describe('SurfaceManager', () => { }) it('foldSurface reports the same invalid replacement failures as the incremental manager', () => { - const s = new Session(SessionId('shared-fold-invalid')) - s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 42, end: 0 }, sourceEventSeqs: [0] }) + const events = [ + provenanceEvent(0, undefined), + { ...provenanceEvent(1, [0]), surfaceOp: { op: 'replace', start: 42, end: 0 } }, + ] as SessionEvent[] - expect(() => foldSurface(s.events)).toThrow(/start seq 42 not found/) - expect(() => s.surface.nodes).toThrow(/start seq 42 not found/) + expect(() => foldSurface(events)).toThrow(/start seq 42 not found/) + expect(() => new Session(SessionId('shared-fold-invalid'), events)) + .toThrow(/start seq 42 not found/) + }) + + it('leaves incremental state unchanged when candidate validation fails', () => { + const s = new Session(SessionId('atomic-validation')) + s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + + expect(() => s.append( + 'assistant/message', + { turn: 1, step: 1, content: [{ type: 'text', text: 'invalid' }] }, + { surfaceOp: { op: 'replace', start: 0, end: 0 } }, + )).toThrow(/missing 0/) + + expect(s.events).toHaveLength(1) + s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + expect(s.surface.nodes.map(node => node.seq)).toEqual([0, 1]) }) it('foldSurface rejects a surface-eligible event without its mandatory marker', () => { @@ -250,21 +265,19 @@ describe('SurfaceManager', () => { it('throws when replace start is not found', () => { const s = new Session(SessionId('bad-start')) s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 0 - s.append('assistant/message', + expect(() => s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, - { surfaceOp: { op: 'replace', start: 5, end: 0 }, sourceEventSeqs: [5, 0] }, - ) - expect(() => s.surface.nodes).toThrow(/surface replace: start seq 5 not found/) + { surfaceOp: { op: 'replace', start: 5, end: 0 }, sourceEventSeqs: [0] }, + )).toThrow(/surface replace: start seq 5 not found/) }) it('throws when replace end is not found', () => { const s = new Session(SessionId('bad-end')) s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 0 - s.append('assistant/message', + expect(() => s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, { surfaceOp: { op: 'replace', start: 0, end: 99 }, sourceEventSeqs: [0] }, - ) - expect(() => s.surface.nodes).toThrow(/surface replace: end seq 99 not found/) + )).toThrow(/surface replace: end seq 99 not found/) }) it('throws when start is after end', () => { @@ -272,22 +285,22 @@ describe('SurfaceManager', () => { s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 0 s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 1 // start=1, end=0 would be reversed order. - s.append('assistant/message', + expect(() => s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, { surfaceOp: { op: 'replace', start: 1, end: 0 }, sourceEventSeqs: [1, 0] }, - ) - expect(() => s.surface.nodes).toThrow(/start seq 1.*after end seq 0/) + )).toThrow(/start seq 1.*after end seq 0/) }) it('sourceEventSeqs is snapshot so caller mutation does not affect logged event', () => { const s = new Session(SessionId('immutable')) - const sources = [10, 20] + s.append('user/message', { content: [{ type: 'text', text: 'source' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + const sources = [0] s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'h' }] }, { surfaceOp: 'append', sourceEventSeqs: sources }) // Mutate caller's array after append. - sources.push(30) + sources.push(1) sources[0] = 99 - const logged = s.events[0]! as SurfaceEvent - expect(logged.sourceEventSeqs).toEqual([10, 20]) + const logged = s.events[1]! as SurfaceEvent + expect(logged.sourceEventSeqs).toEqual([0]) }) it('replace starting at non-head position links to previous node correctly', () => { @@ -369,15 +382,17 @@ describe('deriveMessages with surface', () => { describe('Session.append surface opts', () => { it('records sourceEventSeqs and surfaceOp on the event', () => { const s = new Session(SessionId('opts')) + s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + s.append('step/start', { turn: 1, step: 1 }) const event = s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'h' }] }, - { surfaceOp: 'append', sourceEventSeqs: [3, 5, 7] }, + { surfaceOp: 'append', sourceEventSeqs: [0, 1] }, ) - expect(event.sourceEventSeqs).toEqual([3, 5, 7]) + expect(event.sourceEventSeqs).toEqual([0, 1]) expect(event.surfaceOp).toBe('append') // The logged event matches the returned event. - expect((s.events[0]! as SurfaceEvent).sourceEventSeqs).toEqual([3, 5, 7]) - expect((s.events[0]! as SurfaceEvent).surfaceOp).toBe('append') + expect((s.events[2]! as SurfaceEvent).sourceEventSeqs).toEqual([0, 1]) + expect((s.events[2]! as SurfaceEvent).surfaceOp).toBe('append') }) it('deriveMessages skips a surface node that derives to null (empty assistant/message)', () => { diff --git a/packages/core/session/tests/tool-pairing.spec.ts b/packages/core/session/tests/tool-pairing.spec.ts index 307b0d8658..cc2acd1a2c 100644 --- a/packages/core/session/tests/tool-pairing.spec.ts +++ b/packages/core/session/tests/tool-pairing.spec.ts @@ -261,10 +261,11 @@ describe('isToolPairingBalanced — CBR-001: a head checkpoint left by a replace // summary user/message — appended now, so it carries a high log seq. const u1 = seqOf(s, 'user/message') const result = s.events.find(e => e.type === 'tool/result')!.seq + const shadowedSeqs = s.surface.nodes.map(node => node.seq) s.append('user/message', { content: [{ type: 'text', text: 'CHECKPOINT' }], source: { kind: 'plugin', plugin: 'compact' }, - }, { surfaceOp: { op: 'replace', start: u1, end: result } }) + }, { surfaceOp: { op: 'replace', start: u1, end: result }, sourceEventSeqs: shadowedSeqs }) // The step's own assistant/message lands AFTER the checkpoint in the log, // still inside the open step. s.append('assistant/message', { turn: 2, step: 1, content: [{ type: 'text', text: 'a2' }] }, SURFACE) diff --git a/packages/session-query/session-query/README.md b/packages/session-query/session-query/README.md index 2dcdec085e..4f9f8122b4 100644 --- a/packages/session-query/session-query/README.md +++ b/packages/session-query/session-query/README.md @@ -14,9 +14,9 @@ This is trusted context-wide infrastructure. It performs no caller authorization Persistence is optional and may mount or unmount dynamically. Cross-corpus listing and lineage tracing fail with `SESSION_QUERY_PERSISTENCE_FAILED` while mounted persistence is unreadable. An event read or trace targeting a known live session does not consult persistence, so durable backend health cannot make current in-memory history unreadable. Persisted event operations list before loading and reject a metadata mismatch rather than combining inconsistent observations. -`traceEvent()` validates the whole loaded log with `dsh-session`'s shared surface-metadata checker before returning relationships: surface markers obey event-type eligibility, provenance arrays are nonempty and duplicate-free, references name known earlier events, and each positional replacement names every surface node it removed. Surface-marker and positional-fold violations fail with `SESSION_QUERY_INVALID_SURFACE`; provenance violations use `SESSION_QUERY_INVALID_PROVENANCE`. `listEvents()` only needs surface classification and deliberately does not enforce the trace-specific provenance contract. +`listEvents()` and `traceEvent()` run the same one-pass `dsh-session` surface fold. A loaded log is valid only when surface markers obey event-type eligibility, provenance arrays are nonempty and duplicate-free, references name known earlier events, and each positional replacement names and cites every surface node it removes; every violation fails with `SESSION_QUERY_INVALID_SURFACE`. -`SessionQueryError.code` is a closed union: `SESSION_QUERY_EVENT_NOT_FOUND`, `SESSION_QUERY_INVALID_CONFIG`, `SESSION_QUERY_INVALID_LINEAGE`, `SESSION_QUERY_INVALID_PROVENANCE`, `SESSION_QUERY_INVALID_SURFACE`, `SESSION_QUERY_INVALID_WINDOW`, `SESSION_QUERY_PERSISTENCE_FAILED`, `SESSION_QUERY_SESSION_NOT_FOUND`, and `SESSION_QUERY_SOURCE_CONFLICT`. +`SessionQueryError.code` is a closed union: `SESSION_QUERY_EVENT_NOT_FOUND`, `SESSION_QUERY_INVALID_CONFIG`, `SESSION_QUERY_INVALID_LINEAGE`, `SESSION_QUERY_INVALID_SURFACE`, `SESSION_QUERY_INVALID_WINDOW`, `SESSION_QUERY_PERSISTENCE_FAILED`, `SESSION_QUERY_SESSION_NOT_FOUND`, and `SESSION_QUERY_SOURCE_CONFLICT`. ## Configuration diff --git a/packages/session-query/session-query/src/config.ts b/packages/session-query/session-query/src/config.ts index a6d0ab10fa..4a15366c2c 100644 --- a/packages/session-query/session-query/src/config.ts +++ b/packages/session-query/session-query/src/config.ts @@ -16,7 +16,6 @@ export type SessionQueryErrorCode = | 'SESSION_QUERY_EVENT_NOT_FOUND' | 'SESSION_QUERY_INVALID_CONFIG' | 'SESSION_QUERY_INVALID_LINEAGE' - | 'SESSION_QUERY_INVALID_PROVENANCE' | 'SESSION_QUERY_INVALID_SURFACE' | 'SESSION_QUERY_INVALID_WINDOW' | 'SESSION_QUERY_PERSISTENCE_FAILED' diff --git a/packages/session-query/session-query/src/tracing.ts b/packages/session-query/session-query/src/tracing.ts index 09d3ed65f6..c7b5143b67 100644 --- a/packages/session-query/session-query/src/tracing.ts +++ b/packages/session-query/session-query/src/tracing.ts @@ -1,7 +1,7 @@ /** One-shot session-lineage and event-relationship tracing helpers. */ -import { foldSurface, validateSurfaceMetadata } from '@deepseek-ai/dsh-session' -import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session' +import { foldSurface } from '@deepseek-ai/dsh-session' +import type { SessionEvent, SessionId, SurfaceEventType } from '@deepseek-ai/dsh-session' import { SessionQueryError } from './config.ts' import type { SessionEventRecord, @@ -51,21 +51,6 @@ export function traceEventLog( } const analysis = analyzeEventLog(sessionId, events) - const knownSeqs = new Set() - for (const event of events) { - const violation = validateSurfaceMetadata( - event, - knownSeqs, - analysis.replacedEventSeqs.get(event.seq), - ) - if (violation !== undefined) { - throw new SessionQueryError( - `invalid session provenance: ${violation.message}`, - 'SESSION_QUERY_INVALID_PROVENANCE', - ) - } - knownSeqs.add(event.seq) - } const replacementChain: number[] = [] let replacement = analysis.replacedBy.get(seq) @@ -143,7 +128,9 @@ export function traceLineage( children.push(record) childrenByParent.set(parent, children) } - for (const children of childrenByParent.values()) children.sort(compareSessionsAscending) + for (const children of childrenByParent.values()) { + children.sort((a, b) => a.header.createdAt - b.header.createdAt || a.header.id.localeCompare(b.header.id)) + } const descendants = buildDescendants(childrenByParent, sessionId) const common = { @@ -203,13 +190,8 @@ function analyzeEventLog( } } -function rawEventSources(event: SessionEvent): unknown { - return (event as SessionEvent & { sourceEventSeqs?: unknown }).sourceEventSeqs -} - function eventSources(event: SessionEvent): number[] { - const sources = rawEventSources(event) - return Array.isArray(sources) ? sources as number[] : [] + return (event as SessionEvent).sourceEventSeqs ?? [] } function buildDescendants( @@ -238,10 +220,6 @@ function buildDescendants( return descendants } -function compareSessionsAscending(a: SessionRecord, b: SessionRecord): number { - return a.header.createdAt - b.header.createdAt || a.header.id.localeCompare(b.header.id) -} - function cloneRecord(record: SessionRecord): SessionRecord { return { ...record, header: structuredClone(record.header) } } diff --git a/packages/session-query/session-query/tests/session-query.spec.ts b/packages/session-query/session-query/tests/session-query.spec.ts index 3b50feee45..bb7d01ec73 100644 --- a/packages/session-query/session-query/tests/session-query.spec.ts +++ b/packages/session-query/session-query/tests/session-query.spec.ts @@ -110,7 +110,7 @@ describe('session-query exact reads', () => { session.append( 'assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'replacement' }] }, - { surfaceOp: { op: 'replace', start: first.seq, end: first.seq } }, + { surfaceOp: { op: 'replace', start: first.seq, end: first.seq }, sourceEventSeqs: [first.seq] }, ) expect((await ctx.sessionQuery.listEvents(session.id)).map(record => record.surface)) @@ -227,11 +227,13 @@ describe('session-query exact reads', () => { it('turns malformed surfaces and direct invalid config into typed errors', async () => { const ctx = await liveContext() const session = ctx.sessions.create(SessionId('bad-surface')) - session.append( - 'assistant/message', - { turn: 1, step: 1, content: [] }, - { surfaceOp: { op: 'replace', start: 9, end: 9 } }, - ) + ;(session as unknown as { log: SessionEvent[] }).log.push({ + type: 'assistant/message', + seq: 0, + time: 1, + data: { turn: 1, step: 1, content: [] }, + surfaceOp: { op: 'replace', start: 9, end: 9 }, + }) await expect(ctx.sessionQuery.listEvents(session.id)) .rejects.toThrow(expectCode('SESSION_QUERY_INVALID_SURFACE')) diff --git a/packages/session-query/session-query/tests/tracing.spec.ts b/packages/session-query/session-query/tests/tracing.spec.ts index 0a8b8e6da1..efc32d2216 100644 --- a/packages/session-query/session-query/tests/tracing.spec.ts +++ b/packages/session-query/session-query/tests/tracing.spec.ts @@ -379,7 +379,7 @@ describe('session event tracing', () => { appendEvent(1), { ...appendEvent(2, [0]), surfaceOp: { op: 'replace', start: 1, end: 1 } }, ]], - ] as const)('rejects invalid whole-log provenance: %s', async (_name, rawEvents) => { + ] as const)('rejects an invalid surface log: %s', async (_name, rawEvents) => { const durable = header('invalid-provenance') const events = structuredClone(rawEvents) as unknown as SessionEvent[] TracePersistence.reset([{ meta: durable, events }]) @@ -387,7 +387,7 @@ describe('session event tracing', () => { await ctx.plugin(TracePersistence) await expect(ctx.sessionQuery.traceEvent({ sessionId: durable.id, seq: 0 })) - .rejects.toThrow(expectCode('SESSION_QUERY_INVALID_PROVENANCE')) + .rejects.toThrow(expectCode('SESSION_QUERY_INVALID_SURFACE')) }) it('rejects surfaceOp on a non-surface event as an invalid surface', async () => { @@ -407,15 +407,13 @@ describe('session event tracing', () => { .rejects.toThrow(expectCode('SESSION_QUERY_INVALID_SURFACE')) }) - it('keeps listEvents tolerant of malformed provenance alone', async () => { + it('applies the same surface contract to listEvents', async () => { const durable = header('list-regression') TracePersistence.reset([{ meta: durable, events: [appendEvent(0), appendEvent(1, [0, 0])] }]) const ctx = await queryContext() await ctx.plugin(TracePersistence) - await expect(ctx.sessionQuery.listEvents(durable.id)).resolves.toMatchObject([ - { seq: 0, surface: 'current' }, - { seq: 1, surface: 'current' }, - ]) + await expect(ctx.sessionQuery.listEvents(durable.id)) + .rejects.toThrow(expectCode('SESSION_QUERY_INVALID_SURFACE')) }) }) diff --git a/packages/support/invariants/README.md b/packages/support/invariants/README.md index 2fe2db1f6c..562df0bf3a 100644 --- a/packages/support/invariants/README.md +++ b/packages/support/invariants/README.md @@ -4,7 +4,7 @@ Dev-mode event-contract assertions. This pure-listener plugin checks relationshi **Off in production.** Enable it in tests and the demos, where a contract violation should fail loudly. It costs nothing when not registered, and doubles as executable documentation of the event taxonomy — the assertions *are* the contract. -Session itself owns immutable log storage in every composition: it takes one lossless JSON snapshot of each accepted event, deep-freezes that record, and exposes the log through immutable array snapshots. The invariants plugin checks the cross-record and cross-seam rules that storage immutability cannot express. +Session itself owns immutable, surface-valid log storage in every composition: it takes one lossless JSON snapshot of each candidate, validates the complete surface transition, deep-freezes the accepted record, and exposes the log through immutable array snapshots. The invariants plugin checks the remaining cross-record and cross-seam rules that Session does not own. Session-log assertions run during Cordis `internal/dispatch`, while `Session.append()` is resolving the `session/event` callback snapshot but before it pushes the candidate into the log. A valid transition is staged by exact event identity and applied to the live trace only when that same committed event reaches the plugin's contained post-commit listener. A later internal dispatch check can therefore veto without advancing either the log or the invariant trace, while ordinary `session/event` observer failures remain observe-only. @@ -28,7 +28,6 @@ await ctx.plugin(Invariants) Session log (per session): - **`seq` strictly increases** — the spine of replay equivalence. -- **surface metadata is valid** — `surfaceOp` and `sourceEventSeqs` use the shared `dsh-session` checker for type eligibility, structural shape, nonempty unique earlier references, and complete replacement coverage. - **turns pair and nest** — `turn/start` opens a turn, `turn/end` closes the matching one; no overlapping turns. - **steps nest in turns** — `step/start` opens a step in the open turn; `step/end` closes the matching step. - **chunks belong to an open step** — `step/start` precedes its `assistant/chunk`s. diff --git a/packages/support/invariants/src/index.ts b/packages/support/invariants/src/index.ts index b2fa15080f..db25c42b89 100644 --- a/packages/support/invariants/src/index.ts +++ b/packages/support/invariants/src/index.ts @@ -6,13 +6,12 @@ * `session/event`, `agent/status`, and the scoped dispatch and request seams. * It is **off in production**: enable it in tests and demos, where a contract * violation should be a loud failure rather than a subtle one. It doubles as - * executable documentation of the event taxonomy: these assertions and the - * shared session validators they invoke are the contract. + * executable documentation of the relational event taxonomy. * - * Session owns immutable log storage: it snapshots and deep-freezes every - * accepted event at the source. This plugin checks relationships that one - * event's types and immutability cannot express, including turn/step nesting, - * scoped dispatch, status transitions, and request reconstructability. + * Session owns immutable, surface-valid log storage: it validates, snapshots, + * and deep-freezes every accepted event at the source. This plugin checks the + * remaining relationships that acceptance cannot express, including turn/step + * nesting, scoped dispatch, status transitions, and request reconstructability. * * @module @deepseek-ai/dsh-invariants */ @@ -26,9 +25,8 @@ import { Session, SessionId, foldRequestHeader, - validateSurfaceMetadata, } from '@deepseek-ai/dsh-session' -import type { SessionEvent, SurfaceEventType } from '@deepseek-ai/dsh-session' +import type { SessionEvent } from '@deepseek-ai/dsh-session' export const name = 'invariants' export const inject = ['sessions'] @@ -62,15 +60,6 @@ interface SessionTrace { * `step/end` — a result must arrive in the same step as its call. */ pendingCalls: Set - /** Every seq seen so far — validates `sourceEventSeqs` references. */ - knownSeqs: Set - /** - * The seqs currently on the surface linked list, in linked-list order - * (head to tail). A replace reorders this relative to seq order (the new - * node takes the replaced range's position), so range validation is - * positional, not by seq comparison. - */ - surface: number[] } /** One accepted event's deferred mutation of a live session trace. */ @@ -82,12 +71,6 @@ interface SessionTraceTransition { | { kind: 'none' } | { kind: 'add' | 'delete'; callId: CallId } | { kind: 'clear' } - /** The event's mutation of the derived surface order. */ - surface: - | { kind: 'none' | 'append' } - | { kind: 'replace'; start: number; count: number } - /** The committed event sequence to add to the known-sequence set. */ - seq: number } /** Event payload prefix for scoped seams whose first argument names its agent. */ @@ -122,50 +105,6 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr let nextTurn = trace.nextTurn let nextStep = trace.nextStep let pendingCalls: SessionTraceTransition['pendingCalls'] = { kind: 'none' } - let surface: SessionTraceTransition['surface'] = { kind: 'none' } - - // --- Surface invariants --- - // Cast to surface-eligible event type so we can access surfaceOp and - // sourceEventSeqs (optional on SessionEvent, mandatory on SurfaceEvent). - // SurfaceEvent's mandatory surfaceOp is too strict here — we need to - // CHECK whether surface metadata is present, not assume it. - const se = event as SessionEvent - const metadataViolation = validateSurfaceMetadata(event) - if (metadataViolation !== undefined) throw new InvariantError(metadataViolation.message) - - // Fold this event into the tracked surface linked list, validating the - // replace contract as we go. `append` adds a tail node; `replace` shadows a - // positional range — every shadowed node must appear in sourceEventSeqs. - let shadowed: number[] | undefined - if (se.surfaceOp !== undefined) { - if (se.surfaceOp === 'append') { - surface = { kind: 'append' } - } else { - const { start, end } = se.surfaceOp - const startIdx = trace.surface.indexOf(start) - if (startIdx === -1) { - throw new InvariantError(`surface replace: start seq ${start} is not on the surface`) - } - const endIdx = trace.surface.indexOf(end) - if (endIdx === -1) { - throw new InvariantError(`surface replace: end seq ${end} is not on the surface`) - } - if (startIdx > endIdx) { - throw new InvariantError(`surface replace: start seq ${start} (pos ${startIdx}) is after end seq ${end} (pos ${endIdx}) on the surface`) - } - shadowed = trace.surface.slice(startIdx, endIdx + 1) - surface = { kind: 'replace', start: startIdx, count: shadowed.length } - } - } - - const provenanceViolation = validateSurfaceMetadata( - event, - trace.knownSeqs, - shadowed, - ) - if (provenanceViolation !== undefined) { - throw new InvariantError(provenanceViolation.message) - } // Boundary/step-scoped events have explicit cases; every OTHER event type — // including plugin-added (merge-extensible) SessionEventMap keys — is caught @@ -265,8 +204,6 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr return { scalars: { lastSeq: event.seq, openTurn, openStep, nextTurn, nextStep }, pendingCalls, - surface, - seq: event.seq, } } @@ -289,20 +226,6 @@ function applyTransition(trace: SessionTrace, transition: SessionTraceTransition default: assertNever(transition.pendingCalls, 'session trace pending-call transition') } - switch (transition.surface.kind) { - case 'none': - break - case 'append': - trace.surface.push(transition.seq) - break - case 'replace': - trace.surface.splice(transition.surface.start, transition.surface.count, transition.seq) - break - /* v8 ignore next -- validateEvent produces this closed transition union */ - default: - assertNever(transition.surface, 'session trace surface transition') - } - trace.knownSeqs.add(transition.seq) } /** Validate and apply one event while rebuilding an already-committed log. */ @@ -351,8 +274,6 @@ export function apply(ctx: Context): void { nextTurn: 1, nextStep: 1, pendingCalls: new Set(), - knownSeqs: new Set(), - surface: [], }) /** Build (or rebuild) a session's trace by replaying its whole log. */ diff --git a/packages/support/invariants/tests/invariants.spec.ts b/packages/support/invariants/tests/invariants.spec.ts index a1e824524b..d5f43d1568 100644 --- a/packages/support/invariants/tests/invariants.spec.ts +++ b/packages/support/invariants/tests/invariants.spec.ts @@ -466,7 +466,7 @@ describe('HMR safety', () => { }) }) -describe('surface invariants', () => { +describe('surface contract under the invariants composition', () => { it('accepts well-formed surface metadata', async () => { const { ctx } = await setup() const session = ctx.sessions.create() @@ -495,7 +495,7 @@ describe('surface invariants', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) expect(() => { session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [] }) - }).toThrow(InvariantError) + }).toThrow(/must not be empty/) }) it('rejects duplicate sourceEventSeqs', async () => { @@ -542,15 +542,15 @@ describe('surface invariants', () => { it('rejects sourceEventSeqs referencing unknown seq (gap in event log)', async () => { // The unknown-seq check fires when a ref passes the "earlier" test but is - // not in knownSeqs — only possible with a gap in seqs. We create a gap by + // not in the folded log — only possible with a gap in seqs. We create a gap by // directly manipulating the private log array to skip a seq. const { ctx } = await setup() const session = ctx.sessions.create() session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) // Push a fake event at seq 3 into the internal log, creating a gap at seq 2. - // The invariants plugin replays session.events on every append, so it sees - // this gap during trace reconstruction. + // The canonical surface validator folds the committed delta before checking + // the next append, so it sees this gap. ;(session as unknown as { log: unknown[] }).log.push({ type: 'assistant/chunk', seq: 3, @@ -575,7 +575,7 @@ describe('surface invariants', () => { // Reversed range: start seq 3 is at a later surface position than end seq 2. expect(() => { session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 3, end: 2 }, sourceEventSeqs: [2, 3] }) - }).toThrow(/is after end seq 2 .* on the surface/) + }).toThrow(/is after end seq 2/) }) it('rejects a replace whose sourceEventSeqs omits a shadowed surface node', async () => { @@ -612,7 +612,7 @@ describe('surface invariants', () => { // seq 1 (step/start) is a real earlier event but never entered the surface. expect(() => { session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 1, end: 2 }, sourceEventSeqs: [1, 2] }) - }).toThrow(/start seq 1 is not on the surface/) + }).toThrow(/start seq 1 not found in surface/) }) it('rejects a replace naming an end seq that is not on the surface', async () => { @@ -624,7 +624,7 @@ describe('surface invariants', () => { // start (2) is on the surface but end (99) never entered it. expect(() => { session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 2, end: 99 }, sourceEventSeqs: [2] }) - }).toThrow(/end seq 99 is not on the surface/) + }).toThrow(/end seq 99 not found in surface/) }) it('rejects a replace whose range is reversed in surface position after a prior replace reordered it', async () => { @@ -641,7 +641,7 @@ describe('surface invariants', () => { // reversed positionally (3 is at pos 1, 4 is at pos 0). expect(() => { session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 3, end: 4 }, sourceEventSeqs: [3, 4] }) // seq 5 - }).toThrow(/is after end seq 4 .* on the surface/) + }).toThrow(/is after end seq 4/) }) it('accepts a replace whose start seq exceeds its end seq when the surface position order is valid', async () => { @@ -685,25 +685,6 @@ describe('surface invariants', () => { expect(() => ctx.sessions.create(undefined, { seed: badSeed })).toThrow(/must include every shadowed surface node; missing 3/) }) - it('rejects sourceEventSeqs on a non-surface event', async () => { - const { ctx } = await setup() - const session = ctx.sessions.create() - session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - // Session rejects this at its own acceptance boundary. Emit a hand-built - // record to cover the listener's defensive check for alternate producers. - const event = { type: 'turn/end', seq: 1, time: 1, data: { turn: 1, reason: { kind: 'completed' } }, sourceEventSeqs: [0] } - expect(() => { ctx.emit(scopeTarget(session, undefined), 'session/event', session, event as never) }) - .toThrow(/cannot carry sourceEventSeqs/) - }) - - it('rejects surfaceOp on a non-surface event', async () => { - const { ctx } = await setup() - const session = ctx.sessions.create() - session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - const event = { type: 'turn/end', seq: 1, time: 1, data: { turn: 1, reason: { kind: 'completed' } }, surfaceOp: 'append' } - expect(() => { ctx.emit(scopeTarget(session, undefined), 'session/event', session, event as never) }) - .toThrow(/cannot carry surfaceOp/) - }) }) describe('request-reconstruction cross-check (llm/stream)', () => { From 628006889e07846af0816a127683b3e5aa5f2b5c Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 13:51:21 +0800 Subject: [PATCH 103/359] docs: keep agent-loop map concise --- docs/architecture.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/architecture.md b/docs/architecture.md index 0e83cba072..89bb27604b 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -17,7 +17,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service | `ctx.systemPrompt` | `dsh-system-prompt` | ordered prompt sections, tool schemas, and prompt variables | | `ctx.tools` | `dsh-tools` | tool registry and [execution pipeline](tool-execution-pipeline.md) | | `ctx.agents` | `dsh-agent` | live agent registry, public `Agent` handle, `agent/*` events | -| `ctx.agentLoop` | `dsh-agent-loop` | shipped concrete `Agent` driver | +| `ctx.agentLoop` | `dsh-agent-loop` | concrete `Agent` driver | ### Capability Services From 539850578aabd477c734a6cbf142d93aeb035764 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 14:04:29 +0800 Subject: [PATCH 104/359] fix: reject legacy header deltas on append --- docs/cordis-catalog/services.md | 2 +- .../2026-07-12-simplify-session-log-representation.md | 2 +- packages/core/session/src/index.ts | 3 +++ packages/core/session/tests/request-header.spec.ts | 8 +++++++- .../session-persistence/tests/persistence.spec.ts | 9 ++++----- 5 files changed, 16 insertions(+), 8 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 9501a86c6b..0bd8a8c4a0 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -245,7 +245,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:604`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:607`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` diff --git a/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md b/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md index a1dfb5eafb..dc51986e79 100644 --- a/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md +++ b/docs/rfc/implemented/simplification/2026-07-12-simplify-session-log-representation.md @@ -10,7 +10,7 @@ The session log maintains two representations that cost more machinery than thei The request-header subsystem implements a custom system/tool delta codec and transmission-decision layer even though its contract says deltas are an encoding optimization, not a reconstructability requirement. Retaining the initial/resume full snapshot at each loop-instance boundary, then writing a canonical full `request/header` whenever that instance's assembled header changes, preserves replay while deleting `SystemDelta`, `ToolsDelta`, round-trip fallback, and the durable `request/header-delta` variant. Codec-only vocabulary disappears with the codec, not because its individual arms were invalid. -This proposal deliberately retains append and replacement `sourceEventSeqs`, crash-repair provenance, and all `SessionStartSource` variants: implemented RFCs give those fields an audit/interception role that zero current readers does not overturn. +The implementation retains append and replacement `sourceEventSeqs`, crash-repair provenance, and all `SessionStartSource` variants because those fields have an audit/interception role that zero current readers does not overturn. ## Decision diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index 11451811c3..2850286cde 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -214,6 +214,9 @@ function assertSessionEventEnvelope(value: Record, index: numbe /** Reject request-header vocabulary removed with the legacy delta codec. */ function assertSupportedRequestHeader(type: string, data: unknown, location: string): void { + if (type === 'request/header-delta') { + throw new Error(`${location} uses unsupported legacy request/header-delta format`) + } if (type === 'request/header' && data !== null && typeof data === 'object' && !Array.isArray(data) && (data as Record)['reason'] === 'fallback') { diff --git a/packages/core/session/tests/request-header.spec.ts b/packages/core/session/tests/request-header.spec.ts index 8bc2a4bf6c..da84ea239c 100644 --- a/packages/core/session/tests/request-header.spec.ts +++ b/packages/core/session/tests/request-header.spec.ts @@ -62,11 +62,17 @@ describe('foldRequestHeader', () => { }) describe('legacy request-header format', () => { - it('rejects a v0 seed containing request/header-delta', () => { + it('rejects request/header-delta in seeds and untyped appends', () => { const legacy = [{ type: 'request/header-delta', seq: 0, time: 1, data: { config: CONFIG }, }] as unknown as SessionEvent[] expect(() => new Session(SessionId('legacy'), legacy)).toThrow(/unsupported legacy request\/header-delta/) + + const session = new Session(SessionId('legacy-append-delta')) + const appendLegacy = session.append.bind(session) as (type: string, data: unknown) => SessionEvent + expect(() => appendLegacy('request/header-delta', { config: CONFIG })) + .toThrow(/unsupported legacy request\/header-delta/) + expect(session.events).toHaveLength(0) }) it('rejects the removed fallback reason in seeds and untyped appends', () => { diff --git a/packages/session-persistence/session-persistence/tests/persistence.spec.ts b/packages/session-persistence/session-persistence/tests/persistence.spec.ts index 5d0ba2c607..f8ea43fd05 100644 --- a/packages/session-persistence/session-persistence/tests/persistence.spec.ts +++ b/packages/session-persistence/session-persistence/tests/persistence.spec.ts @@ -185,7 +185,7 @@ describe('SessionPersistence service registration', () => { await fiber.dispose() }) - it('rejects a legacy header delta buffered by a pre-change live producer', async () => { + it('rejects a legacy header delta from a pre-change live producer', async () => { const ctx = new Context() await ctx.plugin(SessionStore) const fiber = await ctx.plugin(MemoryPersistence) @@ -193,10 +193,9 @@ describe('SessionPersistence service registration', () => { // Model the runtime shape available to JavaScript or a hot-loaded plugin // compiled against the obsolete event vocabulary. const appendLegacy = session.append.bind(session) as (type: string, data: unknown) => SessionEvent - appendLegacy('request/header-delta', { config: { model: 'legacy' } }) - - await expect(ctx.sessions.flush(session)) - .rejects.toThrow(/unsupported legacy request\/header-delta event at seq 0/) + expect(() => appendLegacy('request/header-delta', { config: { model: 'legacy' } })) + .toThrow(/unsupported legacy request\/header-delta format/) + expect(session.events).toHaveLength(0) await fiber.dispose() }) From bb40259083f10cb2071c024f05810c74021e4035 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 14:11:33 +0800 Subject: [PATCH 105/359] test: preserve ACP cleanup failures --- examples/acp-agent/tests/acp.e2e.ts | 18 ++++------ examples/acp-agent/tests/cleanup.e2e.ts | 38 ++++++++++++++++++++++ examples/acp-agent/tests/cleanup.ts | 23 +++++++++++++ examples/acp-agent/tests/escalation.e2e.ts | 18 ++++------ examples/acp-agent/tests/hooks.e2e.ts | 18 ++++------ 5 files changed, 82 insertions(+), 33 deletions(-) create mode 100644 examples/acp-agent/tests/cleanup.e2e.ts create mode 100644 examples/acp-agent/tests/cleanup.ts diff --git a/examples/acp-agent/tests/acp.e2e.ts b/examples/acp-agent/tests/acp.e2e.ts index a1ddbeccc6..a0bfc9d943 100644 --- a/examples/acp-agent/tests/acp.e2e.ts +++ b/examples/acp-agent/tests/acp.e2e.ts @@ -1,4 +1,4 @@ -import { mkdtemp, rm, readFile } from 'node:fs/promises' +import { mkdtemp, readFile } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' @@ -9,6 +9,7 @@ import { type AgentUnderTest, type LaunchedAcpTestAgent, } from '@deepseek-ai/dsh-acp-snapshot' +import { cleanupAcpExampleTest } from './cleanup.ts' /** * End-to-end: boot examples/acp-agent as a real subprocess speaking ACP over @@ -31,16 +32,11 @@ let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - try { - await spawned?.close('SIGKILL') - } finally { - spawned = undefined - try { - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - } finally { - workdir = undefined - } - } + const ownedSpawned = spawned + const ownedWorkdir = workdir + spawned = undefined + workdir = undefined + await cleanupAcpExampleTest(ownedSpawned, ownedWorkdir) }) describe('acp-agent over real stdio (no key required)', () => { diff --git a/examples/acp-agent/tests/cleanup.e2e.ts b/examples/acp-agent/tests/cleanup.e2e.ts new file mode 100644 index 0000000000..1f6e6493e0 --- /dev/null +++ b/examples/acp-agent/tests/cleanup.e2e.ts @@ -0,0 +1,38 @@ +/** Regression coverage for ACP example teardown. */ + +import { access, mkdtemp, rm } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { afterEach, describe, expect, it, vi } from 'vitest' +import { cleanupAcpExampleTest } from './cleanup.ts' + +let fallbackWorkdir: string | undefined + +afterEach(async () => { + if (fallbackWorkdir !== undefined) await rm(fallbackWorkdir, { recursive: true, force: true }) + fallbackWorkdir = undefined +}) + +describe('cleanupAcpExampleTest', () => { + it('removes the workspace after process shutdown fails', async () => { + fallbackWorkdir = await mkdtemp(join(tmpdir(), 'acp-cleanup-')) + const closeFailure = new Error('close failed') + const spawned = { close: vi.fn().mockRejectedValue(closeFailure) } + + await expect(cleanupAcpExampleTest(spawned, fallbackWorkdir)) + .rejects.toMatchObject({ errors: [closeFailure] }) + await expect(access(fallbackWorkdir)).rejects.toThrow() + fallbackWorkdir = undefined + }) + + it('reports process and workspace failures together', async () => { + const closeFailure = new Error('close failed') + const spawned = { close: vi.fn().mockRejectedValue(closeFailure) } + + const failure = await cleanupAcpExampleTest(spawned, '\0').catch((error: unknown) => error) + + expect(failure).toBeInstanceOf(AggregateError) + expect((failure as AggregateError).errors).toHaveLength(2) + expect((failure as AggregateError).errors[0]).toBe(closeFailure) + }) +}) diff --git a/examples/acp-agent/tests/cleanup.ts b/examples/acp-agent/tests/cleanup.ts new file mode 100644 index 0000000000..28a896334a --- /dev/null +++ b/examples/acp-agent/tests/cleanup.ts @@ -0,0 +1,23 @@ +/** Shared teardown for ACP example tests. */ + +import { rm } from 'node:fs/promises' +import type { LaunchedAcpTestAgent } from '@deepseek-ai/dsh-acp-snapshot' + +/** + * Close the test agent, then remove its workspace, attempting both operations + * and reporting every failure instead of allowing the later one to mask the + * earlier one. + */ +export async function cleanupAcpExampleTest( + spawned: Pick | undefined, + workdir: string | undefined, +): Promise { + const results: PromiseSettledResult[] = [] + if (spawned !== undefined) results.push(...await Promise.allSettled([spawned.close('SIGKILL')])) + if (workdir !== undefined) results.push(...await Promise.allSettled([rm(workdir, { recursive: true, force: true })])) + + const failures = results + .filter((result): result is PromiseRejectedResult => result.status === 'rejected') + .map(result => result.reason as unknown) + if (failures.length > 0) throw new AggregateError(failures, 'ACP example cleanup failed') +} diff --git a/examples/acp-agent/tests/escalation.e2e.ts b/examples/acp-agent/tests/escalation.e2e.ts index da8d3408c2..3b84dd721c 100644 --- a/examples/acp-agent/tests/escalation.e2e.ts +++ b/examples/acp-agent/tests/escalation.e2e.ts @@ -1,5 +1,5 @@ import { spawnSync } from 'node:child_process' -import { mkdtemp, readFile, rm } from 'node:fs/promises' +import { mkdtemp, readFile } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' @@ -13,6 +13,7 @@ import { type AgentUnderTest, type LaunchedAcpTestAgent, } from '@deepseek-ai/dsh-acp-snapshot' +import { cleanupAcpExampleTest } from './cleanup.ts' /** * The default ACP composition (`cordis.yml`) end to end. @@ -81,16 +82,11 @@ let spawned: Spawned | undefined let workdir: string | undefined afterEach(async () => { - try { - await spawned?.close('SIGKILL') - } finally { - spawned = undefined - try { - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - } finally { - workdir = undefined - } - } + const ownedSpawned = spawned + const ownedWorkdir = workdir + spawned = undefined + workdir = undefined + await cleanupAcpExampleTest(ownedSpawned, ownedWorkdir) }) describe('default sandbox composition keyless smoke (real cordis.yml via the Loader)', () => { diff --git a/examples/acp-agent/tests/hooks.e2e.ts b/examples/acp-agent/tests/hooks.e2e.ts index df231184c3..dbe98ab358 100644 --- a/examples/acp-agent/tests/hooks.e2e.ts +++ b/examples/acp-agent/tests/hooks.e2e.ts @@ -1,4 +1,4 @@ -import { mkdtemp, rm, writeFile, access } from 'node:fs/promises' +import { mkdtemp, writeFile, access } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' @@ -9,6 +9,7 @@ import { type AgentUnderTest, type LaunchedAcpTestAgent, } from '@deepseek-ai/dsh-acp-snapshot' +import { cleanupAcpExampleTest } from './cleanup.ts' /** * With-key e2e: the Claude Code hook bridge running against the REAL acp-agent @@ -38,16 +39,11 @@ let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - try { - await spawned?.close('SIGKILL') - } finally { - spawned = undefined - try { - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - } finally { - workdir = undefined - } - } + const ownedSpawned = spawned + const ownedWorkdir = workdir + spawned = undefined + workdir = undefined + await cleanupAcpExampleTest(ownedSpawned, ownedWorkdir) }) describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: a PreToolUse hook blocks bash (real model)', () => { From dc60fe957272a439fa6ac920e1e42cb638f32d6e Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Tue, 14 Jul 2026 14:23:02 +0800 Subject: [PATCH 106/359] Avoid retaining processed session seqs --- .../2026-07-13-session-query-tracing.md | 2 +- packages/core/session/README.md | 2 +- packages/core/session/src/index.ts | 2 +- packages/core/session/src/surface.ts | 38 ++++++++++--------- packages/core/session/tests/surface.spec.ts | 2 +- .../session-query/session-query/README.md | 2 +- .../invariants/tests/invariants.spec.ts | 28 +------------- 7 files changed, 27 insertions(+), 49 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md b/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md index 9ebb8ee961..f16f543ac5 100644 --- a/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md +++ b/docs/rfc/implemented/feature/2026-07-13-session-query-tracing.md @@ -16,7 +16,7 @@ Session relationships are encoded across immutable headers, positional surface o ## Validation boundary -Event tracing checks target existence before surface analysis. Both event listing and tracing then use `dsh-session`'s one-pass surface fold, which accepts or rejects the loaded log as a whole: surface markers obey event-type eligibility, provenance belongs only to surface event types, present arrays are nonempty and duplicate-free, every source is a known earlier seq, and every positional replacement names and cites all surface nodes it removes. Every contract failure uses `SESSION_QUERY_INVALID_SURFACE`; there is no weaker classification-only surface standard. +Event tracing checks target existence before surface analysis. Both event listing and tracing then use `dsh-session`'s one-pass surface fold, which accepts or rejects the loaded log as a whole: event seqs are zero-based and contiguous, surface markers obey event-type eligibility, provenance belongs only to surface event types, present arrays are nonempty and duplicate-free, every source is an earlier seq, and every positional replacement names and cites all surface nodes it removes. Every contract failure uses `SESSION_QUERY_INVALID_SURFACE`; there is no weaker classification-only surface standard. All returned records and arrays are detached. A known live event trace never consults persistence; persisted event traces preserve the exact-read list/load consistency check. Session lineage is necessarily a cross-corpus operation and therefore preserves cross-corpus persistence failure semantics. diff --git a/packages/core/session/README.md b/packages/core/session/README.md index 7632212621..18eb6ebd82 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -49,7 +49,7 @@ Durable values need one accepted representation, not a check followed by a secon - `SurfaceOp` — how a surface node entered the linked list: `'append'` (normal tail append) or `{ op: 'replace', start, end }` (replace nodes from `start` through `end` inclusive — both must be valid surface node seqs; `start === end` replaces a single node). Used by compaction to shadow old nodes without deleting them. - `SurfaceIntent` — `{ surfaceOp: SurfaceOp; sourceEventSeqs?: number[] }`, the required third parameter to `session.append()` for surface-eligible types. - `SurfaceNode` — `{ seq: number; prev: number | null; next: number | null }`, one node in the surface linked list. -- `foldSurface(events)` — replay the one canonical surface contract into detached current nodes and actual replacement ranges. The same pass rejects misplaced or malformed metadata, empty or duplicate provenance, unknown or non-earlier sources, invalid positional ranges, and replacements that fail to cite every shadowed surface node; `SurfaceManager` shares the atomic transition while retaining its incremental cache. +- `foldSurface(events)` — replay the one canonical surface contract into detached current nodes and actual replacement ranges. The same pass rejects non-contiguous event seqs, misplaced or malformed metadata, empty or duplicate provenance, non-earlier sources, invalid positional ranges, and replacements that fail to cite every shadowed surface node; `SurfaceManager` shares the atomic transition while retaining its incremental cache. - `isSurfaceEvent(event)` / `isSurfaceEligibleType(type)` — the first narrows a `SessionEvent` to a fully-formed surface node (type is surface-eligible AND `surfaceOp` present); the second is the type-only check (is this one of the five `SurfaceEventType` values?), used to detect a surface-eligible event MISSING its marker — e.g. when validating a seed/load log. ### Request-header reconstruction (`request-header.ts`) diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index fc3a7fcd29..3c881882ba 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -328,7 +328,7 @@ export class Session { * (BigInt, function, symbol, undefined, negative zero, non-finite number, * circular reference, sparse array, or an exotic object such as * Map/Set/Date/class instance), or when the candidate violates the - * canonical surface contract (marker shape and eligibility, unique known + * canonical surface contract (marker shape and eligibility, unique * earlier provenance, positional replacement validity, and complete * shadowed-node coverage). One recursive pass reads, validates, and * copies each nested value once, so a stateful getter cannot supply one value diff --git a/packages/core/session/src/surface.ts b/packages/core/session/src/surface.ts index 7e1da76832..0d9e93e961 100644 --- a/packages/core/session/src/surface.ts +++ b/packages/core/session/src/surface.ts @@ -85,7 +85,6 @@ export interface SurfaceFoldResult { interface SurfaceFoldState { nodes: SurfaceNode[] nodeBySeq: Map - knownSeqs: Set replaceGeneration: number } @@ -106,7 +105,6 @@ function createFoldState(replaceGeneration = 0): SurfaceFoldState { return { nodes: [], nodeBySeq: new Map(), - knownSeqs: new Set(), replaceGeneration, } } @@ -163,7 +161,6 @@ function surfaceEventOf(event: SessionEvent): SurfaceEvent | undefined { /** Validate provenance against prior log entries and the replacement range. */ function assertProvenance( event: SurfaceEvent, - knownSeqs: ReadonlySet, shadowedSeqs: readonly number[], ): void { const sources = event.sourceEventSeqs @@ -178,9 +175,6 @@ function assertProvenance( if (source >= event.seq) { throw new Error(`sourceEventSeqs must reference earlier events: ${source} >= current seq ${event.seq}`) } - if (!knownSeqs.has(source)) { - throw new Error(`sourceEventSeqs references unknown seq ${source}`) - } } const missing = shadowedSeqs.filter(seq => !sourceSet.has(seq)) if (missing.length > 0) { @@ -213,16 +207,23 @@ function replacementRange( } } -/** Validate one event and prepare its atomic fold transition. */ -function planSurfaceEvent(state: SurfaceFoldState, event: SessionEvent): SurfacePlan | undefined { +/** Validate one event at its replay boundary and prepare its atomic fold transition. */ +function planSurfaceEvent( + state: SurfaceFoldState, + event: SessionEvent, + expectedSeq: number, +): SurfacePlan | undefined { + if (event.seq !== expectedSeq) { + throw new Error(`session event seq ${event.seq} is not contiguous; expected ${expectedSeq}`) + } const surfaceEvent = surfaceEventOf(event) if (surfaceEvent === undefined) return if (surfaceEvent.surfaceOp === 'append') { - assertProvenance(surfaceEvent, state.knownSeqs, []) + assertProvenance(surfaceEvent, []) return { kind: 'append', seq: event.seq } } const range = replacementRange(state, surfaceEvent.surfaceOp) - assertProvenance(surfaceEvent, state.knownSeqs, range.shadowedSeqs) + assertProvenance(surfaceEvent, range.shadowedSeqs) return { kind: 'replace', seq: event.seq, @@ -257,8 +258,9 @@ function replaceSurface(state: SurfaceFoldState, plan: SurfaceReplacePlan): void function applySurfaceEvent( state: SurfaceFoldState, event: SessionEvent, + expectedSeq: number, ): SurfaceFoldReplacement | undefined { - const plan = planSurfaceEvent(state, event) + const plan = planSurfaceEvent(state, event, expectedSeq) if (plan?.kind === 'append') { const tail = state.nodes.at(-1) const node: SurfaceNode = { seq: plan.seq, prev: tail?.seq ?? null, next: null } @@ -268,7 +270,6 @@ function applySurfaceEvent( } else if (plan?.kind === 'replace') { replaceSurface(state, plan) } - state.knownSeqs.add(event.seq) if (plan?.kind !== 'replace') return return { seq: plan.seq, @@ -287,14 +288,15 @@ function applySurfaceEvent( * @param events - session events in contiguous seq order. * @returns the current surface and every positional replacement. * @throws when any event violates the unified surface contract: metadata must - * be well shaped and type-eligible, provenance must name unique known earlier - * events, and a positional replacement must name and cite its complete range. + * be well shaped and type-eligible, event seqs must be contiguous, provenance + * must name unique earlier events, and a positional replacement must name and + * cite its complete range. */ export function foldSurface(events: readonly SessionEvent[]): SurfaceFoldResult { const state = createFoldState() const replacements: SurfaceFoldReplacement[] = [] - for (const event of events) { - const replacement = applySurfaceEvent(state, event) + for (const [index, event] of events.entries()) { + const replacement = applySurfaceEvent(state, event, index) if (replacement !== undefined) replacements.push(replacement) } return { @@ -326,7 +328,7 @@ export class SurfaceManager { */ validateNext(event: SessionEvent): void { if (this._lastProcessedSeq < this.log.length - 1) this._processDelta() - planSurfaceEvent(this._state, event) + planSurfaceEvent(this._state, event, this.log.length) } /** @@ -370,7 +372,7 @@ export class SurfaceManager { // Index is bounded by i < this.log.length — never undefined. // eslint-disable-next-line @typescript-eslint/no-non-null-assertion const event = this.log[i]! - applySurfaceEvent(this._state, event) + applySurfaceEvent(this._state, event, i) this._lastProcessedSeq = i } } diff --git a/packages/core/session/tests/surface.spec.ts b/packages/core/session/tests/surface.spec.ts index e1f948f2b1..2fab5075aa 100644 --- a/packages/core/session/tests/surface.spec.ts +++ b/packages/core/session/tests/surface.spec.ts @@ -62,7 +62,7 @@ describe('foldSurface provenance', () => { ['a fractional number', [provenanceEvent(0, [0.5])], /non-negative safe integers/], ['a negative number', [provenanceEvent(0, [-1])], /non-negative safe integers/], ['a self reference', [provenanceEvent(0, [0])], /must reference earlier events/], - ['an unknown earlier seq', [provenanceEvent(0, undefined), provenanceEvent(2, [1])], /references unknown seq 1/], + ['a non-contiguous event seq', [provenanceEvent(0, undefined), provenanceEvent(2, [1])], /seq 2 is not contiguous; expected 1/], ['incomplete replacement coverage', [ provenanceEvent(0, undefined), provenanceEvent(1, undefined), diff --git a/packages/session-query/session-query/README.md b/packages/session-query/session-query/README.md index 4f9f8122b4..2be712bd9b 100644 --- a/packages/session-query/session-query/README.md +++ b/packages/session-query/session-query/README.md @@ -14,7 +14,7 @@ This is trusted context-wide infrastructure. It performs no caller authorization Persistence is optional and may mount or unmount dynamically. Cross-corpus listing and lineage tracing fail with `SESSION_QUERY_PERSISTENCE_FAILED` while mounted persistence is unreadable. An event read or trace targeting a known live session does not consult persistence, so durable backend health cannot make current in-memory history unreadable. Persisted event operations list before loading and reject a metadata mismatch rather than combining inconsistent observations. -`listEvents()` and `traceEvent()` run the same one-pass `dsh-session` surface fold. A loaded log is valid only when surface markers obey event-type eligibility, provenance arrays are nonempty and duplicate-free, references name known earlier events, and each positional replacement names and cites every surface node it removes; every violation fails with `SESSION_QUERY_INVALID_SURFACE`. +`listEvents()` and `traceEvent()` run the same one-pass `dsh-session` surface fold. A loaded log is valid only when event seqs are zero-based and contiguous, surface markers obey event-type eligibility, provenance arrays are nonempty and duplicate-free, references name earlier events, and each positional replacement names and cites every surface node it removes; every violation fails with `SESSION_QUERY_INVALID_SURFACE`. `SessionQueryError.code` is a closed union: `SESSION_QUERY_EVENT_NOT_FOUND`, `SESSION_QUERY_INVALID_CONFIG`, `SESSION_QUERY_INVALID_LINEAGE`, `SESSION_QUERY_INVALID_SURFACE`, `SESSION_QUERY_INVALID_WINDOW`, `SESSION_QUERY_PERSISTENCE_FAILED`, `SESSION_QUERY_SESSION_NOT_FOUND`, and `SESSION_QUERY_SOURCE_CONFLICT`. diff --git a/packages/support/invariants/tests/invariants.spec.ts b/packages/support/invariants/tests/invariants.spec.ts index d5f43d1568..7c83f4571d 100644 --- a/packages/support/invariants/tests/invariants.spec.ts +++ b/packages/support/invariants/tests/invariants.spec.ts @@ -520,7 +520,8 @@ describe('surface contract under the invariants composition', () => { }) it('accepts sourceEventSeqs referencing a valid earlier event', async () => { - // Positive test: ref < current seq and ref is in knownSeqs → passes. + // Session seqs are contiguous, so every non-negative ref below the current + // seq necessarily names an existing earlier event. const { ctx } = await setup() const session = ctx.sessions.create() session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) @@ -540,31 +541,6 @@ describe('surface contract under the invariants composition', () => { }).toThrow(/must reference earlier/) }) - it('rejects sourceEventSeqs referencing unknown seq (gap in event log)', async () => { - // The unknown-seq check fires when a ref passes the "earlier" test but is - // not in the folded log — only possible with a gap in seqs. We create a gap by - // directly manipulating the private log array to skip a seq. - const { ctx } = await setup() - const session = ctx.sessions.create() - session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - session.append('step/start', { turn: 1, step: 1 }) - // Push a fake event at seq 3 into the internal log, creating a gap at seq 2. - // The canonical surface validator folds the committed delta before checking - // the next append, so it sees this gap. - ;(session as unknown as { log: unknown[] }).log.push({ - type: 'assistant/chunk', - seq: 3, - time: Date.now(), - data: { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'x' } }, - }) - // Now the log has seqs 0, 1, 3 (gap at 2). Append at what session believes - // is seq 3 (log.length). Reference seq 2: passes earlier (2 < 3) but not - // in knownSeqs ({0, 1, 3} — gap at 2). - expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [2] }) - }).toThrow(/unknown seq 2/) - }) - it('rejects a replace whose start is positioned after its end on the surface', async () => { const { ctx } = await setup() const session = ctx.sessions.create() From b58cf7ec2fdb3ba7d88ec097766dd47f2a188a2a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 14:24:21 +0800 Subject: [PATCH 107/359] fix: coordinate overlapping configured reloads --- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 2 +- docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/index.ts | 35 +++++++++++++++ .../tests/config-session-id.spec.ts | 44 +++++++++++++++++++ packages/ui/stdio-agent/src/stdio-chat.ts | 13 +++++- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 12 +++-- 9 files changed, 103 insertions(+), 11 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 173806572a..9bebe62380 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:354`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:361`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index df3aec8b12..f913b95c36 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -185,7 +185,7 @@ A declarative agent entry failed before it could publish a live agent. Consumers 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` -Source: [`packages/core/agent-loop/src/index.ts:349`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:356`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index d3e8b74edf..e4e68fe17f 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:369`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:376`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index cc155ebb16..2b62ec93eb 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:349`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:356`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index e27e8b625a..881d60027a 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. An overlapping remount waits for an already-disposed same-id agent to finish detaching both registries before it inspects persistence, so asynchronous teardown cannot strand the configured identity. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 06c108d324..3274e36587 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -53,6 +53,7 @@ function renderThrown(value: unknown): string { /** Factory-level ownership of every preparing or live transaction. */ class FactoryOwnership { private accepting = true + private readonly inactive = Promise.withResolvers() private transactions = new Set() private startupTasks = new Set>() @@ -74,8 +75,14 @@ class FactoryOwnership { void task.then(forget, forget) } + /** Resolve `task`, or stop waiting when factory teardown begins. */ + async waitWhileActive(task: Promise): Promise { + await Promise.race([task, this.inactive.promise]) + } + async dispose(): Promise { this.accepting = false + this.inactive.resolve() const reason = new Error('agent loop is not active') await Promise.all([ ...[...this.transactions].map(transaction => transaction.disposeForFactory(reason)), @@ -455,6 +462,8 @@ export class AgentLoop extends Service implements AgentFactory { agentOptions: AgentOptions, meta: Pick, ): Promise { + await this.waitForDrainingConfiguredIdentity(ownerCtx, sessionId) + if (!this.ownership.isActive()) return const exists = (await persistence.list()).some(header => header.id === sessionId) if (!this.ownership.isActive()) return if (exists) { @@ -464,6 +473,32 @@ export class AgentLoop extends Service implements AgentFactory { this.create(sessionId, agentOptions, meta) } + /** Wait for an already-disposed same-id lifecycle to finish registry teardown. */ + private async waitForDrainingConfiguredIdentity(ownerCtx: Context, sessionId: SessionId): Promise { + const current = ownerCtx.agents.get(sessionId) + if (current?.status !== 'disposed') return + + const released = Promise.withResolvers() + const checkReleased = (): void => { + if (ownerCtx.agents.get(sessionId) === undefined && ownerCtx.sessions.get(sessionId) === undefined) { + released.resolve() + } + } + const disposeAgentListener = ownerCtx.on('agent/disposed', (agent) => { + if (agent.id === sessionId) checkReleased() + }) + const disposeSessionListener = ownerCtx.on('session/disposed', (session) => { + if (session.id === sessionId) checkReleased() + }) + try { + checkReleased() + await this.ownership.waitWhileActive(released.promise) + } finally { + disposeAgentListener() + disposeSessionListener() + } + } + /** * Create an agent and session under one caller-supplied identity, owned by * the accessing fiber. Constructor-driven config calls mint a fresh combined diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 53782fe03c..fda5681c29 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -92,6 +92,50 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('waits for a draining exact-id lifecycle during an overlapping reload', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-overlap-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const sessionId = SessionId('stdio-exact-overlap') + const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] } + const firstLoop = await ctx.plugin(AgentLoop, config) + await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() + const first = ctx.agents.get(sessionId) as ReactLoopAgent + + const flushGate = Promise.withResolvers() + let flushStarted = false + ctx.on('session/flush', (session) => { + if (session !== first.session) return + flushStarted = true + return flushGate.promise + }) + first.inject([{ type: 'text', text: 'persist before replacement' }], { + source: { kind: 'plugin', plugin: 'test' }, + }) + expect(flushStarted).toBe(true) + + const firstDisposal = firstLoop.dispose() + await expect.poll(() => first.status).toBe('disposed') + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', (_id, error) => { failures.push(error) }) + const secondLoop = await ctx.plugin(AgentLoop, config) + await new Promise(resolve => setTimeout(resolve, 0)) + expect(ctx.agents.get(sessionId)).toBe(first) + expect(failures).toEqual([]) + + flushGate.resolve(undefined) + await firstDisposal + await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() + const second = ctx.agents.get(sessionId) as ReactLoopAgent + expect(second).not.toBe(first) + expect(JSON.stringify(second.session.deriveMessages())).toContain('persist before replacement') + expect(failures).toEqual([]) + + await secondLoop.dispose() + await ctx.fiber.dispose() + }) + it('contains an exact-id persistence lookup failure', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-')) dirs.push(root) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 39d59dfdc0..4505f19b98 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -67,6 +67,15 @@ function isTTYPair(input: Readable, output: Writable): boolean { return Boolean((input as { isTTY?: boolean }).isTTY && (output as { isTTY?: boolean }).isTTY) } +/** Render an arbitrary failure without allowing hostile coercion to escape the UI boundary. */ +function renderThrown(value: unknown): string { + try { + return String(value) + } catch { + return '' + } +} + interface PendingQuestion { request: AskUserQuestionRequest questionIndex: number @@ -230,7 +239,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt queuedInput.length = 0 submittedWork = sawRunning if (dropped > 0) { - ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (${dropped} line(s)): ${String(error)}`) + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (${dropped} line(s)): ${renderThrown(error)}`) } maybeExit() }) @@ -390,7 +399,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const text = line.trim() if (!text) return if (failedStartup !== undefined) { - ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ${String(failedStartup.error)}`) + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ${renderThrown(failedStartup.error)}`) return } const agent = target diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 11e64ac19c..c303577c48 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -83,6 +83,10 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { const CONFIG: Config = { welcome: 'hi there', sessionId: 'main' } +function unrenderableFailure(): unknown { + return { [Symbol.toPrimitive](): never { throw new Error('coercion escaped') } } +} + async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() await ctx.plugin(AgentRegistry) @@ -753,14 +757,14 @@ describe('createStdioChat input', () => { it('drops later input after the configured startup fails', async () => { const { ctx, input } = await setup() const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) - const failure = new Error('persisted session is corrupt') + const failure = unrenderableFailure() ctx.emit('agent-loop/config-start-failed', SessionId('main'), failure) input.feed('cannot run') await new Promise(r => setImmediate(r)) expect(error).toHaveBeenCalledWith( - 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: persisted session is corrupt', + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ', ) }) @@ -844,11 +848,11 @@ describe('createStdioChat EOF exit', () => { await flushExit() expect(exit).not.toHaveBeenCalled() - ctx.emit('agent-loop/config-start-failed', SessionId('main'), new Error('missing persisted session')) + ctx.emit('agent-loop/config-start-failed', SessionId('main'), unrenderableFailure()) await flushExit() expect(error).toHaveBeenCalledWith( - 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: missing persisted session', + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ', ) expect(exit).toHaveBeenCalledWith(0) }) From 7e9bf9b951913b1c5d70b5e94e22ccd8f60bed76 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 15:03:01 +0800 Subject: [PATCH 108/359] refactor: remove impossible ACP drain branch --- packages/support/acp-snapshot/src/launcher.ts | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 30ca0b42b8..c0dc21dc06 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -178,14 +178,13 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // `closed` follows parser exhaustion. Capture both eagerly so a caller that // invokes close after process exit still joins the complete drain boundary. const stdioClosed = new Promise(resolve => child.once('close', () => { resolve() })) - const drained = Promise.allSettled([stdioClosed, client.closed]).then(async ([, clientResult]) => { + const drained = Promise.all([stdioClosed, client.closed]).then(async () => { // The ACP SDK's readable loop dispatches client callbacks without awaiting // them. Once `closed` settles no new callbacks can start, but callbacks // already in flight still belong to this launch's teardown boundary. while (inFlightClientCallbacks.size > 0) { await Promise.allSettled([...inFlightClientCallbacks]) } - if (clientResult.status === 'rejected') throw clientResult.reason }) // A caller may await a pending update without calling close(). Make natural // stream exhaustion terminal for those waiters too, but only after the @@ -207,7 +206,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe try { await spawned } catch (error: unknown) { - await drained.catch(() => undefined) + await drained closeUpdateStream() throw error } From d83aa8d11aa217fdbee379dce37aa5146228dd21 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 15:31:00 +0800 Subject: [PATCH 109/359] test: cover exact-id reload cancellation --- packages/core/agent-loop/src/index.ts | 8 +- .../tests/config-session-id.spec.ts | 85 +++++++++++++------ 2 files changed, 62 insertions(+), 31 deletions(-) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 3274e36587..ff0c692928 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -484,12 +484,8 @@ export class AgentLoop extends Service implements AgentFactory { released.resolve() } } - const disposeAgentListener = ownerCtx.on('agent/disposed', (agent) => { - if (agent.id === sessionId) checkReleased() - }) - const disposeSessionListener = ownerCtx.on('session/disposed', (session) => { - if (session.id === sessionId) checkReleased() - }) + const disposeAgentListener = ownerCtx.on('agent/disposed', checkReleased) + const disposeSessionListener = ownerCtx.on('session/disposed', checkReleased) try { checkReleased() await this.ownership.waitWhileActive(released.promise) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index fda5681c29..ceaf6597cb 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -136,6 +136,37 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('cancels an exact-id reload while the prior lifecycle is still draining', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-cancel-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const sessionId = SessionId('stdio-exact-cancel') + const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] } + const firstLoop = await ctx.plugin(AgentLoop, config) + await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() + const first = ctx.agents.get(sessionId) as ReactLoopAgent + + const flushGate = Promise.withResolvers() + ctx.on('session/flush', (session) => { + if (session === first.session) return flushGate.promise + }) + first.inject([{ type: 'text', text: 'persist before cancellation' }], { + source: { kind: 'plugin', plugin: 'test' }, + }) + + const firstDisposal = firstLoop.dispose() + await expect.poll(() => first.status).toBe('disposed') + const secondLoop = await ctx.plugin(AgentLoop, config) + await secondLoop.dispose() + expect(ctx.agents.get(sessionId)).toBe(first) + + flushGate.resolve(undefined) + await firstDisposal + expect(ctx.agents.get(sessionId)).toBeUndefined() + await ctx.fiber.dispose() + }) + it('contains an exact-id persistence lookup failure', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-')) dirs.push(root) @@ -208,33 +239,37 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) - it('joins an exact-id persistence lookup before AgentLoop disposal completes', async () => { - const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) - dirs.push(root) - const ctx = await makeCoreContext() - await ctx.plugin(SessionPersistenceJsonl, { root }) - const listing = Promise.withResolvers>>() - vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) - const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const failures: unknown[] = [] - ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) + it.each(['resolve', 'reject'] as const)( + 'joins an exact-id persistence lookup that will %s before AgentLoop disposal completes', + async (outcome) => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const listing = Promise.withResolvers>>() + vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) - const loop = await ctx.plugin(AgentLoop, { - agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], - }) - let disposed = false - const disposal = loop.dispose().then(() => { disposed = true }) - await Promise.resolve() - expect(disposed).toBe(false) + const loop = await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], + }) + let disposed = false + const disposal = loop.dispose().then(() => { disposed = true }) + await Promise.resolve() + expect(disposed).toBe(false) - listing.reject(new Error('startup cancelled by teardown')) - await disposal - expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() - expect(failures).toEqual([]) - expect(warn).not.toHaveBeenCalled() - warn.mockRestore() - await ctx.fiber.dispose() - }) + if (outcome === 'resolve') listing.resolve([]) + else listing.reject(new Error('startup cancelled by teardown')) + await disposal + expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() + expect(failures).toEqual([]) + expect(warn).not.toHaveBeenCalled() + warn.mockRestore() + await ctx.fiber.dispose() + }, + ) it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() From 4a5463cfc49b8f505b5f47aa7634909c08602a08 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 16:53:38 +0800 Subject: [PATCH 110/359] test: use the public agent type --- packages/core/agent-loop/tests/config-session-id.spec.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index f001fa3154..2c8a5c31bd 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -145,7 +145,7 @@ describe('config-driven session id', () => { const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] } const firstLoop = await ctx.plugin(AgentLoop, config) await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() - const first = ctx.agents.get(sessionId) as ReactLoopAgent + const first = ctx.agents.get(sessionId) as Agent const flushGate = Promise.withResolvers() ctx.on('session/flush', (session) => { From c5ac667e863050c91a5308f55d62cb8eeabf05fd Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Tue, 14 Jul 2026 17:20:57 +0800 Subject: [PATCH 111/359] refactor(session-query): simplify tracing helpers --- .../session-query/session-query/src/index.ts | 8 ++++---- .../session-query/src/tracing.ts | 19 ++++++++----------- 2 files changed, 12 insertions(+), 15 deletions(-) diff --git a/packages/session-query/session-query/src/index.ts b/packages/session-query/session-query/src/index.ts index e5659c554a..bd35b51442 100644 --- a/packages/session-query/session-query/src/index.ts +++ b/packages/session-query/session-query/src/index.ts @@ -22,7 +22,7 @@ import { type Config, } from './config.ts' import { SessionCorpus } from './corpus.ts' -import { eventRecords, traceEventLog, traceLineage } from './tracing.ts' +import * as tracing from './tracing.ts' export type * from './types.ts' export type { Config, SessionQueryErrorCode } from './config.ts' @@ -71,7 +71,7 @@ export class SessionQueryService extends Service { */ async listEvents(sessionId: SessionId): Promise { const loaded = await this._corpus.load(sessionId) - return eventRecords(sessionId, loaded.events) + return tracing.eventRecords(sessionId, loaded.events) } /** @@ -82,7 +82,7 @@ export class SessionQueryService extends Service { */ async traceSession(sessionId: SessionId): Promise { const records = await this._corpus.listSessions() - return traceLineage(records, sessionId) + return tracing.traceSession(records, sessionId) } /** @@ -93,7 +93,7 @@ export class SessionQueryService extends Service { */ async traceEvent(request: SessionEventTraceRequest): Promise { const loaded = await this._corpus.load(request.sessionId) - return traceEventLog(request.sessionId, loaded.events, request.seq) + return tracing.traceEvent(request.sessionId, loaded.events, request.seq) } /** diff --git a/packages/session-query/session-query/src/tracing.ts b/packages/session-query/session-query/src/tracing.ts index c7b5143b67..2f422d6c26 100644 --- a/packages/session-query/session-query/src/tracing.ts +++ b/packages/session-query/session-query/src/tracing.ts @@ -37,7 +37,7 @@ export function eventRecords( * @param seq - target event seq. * @returns direct surface and provenance relationships. */ -export function traceEventLog( +export function traceEvent( sessionId: SessionId, events: readonly SessionEvent[], seq: number, @@ -59,7 +59,6 @@ export function traceEventLog( replacement = analysis.replacedBy.get(replacement) } - const sourceEventSeqs = eventSources(target) const derivedEventSeqs: number[] = [] for (const event of events) { if (event.seq <= seq) continue @@ -71,11 +70,11 @@ export function traceEventLog( const targetRecord = analysis.records[seq]! const replacedBy = analysis.replacedBy.get(seq) return { - target: { ...targetRecord }, + target: targetRecord, ...replacedBy === undefined ? {} : { replacedBy }, replacementChain, - replacedEventSeqs: [...(analysis.replacedEventSeqs.get(seq) ?? [])], - sourceEventSeqs: [...sourceEventSeqs], + replacedEventSeqs: analysis.replacedEventSeqs.get(seq) ?? [], + sourceEventSeqs: [...eventSources(target)], derivedEventSeqs, } } @@ -86,7 +85,7 @@ export function traceEventLog( * @param sessionId - target session id. * @returns complete or explicitly partial lineage. */ -export function traceLineage( +export function traceSession( records: readonly SessionRecord[], sessionId: SessionId, ): SessionLineageTrace { @@ -164,14 +163,12 @@ function analyzeEventLog( ) } const current = new Set(folded.nodes.map(node => node.seq)) - const shadowed = new Set() const replacedBy = new Map() const replacedEventSeqs = new Map() for (const replacement of folded.replacements) { - const removed = [...replacement.shadowedSeqs] + const removed = replacement.shadowedSeqs replacedEventSeqs.set(replacement.seq, removed) for (const removedSeq of removed) { - shadowed.add(removedSeq) replacedBy.set(removedSeq, replacement.seq) } } @@ -183,14 +180,14 @@ function analyzeEventLog( time: event.time, surface: current.has(event.seq) ? 'current' - : shadowed.has(event.seq) ? 'shadowed' : 'log-only', + : replacedBy.has(event.seq) ? 'shadowed' : 'log-only', })), replacedBy, replacedEventSeqs, } } -function eventSources(event: SessionEvent): number[] { +function eventSources(event: SessionEvent): readonly number[] { return (event as SessionEvent).sourceEventSeqs ?? [] } From 64a3933270a0f4636b36b485197597c66945599b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 19:03:07 +0800 Subject: [PATCH 112/359] docs: refresh config catalog after parent merge --- docs/config-catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 14cc973995..6f74792213 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -899,7 +899,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) -Source: [`packages/subagent/tool-subagent/src/index.ts:24`](../packages/subagent/tool-subagent/src/index.ts) +Source: [`packages/subagent/tool-subagent/src/index.ts:47`](../packages/subagent/tool-subagent/src/index.ts) ## `@deepseek-ai/dsh-tool-web` From 5409452cc705804386fe029908f14b31840efe96 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 19:30:29 +0800 Subject: [PATCH 113/359] test: refresh snapshots after master merge --- .../tests/snapshots/advanced-toolchain/session.1.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.2.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/stdout.golden.jsonl | 2 +- .../snapshots/advanced-toolchain/system-prompt.golden.md | 2 +- .../acp-agent/tests/snapshots/both-mode-turn/session.jsonl | 2 +- .../tests/snapshots/both-mode-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/both-mode-turn/system-prompt.golden.md | 2 +- .../acp-agent/tests/snapshots/cancel/stdout.golden.jsonl | 2 +- .../tests/snapshots/code-mode-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/code-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/config-options/stdout.golden.jsonl | 6 +++--- .../tests/snapshots/error-finish/stdout.golden.jsonl | 2 +- .../tests/snapshots/escalation-approved/session.jsonl | 4 ++-- .../tests/snapshots/escalation-approved/stdout.golden.jsonl | 4 ++-- .../tests/snapshots/escalation-rejected/session.jsonl | 4 ++-- .../tests/snapshots/escalation-rejected/stdout.golden.jsonl | 4 ++-- .../acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-policy-reject/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-read-window/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-terminal-card/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-write-overwrite/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/handshake/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-posttool-block/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-posttool-context/stdout.golden.jsonl | 2 +- .../tests/snapshots/hook-cc-pretool-ask/session.jsonl | 4 ++-- .../tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-pretool-deny/stdout.golden.jsonl | 2 +- .../hook-cc-promptsubmit-block/stdout.golden.jsonl | 2 +- .../hook-cc-promptsubmit-context/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-stop-continue/stdout.golden.jsonl | 2 +- .../snapshots/hook-codex-posttool-block/stdout.golden.jsonl | 2 +- .../hook-codex-posttool-context/stdout.golden.jsonl | 2 +- .../snapshots/hook-codex-pretool-block/stdout.golden.jsonl | 2 +- .../hook-codex-promptsubmit-block/stdout.golden.jsonl | 2 +- .../hook-codex-promptsubmit-context/stdout.golden.jsonl | 2 +- .../snapshots/hook-codex-stop-continue/stdout.golden.jsonl | 2 +- .../tests/snapshots/multi-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/permission-switching/session.jsonl | 2 +- .../snapshots/permission-switching/stdout.golden.jsonl | 6 +++--- .../tests/snapshots/repeat-tool-guard/stdout.golden.jsonl | 2 +- examples/acp-agent/tests/snapshots/skill-load/session.jsonl | 2 +- .../tests/snapshots/skill-load/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-fork/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-mixed/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-multi/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-spawn/stdout.golden.jsonl | 2 +- examples/acp-agent/tests/snapshots/text-turn/session.jsonl | 2 +- .../acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl | 2 +- .../tests/snapshots/tool-call-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/workflow-run/stdout.golden.jsonl | 2 +- .../tests/snapshots/workspace-edit/stdout.golden.jsonl | 2 +- 55 files changed, 64 insertions(+), 64 deletions(-) diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index 991806d74b..cdc09c92c0 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index a6a3371913..79d9b94ad9 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl index c6213cd558..7155b1c2a6 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl index bc4da17bb0..80a9cc9339 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-mount","title":"Mount plugin into live cordis runtime","kind":"execute","status":"in_progress","rawInput":{"code":"return { name: 'snapshot-marker', apply() {} }"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"advanced-mount","status":"completed","content":[{"type":"content","content":{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-code","title":"return await tools.cordis_inspect({ what: 'dynamic' })","kind":"execute","status":"in_progress","rawInput":"return await tools.cordis_inspect({ what: 'dynamic' })"}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index 5ad12cddff..6e8f157ace 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index a68bb37f9f..66cdecedfb 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl index 577f10445b..c9d2c87c27 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index ed60d52258..98b4f97fee 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl index 60235cac75..1f8c0ca024 100644 --- a/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl @@ -1,4 +1,4 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"partial"}}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl index bfa379815e..5fe0944ac7 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index ed60d52258..98b4f97fee 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl index aa033fb673..7c85717676 100644 --- a/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":5,"error":{"code":-32602,"message":"Invalid params: unknown permission value \"plan\""}} {"jsonrpc":"2.0","id":6,"error":{"code":-32602,"message":"Invalid params: unknown config option \"reasoning-effort\""}} diff --git a/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl index d5d4f1c400..99e00460c6 100644 --- a/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"error":{"code":-32603,"message":"Internal error: turn failed: simulated provider error (HTTP 401)"}} diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl index 8aac1627bc..74fbed6ee3 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl @@ -131,8 +131,8 @@ {"type":"assistant/chunk","seq":129,"time":1783962245385,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":130,"time":1783962245385,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a command with sandbox_permissions set to danger-full-access, no prior run needed, justified as instructed."},{"type":"tool-call","id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"usage":{"inputTokens":1501,"outputTokens":174,"cacheReadTokens":0,"reasoningTokens":28}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} {"type":"tool/call","seq":131,"time":1783962245385,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} -{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"3b0efb0e-5b4a-4911-87cf-9914bd346c17","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} -{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"3b0efb0e-5b4a-4911-87cf-9914bd346c17","outcome":"allowed-once"}} +{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"daa6d214-9e99-4cb6-b4f7-7f6086379133","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"daa6d214-9e99-4cb6-b4f7-7f6086379133","outcome":"allowed-once"}} {"type":"tool/result","seq":134,"time":1783962245399,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[131],"surfaceOp":"append"} {"type":"step/end","seq":135,"time":1783962245400,"data":{"turn":1,"step":1}} {"type":"step/start","seq":136,"time":1783962245400,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl index f438444dc4..5c63764aae 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl index 7c0a743413..bf86999cd9 100644 --- a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl @@ -155,8 +155,8 @@ {"type":"assistant/chunk","seq":153,"time":1783962246274,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":154,"time":1783962246274,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command with `sandbox_permissions` set to `danger-full-access` and a specific justification. They explicitly said NOT to run it without sandbox_permissions first. Let me do exactly that."},{"type":"tool-call","id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"usage":{"inputTokens":1509,"outputTokens":198,"cacheReadTokens":0,"reasoningTokens":48}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153],"surfaceOp":"append"} {"type":"tool/call","seq":155,"time":1783962246274,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} -{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"9e6c7946-af56-4535-9cce-993e0165c2f9","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} -{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"9e6c7946-af56-4535-9cce-993e0165c2f9","outcome":"rejected"}} +{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"71281495-1503-47de-bbdf-11d5de1e5f06","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"71281495-1503-47de-bbdf-11d5de1e5f06","outcome":"rejected"}} {"type":"tool/result","seq":158,"time":1783962246275,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"danger-full-access\""}],"isError":true},"sourceEventSeqs":[155],"surfaceOp":"append"} {"type":"step/end","seq":159,"time":1783962246276,"data":{"turn":1,"step":1}} {"type":"step/start","seq":160,"time":1783962246276,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl index b926355bd7..07e48d9e22 100644 --- a/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl index acc193ad1e..919c0f169e 100644 --- a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl index 5aa75c026c..c27544a176 100644 --- a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl index 05832400c8..8b75c30e8c 100644 --- a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl index 19abb7f418..30aa0d2460 100644 --- a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl index 0e7dcca6f8..e045c7b228 100644 --- a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl index 4801d9410d..f554fa3123 100644 --- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl index d5b3ca5d15..d04def6af2 100644 --- a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl index e4c4984fc5..312569a491 100644 --- a/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl @@ -1,2 +1,2 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl index 0a93b649da..36f050a694 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl index e9243d8a05..bbc16779ba 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl index b975c54aac..faed620b4c 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl @@ -55,8 +55,8 @@ {"type":"tool/call","seq":53,"time":1783352172557,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}} {"type":"hook/invoked","seq":54,"time":1783352172558,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":55,"time":1783352172573,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"ask","exitCode":0,"durationMs":14.113374999999905}} -{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"da1d1e2e-c13f-4e70-8039-a42ae8f84fd5","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} -{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"da1d1e2e-c13f-4e70-8039-a42ae8f84fd5","outcome":"rejected"}} +{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"7b519d67-ef63-4ba2-9b37-1493e1525329","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} +{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"7b519d67-ef63-4ba2-9b37-1493e1525329","outcome":"rejected"}} {"type":"tool/result","seq":58,"time":1783962235814,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","content":[{"type":"text","text":"Error: the user rejected tool \"bash\""}],"isError":true},"sourceEventSeqs":[53],"surfaceOp":"append"} {"type":"step/end","seq":59,"time":1783962235814,"data":{"turn":1,"step":1}} {"type":"step/start","seq":60,"time":1783962235814,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl index 3905e82ca7..db38650167 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl index 92906adb59..f0c5e005d9 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl index 6304582220..5d88350cad 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl index c4ad3ba541..ac203d50cc 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"'s"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl index 5c4a564d26..01297aa39d 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl index cbaec45f9f..57b297ccfc 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl index 4bf92f3197..faa1255a32 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl index 5459da1a17..11b47d6e58 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl index 6304582220..5d88350cad 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl index 8cae81a5c9..116a8ebbbd 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl index 66d8c816be..d231f60e0a 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl index 1d9d45954a..b45d9e947c 100644 --- a/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl index 0d8e018ae5..a30f9e4a46 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl @@ -5,7 +5,7 @@ {"type":"approval/policy","seq":3,"time":1783962244578,"data":{"policy":"ask"}} {"type":"user/message","seq":4,"time":1783962244578,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly this one command in a single call: printf 'before\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783962244579,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":7,"time":1783860667444,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":8,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":9,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl index 651897e850..9c3c78be5c 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} @@ -44,7 +44,7 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","id":4,"result":{"stopReason":"end_turn"}} -{"jsonrpc":"2.0","id":5,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":5,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl index a0901b6297..876f6c490a 100644 --- a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_1","title":"Update todo list","kind":"other","status":"in_progress","rawInput":[{"content":"watch the kettle boil","status":"in_progress"}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"plan","entries":[{"content":"watch the kettle boil","priority":"medium","status":"in_progress"}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_1","status":"completed","content":[{"type":"content","content":{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}}]}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 9a26fa2efe..1c85ee81ba 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl index 10198918d6..b5f25f2c07 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Load the requested skill."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skill_load","title":"Load skill snapshot-skill","kind":"read","status":"in_progress","rawInput":"snapshot-skill"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skill_load","status":"completed","content":[{"type":"content","content":{"type":"text","text":"\n\nBase directory for this skill: {{cwd}}/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n\n\n\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n\n"}}]}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl index 44fc4402fc..e390bda86a 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl index 08ad14dc9c..db5f28fa79 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl index 93b38e33cb..4c0c7d2601 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl index 26d45699cc..ce114fccf0 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index 0643740e4f..c66f5676cc 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl index 1059a9cc6c..8de447de6d 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl index f060b6b92f..a947ed4997 100644 --- a/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl index 041ea02703..9d06e9d6ac 100644 --- a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl index 9c0bbd37be..56b8f3537a 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl index 23f13ff3c2..513a02a6af 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} From b12b5f8a9536e99fad72024451b9c1df84300c8e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 20:03:28 +0800 Subject: [PATCH 114/359] test: refresh permission-switching header snapshot --- .../tests/snapshots/permission-switching/session.jsonl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl index 0d8e018ae5..07cd6233b3 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl @@ -107,7 +107,7 @@ {"type":"user/message","seq":105,"time":1783962244624,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"context/message","seq":106,"time":1783962244624,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"user-approval"}},"surfaceOp":"append"} {"type":"step/start","seq":107,"time":1783962244624,"data":{"turn":2,"step":1}} -{"type":"request/header","seq":108,"time":1784000791271,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"change"}} +{"type":"request/header","seq":108,"time":1784000791271,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"change"}} {"type":"assistant/chunk","seq":109,"time":1783860671025,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":110,"time":1783860671026,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":111,"time":1783860671026,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} From 8be096c540c6b82187051eab9febd461a46e4fc2 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 20:08:37 +0800 Subject: [PATCH 115/359] fix: preserve master bash guidance wording --- packages/bash/tool-bash/src/index.ts | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index 662b7a065f..4c699cd6c0 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -173,15 +173,15 @@ function bashDescription(escalationModes: readonly SandboxMode[]): string { + 'poll it with `bash_output` and stop it with `bash_kill`.' if (escalationModes.length === 0) return base return base + ' Attempting a command the sandbox may deny is safe and expected: run it and read the ' - + 'marker rather than assuming the denial. When a command IS denied and a wider mode would let it ' - + 'succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry ' + + 'marker rather than assuming the denial. When a command is denied and a wider mode would let it ' + + 'succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry ' + 'the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) ' + 'plus a one-sentence `justification`. Do not detour through chat to ask permission first — the ' - + 'approval prompt raised by that retry IS how the user consents. If the session states approval ' + + 'approval prompt raised by that retry is how the user consents. If the session states approval ' + 'prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. ' - + 'Never escalate speculatively: ground the request in a real denial — normally the one THIS command ' + + 'Never escalate speculatively: ground the request in a real denial — normally the one this command ' + 'just hit; escalating up front is fine only when this session already denied the same access. ' - + 'A rejected escalation is final for THAT command — stop and explain, never work around ' + + 'A rejected escalation is final for that command — stop and explain, never work around ' + 'it — but it does not forbid attempting or escalating other commands later.' } From 5a1194bf301ecd9f2ab007a599a2e121e57b72e6 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 20:18:24 +0800 Subject: [PATCH 116/359] test: refresh snapshots after bash guidance merge --- .../tests/snapshots/advanced-toolchain/session.1.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.2.jsonl | 2 +- .../acp-agent/tests/snapshots/advanced-toolchain/session.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/system-prompt.golden.md | 2 +- examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl | 2 +- .../tests/snapshots/both-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/code-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/permission-switching/session.jsonl | 2 +- examples/acp-agent/tests/snapshots/skill-load/session.jsonl | 2 +- examples/acp-agent/tests/snapshots/text-turn/session.jsonl | 2 +- 10 files changed, 10 insertions(+), 10 deletions(-) diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index cdc09c92c0..991806d74b 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index 79d9b94ad9..a6a3371913 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl index 7155b1c2a6..c6213cd558 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index 6e8f157ace..5ad12cddff 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index 66cdecedfb..a68bb37f9f 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index 98b4f97fee..ed60d52258 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index 98b4f97fee..ed60d52258 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl index 1f33766ec9..07cd6233b3 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl @@ -5,7 +5,7 @@ {"type":"approval/policy","seq":3,"time":1783962244578,"data":{"policy":"ask"}} {"type":"user/message","seq":4,"time":1783962244578,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly this one command in a single call: printf 'before\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783962244579,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":7,"time":1783860667444,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":8,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":9,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 1c85ee81ba..9a26fa2efe 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index c66f5676cc..0643740e4f 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} From e547980d77368fe83f6e4ad20956dc64f2d4e20d Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Tue, 14 Jul 2026 21:57:52 +0800 Subject: [PATCH 117/359] feat(llm): route adapters by provider --- docs/architecture.md | 2 +- docs/config-catalog.md | 71 ++- docs/cookbook/adding-an-llm-adapter.md | 7 +- docs/cordis-catalog/events.md | 28 +- docs/cordis-catalog/services.md | 8 +- docs/core-data-structures/compaction.md | 2 +- docs/core-data-structures/core.md | 26 +- docs/core-data-structures/llm-streaming.md | 14 +- docs/core-data-structures/session.md | 8 +- docs/event-producer-consumer.md | 28 +- docs/persistence-catalog.md | 8 +- docs/rfc/INDEX.md | 1 + ...2026-07-14-provider-routed-llm-adapters.md | 89 ++++ docs/tool-catalog.md | 8 +- .../acp-agent/advanced.cordis.snapshot.yml | 1 + examples/acp-agent/advanced.cordis.yml | 1 + .../acp-agent/both-mode.cordis.snapshot.yml | 1 + examples/acp-agent/both-mode.cordis.yml | 1 + .../acp-agent/code-mode.cordis.snapshot.yml | 1 + examples/acp-agent/code-mode.cordis.yml | 1 + examples/acp-agent/cordis.yml | 4 +- .../advanced-toolchain/session.1.jsonl | 4 +- .../advanced-toolchain/session.2.jsonl | 4 +- .../advanced-toolchain/session.jsonl | 14 +- .../system-prompt.golden.md | 4 +- .../snapshots/both-mode-turn/session.jsonl | 6 +- .../both-mode-turn/system-prompt.golden.md | 4 +- .../tests/snapshots/cancel/session.jsonl | 2 +- .../snapshots/code-mode-turn/session.jsonl | 6 +- .../code-mode-turn/system-prompt.golden.md | 4 +- .../snapshots/error-finish/session.jsonl | 2 +- .../tests/snapshots/fs-edit/session.jsonl | 8 +- .../snapshots/fs-policy-reject/session.jsonl | 10 +- .../snapshots/fs-read-window/session.jsonl | 6 +- .../tests/snapshots/fs-read/session.jsonl | 6 +- .../snapshots/fs-terminal-card/session.jsonl | 6 +- .../fs-write-overwrite/session.jsonl | 8 +- .../tests/snapshots/fs-write/session.jsonl | 6 +- .../hook-cc-posttool-block/session.jsonl | 20 +- .../hook-cc-posttool-context/session.jsonl | 6 +- .../hook-cc-pretool-ask/session.jsonl | 6 +- .../hook-cc-pretool-deny/session.jsonl | 6 +- .../session.jsonl | 4 +- .../hook-cc-stop-continue/session.jsonl | 6 +- .../hook-codex-posttool-block/session.jsonl | 6 +- .../hook-codex-posttool-context/session.jsonl | 6 +- .../hook-codex-pretool-block/session.jsonl | 6 +- .../session.jsonl | 4 +- .../hook-codex-stop-continue/session.jsonl | 6 +- .../tests/snapshots/multi-turn/session.jsonl | 6 +- .../snapshots/repeat-tool-guard/session.jsonl | 14 +- .../tests/snapshots/skill-load/session.jsonl | 6 +- .../snapshots/subagent-fork/session.1.jsonl | 8 +- .../snapshots/subagent-fork/session.jsonl | 8 +- .../snapshots/subagent-mixed/session.1.jsonl | 4 +- .../snapshots/subagent-mixed/session.2.jsonl | 8 +- .../snapshots/subagent-mixed/session.jsonl | 10 +- .../snapshots/subagent-multi/session.1.jsonl | 4 +- .../snapshots/subagent-multi/session.2.jsonl | 4 +- .../snapshots/subagent-multi/session.jsonl | 8 +- .../snapshots/subagent-spawn/session.1.jsonl | 4 +- .../snapshots/subagent-spawn/session.jsonl | 6 +- .../tests/snapshots/text-turn/session.jsonl | 4 +- .../tests/snapshots/todo-plan/session.jsonl | 6 +- .../snapshots/tool-call-turn/session.jsonl | 6 +- .../snapshots/workflow-run/session.1.jsonl | 4 +- .../snapshots/workflow-run/session.jsonl | 6 +- .../snapshots/workspace-edit/session.jsonl | 10 +- examples/coding-agent/code-mode.cordis.yml | 1 + examples/coding-agent/cordis.yml | 8 +- examples/coding-agent/tests/code-mode.e2e.ts | 4 +- .../coding-agent/tests/coding-task.e2e.ts | 2 +- examples/coding-agent/tests/compaction.e2e.ts | 3 +- examples/coding-agent/tests/full-loop.e2e.ts | 2 +- examples/coding-agent/tests/harness.ts | 2 +- examples/coding-agent/tests/resume.e2e.ts | 4 +- examples/coding-agent/tests/todo-write.e2e.ts | 2 +- examples/cordis-agent/cordis.yml | 4 +- .../cordis-agent/tests/cordis-tools.e2e.ts | 6 +- examples/cordis-agent/tests/harness.ts | 2 +- examples/echo-agent/cordis.yml | 1 + examples/echo-agent/src/mock-llm.ts | 2 +- examples/sandbox-acp-agent/cordis.yml | 3 +- .../escalation-approved/session.jsonl | 6 +- .../escalation-rejected/session.jsonl | 6 +- .../snapshots/mode-switching/session.jsonl | 12 +- .../bash/tool-bash/tests/integration.spec.ts | 6 +- packages/compact/compact-basic/README.md | 8 +- packages/compact/compact-basic/src/index.ts | 29 +- packages/compact/compact-basic/src/types.ts | 10 +- .../compact-basic/tests/compact-basic.spec.ts | 56 ++- .../tests/compact-loop-repro.spec.ts | 7 +- packages/compact/compact/README.md | 2 +- packages/compact/compact/src/types.ts | 2 + .../compact/compact/tests/compact.spec.ts | 1 + packages/compact/compact/tests/render.spec.ts | 4 +- .../cordis/tool-cordis/src/api-catalog.ts | 20 +- .../tool-cordis/tests/integration.spec.ts | 2 +- .../core/agent-core/tests/agent-core.spec.ts | 2 +- packages/core/agent-loop/README.md | 3 +- packages/core/agent-loop/src/index.ts | 2 + packages/core/agent-loop/src/loop.ts | 70 ++- packages/core/agent-loop/tests/agent.spec.ts | 50 +- packages/core/agent-loop/tests/cancel.spec.ts | 34 +- .../tests/config-session-id.spec.ts | 10 +- .../agent-loop/tests/coverage-edges.spec.ts | 16 +- .../agent-loop/tests/interception.spec.ts | 50 +- packages/core/agent-loop/tests/loop.spec.ts | 80 +-- .../core/agent-loop/tests/properties.spec.ts | 6 +- .../agent-loop/tests/request-cache.e2e.ts | 4 +- .../core/agent-loop/tests/request-log.spec.ts | 12 +- .../tests/request-reconstruction.spec.ts | 20 +- packages/core/agent-loop/tests/resume.spec.ts | 16 +- .../agent-loop/tests/review-fixes.spec.ts | 105 ++-- .../agent-loop/tests/scope-lifecycle.spec.ts | 86 ++-- .../core/agent-loop/tests/tool-order.spec.ts | 4 +- .../core/agent-loop/tests/turn-stop.spec.ts | 14 +- packages/core/agent/src/types.ts | 4 +- packages/core/session/README.md | 6 +- packages/core/session/src/index.ts | 29 +- packages/core/session/src/types.ts | 8 +- .../core/session/tests/derived-cache.spec.ts | 6 +- packages/core/session/tests/fork.spec.ts | 4 +- .../core/session/tests/properties.spec.ts | 4 +- packages/core/session/tests/repair.spec.ts | 14 +- .../core/session/tests/request-header.spec.ts | 16 +- packages/core/session/tests/session.spec.ts | 41 +- packages/core/session/tests/surface.spec.ts | 30 +- .../core/session/tests/tool-pairing.spec.ts | 14 +- packages/fs/tool-fs/tests/fs-tools.e2e.ts | 4 +- packages/fs/tool-fs/tests/harness.ts | 2 +- .../tests/repeat-tool-guard.spec.ts | 34 +- .../hooks/hooks-claude/tests/bridge.spec.ts | 20 +- .../hooks/hooks-claude/tests/coverage.spec.ts | 58 +-- .../hooks/hooks-codex/tests/bridge.spec.ts | 12 +- .../hooks/hooks-codex/tests/coverage.spec.ts | 68 +-- packages/llm/README.md | 4 +- packages/llm/llm-deepseek/README.md | 5 +- packages/llm/llm-deepseek/src/index.ts | 11 +- .../llm/llm-deepseek/tests/adapter.e2e.ts | 5 +- .../llm/llm-deepseek/tests/adapter.spec.ts | 25 +- packages/llm/llm-deepseek/tests/assemble.ts | 14 +- .../llm/llm-deepseek/tests/serialize.spec.ts | 2 +- packages/llm/llm-pi-ai/README.md | 58 ++- packages/llm/llm-pi-ai/src/adapter.ts | 209 +++----- packages/llm/llm-pi-ai/src/config.ts | 99 ++++ packages/llm/llm-pi-ai/src/context.ts | 85 ++++ packages/llm/llm-pi-ai/src/convert.ts | 289 ----------- packages/llm/llm-pi-ai/src/index.ts | 79 +-- packages/llm/llm-pi-ai/src/replay.ts | 208 ++++++++ packages/llm/llm-pi-ai/src/stream.ts | 141 ++++++ packages/llm/llm-pi-ai/tests/adapter.e2e.ts | 32 +- packages/llm/llm-pi-ai/tests/adapter.spec.ts | 462 ++++++------------ packages/llm/llm-pi-ai/tests/assemble.ts | 14 +- packages/llm/llm-pi-ai/tests/convert.spec.ts | 215 +++++++- packages/llm/llm/README.md | 12 +- packages/llm/llm/src/assembler.ts | 7 + packages/llm/llm/src/call-config.ts | 11 +- packages/llm/llm/src/index.ts | 66 ++- packages/llm/llm/src/types.ts | 30 +- packages/llm/llm/tests/call-config.spec.ts | 18 +- packages/llm/llm/tests/service.spec.ts | 125 ++++- .../tests/jsonl.spec.ts | 2 +- .../tests/sqlite.spec.ts | 2 +- .../session-persistence/tests/contract.ts | 4 +- .../tests/multi-subagent.spec.ts | 2 +- .../subagent-fork/tests/subagent-fork.spec.ts | 2 +- .../subagent/subagent-inprocess/src/index.ts | 2 + .../tests/structured.spec.ts | 2 +- .../tests/subagent-inprocess.spec.ts | 2 +- .../subagent/subagent-spawn/tests/harness.ts | 2 +- .../subagent-spawn/tests/spawn.e2e.ts | 2 +- .../tests/subagent-spawn.spec.ts | 14 +- packages/subagent/tool-subagent/src/index.ts | 3 +- .../invariants/tests/invariants.spec.ts | 52 +- .../llm-replay/tests/llm-replay.spec.ts | 44 +- .../todo/tool-todo/tests/integration.spec.ts | 4 +- packages/ui/acp-agent/README.md | 3 +- packages/ui/acp-agent/src/index.ts | 13 +- packages/ui/acp-agent/tests/acp-agent.spec.ts | 9 +- packages/ui/acp-agent/tests/built-bin.e2e.ts | 2 +- packages/ui/acp-agent/tests/load-path.e2e.ts | 2 +- packages/ui/acp/README.md | 1 + packages/ui/acp/src/index.ts | 10 +- packages/ui/acp/tests/dispose.spec.ts | 8 +- packages/ui/acp/tests/edges.spec.ts | 2 +- packages/ui/acp/tests/harness.ts | 9 +- packages/ui/acp/tests/stream-update.spec.ts | 1 + packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 23 +- .../ui/jsonrpc/tests/plugin-apply.spec.ts | 10 +- packages/ui/jsonrpc/tests/server.spec.ts | 44 +- packages/ui/stdio-agent/README.md | 7 +- packages/ui/stdio-agent/src/index.ts | 8 +- .../ui/stdio-agent/tests/built-bin.e2e.ts | 1 + .../ui/stdio-agent/tests/stdio-agent.spec.ts | 10 +- .../ui/user-approval/tests/approval.spec.ts | 2 +- packages/workflow/tool-workflow/src/index.ts | 12 +- .../workflow-workerthread/src/host.ts | 9 +- .../workflow-workerthread/src/meta.ts | 4 +- .../workflow-workerthread/src/runtime.ts | 16 +- .../workflow-workerthread/src/types.ts | 2 + .../tests/integration.spec.ts | 2 +- .../workflow-workerthread/tests/meta.spec.ts | 5 +- .../tests/session.spec.ts | 13 +- .../tests/workflow-workerthread.e2e.ts | 4 +- .../tests/workflow-workerthread.spec.ts | 8 + packages/workflow/workflow/src/types.ts | 2 + .../runtime/cordis.yml | 3 - python/sdk/README.i18n.yaml | 4 +- python/sdk/README.md | 3 + python/sdk/README.zh.md | 3 + python/sdk/src/deepseek_harness/api.py | 2 + python/sdk/src/deepseek_harness/client.py | 2 + python/sdk/tests/test_bundled_runtime.py | 4 +- python/sdk/tests/test_client.py | 26 +- scripts/smoke-python-runtime.py | 5 +- scripts/type-equiv.manifest.json | 1 + 218 files changed, 2605 insertions(+), 1844 deletions(-) create mode 100644 docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md create mode 100644 packages/llm/llm-pi-ai/src/config.ts create mode 100644 packages/llm/llm-pi-ai/src/context.ts delete mode 100644 packages/llm/llm-pi-ai/src/convert.ts create mode 100644 packages/llm/llm-pi-ai/src/replay.ts create mode 100644 packages/llm/llm-pi-ai/src/stream.ts diff --git a/docs/architecture.md b/docs/architecture.md index a1f0cae9a8..23f2268ff7 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -125,7 +125,7 @@ Durability is a plugin concern. Persistence backends buffer synchronous `session Messages are arrays of typed content blocks (`text`, `reasoning`, `tool-call`, `tool-result`). The union derives from the merge-extensible `ContentBlockMap`; the same pattern types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New block types are coordinated across adapters, UI bridges, compaction pricing, and persistence, so block types remain a repo-wide contract. -Streaming is a raw chunk protocol (`block-start` through `finish`) with `BlockAssembler` as the shared chunk-to-block assembler. The loop logs raw chunks while assembling them for dispatch. `LlmAdapter` is the provider seam: subclass, implement `stream()`, and register with `ctx.llm.registerAdapter(models, adapter)`. StreamChunk conventions live in [llm-streaming.md](core-data-structures/llm-streaming.md). +Streaming uses raw chunks (`block-start` through `finish`) and `BlockAssembler`. The loop logs and assembles chunks, storing assistant provider/model provenance plus replay state. An `LlmAdapter` implements `stream()` and registers routes with `ctx.llm.registerAdapter(providers, adapter)`; requests route by `provider`, while the adapter resolves `model`. Replay state reaches a target only when both routes map to the same adapter instance, which owns validation and conversion. The contract lives in [llm-streaming.md](core-data-structures/llm-streaming.md). ## Extension And Composition diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 9d4b8038b5..7d346f076f 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -16,6 +16,8 @@ Requires: `agents` · `sessions` · `sessionPersistence` · `tools` · `userInte ```ts config-catalog /** Plugin config: the agent template ACP sessions are created from. */ export interface AcpConfig { + /** Provider route for created agents. */ + provider?: string /** Model name for created agents (must have a registered adapter). */ model?: string /** @@ -37,7 +39,7 @@ Source: [`packages/ui/acp/src/index.ts:250`](../packages/ui/acp/src/index.ts) ```ts config-catalog /** - * App config: the swappable per-deployment values. `model` configures the + * App config: the swappable per-deployment values. `provider` and `model` configure the * agent template the ACP bridge creates each session's agent from (NOT a * pre-created agent — ACP creates agents at `session/new`); `persona` is the * deployment persona (forwarded to the system-prompt plugin); `toolOrder` is @@ -46,6 +48,8 @@ Source: [`packages/ui/acp/src/index.ts:250`](../packages/ui/acp/src/index.ts) * through agent-core); `persistenceRoot` is the JSONL backend's directory. */ export interface Config { + /** Provider route for ACP-created agents. */ + provider: string /** Model name for ACP-created agents (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ @@ -234,7 +238,9 @@ export interface BasicCompactConfig { thresholdRatio: number /** Number of tokens of recent context to retain during compaction. */ retainTokens: number - /** Model to use for summarization (`''` — uses the agent's model). */ + /** Provider to use for summarization (`''` with an empty model inherits the conversation target). */ + summarizationProvider: string + /** Model to use for summarization (`''` with an empty provider inherits the conversation target). */ summarizationModel: string /** Provider generation cap for the summarization call. */ maxTokens: number @@ -380,8 +386,6 @@ export interface Config { apiKey?: string /** Endpoint base; falls back to $DEEPSEEK_BASE_URL, then the public API. */ baseURL?: string - /** Model names to register (sent verbatim on the wire). */ - models?: string[] /** Thinking-mode default for every request (provider default: enabled). */ thinking?: 'enabled' | 'disabled' /** Thinking effort (only meaningful with thinking enabled). */ @@ -389,38 +393,51 @@ export interface Config { } ``` -Source: [`packages/llm/llm-deepseek/src/index.ts:43`](../packages/llm/llm-deepseek/src/index.ts) +Source: [`packages/llm/llm-deepseek/src/index.ts:42`](../packages/llm/llm-deepseek/src/index.ts) ## `@deepseek-ai/dsh-llm-pi-ai` Requires: `llm` ```ts config-catalog -/** - * Plugin config, validated by the same-named schemastery schema. Every field - * is optional in yml: credentials/endpoint fall back to the environment (a - * missing API key fails plugin load, not the first call). - */ +/** Plugin configuration: the non-empty provider profiles this instance owns. */ export interface Config { - /** API key; falls back to $DEEPSEEK_API_KEY. Required one way or the other. */ - apiKey?: string - /** Endpoint base; falls back to $DEEPSEEK_BASE_URL, then the public API. */ - baseURL?: string - /** Model names to register (sent verbatim on the wire). */ - models?: string[] - /** - * Thinking level for every request: 'off' disables thinking mode; 'high' - * and 'xhigh' (wire 'max') set the effort. Omitted = provider default - * (thinking enabled), matching llm-deepseek's omission semantics. - */ - reasoning?: PiAiReasoning + /** Non-empty set of pi-ai provider routes this adapter instance owns. */ + providers: PiAiProviderProfile[] } -/** Reasoning levels surfaced by this adapter (DeepSeek wire: high|max). */ -export type PiAiReasoning = 'off' | 'high' | 'xhigh' +/** Configuration for one pi-ai provider route. */ +export interface PiAiProviderProfile { + /** pi-ai provider catalog name and Harness route key. */ + provider: string + /** Provider credential; when absent pi-ai uses its provider-native ambient discovery. */ + apiKey?: string + /** Override the selected catalog model's endpoint without changing its protocol metadata. */ + baseURL?: string + /** Provider request headers; Harness attribution wins reserved names. */ + headers?: Record + /** Provider-neutral pi-ai reasoning level. */ + reasoning?: ThinkingLevel + /** Token budgets used by reasoning providers that support them. */ + thinkingBudgets?: ThinkingBudgets + /** Prompt-cache retention preference. */ + cacheRetention?: CacheRetention + /** Streaming transport preference. */ + transport?: Transport + /** HTTP/provider SDK timeout in milliseconds. */ + timeoutMs?: number + /** WebSocket connection timeout in milliseconds. */ + websocketConnectTimeoutMs?: number + /** Provider SDK retry count. */ + maxRetries?: number + /** Maximum provider-requested retry delay in milliseconds. */ + maxRetryDelayMs?: number +} ``` -Source: [`packages/llm/llm-pi-ai/src/index.ts:37`](../packages/llm/llm-pi-ai/src/index.ts) +Depends on: `CacheRetention` (`@earendil-works/pi-ai`) · `ThinkingBudgets` (`@earendil-works/pi-ai`) · `ThinkingLevel` (`@earendil-works/pi-ai`) · `Transport` (`@earendil-works/pi-ai`) + +Source: [`packages/llm/llm-pi-ai/src/config.ts:40`](../packages/llm/llm-pi-ai/src/config.ts) ## `@deepseek-ai/dsh-llm-replay` @@ -611,7 +628,7 @@ Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-l ```ts config-catalog /** * App config: the swappable per-demo values, each routed to where the app wires - * it. `model`/`resumeSessionId` configure the pre-created `main` agent (through + * it. `provider`/`model`/`resumeSessionId` configure the pre-created `main` agent (through * {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list); `persona` is * the deployment persona (forwarded to the system-prompt plugin); `toolOrder` * is the explicit model-facing tool order (forwarded to the system-prompt plugin); @@ -620,6 +637,8 @@ Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-l * `welcome` is the UI banner. */ export interface Config { + /** Provider route for the `main` agent. */ + provider: string /** Model name for the `main` agent (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ diff --git a/docs/cookbook/adding-an-llm-adapter.md b/docs/cookbook/adding-an-llm-adapter.md index fb59969e52..866f401d42 100644 --- a/docs/cookbook/adding-an-llm-adapter.md +++ b/docs/cookbook/adding-an-llm-adapter.md @@ -14,11 +14,11 @@ export const inject = ['llm'] export const Config: z = z.object({ apiKey: z.string(), … }) export function apply(ctx: Context, config: Config) { - ctx.llm.registerAdapter(['model-a', 'model-b'], new MyAdapter(…)) + ctx.llm.registerAdapter(['my-provider'], new MyAdapter(…)) } ``` -Registration is effect-based (HMR-safe); one adapter per model name — duplicates throw. Secrets are cordis-native: schemastery Config with env fallbacks, fed from cordis.yml via `!!js process.env.MY_KEY`. Never read ad-hoc key files in code. +Registration is effect-based (HMR-safe); one adapter per provider route — duplicates throw, and multi-route registration is all-or-nothing. `options.provider` selects the adapter and `options.model` is the provider model id, so a dynamic catalog adapter can serve new models without lifecycle reconfiguration. Secrets are cordis-native: schemastery Config with env fallbacks, fed from cordis.yml via `!!js process.env.MY_KEY`. Never read ad-hoc key files in code. ## Protocol obligations (the contract two implementations verified) @@ -28,6 +28,7 @@ Registration is effect-based (HMR-safe); one adapter per model name — duplicat - Errors have exactly two sanctioned paths: THROW from `stream()` (transport and protocol failures — use `LlmError` with a stable code), or end the stream with `finish {kind: 'error' | 'aborted'}` (provider in-band failures). Consumers handle both; pick per failure class and document it. - Honor `options.signal` (pass it to fetch / your SDK). - A `GenerateOptions` field your provider cannot honor (e.g. a `stop` list on a provider without stop sequences): throw `LlmError(..., 'UNSUPPORTED')` rather than silently dropping it. +- If the provider requires response ids, signatures, or other native metadata on follow-up calls, emit the minimal lossless-JSON projection as `finish.replayState`. Validate it when rebuilding history. `LlmService` passes it only when the historical provider route and target provider route are currently owned by the exact same adapter instance; your adapter decides whether same-model, cross-model, or cross-provider restoration is legal. Never infer native replay from provider/model names alone when state is absent. Provider-specific request knobs (thinking modes, effort levels) belong in the ADAPTER's Config, not in `GenerateOptions` — the core vocabulary stays provider-neutral. @@ -39,5 +40,5 @@ Split the adapter into testable stages (llm-deepseek's layout): wire types (`typ - **Unit: mock the provider, not the harness.** A scripted `node:http` server speaking the provider's wire format covers happy paths, every error status, malformed payloads, premature closes, and aborts — no network, and it drives the 100% per-file coverage gate. Works for SDK-backed adapters too (point the SDK's baseURL at the mock). - **Hostile framing tests.** Split stream payloads at arbitrary byte positions (including mid-UTF-8) — real networks do. -- **E2E: `tests/*.e2e.ts`** under `pnpm run test:e2e`, gated with `describe.skipIf(!process.env.MY_KEY)` so CI (no secrets) stays green. Cover each model × each provider mode you map (thinking on/off, effort levels), a tool-call round trip INCLUDING the follow-up turn with results in history, and loose assertions only (substring/structure, bounded maxTokens — real models are nondeterministic). +- **E2E: `tests/*.e2e.ts`** under `pnpm run test:e2e`, gated with `describe.skipIf(!process.env.MY_KEY)` so CI (no secrets) stays green. Cover representative model/provider/API families and every provider mode you map, a tool-call round trip INCLUDING the follow-up turn with results in history, and loose assertions only (substring/structure, bounded maxTokens — real models are nondeterministic). - Register the e2e file pattern in `knip.json` (per-workspace `entry` override) or knip flags it unused. diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index acbd39b8fa..9e005006bd 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -23,7 +23,7 @@ An agent's fully composed scoped world was published in the AgentRegistry. Its s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:316`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:318`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -35,7 +35,7 @@ An agent was removed from the registry. The concrete AgentLoop lifecycle emits t Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:331`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:333`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:605`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:607`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -61,7 +61,7 @@ Serial (awaited in registration order), not a waterfall: a listener mutates the Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:438`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:440`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -73,7 +73,7 @@ Waterfall: decide what happens to ONE drained queued message before it becomes a Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:456`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:458`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -85,7 +85,7 @@ A message entered the agent's inbox (queued or steering). Content and the resolv Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:360`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:362`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -97,7 +97,7 @@ Waterfall: shape the step's call configuration — model switching, sampling ove Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:485`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:487`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -113,7 +113,7 @@ The seed is a frozen empty list; a contributing listener returns a NEW array — Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:537`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:539`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -125,7 +125,7 @@ The agent's session lifecycle began, fired once before its first turn. `source` Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:381`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:383`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -137,7 +137,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). Drive lifecycle Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:345`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:347`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -149,7 +149,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:552`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:554`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -161,7 +161,7 @@ Waterfall: override the turn-continuation decision via a typed ContinuationDecis Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:570`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:572`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -173,7 +173,7 @@ Serial terminal-stop checkpoint after the ordinary `agent/turn-continuation` wat Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:588`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:590`](../../packages/core/agent/src/types.ts) ## `approval/*` @@ -239,7 +239,7 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:39`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:40`](../../packages/llm/llm/src/index.ts) ## `session/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 0aea3f1589..5011f83066 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -152,14 +152,14 @@ Source: [`packages/fs/fs/src/index.ts:172`](../../packages/fs/fs/src/index.ts) The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall. ```ts cordis-catalog -registerAdapter(models: string[], adapter: LlmAdapter): () => void -models(): string[] +registerAdapter(providers: string[], adapter: LlmAdapter): () => void +providers(): string[] stream(options: GenerateOptions): AsyncIterable ``` Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:88`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:89`](../../packages/llm/llm/src/index.ts) ## `ctx.sandbox` — `SandboxProvider` (abstract seam) @@ -218,7 +218,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:590`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:617`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 2f402be57d..32d1ac3715 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -11,7 +11,7 @@ Compaction extends [`SessionEventMap`](session.md) with three event types via de | Event | Payload | Role | |---|---|---| | `compact/start` | `{ turn }` | acquires the log-recorded lock | -| `compact/summary` | `{ summary, shadowedRange, shadowedSeqs, shadowedTokenCount, model, maxTokens? }` | provenance: the summary blocks, the shadowed surface-boundary pair (`start`/`end` seqs — a position span, not a numeric interval), the shadowed seqs in surface order, the estimated token count, and the summarize call's envelope (`model`, plus its generation cap when one applied) — logged so the one-shot request is reconstructable from log + code (the reconstructability RFC) | +| `compact/summary` | `{ summary, shadowedRange, shadowedSeqs, shadowedTokenCount, provider, model, maxTokens? }` | provenance: the summary blocks, the shadowed surface-boundary pair (`start`/`end` seqs — a position span, not a numeric interval), the shadowed seqs in surface order, the estimated token count, and the summarize call's envelope (`provider`, `model`, plus its generation cap when one applied) — logged so the one-shot request is reconstructable from log + code (the reconstructability RFC) | | `compact/end` | `{ turn, error? }` | releases the lock (`error` set when summarization threw) | The lock brackets the **whole** operation: `compact/start` is appended first, then summarization, the `compact/summary` provenance record, and the `user/message` replacement all land, and only then `compact/end`. Releasing the lock last turns a crash mid-operation into a detectable orphaned lock (a `compact/start` with no matching `compact/end`) rather than a `compact/end` that falsely claims compaction finished. diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 757c74f399..5a3ea6680b 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -102,12 +102,29 @@ interface ContentBlockMap { The block interfaces (full fields in source): `TextBlock` (`text`), `ReasoningBlock` (thinking, distinct from visible text), `ToolCallBlock` (`id: CallId`, `name`, raw-JSON `arguments`), `ToolResultBlock` (`toolCallId`, nested `content: ContentBlock[]`, `isError?`). `ContentBlock = ContentBlockMap[ContentBlockType]`. The core set is limited to blocks every shipping path honors — multimodal content (images, audio, …) has no core block type; a feature that needs one adds it via the merge-extensible map together with the adapter/UI/compaction support that honors it. -A `Message` is a role plus blocks: +A `Message` is a role plus blocks. Loop-derived assistant messages carry their durable provider/model identity and optional adapter-private replay metadata: + +```ts type-equiv +interface AssistantProvenance { + /** Provider route that produced the message. */ + provider: string + /** Provider model id that produced the message. */ + model: string + /** + * Lossless-JSON adapter state needed to replay the provider response. + * `LlmService` exposes it to a target adapter only when that adapter instance + * currently owns both this historical provider and the target provider. + */ + replayState?: unknown +} +``` ```ts type-equiv interface Message { role: 'system' | 'user' | 'assistant' content: ContentBlock[] + /** Present only on assistant messages produced by a routed adapter. */ + provenance?: AssistantProvenance } ``` @@ -134,6 +151,8 @@ Source: [`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts) ```ts type-equiv interface GenerateOptions { + /** Registered provider route selecting the adapter instance. */ + provider: string model: string /** * Ordered conversation messages, exactly as the provider sees them (after @@ -201,7 +220,7 @@ The model-facing `ToolSchema` is the wire shape; the registered `ToolDefinition` ### The request envelope: `LlmCallConfig` and the logged header -Requests are built by the loop, not shaped per call: the non-history half of a request — the `EpochHeader`: this call configuration plus the rendered system prompt, the tool schemas in the authoritative returned assembly order (initially canonicalized by dsh-system-prompt's `toolOrder` config, or lexicographically when unset), and the session prefix — is logged session state (`request/header` snapshot and delta events, [session.md](session.md#the-request-header-events-requestheader-and-requestheader-delta)), so every conversation request is a pure function of the session log ([reconstructability RFC](../rfc/implemented/architecture/2026-07-05-reconstructable-requests.md)). The `agent/request` waterfall receives a frozen `LlmCallConfig` seed and a listener returns a replacement to switch model or sampling; the `agent/session-prefix` waterfall — fired once per loop instance — composes the request-only messages fronting the derived history (recorded as the header's `messagePrefix`) — the loop logs whatever the request actually uses. Loop-built requests arrive at `llm/stream` deep-frozen; mutation throws. +Requests are built by the loop, not shaped per call: the non-history half of a request — the `EpochHeader`: this call configuration plus the rendered system prompt, the tool schemas in the authoritative returned assembly order (initially canonicalized by dsh-system-prompt's `toolOrder` config, or lexicographically when unset), and the session prefix — is logged session state (`request/header` snapshot and delta events, [session.md](session.md#the-request-header-events-requestheader-and-requestheader-delta)), so every conversation request is a pure function of the session log ([reconstructability RFC](../rfc/implemented/architecture/2026-07-05-reconstructable-requests.md)). The `agent/request` waterfall receives a frozen `LlmCallConfig` seed and a listener returns a replacement to switch provider, model, or sampling; the `agent/session-prefix` waterfall — fired once per loop instance — composes the request-only messages fronting the derived history (recorded as the header's `messagePrefix`) — the loop logs whatever the request actually uses. Loop-built requests arrive at `llm/stream` deep-frozen; mutation throws. On the wire, a loop-built request reads in this order: the `system` slot (the rendered prompt assembly) → `messagePrefix` (the frozen session prefix) → the derived history — the boundary snapshot, whose tail is the newest `user/message` on a turn's first step and the previous step's tool results on later steps. The prefix never enters the derived history; its durable record is the header events, and the dev invariant recomputes exactly this equation against every loop-built request. @@ -209,6 +228,7 @@ FIXME(call-config-shape): revisit the exact definition of this type — which fi ```ts type-equiv interface LlmCallConfig { + provider: string model: string temperature?: number maxTokens?: number @@ -353,7 +373,7 @@ interface Agent { } ``` -`AgentStatus` is `'idle' | 'running' | 'disposed'`. `AgentId` is a branded string. `AgentOptions` (`model?`) is merge-extensible — plugins add creation options by declaration merging. Persona is not an agent option: the `dsh-system-prompt` config supplies the global default, and an agent-scoped `deployment:persona` section may shadow it. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, serial `agent/pre-step`/`agent/turn-stop` checkpoints, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits. +`AgentStatus` is `'idle' | 'running' | 'disposed'`. `AgentId` is a branded string. `AgentOptions` (`provider?`, `model?`) is merge-extensible — plugins add creation options by declaration merging. A model dispatch requires both route fields after the `agent/request` waterfall. Persona is not an agent option: the `dsh-system-prompt` config supplies the global default, and an agent-scoped `deployment:persona` section may shadow it. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, serial `agent/pre-step`/`agent/turn-stop` checkpoints, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits. ## Interception decisions diff --git a/docs/core-data-structures/llm-streaming.md b/docs/core-data-structures/llm-streaming.md index fff329310a..b4b9d0f840 100644 --- a/docs/core-data-structures/llm-streaming.md +++ b/docs/core-data-structures/llm-streaming.md @@ -16,7 +16,12 @@ type StreamChunk = | { type: 'tool-call-delta'; index: number; id: CallId; name?: string; argumentsDelta: string } | { type: 'block-end'; index: number; block: ContentBlock } | { type: 'usage'; usage: TokenUsage } - | { type: 'finish'; reason: FinishReason } + | { + type: 'finish' + reason: FinishReason + /** Adapter-private lossless-JSON state for replaying a successful response. */ + replayState?: unknown + } ``` ## The adapter contract @@ -27,8 +32,9 @@ Every adapter MUST obey these, and every consumer may rely on them: - **Tool-call `arguments` stay raw JSON strings end-to-end.** Partial fragments stream via `argumentsDelta`; a provider that hands back parsed objects re-stringifies at `block-end`. - **Two sanctioned error paths.** A failure may either THROW from `stream()` (transport/protocol errors) **or** end the stream with `finish {kind:'error'|'aborted'}` (provider in-band errors, for adapters that can't throw mid-stream). Consumers must handle *both*. The agent loop translates a finish-error/aborted into a turn error — it never logs a normal completed assistant message for a failed step. - **Every provider HTTP request carries the app-attribution header.** Adapters send `attributionHeaders()` (below) - the `User-Agent` baseline - and prove it with a wire-level test (mock server asserting the received header, or the library's header hook for a library-backed adapter). +- **Replay state is adapter-owned.** A successful `finish` may carry lossless-JSON state needed to reconstruct a native provider response. The loop stores it with the assembled assistant message unless an `agent/step-result` listener rewrote the content. On a later request, `LlmService` passes the state only when the historical provider and target provider are currently registered to the exact same adapter instance. That adapter validates the state and owns any cross-model or cross-provider conversion; other adapters receive the provider-neutral content and provenance without the private state. -This contract is why two adapters exist as a deliberate pair: `dsh-llm-deepseek` (hand-rolled fetch/SSE) and `dsh-llm-pi-ai` (the same endpoint through `@earendil-works/pi-ai`). Two independent internals over one contract is what pinned the protocol down — the library-backed adapter can't throw mid-stream, so it exercises the finish-chunk error path the hand-rolled one might not. +This contract was pinned down by two deliberately independent implementations: `dsh-llm-deepseek` (hand-rolled fetch/SSE) and `dsh-llm-pi-ai` (a generic multi-provider adapter through `@earendil-works/pi-ai`). The library-backed adapter cannot throw mid-stream, so it exercises the finish-chunk error path the hand-rolled one might not. ## `AppIdentity` — app attribution @@ -58,11 +64,11 @@ interface TokenUsage { ## `BlockAssembler` -`BlockAssembler` ([`packages/llm/llm/src/assembler.ts`](../../packages/llm/llm/src/assembler.ts)) is the single shared implementation that folds a `StreamChunk` stream back into `ContentBlock`s and a final `Message`. The loop logs the raw chunks (for replay fidelity) while feeding the same chunks through an assembler — so the canonical log keeps token-level detail and the derived message is rebuilt deterministically. A consumer that needs the assembled result without re-implementing the fold uses this. +`BlockAssembler` ([`packages/llm/llm/src/assembler.ts`](../../packages/llm/llm/src/assembler.ts)) is the single shared implementation that folds a `StreamChunk` stream back into `ContentBlock`s, usage, finish reason, and replay state. The loop logs the raw chunks while feeding the same chunks through an assembler, then stores the assembled assistant content with its provider/model provenance. A consumer that needs the assembled result without re-implementing the fold uses this. ## The seam -`LlmAdapter` is the provider seam: subclass, implement `stream()`, register with `ctx.llm.registerAdapter(models, adapter)`. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm). +`LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm). `ContentBlockType` (the key set the `index`-correlated blocks carry) derives from `ContentBlockMap`: diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index 1b12c3fc48..e45a39957e 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -41,7 +41,7 @@ interface SessionEventMap { * the model output and its accounting travel together (there is no separate * usage record). `usage` is absent when the adapter reported none. */ - 'assistant/message': { turn: number; step: number; content: ContentBlock[]; usage?: TokenUsage } + 'assistant/message': { turn: number; step: number; content: ContentBlock[]; provenance: AssistantProvenance; usage?: TokenUsage } 'tool/call': { turn: number; step: number; callId: CallId; name: string; arguments: string } 'tool/result': { turn: number; step: number; callId: CallId; content: ContentBlock[]; isError: boolean; error?: { name: string; code: string }; meta?: unknown } /** Steering content injected between steps of a running turn. */ @@ -103,7 +103,7 @@ The request envelope — the `EpochHeader` (call config + rendered system prompt ```ts type-equiv export interface EpochHeader { - /** The conversation's call configuration (model + sampling scalars). */ + /** The conversation's call configuration (provider + model + sampling scalars). */ config: LlmCallConfig /** Rendered system prompt text; absent for a system-less request. */ system?: string @@ -201,11 +201,11 @@ export interface SurfaceNode { `Session.deriveMessages()` projects the event log into the `Message[]` the model sees — cached (each surface node projected once, when first seen; a surface rewrite rebuilds) and frozen (a fresh array per call over shared, deep-frozen messages, so mutating logged history through a projection is unrepresentable). `deriveEventMessage(event)` is the per-node pure function the fold applies — public so external reconstructors and the dev invariant project a log prefix with exactly the same rules and cannot disagree with the cache. The projection rules: - `user/message` → a user message. -- `assistant/message` → an assistant message. Raw `assistant/chunk` events are replay/UI data and are **skipped** in derivation (the assembled message is authoritative). An **empty-content** `assistant/message` is also skipped — a max-tokens step cut off with no content still records an `assistant/message` to host its `usage`, but a content-less assistant turn must not enter the provider transcript. +- `assistant/message` → an assistant message with the event's provider/model provenance and optional adapter-private replay state. Raw `assistant/chunk` events are replay/UI data and are **skipped** in derivation (the assembled message is authoritative). An **empty-content** `assistant/message` is also skipped — a max-tokens step cut off with no content still records an `assistant/message` to host its usage/provenance, but a content-less assistant turn must not enter the provider transcript. - `tool/result` → a user message carrying a `tool-result` block. - `context/message`, `steering/message` → user-role messages wrapped in a tagged envelope (`…`) at their chronological position — the "system-reminder" pattern; the model distinguishes them from real prompts by the envelope. -Everything else (`turn/*`, `step/*`) is structural and does not project into a message. Token usage is observed on `assistant/message.usage` (the step that produced it); an operational error's step number is on `turn/end.reason` for `kind: 'error'`. +Everything else (`turn/*`, `step/*`) is structural and does not project into a message. Token usage is observed on `assistant/message.usage` (the step that produced it); an operational error's step number is on `turn/end.reason` for `kind: 'error'`. Because this unreleased format intentionally has no compatibility promise, seed/load validation rejects request headers without provider+model and assistant messages without provider/model provenance instead of guessing a route for historical data. ## Live-session fork API diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 5b0a82673e..3665232b86 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,24 +7,24 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:316`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:331`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:605`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:438`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:456`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:360`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:485`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:537`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:381`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:345`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:552`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:570`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:588`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:318`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:607`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:440`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:458`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:362`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:487`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:539`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:383`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:347`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:554`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:572`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:590`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:70`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:123`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:138`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:109`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | -| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | +| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:40`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | | `session/created` | `emit` | [`packages/core/session/src/index.ts:52`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:64`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | | `session/event` | `emit` | [`packages/core/session/src/index.ts:83`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) | diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index 245d25fa5f..8f2118d7ba 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -64,7 +64,7 @@ Source: [`packages/core/session/src/types.ts:322`](../packages/core/session/src/ Assembled assistant message for one step (derived history uses this). Carries the step's `usage` when the adapter reported token accounting, so the model output and its accounting travel together (there is no separate usage record). `usage` is absent when the adapter reported none. ```ts persistence-catalog -'assistant/message': { turn: number; step: number; content: ContentBlock[]; usage?: TokenUsage } +'assistant/message': { turn: number; step: number; content: ContentBlock[]; provenance: AssistantProvenance; usage?: TokenUsage } ``` Types: [ContentBlock](core-data-structures/core.md) · [TokenUsage](core-data-structures/llm-streaming.md) @@ -93,7 +93,7 @@ Marks the end of a compaction — log-only, releases the lock. `error` set if su 'compact/end': { turn: number; error?: string } ``` -Source: [`packages/compact/compact/src/types.ts:46`](../packages/compact/compact/src/types.ts) +Source: [`packages/compact/compact/src/types.ts:48`](../packages/compact/compact/src/types.ts) #### `compact/start` — log-only @@ -110,7 +110,7 @@ Source: [`packages/compact/compact/src/types.ts:23`](../packages/compact/compact Provenance record of a completed summarization — log-only, no surfaceOp. The summary content is in `data.summary`; the actual surface replacement is performed by a subsequent `user/message` event that shadows the compacted range. ```ts persistence-catalog -'compact/summary': { summary: ContentBlock[]; shadowedRange: { start: number; end: number }; shadowedSeqs: number[]; shadowedTokenCount: number; model: string; maxTokens?: number } +'compact/summary': { summary: ContentBlock[]; shadowedRange: { start: number; end: number }; shadowedSeqs: number[]; shadowedTokenCount: number; provider: string; model: string; maxTokens?: number } ``` Types: [ContentBlock](core-data-structures/core.md) @@ -181,7 +181,7 @@ Source: [`packages/core/session/src/types.ts:374`](../packages/core/session/src/ #### `request/header-delta` — log-only -Amendment to the folded EpochHeader: at least one of a SystemDelta, a ToolsDelta, a whole replacement LlmCallConfig (four scalars — not worth diffing), or a whole replacement session prefix (`messagePrefix` — small advisory content, replaced whole; an EMPTY array encodes the transition to "none", mirroring the canonical form's absent field — the loop never produces one in practice: the prefix is composed once per instance and anchored by that instance's snapshot, so this arm exists for codec totality). Appended by the loop inside the step, before dispatch, when the header for this request differs from the fold of the log so far; the writer verifies `applyHeaderDelta(previous, delta)` reproduces the new header exactly and falls back to a `'fallback'` `request/header` snapshot when it cannot, so a logged delta ALWAYS round-trips. NOT a SurfaceEventType. +Amendment to the folded EpochHeader: at least one of a SystemDelta, a ToolsDelta, a whole replacement LlmCallConfig (provider/model plus sampling scalars — not worth diffing), or a whole replacement session prefix (`messagePrefix` — small advisory content, replaced whole; an EMPTY array encodes the transition to "none", mirroring the canonical form's absent field — the loop never produces one in practice: the prefix is composed once per instance and anchored by that instance's snapshot, so this arm exists for codec totality). Appended by the loop inside the step, before dispatch, when the header for this request differs from the fold of the log so far; the writer verifies `applyHeaderDelta(previous, delta)` reproduces the new header exactly and falls back to a `'fallback'` `request/header` snapshot when it cannot, so a logged delta ALWAYS round-trips. NOT a SurfaceEventType. ```ts persistence-catalog 'request/header-delta': { system?: SystemDelta; tools?: ToolsDelta; config?: LlmCallConfig; messagePrefix?: Message[] } diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index b338edfc52..3823f04022 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -141,6 +141,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [The agent is a registration scope](implemented/architecture/2026-07-08-agent-scope-contexts.md) | 2026-07-08 | | [Single-file executable SDK runtime distribution (single-exe)](implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) | 2026-07-10 | | [Agent-scope runtime design and correctness](implemented/architecture/2026-07-12-agent-scope-runtime-design.md) | 2026-07-12 | +| [Provider-routed LLM adapters and a generic pi-ai backend](implemented/architecture/2026-07-14-provider-routed-llm-adapters.md) | 2026-07-14 | ### Process diff --git a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md new file mode 100644 index 0000000000..e43fb1f2e7 --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md @@ -0,0 +1,89 @@ +# RFC: Provider-routed LLM adapters and a generic pi-ai backend + +Status: implemented + +## Problem + +`dsh-llm` registered adapters by exact model name. A plugin supplied a model list at Cordis startup, `LlmService` stored one adapter per listed string, and `GenerateOptions.model` selected the adapter and the provider model at once. This worked while both shipping adapters targeted the same two DeepSeek models, but it conflated two independent decisions: which upstream provider owns a request, and which model that provider should run. + +The conflation prevents a provider gateway from serving an open-ended model catalog. OpenRouter, for example, is one provider with many model ids, while a private OpenAI-compatible endpoint may add models without changing the Harness plugin tree. Every newly selected model currently needs to have been registered during plugin startup. The same model id can also exist at multiple providers, so model-only registration cannot state which provider the caller intended. + +`dsh-llm-pi-ai` exposed none of pi-ai's provider abstraction. It constructed an inline DeepSeek `openai-completions` model, applied DeepSeek-specific payload patches, and stamped every replayed assistant message as DeepSeek. pi-ai itself has a provider/model catalog, selects APIs such as `openai-responses`, `anthropic-messages`, and `google-generative-ai`, and preserves provider-specific response ids and reasoning/tool signatures for later turns. The Harness conversion dropped that provenance, so simply replacing the inline model with a catalog lookup would have made same-model replay and cross-provider handoff incomplete. + +The adapter configuration also assumes one DeepSeek API key and endpoint. A generic backend needs independent credentials and endpoint overrides per provider while leaving AWS, Google ADC, OAuth, and other ambient authentication mechanisms to pi-ai. + +## Decision + +### Provider is the adapter registration key + +`GenerateOptions` and `LlmCallConfig` carry `provider: string` beside `model: string`; `AgentOptions` carries the corresponding optional creation field. A loop request is valid only after both values are non-empty, and both values are part of the logged request header. `agent/request` may return a replacement pair on any step, so a session can switch providers and models without changing the Cordis plugin lifecycle. + +`LlmService` registers and resolves adapters by provider. `registerAdapter(providers, adapter)` checks the entire provider list before mutating the registry, rejects a duplicate with `DUPLICATE_ADAPTER`, and disposes the whole registration as one effect. `providers()` reports the registered keys. Model ids are not registered or enumerated by the service; the selected adapter validates or forwards them. + +A provider has exactly one adapter owner in a Cordis context. `dsh-llm-deepseek` registers `deepseek`; `dsh-llm-pi-ai` may also register `deepseek`, but loading both owners is a configuration error rather than an ordering rule or fallback. A deployment that wants the hand-rolled DeepSeek implementation excludes `deepseek` from the pi-ai profiles. A deployment that wants pi-ai's DeepSeek implementation does not mount `dsh-llm-deepseek`. + +`dsh-llm-deepseek` removes its model registration list and accepts any model string routed through provider `deepseek`. Its request serialization, `/chat/completions` endpoint, thinking options, SSE parsing, and error behavior remain unchanged; `options.model` is still sent verbatim. + +### Explicit pi-ai provider profiles + +`dsh-llm-pi-ai` takes one non-empty list of provider profiles. Provider names must be unique within the list and present in pi-ai's `getProviders()` result. Each profile contains the provider name plus optional `apiKey`, `baseURL`, headers, reasoning level and budgets, cache retention, transport, timeouts, and retry settings. Credentials are never global: an explicit key applies only to its profile, while an absent key lets pi-ai resolve its standard environment variable, OAuth token, AWS credential chain, Google ADC, or other provider-native ambient authentication. An explicitly empty key is invalid configuration rather than an environment fallback. + +The plugin registers all configured provider names against one `PiAiAdapter` in one all-or-nothing call. A request uses its provider to select the matching profile and finds its model in `getModels(provider)` to obtain the catalog descriptor. An unknown provider fails at plugin load; an unknown model fails before network I/O with `UNKNOWN_MODEL`. The catalog object is never mutated. When a profile supplies `baseURL`, the adapter clones the selected descriptor and overrides only `baseUrl`, so a private endpoint can retain pi-ai's API, capabilities, compatibility flags, context limits, and reasoning map. The private endpoint must implement the selected provider's protocol, and the model id must still exist in the installed pi-ai catalog. + +The adapter calls pi-ai's `streamSimple()` so each catalog model chooses its registered API implementation, including OpenAI Responses instead of Chat Completions where the descriptor says `openai-responses`. Harness temperature, maximum tokens, signal, session id, and the profile's common stream options flow through directly. Profile headers merge with the mandatory Harness attribution headers, with Harness attribution winning its reserved names. The adapter no longer maintains DeepSeek-specific payload rewrites or a provider-protocol matrix. + +pi-ai's common stream options do not expose stop sequences. `dsh-llm-pi-ai` rejects a defined Harness `stop` option with `UNSUPPORTED_OPTION` rather than silently ignoring it or growing a second provider-specific payload implementation. `dsh-llm-deepseek` continues to support `stop` through its native request serializer. + +### Durable assistant provenance and replay state + +Assistant messages carry provider-neutral provenance containing the request's `provider` and `model`, plus an optional JSON-serializable adapter replay state. A successful `assistant/message` session event records this provenance and `deriveMessages()` returns it with the assistant message. User, system, context, and tool-result messages carry no assistant provenance. The provider/model fields are authoritative loop data; an adapter owns only its opaque replay-state payload. + +A terminal successful `finish` chunk may carry replay state, and `BlockAssembler` retains it alongside usage and finish reason. The loop attaches it to the assistant provenance only when the post-`agent/step-result` content is structurally equal to the assembled provider output. A listener that rewrites content keeps the provider/model provenance but loses the now-stale replay state. Error and aborted responses do not produce a normal assistant message and therefore do not enter future model history. + +The pi-ai replay state is a versioned, minimal projection of its successful `AssistantMessage`: source API/provider/model, response id/model, stop reason, and index-aligned text, thinking, and tool-call signatures. It does not duplicate text or tool arguments already carried by Harness content blocks, and it omits diagnostics, timestamps, usage, and errors. On a later request, `LlmService` gives replay state to the target adapter only when the historical provider and target provider are currently owned by the same adapter instance. That adapter combines the logged Harness content with replay state when it can restore the historical response, and owns any required cross-model or cross-provider conversion. An adapter receiving replay state with an unknown version or mismatched block shape fails explicitly; a different adapter receives only provider-neutral content and provenance. + +This state is model-visible replay input and therefore follows the existing [reconstructable-request rule](../../implemented/architecture/2026-07-05-reconstructable-requests.md): it is present in both the terminal `finish` chunk and the assembled `assistant/message` provenance that drives derivation. Resume and fork preserve it verbatim. Compaction that shadows the assistant message also removes its replay state from the active surface; the summary is ordinary provider-neutral content. + +### Propagate the target through every request producer + +Every model-selection surface carries provider and model together: declarative agents, ACP and stdio app config, the JSON-RPC initialize request, subagent overrides and inheritance, workflow child overrides, and direct compaction summarization. Subagents inherit both fields from their parent before applying request overrides. The system-prompt variable set gains `provider` beside `model`. + +Compaction configuration gains `summarizationProvider` beside `summarizationModel`. Both are empty to inherit, or both are non-empty to select an explicit target; a half-configured pair fails load. Inheritance uses the last logged request target when one exists and falls back to the agent's creation options. `compact/summary` records both fields with the existing model-call envelope. + +The JSON-RPC runtime receives provider and model explicitly. Its convenience fallback mounts `dsh-llm-deepseek` only for provider `deepseek` when that provider has no registered owner; other missing providers fail without guessing an adapter. + +The on-disk session format remains the pre-release pinned version `0`, with no compatibility promise. Seed/load validation rejects request headers lacking provider and assistant messages lacking required provenance instead of accepting an old shape that can no longer reconstruct the request. + +## Alternatives considered + +**Keep model names as registry keys and add wildcard adapters.** A wildcard introduces fallback ordering between exact registrations and catch-all plugins, makes duplicate ownership dependent on listener order, and still cannot distinguish the same model id at two providers without another convention. + +**Encode provider and model into one string.** Values such as OpenRouter's `openai/gpt-*` already contain provider-like prefixes and slashes. A delimiter convention would leak routing syntax into every model selector and require escaping rules; two explicit fields are unambiguous and independently loggable. + +**Add `backend + provider + model`.** A backend key would allow `dsh-llm-deepseek` and pi-ai's DeepSeek implementation to coexist and switch per request. The accepted deployment rule is instead one adapter owner per provider: implementations of the same upstream are alternatives selected by plugin composition. A third routing dimension would burden every request and configuration for a capability with no current consumer. + +**Let `dsh-llm-pi-ai` automatically register every pi-ai provider.** This would claim ambient credentials and provider names the deployment never intended to expose, and would conflict with native adapters such as `dsh-llm-deepseek`. Explicit profiles make capability and credential scope reviewable. + +**Mount one pi-ai plugin instance per provider.** Separate instances isolate config but repeat plugin declarations and cannot make profile registration atomic. One adapter already receives provider on every request, so a validated profile map is the smaller lifecycle surface. + +**Accept arbitrary inline pi-ai model descriptors.** This would support catalog-external private model ids, but it exposes pi-ai's model and compatibility schema as Harness configuration and makes the adapter responsible for validating protocol-specific combinations. The first version supports custom endpoints by overriding `baseURL` on catalog models; custom descriptors require a separate decision after a real catalog-external deployment is identified. + +## Consequences + +- Provider names are deployment-wide route ownership keys: two providers may use the same model string, but mounting two adapters for one provider fails at load instead of creating fallback order. +- Model selection no longer changes the Cordis plugin graph. Catalog-backed adapters can accept any installed catalog model selected after startup, while the native DeepSeek adapter forwards arbitrary DeepSeek model ids. +- A custom `baseURL` preserves the selected catalog model's protocol and capabilities; it does not make catalog-external model ids valid. Private endpoints must implement that catalog entry's protocol. +- pi-ai credentials and transport knobs are scoped per provider profile. An omitted key delegates to pi-ai ambient authentication, while an explicitly empty key is invalid. +- `dsh-llm-pi-ai` rejects stop sequences because pi-ai's common stream API cannot express them; the native DeepSeek adapter retains its stop support. +- Replay state is portable only within the adapter instance that owns both the historical and target providers. Cross-provider and cross-model restoration is an adapter responsibility, and another adapter receives provider-neutral history without the opaque state. +- Current pre-release session JSONL requires provider/model request headers and assistant provenance. Older shapes remain version `0` but are rejected rather than migrated. + +## Testing + +- Unit coverage exercises registry conflicts, request reconstruction, session validation, profile resolution, option forwarding, native API selection including OpenAI Responses, conversion, replay validation, error mapping, cancellation, content rewrites, and same-instance versus different-instance replay dispatch. +- Keyless loop/session tests and ACP snapshots exercise durable provider/model metadata, resume and fork propagation, workflow/subagent overrides, and unchanged user-visible transcripts; the key-gated DeepSeek e2e retains real provider streaming and tool follow-up coverage. +- Public JSDoc, package READMEs, architecture and core-data-structure docs, generated catalogs, examples, session fixtures, and Python SDK pairs use provider/model targets consistently and are checked by the repository documentation and type-equivalence gates. + +## Risks + +This is a repo-wide pre-release API break: model-only request construction, adapter registration, app protocols, fixtures, and persisted version-0 event shapes all change together, with no compatibility aliases. The provider exclusivity rule deliberately prevents two implementations of the same upstream from coexisting in one context. A pi-ai dependency update can change the accepted provider/model catalog, so the lockfile and adapter e2e matrix define the tested set. Custom `baseURL` endpoints inherit the chosen catalog model's protocol assumptions and cannot repair an incompatible proxy. Catalog-external model descriptors and multimodal content remain unsupported. pi-ai replay state may contain opaque encrypted reasoning signatures; it is persisted because the provider requires it for continuity, but it is never rendered or logged outside the existing session record. diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 9ea71d3005..292b592d93 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -477,10 +477,10 @@ todo_write is session-owned state; UIs render the latest todo/write event as a c Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. -The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. +The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: -- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. +- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. @@ -527,6 +527,10 @@ Constraints: concurrency and total-agent caps apply; no filesystem, network, tim "type": "string", "description": "Optional one-line description of the phase." }, + "provider": { + "type": "string", + "description": "Optional provider override this phase is expected to use." + }, "model": { "type": "string", "description": "Optional model override this phase is expected to use." diff --git a/examples/acp-agent/advanced.cordis.snapshot.yml b/examples/acp-agent/advanced.cordis.snapshot.yml index 64802e1da9..8768407050 100644 --- a/examples/acp-agent/advanced.cordis.snapshot.yml +++ b/examples/acp-agent/advanced.cordis.snapshot.yml @@ -12,6 +12,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' tools: diff --git a/examples/acp-agent/advanced.cordis.yml b/examples/acp-agent/advanced.cordis.yml index 772369578f..ef1155d39d 100644 --- a/examples/acp-agent/advanced.cordis.yml +++ b/examples/acp-agent/advanced.cordis.yml @@ -10,6 +10,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' tools: diff --git a/examples/acp-agent/both-mode.cordis.snapshot.yml b/examples/acp-agent/both-mode.cordis.snapshot.yml index 8ee54b3078..4d12851fa5 100644 --- a/examples/acp-agent/both-mode.cordis.snapshot.yml +++ b/examples/acp-agent/both-mode.cordis.snapshot.yml @@ -15,6 +15,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' tools: diff --git a/examples/acp-agent/both-mode.cordis.yml b/examples/acp-agent/both-mode.cordis.yml index 3dff66d60a..da70c572a4 100644 --- a/examples/acp-agent/both-mode.cordis.yml +++ b/examples/acp-agent/both-mode.cordis.yml @@ -14,6 +14,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' tools: diff --git a/examples/acp-agent/code-mode.cordis.snapshot.yml b/examples/acp-agent/code-mode.cordis.snapshot.yml index d525afc5d6..de5666bd15 100644 --- a/examples/acp-agent/code-mode.cordis.snapshot.yml +++ b/examples/acp-agent/code-mode.cordis.snapshot.yml @@ -15,6 +15,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' tools: diff --git a/examples/acp-agent/code-mode.cordis.yml b/examples/acp-agent/code-mode.cordis.yml index 323c35b5b4..439c31111a 100644 --- a/examples/acp-agent/code-mode.cordis.yml +++ b/examples/acp-agent/code-mode.cordis.yml @@ -15,6 +15,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' tools: diff --git a/examples/acp-agent/cordis.yml b/examples/acp-agent/cordis.yml index dc03ea6b03..014222951b 100644 --- a/examples/acp-agent/cordis.yml +++ b/examples/acp-agent/cordis.yml @@ -19,9 +19,6 @@ config: apiKey: !!js process.env.DEEPSEEK_API_KEY baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: - - deepseek-v4-flash - - deepseek-v4-pro # Local bash executor for agent-core's tool-bash schema (one of several tool # stacks in this tree: filesystem, subagent, and todo_write load below). @@ -36,6 +33,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' # The persona: identity + behavior only, nothing about transports or diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index 1eabba53b3..580b20280f 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -2,12 +2,12 @@ {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} {"type":"assistant/chunk","seq":7,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":8,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":9,"time":1783957884564,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"assistant/message","seq":9,"time":1783957884564,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} {"type":"step/end","seq":10,"time":1783957884564,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":11,"time":1783957884564,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index 7787ed2ab1..abbbf5fef5 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -2,12 +2,12 @@ {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} {"type":"assistant/chunk","seq":7,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":8,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":9,"time":1783957884701,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"assistant/message","seq":9,"time":1783957884701,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} {"type":"step/end","seq":10,"time":1783957884701,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":11,"time":1783957884701,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl index bb74382b22..55717bbc1b 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -2,13 +2,13 @@ {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} {"type":"assistant/chunk","seq":7,"time":1783950000008,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":8,"time":1783950000009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":9,"time":1783957884487,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"assistant/message","seq":9,"time":1783957884487,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} {"type":"tool/call","seq":10,"time":1783957884487,"data":{"turn":1,"step":1,"callId":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}} {"type":"tool/result","seq":11,"time":1783957884488,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"} {"type":"step/end","seq":12,"time":1783957884489,"data":{"turn":1,"step":1}} @@ -18,7 +18,7 @@ {"type":"assistant/chunk","seq":16,"time":1783950000017,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}}} {"type":"assistant/chunk","seq":17,"time":1783950000018,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":18,"time":1783950000019,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":19,"time":1783957884490,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"} +{"type":"assistant/message","seq":19,"time":1783957884490,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"} {"type":"tool/call","seq":20,"time":1783957884490,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}} {"type":"tool/code-dispatch","seq":21,"time":1783957884560,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"},"isError":false,"resultSummary":"## dynamic\n- dyn-1: snapshot-marker [active]"}} {"type":"tool/result","seq":22,"time":1783957884561,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}],"isError":false,"meta":{"logs":[],"dispatches":1}},"sourceEventSeqs":[20],"surfaceOp":"append"} @@ -29,7 +29,7 @@ {"type":"assistant/chunk","seq":27,"time":1783950000028,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":28,"time":1783950000029,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":29,"time":1783950000030,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":30,"time":1783957884562,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"} +{"type":"assistant/message","seq":30,"time":1783957884562,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"} {"type":"tool/call","seq":31,"time":1783957884562,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}} {"type":"tool/result","seq":32,"time":1783957884593,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"isError":false},"sourceEventSeqs":[31],"surfaceOp":"append"} {"type":"step/end","seq":33,"time":1783957884593,"data":{"turn":1,"step":3}} @@ -39,7 +39,7 @@ {"type":"assistant/chunk","seq":37,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}} {"type":"assistant/chunk","seq":38,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":39,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":40,"time":1783957884594,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"} +{"type":"assistant/message","seq":40,"time":1783957884594,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"} {"type":"tool/call","seq":41,"time":1783957884594,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}} {"type":"tool/result","seq":42,"time":1783957884717,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-acp-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[41],"surfaceOp":"append"} {"type":"step/end","seq":43,"time":1783957884718,"data":{"turn":1,"step":4}} @@ -49,7 +49,7 @@ {"type":"assistant/chunk","seq":47,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}}} {"type":"assistant/chunk","seq":48,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":49,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":50,"time":1783957884719,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"} +{"type":"assistant/message","seq":50,"time":1783957884719,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"} {"type":"tool/call","seq":51,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}} {"type":"tool/result","seq":52,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"unmounted dyn-1 (plugin \"snapshot-marker\")"}],"isError":false},"sourceEventSeqs":[51],"surfaceOp":"append"} {"type":"step/end","seq":53,"time":1783957884719,"data":{"turn":1,"step":5}} @@ -59,6 +59,6 @@ {"type":"assistant/chunk","seq":57,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_ACP_OK"}}}} {"type":"assistant/chunk","seq":58,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":59,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":60,"time":1783957884720,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_ACP_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"} +{"type":"assistant/message","seq":60,"time":1783957884720,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_ACP_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"} {"type":"step/end","seq":61,"time":1783957884721,"data":{"turn":1,"step":6}} {"type":"turn/end","seq":62,"time":1783957884721,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index e70cfcce44..d5edb3e296 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -115,7 +115,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ + /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ script: string; @@ -133,6 +133,8 @@ declare const tools: { title: string; /** Optional one-line description of the phase. */ detail?: string; + /** Optional provider override this phase is expected to use. */ + provider?: string; /** Optional model override this phase is expected to use. */ model?: string; }[]; diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index b49097188e..8d422579ed 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -84,7 +84,7 @@ {"type":"assistant/chunk","seq":82,"time":1783611775498,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_AZFzvUwuC4vAUoICrfke5147","name":"run_code","arguments":"{\"code\": \"const result = await tools.bash({ command: \\\"echo BOTH_OK\\\", description: \\\"Echo BOTH_OK\\\" });\\nreturn result;\"}"}}}} {"type":"assistant/chunk","seq":83,"time":1783611775498,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":5530,"outputTokens":108,"cacheReadTokens":0,"reasoningTokens":37}}}} {"type":"assistant/chunk","seq":84,"time":1783611775498,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":85,"time":1783611775503,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the `run_code` tool to execute a program that calls `tools.bash` with the command `echo BOTH_OK` and returns its output."},{"type":"tool-call","id":"call_00_AZFzvUwuC4vAUoICrfke5147","name":"run_code","arguments":"{\"code\": \"const result = await tools.bash({ command: \\\"echo BOTH_OK\\\", description: \\\"Echo BOTH_OK\\\" });\\nreturn result;\"}"}],"usage":{"inputTokens":5530,"outputTokens":108,"cacheReadTokens":0,"reasoningTokens":37}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84],"surfaceOp":"append"} +{"type":"assistant/message","seq":85,"time":1783611775503,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the `run_code` tool to execute a program that calls `tools.bash` with the command `echo BOTH_OK` and returns its output."},{"type":"tool-call","id":"call_00_AZFzvUwuC4vAUoICrfke5147","name":"run_code","arguments":"{\"code\": \"const result = await tools.bash({ command: \\\"echo BOTH_OK\\\", description: \\\"Echo BOTH_OK\\\" });\\nreturn result;\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":5530,"outputTokens":108,"cacheReadTokens":0,"reasoningTokens":37}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84],"surfaceOp":"append"} {"type":"tool/call","seq":86,"time":1783611775504,"data":{"turn":1,"step":1,"callId":"call_00_AZFzvUwuC4vAUoICrfke5147","name":"run_code","arguments":"{\"code\": \"const result = await tools.bash({ command: \\\"echo BOTH_OK\\\", description: \\\"Echo BOTH_OK\\\" });\\nreturn result;\"}"}} {"type":"tool/code-dispatch","seq":87,"time":1783611775590,"data":{"parentCallId":"call_00_AZFzvUwuC4vAUoICrfke5147","subCallId":"call_00_AZFzvUwuC4vAUoICrfke5147:code:1","name":"bash","arguments":{"command":"echo BOTH_OK","description":"Echo BOTH_OK"},"isError":false,"resultSummary":"BOTH_OK\n"}} {"type":"tool/result","seq":88,"time":1783611775592,"data":{"turn":1,"step":1,"callId":"call_00_AZFzvUwuC4vAUoICrfke5147","content":[{"type":"text","text":"BOTH_OK\n"}],"isError":false,"meta":{"logs":[],"dispatches":1}},"sourceEventSeqs":[86],"surfaceOp":"append"} @@ -116,6 +116,6 @@ {"type":"assistant/chunk","seq":114,"time":1783611776440,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"BOTH_OK"}}}} {"type":"assistant/chunk","seq":115,"time":1783611776440,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":22,"outputTokens":21,"cacheReadTokens":5632,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":116,"time":1783611776440,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":117,"time":1783611776441,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output is \"BOTH_OK\". I need to reply with that output only."},{"type":"text","text":"BOTH_OK"}],"usage":{"inputTokens":22,"outputTokens":21,"cacheReadTokens":5632,"reasoningTokens":17}},"sourceEventSeqs":[91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116],"surfaceOp":"append"} +{"type":"assistant/message","seq":117,"time":1783611776441,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output is \"BOTH_OK\". I need to reply with that output only."},{"type":"text","text":"BOTH_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":22,"outputTokens":21,"cacheReadTokens":5632,"reasoningTokens":17}},"sourceEventSeqs":[91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116],"surfaceOp":"append"} {"type":"step/end","seq":118,"time":1783611776441,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":119,"time":1783611776441,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index 5dd8547aa8..8c44068330 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -100,7 +100,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ + /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ script: string; @@ -118,6 +118,8 @@ declare const tools: { title: string; /** Optional one-line description of the phase. */ detail?: string; + /** Optional provider override this phase is expected to use. */ + provider?: string; /** Optional model override this phase is expected to use. */ model?: string; }[]; diff --git a/examples/acp-agent/tests/snapshots/cancel/session.jsonl b/examples/acp-agent/tests/snapshots/cancel/session.jsonl index 7b2f5adff1..347951db62 100644 --- a/examples/acp-agent/tests/snapshots/cancel/session.jsonl +++ b/examples/acp-agent/tests/snapshots/cancel/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Start a long task; this turn will be cancelled mid-stream."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"partial"}}} {"type":"step/end","seq":6,"time":0,"data":{"turn":1,"step":1}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl index 9367e2deb0..deb4b7e136 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611771394,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611771394,"data":{"content":[{"type":"text","text":"Using ONE run_code program: call the bash tool twice — exactly `echo CODE_ONE` then exactly `echo CODE_TWO` — and return the two outputs joined with a plus sign. Then reply with that joined string only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611771396,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611771396,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611771396,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611771869,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611771869,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611771978,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -108,7 +108,7 @@ {"type":"assistant/chunk","seq":106,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.trim() + \\\"+\\\" + out2.trim();\"}"}}}} {"type":"assistant/chunk","seq":107,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3009,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":29}}}} {"type":"assistant/chunk","seq":108,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":109,"time":1783611772840,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants a single run_code program that calls bash twice, then returns the two outputs joined with a plus sign. Let me write this."},{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.trim() + \\\"+\\\" + out2.trim();\"}"}],"usage":{"inputTokens":3009,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} +{"type":"assistant/message","seq":109,"time":1783611772840,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants a single run_code program that calls bash twice, then returns the two outputs joined with a plus sign. Let me write this."},{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.trim() + \\\"+\\\" + out2.trim();\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3009,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} {"type":"tool/call","seq":110,"time":1783611772840,"data":{"turn":1,"step":1,"callId":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.trim() + \\\"+\\\" + out2.trim();\"}"}} {"type":"tool/code-dispatch","seq":111,"time":1783611772933,"data":{"parentCallId":"call_00_DRxnM6R1TThfDwcudW0f2050","subCallId":"call_00_DRxnM6R1TThfDwcudW0f2050:code:1","name":"bash","arguments":{"command":"echo CODE_ONE","description":"First echo"},"isError":false,"resultSummary":"CODE_ONE\n"}} {"type":"tool/code-dispatch","seq":112,"time":1783611772936,"data":{"parentCallId":"call_00_DRxnM6R1TThfDwcudW0f2050","subCallId":"call_00_DRxnM6R1TThfDwcudW0f2050:code:2","name":"bash","arguments":{"command":"echo CODE_TWO","description":"Second echo"},"isError":false,"resultSummary":"CODE_TWO\n"}} @@ -145,6 +145,6 @@ {"type":"assistant/chunk","seq":143,"time":1783611773686,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"CODE_ONE+CODE_TWO"}}}} {"type":"assistant/chunk","seq":144,"time":1783611773686,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":89,"outputTokens":25,"cacheReadTokens":3072,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":145,"time":1783611773686,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":146,"time":1783611773687,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output is exactly what the user asked for: CODE_ONE+CODE_TWO"},{"type":"text","text":"CODE_ONE+CODE_TWO"}],"usage":{"inputTokens":89,"outputTokens":25,"cacheReadTokens":3072,"reasoningTokens":17}},"sourceEventSeqs":[116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145],"surfaceOp":"append"} +{"type":"assistant/message","seq":146,"time":1783611773687,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output is exactly what the user asked for: CODE_ONE+CODE_TWO"},{"type":"text","text":"CODE_ONE+CODE_TWO"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":89,"outputTokens":25,"cacheReadTokens":3072,"reasoningTokens":17}},"sourceEventSeqs":[116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145],"surfaceOp":"append"} {"type":"step/end","seq":147,"time":1783611773687,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":148,"time":1783611773687,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index 5dd8547aa8..8c44068330 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -100,7 +100,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ + /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ script: string; @@ -118,6 +118,8 @@ declare const tools: { title: string; /** Optional one-line description of the phase. */ detail?: string; + /** Optional provider override this phase is expected to use. */ + provider?: string; /** Optional model override this phase is expected to use. */ model?: string; }[]; diff --git a/examples/acp-agent/tests/snapshots/error-finish/session.jsonl b/examples/acp-agent/tests/snapshots/error-finish/session.jsonl index 98538a94c2..f0ef4267ac 100644 --- a/examples/acp-agent/tests/snapshots/error-finish/session.jsonl +++ b/examples/acp-agent/tests/snapshots/error-finish/session.jsonl @@ -2,6 +2,6 @@ {"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"This prompt triggers a recorded provider error."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"step/end","seq":4,"time":0,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":5,"time":0,"data":{"turn":1,"reason":{"kind":"error","step":1,"message":"simulated provider error (HTTP 401)","code":"AUTH"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl index 90f009946d..00587e34c2 100644 --- a/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352084740,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352084740,"data":{"content":[{"type":"text","text":"First use the read tool to read config.txt in the current directory. Then use the edit tool (NOT bash) to replace the literal text DEBUG with RELEASE in that file. Then reply with exactly the single word DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352084742,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352084742,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352084742,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352085426,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352085426,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352085563,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -67,7 +67,7 @@ {"type":"assistant/chunk","seq":65,"time":1783352086057,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_S6krdIDHoSCGWv7WnXX97617","name":"read","arguments":"{\"file_path\": \"config.txt\"}"}}}} {"type":"assistant/chunk","seq":66,"time":1783352086057,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2900,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":46}}}} {"type":"assistant/chunk","seq":67,"time":1783352086057,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":68,"time":1783352086059,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read config.txt in the current directory\n2. Use the edit tool to replace DEBUG with RELEASE\n3. Reply with exactly \"DONE\"\n\nLet me start by reading the file."},{"type":"tool-call","id":"call_00_S6krdIDHoSCGWv7WnXX97617","name":"read","arguments":"{\"file_path\": \"config.txt\"}"}],"usage":{"inputTokens":2900,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":46}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67],"surfaceOp":"append"} +{"type":"assistant/message","seq":68,"time":1783352086059,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read config.txt in the current directory\n2. Use the edit tool to replace DEBUG with RELEASE\n3. Reply with exactly \"DONE\"\n\nLet me start by reading the file."},{"type":"tool-call","id":"call_00_S6krdIDHoSCGWv7WnXX97617","name":"read","arguments":"{\"file_path\": \"config.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2900,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":46}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67],"surfaceOp":"append"} {"type":"tool/call","seq":69,"time":1783352086059,"data":{"turn":1,"step":1,"callId":"call_00_S6krdIDHoSCGWv7WnXX97617","name":"read","arguments":"{\"file_path\": \"config.txt\"}"}} {"type":"tool/result","seq":70,"time":1783352086065,"data":{"turn":1,"step":1,"callId":"call_00_S6krdIDHoSCGWv7WnXX97617","content":[{"type":"text","text":"/tmp/acp-snap-cwd-0BxHdV/config.txt\nfile\n\n1: mode=DEBUG\n2: level=info\n\n(End of file - total 2 lines)\n"}],"isError":false},"sourceEventSeqs":[69],"surfaceOp":"append"} {"type":"step/end","seq":71,"time":1783352086065,"data":{"turn":1,"step":1}} @@ -127,7 +127,7 @@ {"type":"assistant/chunk","seq":125,"time":1783352087469,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_vOytneZ0XpsLslEEJAxR6398","name":"edit","arguments":"{\"file_path\": \"config.txt\", \"old_string\": \"DEBUG\", \"new_string\": \"RELEASE\"}"}}}} {"type":"assistant/chunk","seq":126,"time":1783352087469,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":241,"outputTokens":98,"cacheReadTokens":2816,"reasoningTokens":18}}}} {"type":"assistant/chunk","seq":127,"time":1783352087469,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":128,"time":1783352087469,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"Now I need to replace \"DEBUG\" with \"RELEASE\" using the edit tool."},{"type":"tool-call","id":"call_00_vOytneZ0XpsLslEEJAxR6398","name":"edit","arguments":"{\"file_path\": \"config.txt\", \"old_string\": \"DEBUG\", \"new_string\": \"RELEASE\"}"}],"usage":{"inputTokens":241,"outputTokens":98,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127],"surfaceOp":"append"} +{"type":"assistant/message","seq":128,"time":1783352087469,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"Now I need to replace \"DEBUG\" with \"RELEASE\" using the edit tool."},{"type":"tool-call","id":"call_00_vOytneZ0XpsLslEEJAxR6398","name":"edit","arguments":"{\"file_path\": \"config.txt\", \"old_string\": \"DEBUG\", \"new_string\": \"RELEASE\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":241,"outputTokens":98,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127],"surfaceOp":"append"} {"type":"tool/call","seq":129,"time":1783352087469,"data":{"turn":1,"step":2,"callId":"call_00_vOytneZ0XpsLslEEJAxR6398","name":"edit","arguments":"{\"file_path\": \"config.txt\", \"old_string\": \"DEBUG\", \"new_string\": \"RELEASE\"}"}} {"type":"tool/result","seq":130,"time":1783352087476,"data":{"turn":1,"step":2,"callId":"call_00_vOytneZ0XpsLslEEJAxR6398","content":[{"type":"text","text":"The file /tmp/acp-snap-cwd-0BxHdV/config.txt has been updated successfully."}],"isError":false,"meta":{"diffs":[{"path":"config.txt","oldText":"mode=DEBUG\nlevel=info","newText":"mode=RELEASE\nlevel=info"}]}},"sourceEventSeqs":[129],"surfaceOp":"append"} {"type":"step/end","seq":131,"time":1783352087477,"data":{"turn":1,"step":2}} @@ -154,6 +154,6 @@ {"type":"assistant/chunk","seq":152,"time":1783352088523,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":153,"time":1783352088523,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":244,"outputTokens":17,"cacheReadTokens":2944,"reasoningTokens":14}}}} {"type":"assistant/chunk","seq":154,"time":1783352088523,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":155,"time":1783352088523,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"Done. The user wants me to reply with exactly \"DONE\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":244,"outputTokens":17,"cacheReadTokens":2944,"reasoningTokens":14}},"sourceEventSeqs":[133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154],"surfaceOp":"append"} +{"type":"assistant/message","seq":155,"time":1783352088523,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"Done. The user wants me to reply with exactly \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":244,"outputTokens":17,"cacheReadTokens":2944,"reasoningTokens":14}},"sourceEventSeqs":[133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154],"surfaceOp":"append"} {"type":"step/end","seq":156,"time":1783352088523,"data":{"turn":1,"step":3}} {"type":"turn/end","seq":157,"time":1783352088524,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl index 802120fd9c..03a64d2e39 100644 --- a/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611702550,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611702550,"data":{"content":[{"type":"text","text":"Do NOT use the read tool and do NOT use bash or shell commands. Immediately use the edit tool to replace the literal text blue with green in settings.txt in the current directory. Do not read the file first. After the tool result, reply with exactly the single word DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611702550,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611702551,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611702551,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611703185,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611703185,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611703352,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -75,7 +75,7 @@ {"type":"assistant/chunk","seq":73,"time":1783611703969,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}}}} {"type":"assistant/chunk","seq":74,"time":1783611703969,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3132,"outputTokens":115,"cacheReadTokens":0,"reasoningTokens":36}}}} {"type":"assistant/chunk","seq":75,"time":1783611703969,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":76,"time":1783611703972,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the edit tool to replace \"blue\" with \"green\" in settings.txt without reading the file first, and then reply with just \"DONE\"."},{"type":"tool-call","id":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"usage":{"inputTokens":3132,"outputTokens":115,"cacheReadTokens":0,"reasoningTokens":36}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75],"surfaceOp":"append"} +{"type":"assistant/message","seq":76,"time":1783611703972,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the edit tool to replace \"blue\" with \"green\" in settings.txt without reading the file first, and then reply with just \"DONE\"."},{"type":"tool-call","id":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3132,"outputTokens":115,"cacheReadTokens":0,"reasoningTokens":36}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75],"surfaceOp":"append"} {"type":"tool/call","seq":77,"time":1783611703972,"data":{"turn":1,"step":1,"callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}} {"type":"tool/result","seq":78,"time":1783611703978,"data":{"turn":1,"step":1,"callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","content":[{"type":"text","text":"Error: edit requires reading \"/var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt\" first"}],"isError":true,"error":{"name":"FsError","code":"FS_NOT_OBSERVED"}},"sourceEventSeqs":[77],"surfaceOp":"append"} {"type":"step/end","seq":79,"time":1783611703978,"data":{"turn":1,"step":1}} @@ -142,7 +142,7 @@ {"type":"assistant/chunk","seq":140,"time":1783611705572,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_tfr0gdIclW92oIEgi7NF0891","name":"read","arguments":"{\"file_path\": \"settings.txt\"}"}}}} {"type":"assistant/chunk","seq":141,"time":1783611705572,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":235,"outputTokens":89,"cacheReadTokens":3072,"reasoningTokens":44}}}} {"type":"assistant/chunk","seq":142,"time":1783611705572,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":143,"time":1783611705573,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The edit tool requires reading the file first. The user said \"Do not read the file first\" but the tool's own constraints require reading. I need to follow the tool requirements. Let me read the file first."},{"type":"tool-call","id":"call_00_tfr0gdIclW92oIEgi7NF0891","name":"read","arguments":"{\"file_path\": \"settings.txt\"}"}],"usage":{"inputTokens":235,"outputTokens":89,"cacheReadTokens":3072,"reasoningTokens":44}},"sourceEventSeqs":[81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"surfaceOp":"append"} +{"type":"assistant/message","seq":143,"time":1783611705573,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The edit tool requires reading the file first. The user said \"Do not read the file first\" but the tool's own constraints require reading. I need to follow the tool requirements. Let me read the file first."},{"type":"tool-call","id":"call_00_tfr0gdIclW92oIEgi7NF0891","name":"read","arguments":"{\"file_path\": \"settings.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":235,"outputTokens":89,"cacheReadTokens":3072,"reasoningTokens":44}},"sourceEventSeqs":[81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"surfaceOp":"append"} {"type":"tool/call","seq":144,"time":1783611705573,"data":{"turn":1,"step":2,"callId":"call_00_tfr0gdIclW92oIEgi7NF0891","name":"read","arguments":"{\"file_path\": \"settings.txt\"}"}} {"type":"tool/result","seq":145,"time":1783611705579,"data":{"turn":1,"step":2,"callId":"call_00_tfr0gdIclW92oIEgi7NF0891","content":[{"type":"text","text":"/var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt\nfile\n\n1: color: blue\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[144],"surfaceOp":"append"} {"type":"step/end","seq":146,"time":1783611705579,"data":{"turn":1,"step":2}} @@ -223,7 +223,7 @@ {"type":"assistant/chunk","seq":221,"time":1783611707096,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_GVknJu2tksKkP4lALCwh0926","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}}}} {"type":"assistant/chunk","seq":222,"time":1783611707096,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":281,"outputTokens":119,"cacheReadTokens":3200,"reasoningTokens":40}}}} {"type":"assistant/chunk","seq":223,"time":1783611707096,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":224,"time":1783611707097,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The file contains \"color: blue\". I need to replace \"blue\" with \"green\". The edit tool said it requires reading first — now I've read it, so the edit should work."},{"type":"tool-call","id":"call_00_GVknJu2tksKkP4lALCwh0926","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"usage":{"inputTokens":281,"outputTokens":119,"cacheReadTokens":3200,"reasoningTokens":40}},"sourceEventSeqs":[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223],"surfaceOp":"append"} +{"type":"assistant/message","seq":224,"time":1783611707097,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The file contains \"color: blue\". I need to replace \"blue\" with \"green\". The edit tool said it requires reading first — now I've read it, so the edit should work."},{"type":"tool-call","id":"call_00_GVknJu2tksKkP4lALCwh0926","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":281,"outputTokens":119,"cacheReadTokens":3200,"reasoningTokens":40}},"sourceEventSeqs":[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223],"surfaceOp":"append"} {"type":"tool/call","seq":225,"time":1783611707097,"data":{"turn":1,"step":3,"callId":"call_00_GVknJu2tksKkP4lALCwh0926","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}} {"type":"tool/result","seq":226,"time":1783611707114,"data":{"turn":1,"step":3,"callId":"call_00_GVknJu2tksKkP4lALCwh0926","content":[{"type":"text","text":"The file /var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt has been updated successfully."}],"isError":false,"meta":{"diffs":[{"path":"settings.txt","oldText":"color: blue","newText":"color: green"}]}},"sourceEventSeqs":[225],"surfaceOp":"append"} {"type":"step/end","seq":227,"time":1783611707114,"data":{"turn":1,"step":3}} @@ -253,6 +253,6 @@ {"type":"assistant/chunk","seq":251,"time":1783611707952,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":252,"time":1783611707952,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":202,"outputTokens":20,"cacheReadTokens":3456,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":253,"time":1783611707952,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":254,"time":1783611707953,"data":{"turn":1,"step":4,"content":[{"type":"reasoning","text":"The replacement was successful. I'll reply with just \"DONE\" as instructed."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":202,"outputTokens":20,"cacheReadTokens":3456,"reasoningTokens":17}},"sourceEventSeqs":[229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253],"surfaceOp":"append"} +{"type":"assistant/message","seq":254,"time":1783611707953,"data":{"turn":1,"step":4,"content":[{"type":"reasoning","text":"The replacement was successful. I'll reply with just \"DONE\" as instructed."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":202,"outputTokens":20,"cacheReadTokens":3456,"reasoningTokens":17}},"sourceEventSeqs":[229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253],"surfaceOp":"append"} {"type":"step/end","seq":255,"time":1783611707953,"data":{"turn":1,"step":4}} {"type":"turn/end","seq":256,"time":1783611707953,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl index becc503c65..e587011cfd 100644 --- a/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352099838,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352099839,"data":{"content":[{"type":"text","text":"Use the read tool (NOT bash) with offset 5 and limit 4 to read lines 5 through 8 of big.txt in the current directory. Then reply with exactly the single word DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352099840,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352099841,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352099841,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352100468,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352100468,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352100587,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -89,7 +89,7 @@ {"type":"assistant/chunk","seq":87,"time":1783352101346,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_GIZwZS9a7vhWTFCIc7Z35497","name":"read","arguments":"{\"file_path\": \"big.txt\", \"offset\": 5, \"limit\": 4}"}}}} {"type":"assistant/chunk","seq":88,"time":1783352101346,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2894,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":56}}}} {"type":"assistant/chunk","seq":89,"time":1783352101346,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":90,"time":1783352101348,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the read tool with offset 5 and limit 4 to read lines 5 through 8 of big.txt in the current directory. Then reply with exactly the single word DONE.\n\nLet me first check the current directory, then read the file."},{"type":"tool-call","id":"call_00_GIZwZS9a7vhWTFCIc7Z35497","name":"read","arguments":"{\"file_path\": \"big.txt\", \"offset\": 5, \"limit\": 4}"}],"usage":{"inputTokens":2894,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":56}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89],"surfaceOp":"append"} +{"type":"assistant/message","seq":90,"time":1783352101348,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the read tool with offset 5 and limit 4 to read lines 5 through 8 of big.txt in the current directory. Then reply with exactly the single word DONE.\n\nLet me first check the current directory, then read the file."},{"type":"tool-call","id":"call_00_GIZwZS9a7vhWTFCIc7Z35497","name":"read","arguments":"{\"file_path\": \"big.txt\", \"offset\": 5, \"limit\": 4}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2894,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":56}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89],"surfaceOp":"append"} {"type":"tool/call","seq":91,"time":1783352101348,"data":{"turn":1,"step":1,"callId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","name":"read","arguments":"{\"file_path\": \"big.txt\", \"offset\": 5, \"limit\": 4}"}} {"type":"tool/result","seq":92,"time":1783352101353,"data":{"turn":1,"step":1,"callId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","content":[{"type":"text","text":"/tmp/acp-snap-cwd-N9HCkt/big.txt\nfile\n\n5: line five\n6: line six\n7: line seven\n8: line eight\n\n(Showing lines 5-8 of 10. Use offset=9 to continue.)\n"}],"isError":false},"sourceEventSeqs":[91],"surfaceOp":"append"} {"type":"step/end","seq":93,"time":1783352101353,"data":{"turn":1,"step":1}} @@ -129,6 +129,6 @@ {"type":"assistant/chunk","seq":127,"time":1783352102357,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":128,"time":1783352102358,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":292,"outputTokens":30,"cacheReadTokens":2816,"reasoningTokens":27}}}} {"type":"assistant/chunk","seq":129,"time":1783352102358,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":130,"time":1783352102358,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The read tool returned lines 5 through 8 as expected. Now I need to reply with exactly the single word \"DONE\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":292,"outputTokens":30,"cacheReadTokens":2816,"reasoningTokens":27}},"sourceEventSeqs":[95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} +{"type":"assistant/message","seq":130,"time":1783352102358,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The read tool returned lines 5 through 8 as expected. Now I need to reply with exactly the single word \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":292,"outputTokens":30,"cacheReadTokens":2816,"reasoningTokens":27}},"sourceEventSeqs":[95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} {"type":"step/end","seq":131,"time":1783352102358,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":132,"time":1783352102358,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read/session.jsonl b/examples/acp-agent/tests/snapshots/fs-read/session.jsonl index 3af4b2ac61..81737364f8 100644 --- a/examples/acp-agent/tests/snapshots/fs-read/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352072468,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352072469,"data":{"content":[{"type":"text","text":"Use the read tool (NOT bash) to read the file greeting.txt in the current directory, then reply with exactly the single word DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352072470,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352072471,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352072471,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352073089,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352073090,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352073210,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -51,7 +51,7 @@ {"type":"assistant/chunk","seq":49,"time":1783352073705,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_hHPZCcivsIkXAGS9jTGy8417","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}}}} {"type":"assistant/chunk","seq":50,"time":1783352073705,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2882,"outputTokens":75,"cacheReadTokens":0,"reasoningTokens":29}}}} {"type":"assistant/chunk","seq":51,"time":1783352073705,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":52,"time":1783352073708,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to read the file greeting.txt using the read tool (not bash), then reply with exactly the single word \"DONE\"."},{"type":"tool-call","id":"call_00_hHPZCcivsIkXAGS9jTGy8417","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}],"usage":{"inputTokens":2882,"outputTokens":75,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} +{"type":"assistant/message","seq":52,"time":1783352073708,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to read the file greeting.txt using the read tool (not bash), then reply with exactly the single word \"DONE\"."},{"type":"tool-call","id":"call_00_hHPZCcivsIkXAGS9jTGy8417","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2882,"outputTokens":75,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} {"type":"tool/call","seq":53,"time":1783352073709,"data":{"turn":1,"step":1,"callId":"call_00_hHPZCcivsIkXAGS9jTGy8417","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}} {"type":"tool/result","seq":54,"time":1783352073717,"data":{"turn":1,"step":1,"callId":"call_00_hHPZCcivsIkXAGS9jTGy8417","content":[{"type":"text","text":"/tmp/acp-snap-cwd-PEETkS/greeting.txt\nfile\n\n1: hello\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[53],"surfaceOp":"append"} {"type":"step/end","seq":55,"time":1783352073718,"data":{"turn":1,"step":1}} @@ -101,6 +101,6 @@ {"type":"assistant/chunk","seq":99,"time":1783352075045,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":100,"time":1783352075045,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":200,"outputTokens":40,"cacheReadTokens":2816,"reasoningTokens":37}}}} {"type":"assistant/chunk","seq":101,"time":1783352075045,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":102,"time":1783352075045,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user asked me to read the file and then reply with exactly the single word \"DONE\". I've read the file. Now I just need to reply with \"DONE\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":200,"outputTokens":40,"cacheReadTokens":2816,"reasoningTokens":37}},"sourceEventSeqs":[57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101],"surfaceOp":"append"} +{"type":"assistant/message","seq":102,"time":1783352075045,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user asked me to read the file and then reply with exactly the single word \"DONE\". I've read the file. Now I just need to reply with \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":200,"outputTokens":40,"cacheReadTokens":2816,"reasoningTokens":37}},"sourceEventSeqs":[57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101],"surfaceOp":"append"} {"type":"step/end","seq":103,"time":1783352075046,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":104,"time":1783352075046,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-terminal-card/session.jsonl b/examples/acp-agent/tests/snapshots/fs-terminal-card/session.jsonl index 9552a7a8f9..e53f4b3da3 100644 --- a/examples/acp-agent/tests/snapshots/fs-terminal-card/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-terminal-card/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352050753,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352050753,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo TERMINAL_OK. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352050755,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352050756,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352050756,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352051421,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352051422,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352051590,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -58,7 +58,7 @@ {"type":"assistant/chunk","seq":56,"time":1783352052118,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","arguments":"{\"command\": \"echo TERMINAL_OK\", \"description\": \"Echo TERMINAL_OK to verify terminal access\"}"}}}} {"type":"assistant/chunk","seq":57,"time":1783352052118,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2877,"outputTokens":90,"cacheReadTokens":0,"reasoningTokens":18}}}} {"type":"assistant/chunk","seq":58,"time":1783352052118,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":59,"time":1783352052121,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","arguments":"{\"command\": \"echo TERMINAL_OK\", \"description\": \"Echo TERMINAL_OK to verify terminal access\"}"}],"usage":{"inputTokens":2877,"outputTokens":90,"cacheReadTokens":0,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58],"surfaceOp":"append"} +{"type":"assistant/message","seq":59,"time":1783352052121,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","arguments":"{\"command\": \"echo TERMINAL_OK\", \"description\": \"Echo TERMINAL_OK to verify terminal access\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2877,"outputTokens":90,"cacheReadTokens":0,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58],"surfaceOp":"append"} {"type":"tool/call","seq":60,"time":1783352052121,"data":{"turn":1,"step":1,"callId":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","arguments":"{\"command\": \"echo TERMINAL_OK\", \"description\": \"Echo TERMINAL_OK to verify terminal access\"}"}} {"type":"tool/result","seq":61,"time":1783352052136,"data":{"turn":1,"step":1,"callId":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","content":[{"type":"text","text":"TERMINAL_OK\n"}],"isError":false},"sourceEventSeqs":[60],"surfaceOp":"append"} {"type":"step/end","seq":62,"time":1783352052137,"data":{"turn":1,"step":1}} @@ -93,6 +93,6 @@ {"type":"assistant/chunk","seq":91,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":92,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":168,"outputTokens":25,"cacheReadTokens":2816,"reasoningTokens":22}}}} {"type":"assistant/chunk","seq":93,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":94,"time":1783352052987,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command ran successfully and output \"TERMINAL_OK\". I should now reply with just \"DONE\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":168,"outputTokens":25,"cacheReadTokens":2816,"reasoningTokens":22}},"sourceEventSeqs":[64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93],"surfaceOp":"append"} +{"type":"assistant/message","seq":94,"time":1783352052987,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command ran successfully and output \"TERMINAL_OK\". I should now reply with just \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":168,"outputTokens":25,"cacheReadTokens":2816,"reasoningTokens":22}},"sourceEventSeqs":[64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93],"surfaceOp":"append"} {"type":"step/end","seq":95,"time":1783352052987,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":96,"time":1783352052987,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl index 47627ae7a5..08ec0f1323 100644 --- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352092220,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352092221,"data":{"content":[{"type":"text","text":"First use the read tool to read data.txt in the current directory. Then use the write tool (NOT bash) to replace its entire contents with exactly the single line: replaced. Then reply with exactly the single word DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352092223,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352092223,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352092223,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352092902,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352092902,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352093090,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -63,7 +63,7 @@ {"type":"assistant/chunk","seq":61,"time":1783352093614,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_n4eRJuGoxNR07svgNtk82243","name":"read","arguments":"{\"file_path\": \"data.txt\"}"}}}} {"type":"assistant/chunk","seq":62,"time":1783352093614,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2899,"outputTokens":87,"cacheReadTokens":0,"reasoningTokens":42}}}} {"type":"assistant/chunk","seq":63,"time":1783352093614,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":64,"time":1783352093617,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read data.txt using the read tool\n2. Replace its entire contents with exactly \"replaced\" using the write tool\n3. Reply with exactly \"DONE\""},{"type":"tool-call","id":"call_00_n4eRJuGoxNR07svgNtk82243","name":"read","arguments":"{\"file_path\": \"data.txt\"}"}],"usage":{"inputTokens":2899,"outputTokens":87,"cacheReadTokens":0,"reasoningTokens":42}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63],"surfaceOp":"append"} +{"type":"assistant/message","seq":64,"time":1783352093617,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read data.txt using the read tool\n2. Replace its entire contents with exactly \"replaced\" using the write tool\n3. Reply with exactly \"DONE\""},{"type":"tool-call","id":"call_00_n4eRJuGoxNR07svgNtk82243","name":"read","arguments":"{\"file_path\": \"data.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2899,"outputTokens":87,"cacheReadTokens":0,"reasoningTokens":42}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63],"surfaceOp":"append"} {"type":"tool/call","seq":65,"time":1783352093617,"data":{"turn":1,"step":1,"callId":"call_00_n4eRJuGoxNR07svgNtk82243","name":"read","arguments":"{\"file_path\": \"data.txt\"}"}} {"type":"tool/result","seq":66,"time":1783352093624,"data":{"turn":1,"step":1,"callId":"call_00_n4eRJuGoxNR07svgNtk82243","content":[{"type":"text","text":"/tmp/acp-snap-cwd-hH2sGY/data.txt\nfile\n\n1: original contents\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[65],"surfaceOp":"append"} {"type":"step/end","seq":67,"time":1783352093624,"data":{"turn":1,"step":1}} @@ -112,7 +112,7 @@ {"type":"assistant/chunk","seq":110,"time":1783352094988,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_N23EvXjDo4c8enyWpIUq4043","name":"write","arguments":"{\"file_path\": \"data.txt\", \"content\": \"replaced\"}"}}}} {"type":"assistant/chunk","seq":111,"time":1783352094988,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":228,"outputTokens":79,"cacheReadTokens":2816,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":112,"time":1783352094988,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":113,"time":1783352094988,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file contains \"original contents\". Now I'll replace it with \"replaced\"."},{"type":"tool-call","id":"call_00_N23EvXjDo4c8enyWpIUq4043","name":"write","arguments":"{\"file_path\": \"data.txt\", \"content\": \"replaced\"}"}],"usage":{"inputTokens":228,"outputTokens":79,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} +{"type":"assistant/message","seq":113,"time":1783352094988,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file contains \"original contents\". Now I'll replace it with \"replaced\"."},{"type":"tool-call","id":"call_00_N23EvXjDo4c8enyWpIUq4043","name":"write","arguments":"{\"file_path\": \"data.txt\", \"content\": \"replaced\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":228,"outputTokens":79,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} {"type":"tool/call","seq":114,"time":1783352094988,"data":{"turn":1,"step":2,"callId":"call_00_N23EvXjDo4c8enyWpIUq4043","name":"write","arguments":"{\"file_path\": \"data.txt\", \"content\": \"replaced\"}"}} {"type":"tool/result","seq":115,"time":1783352094995,"data":{"turn":1,"step":2,"callId":"call_00_N23EvXjDo4c8enyWpIUq4043","content":[{"type":"text","text":"/tmp/acp-snap-cwd-hH2sGY/data.txt\nfile\n\nUpdated file\n"}],"isError":false,"meta":{"diffs":[{"path":"data.txt","oldText":"original contents","newText":"replaced"}]}},"sourceEventSeqs":[114],"surfaceOp":"append"} {"type":"step/end","seq":116,"time":1783352094995,"data":{"turn":1,"step":2}} @@ -141,6 +141,6 @@ {"type":"assistant/chunk","seq":139,"time":1783352096309,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":140,"time":1783352096309,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":225,"outputTokens":19,"cacheReadTokens":2944,"reasoningTokens":16}}}} {"type":"assistant/chunk","seq":141,"time":1783352096309,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":142,"time":1783352096310,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The file has been replaced successfully. Now I just reply with \"DONE\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":225,"outputTokens":19,"cacheReadTokens":2944,"reasoningTokens":16}},"sourceEventSeqs":[118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141],"surfaceOp":"append"} +{"type":"assistant/message","seq":142,"time":1783352096310,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The file has been replaced successfully. Now I just reply with \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":225,"outputTokens":19,"cacheReadTokens":2944,"reasoningTokens":16}},"sourceEventSeqs":[118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141],"surfaceOp":"append"} {"type":"step/end","seq":143,"time":1783352096310,"data":{"turn":1,"step":3}} {"type":"turn/end","seq":144,"time":1783352096310,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write/session.jsonl b/examples/acp-agent/tests/snapshots/fs-write/session.jsonl index 7e4b2dda01..59ba868817 100644 --- a/examples/acp-agent/tests/snapshots/fs-write/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352078754,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352078754,"data":{"content":[{"type":"text","text":"Use the write tool (NOT bash) to create a file named notes.txt in the current directory containing exactly the single line: hello world. Then reply with exactly the single word DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352078756,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352078756,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352078756,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352079254,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352079254,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352079333,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -60,7 +60,7 @@ {"type":"assistant/chunk","seq":58,"time":1783352079886,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_APMUCJJm9lrTSlVbg6dB0185","name":"write","arguments":"{\"file_path\": \"notes.txt\", \"content\": \"hello world\"}"}}}} {"type":"assistant/chunk","seq":59,"time":1783352079886,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2891,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":30}}}} {"type":"assistant/chunk","seq":60,"time":1783352079886,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":61,"time":1783352079888,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to create a file named notes.txt with the content \"hello world\" using the write tool, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_APMUCJJm9lrTSlVbg6dB0185","name":"write","arguments":"{\"file_path\": \"notes.txt\", \"content\": \"hello world\"}"}],"usage":{"inputTokens":2891,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":30}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} +{"type":"assistant/message","seq":61,"time":1783352079888,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to create a file named notes.txt with the content \"hello world\" using the write tool, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_APMUCJJm9lrTSlVbg6dB0185","name":"write","arguments":"{\"file_path\": \"notes.txt\", \"content\": \"hello world\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2891,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":30}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} {"type":"tool/call","seq":62,"time":1783352079888,"data":{"turn":1,"step":1,"callId":"call_00_APMUCJJm9lrTSlVbg6dB0185","name":"write","arguments":"{\"file_path\": \"notes.txt\", \"content\": \"hello world\"}"}} {"type":"tool/result","seq":63,"time":1783352079897,"data":{"turn":1,"step":1,"callId":"call_00_APMUCJJm9lrTSlVbg6dB0185","content":[{"type":"text","text":"/tmp/acp-snap-cwd-sNvn5N/notes.txt\nfile\n\nCreated file\n"}],"isError":false},"sourceEventSeqs":[62],"surfaceOp":"append"} {"type":"step/end","seq":64,"time":1783352079898,"data":{"turn":1,"step":1}} @@ -90,6 +90,6 @@ {"type":"assistant/chunk","seq":88,"time":1783352081056,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":89,"time":1783352081056,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":214,"outputTokens":20,"cacheReadTokens":2816,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":90,"time":1783352081056,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":91,"time":1783352081057,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file has been created. Now I just need to reply with \"DONE\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":214,"outputTokens":20,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90],"surfaceOp":"append"} +{"type":"assistant/message","seq":91,"time":1783352081057,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file has been created. Now I just need to reply with \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":214,"outputTokens":20,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90],"surfaceOp":"append"} {"type":"step/end","seq":92,"time":1783352081057,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":93,"time":1783352081057,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl index 1a72a2e5ef..07bd28c2cd 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352177366,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352177367,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352177368,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352177372,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352177372,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352178017,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352178018,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352178131,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -59,7 +59,7 @@ {"type":"assistant/chunk","seq":57,"time":1783352178592,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_qcIzLImnOm5qiKOBJUqY5047","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}}}} {"type":"assistant/chunk","seq":58,"time":1783352178592,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2879,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":23}}}} {"type":"assistant/chunk","seq":59,"time":1783352178592,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":60,"time":1783352178594,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `echo HELLO` using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_qcIzLImnOm5qiKOBJUqY5047","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}],"usage":{"inputTokens":2879,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59],"surfaceOp":"append"} +{"type":"assistant/message","seq":60,"time":1783352178594,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `echo HELLO` using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_qcIzLImnOm5qiKOBJUqY5047","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2879,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59],"surfaceOp":"append"} {"type":"tool/call","seq":61,"time":1783352178594,"data":{"turn":1,"step":1,"callId":"call_00_qcIzLImnOm5qiKOBJUqY5047","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}} {"type":"hook/invoked","seq":62,"time":1783352178614,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":63,"time":1783352178624,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:1","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":9.49630100000013}} @@ -130,7 +130,7 @@ {"type":"assistant/chunk","seq":128,"time":1783352180488,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_nzhKxYvCYj8OqI2tjOKb8506","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO command\"}"}}}} {"type":"assistant/chunk","seq":129,"time":1783352180489,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":178,"outputTokens":99,"cacheReadTokens":2816,"reasoningTokens":32}}}} {"type":"assistant/chunk","seq":130,"time":1783352180489,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":131,"time":1783352180489,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The tool output was rejected by policy, which says \"rerun with a summary instead\". Let me try again with a description that summarizes what we're doing."},{"type":"tool-call","id":"call_00_nzhKxYvCYj8OqI2tjOKb8506","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO command\"}"}],"usage":{"inputTokens":178,"outputTokens":99,"cacheReadTokens":2816,"reasoningTokens":32}},"sourceEventSeqs":[67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130],"surfaceOp":"append"} +{"type":"assistant/message","seq":131,"time":1783352180489,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The tool output was rejected by policy, which says \"rerun with a summary instead\". Let me try again with a description that summarizes what we're doing."},{"type":"tool-call","id":"call_00_nzhKxYvCYj8OqI2tjOKb8506","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO command\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":178,"outputTokens":99,"cacheReadTokens":2816,"reasoningTokens":32}},"sourceEventSeqs":[67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130],"surfaceOp":"append"} {"type":"tool/call","seq":132,"time":1783352180489,"data":{"turn":1,"step":2,"callId":"call_00_nzhKxYvCYj8OqI2tjOKb8506","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO command\"}"}} {"type":"hook/invoked","seq":133,"time":1783352180524,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:2","matcher":"bash"}} {"type":"hook/result","seq":134,"time":1783352180530,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:2","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":6.622174999999515}} @@ -182,7 +182,7 @@ {"type":"assistant/chunk","seq":180,"time":1783352181933,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_VumDDhhB4n5507EUXq650912","name":"bash","arguments":"{\"description\": \"Print HELLO to stdout\", \"command\": \"echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":181,"time":1783352181933,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":173,"outputTokens":80,"cacheReadTokens":2944,"reasoningTokens":13}}}} {"type":"assistant/chunk","seq":182,"time":1783352181933,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":183,"time":1783352181934,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The tool keeps rejecting. Let me try a slightly different description."},{"type":"tool-call","id":"call_00_VumDDhhB4n5507EUXq650912","name":"bash","arguments":"{\"description\": \"Print HELLO to stdout\", \"command\": \"echo HELLO\"}"}],"usage":{"inputTokens":173,"outputTokens":80,"cacheReadTokens":2944,"reasoningTokens":13}},"sourceEventSeqs":[138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182],"surfaceOp":"append"} +{"type":"assistant/message","seq":183,"time":1783352181934,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The tool keeps rejecting. Let me try a slightly different description."},{"type":"tool-call","id":"call_00_VumDDhhB4n5507EUXq650912","name":"bash","arguments":"{\"description\": \"Print HELLO to stdout\", \"command\": \"echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":173,"outputTokens":80,"cacheReadTokens":2944,"reasoningTokens":13}},"sourceEventSeqs":[138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182],"surfaceOp":"append"} {"type":"tool/call","seq":184,"time":1783352181934,"data":{"turn":1,"step":3,"callId":"call_00_VumDDhhB4n5507EUXq650912","name":"bash","arguments":"{\"description\": \"Print HELLO to stdout\", \"command\": \"echo HELLO\"}"}} {"type":"hook/invoked","seq":185,"time":1783352181945,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:3","matcher":"bash"}} {"type":"hook/result","seq":186,"time":1783352181953,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:3","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":7.827785000000404}} @@ -234,7 +234,7 @@ {"type":"assistant/chunk","seq":232,"time":1783352183049,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_i5NCqPa2LGAy1wk8uJQR2369","name":"bash","arguments":"{\"description\": \"echo HELLO\", \"command\": \"echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":233,"time":1783352183049,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":149,"outputTokens":80,"cacheReadTokens":3072,"reasoningTokens":15}}}} {"type":"assistant/chunk","seq":234,"time":1783352183049,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":235,"time":1783352183049,"data":{"turn":1,"step":4,"content":[{"type":"reasoning","text":"The policy keeps rejecting my attempts. Let me try a very short description."},{"type":"tool-call","id":"call_00_i5NCqPa2LGAy1wk8uJQR2369","name":"bash","arguments":"{\"description\": \"echo HELLO\", \"command\": \"echo HELLO\"}"}],"usage":{"inputTokens":149,"outputTokens":80,"cacheReadTokens":3072,"reasoningTokens":15}},"sourceEventSeqs":[190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234],"surfaceOp":"append"} +{"type":"assistant/message","seq":235,"time":1783352183049,"data":{"turn":1,"step":4,"content":[{"type":"reasoning","text":"The policy keeps rejecting my attempts. Let me try a very short description."},{"type":"tool-call","id":"call_00_i5NCqPa2LGAy1wk8uJQR2369","name":"bash","arguments":"{\"description\": \"echo HELLO\", \"command\": \"echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":149,"outputTokens":80,"cacheReadTokens":3072,"reasoningTokens":15}},"sourceEventSeqs":[190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234],"surfaceOp":"append"} {"type":"tool/call","seq":236,"time":1783352183050,"data":{"turn":1,"step":4,"callId":"call_00_i5NCqPa2LGAy1wk8uJQR2369","name":"bash","arguments":"{\"description\": \"echo HELLO\", \"command\": \"echo HELLO\"}"}} {"type":"hook/invoked","seq":237,"time":1783352183069,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:4","matcher":"bash"}} {"type":"hook/result","seq":238,"time":1783352183077,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:4","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":8.41934399999991}} @@ -280,7 +280,7 @@ {"type":"assistant/chunk","seq":278,"time":1783352184233,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_0IuOIk6iuG6ZesROSyAM3669","name":"bash","arguments":"{\"command\": \"echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":279,"time":1783352184233,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":125,"outputTokens":66,"cacheReadTokens":3200,"reasoningTokens":20}}}} {"type":"assistant/chunk","seq":280,"time":1783352184233,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":281,"time":1783352184233,"data":{"turn":1,"step":5,"content":[{"type":"reasoning","text":"Hmm, the policy keeps rejecting. Let me try without the description field, just the command."},{"type":"tool-call","id":"call_00_0IuOIk6iuG6ZesROSyAM3669","name":"bash","arguments":"{\"command\": \"echo HELLO\"}"}],"usage":{"inputTokens":125,"outputTokens":66,"cacheReadTokens":3200,"reasoningTokens":20}},"sourceEventSeqs":[242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280],"surfaceOp":"append"} +{"type":"assistant/message","seq":281,"time":1783352184233,"data":{"turn":1,"step":5,"content":[{"type":"reasoning","text":"Hmm, the policy keeps rejecting. Let me try without the description field, just the command."},{"type":"tool-call","id":"call_00_0IuOIk6iuG6ZesROSyAM3669","name":"bash","arguments":"{\"command\": \"echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":125,"outputTokens":66,"cacheReadTokens":3200,"reasoningTokens":20}},"sourceEventSeqs":[242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280],"surfaceOp":"append"} {"type":"tool/call","seq":282,"time":1783352184233,"data":{"turn":1,"step":5,"callId":"call_00_0IuOIk6iuG6ZesROSyAM3669","name":"bash","arguments":"{\"command\": \"echo HELLO\"}"}} {"type":"hook/invoked","seq":283,"time":1783352184234,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:5","matcher":"bash"}} {"type":"hook/result","seq":284,"time":1783352184243,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:5","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":8.810661999999866}} @@ -428,7 +428,7 @@ {"type":"assistant/chunk","seq":426,"time":1783352186527,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_mGqWmySh60rWKNcyVBFk2747","name":"bash","arguments":"{\"description\": \"Echo the string HELLO\", \"command\": \"echo \\\"HELLO\\\"\"}"}}}} {"type":"assistant/chunk","seq":427,"time":1783352186527,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":215,"outputTokens":176,"cacheReadTokens":3200,"reasoningTokens":106}}}} {"type":"assistant/chunk","seq":428,"time":1783352186527,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":429,"time":1783352186527,"data":{"turn":1,"step":6,"content":[{"type":"reasoning","text":"The tool is consistently being rejected by policy. The policy says \"rerun with a summary instead\" - it seems the content of the output (which would be \"HELLO\") is being blocked. Let me try a different approach - maybe I need to use a different command or approach to satisfy the policy.\n\nWait, the user explicitly asked me to \"run exactly: echo HELLO\" and \"Report the tool result you got back verbatim\". Let me try `echo \"HELLO\"` with quotes."},{"type":"tool-call","id":"call_00_mGqWmySh60rWKNcyVBFk2747","name":"bash","arguments":"{\"description\": \"Echo the string HELLO\", \"command\": \"echo \\\"HELLO\\\"\"}"}],"usage":{"inputTokens":215,"outputTokens":176,"cacheReadTokens":3200,"reasoningTokens":106}},"sourceEventSeqs":[288,289,290,291,292,293,294,295,296,297,298,299,300,301,302,303,304,305,306,307,308,309,310,311,312,313,314,315,316,317,318,319,320,321,322,323,324,325,326,327,328,329,330,331,332,333,334,335,336,337,338,339,340,341,342,343,344,345,346,347,348,349,350,351,352,353,354,355,356,357,358,359,360,361,362,363,364,365,366,367,368,369,370,371,372,373,374,375,376,377,378,379,380,381,382,383,384,385,386,387,388,389,390,391,392,393,394,395,396,397,398,399,400,401,402,403,404,405,406,407,408,409,410,411,412,413,414,415,416,417,418,419,420,421,422,423,424,425,426,427,428],"surfaceOp":"append"} +{"type":"assistant/message","seq":429,"time":1783352186527,"data":{"turn":1,"step":6,"content":[{"type":"reasoning","text":"The tool is consistently being rejected by policy. The policy says \"rerun with a summary instead\" - it seems the content of the output (which would be \"HELLO\") is being blocked. Let me try a different approach - maybe I need to use a different command or approach to satisfy the policy.\n\nWait, the user explicitly asked me to \"run exactly: echo HELLO\" and \"Report the tool result you got back verbatim\". Let me try `echo \"HELLO\"` with quotes."},{"type":"tool-call","id":"call_00_mGqWmySh60rWKNcyVBFk2747","name":"bash","arguments":"{\"description\": \"Echo the string HELLO\", \"command\": \"echo \\\"HELLO\\\"\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":215,"outputTokens":176,"cacheReadTokens":3200,"reasoningTokens":106}},"sourceEventSeqs":[288,289,290,291,292,293,294,295,296,297,298,299,300,301,302,303,304,305,306,307,308,309,310,311,312,313,314,315,316,317,318,319,320,321,322,323,324,325,326,327,328,329,330,331,332,333,334,335,336,337,338,339,340,341,342,343,344,345,346,347,348,349,350,351,352,353,354,355,356,357,358,359,360,361,362,363,364,365,366,367,368,369,370,371,372,373,374,375,376,377,378,379,380,381,382,383,384,385,386,387,388,389,390,391,392,393,394,395,396,397,398,399,400,401,402,403,404,405,406,407,408,409,410,411,412,413,414,415,416,417,418,419,420,421,422,423,424,425,426,427,428],"surfaceOp":"append"} {"type":"tool/call","seq":430,"time":1783352186527,"data":{"turn":1,"step":6,"callId":"call_00_mGqWmySh60rWKNcyVBFk2747","name":"bash","arguments":"{\"description\": \"Echo the string HELLO\", \"command\": \"echo \\\"HELLO\\\"\"}"}} {"type":"hook/invoked","seq":431,"time":1783352186538,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:6","matcher":"bash"}} {"type":"hook/result","seq":432,"time":1783352186545,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:6","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":6.910448999999062}} @@ -549,7 +549,7 @@ {"type":"assistant/chunk","seq":547,"time":1783352188511,"data":{"turn":1,"step":7,"chunk":{"type":"block-end","index":2,"block":{"type":"tool-call","id":"call_00_Y371DzUR0Pz6IrkO8qgB9050","name":"bash","arguments":"{\"description\": \"Echo test message\", \"command\": \"echo \\\"TEST\\\"\"}"}}}} {"type":"assistant/chunk","seq":548,"time":1783352188511,"data":{"turn":1,"step":7,"chunk":{"type":"usage","usage":{"inputTokens":287,"outputTokens":146,"cacheReadTokens":3328,"reasoningTokens":70}}}} {"type":"assistant/chunk","seq":549,"time":1783352188512,"data":{"turn":1,"step":7,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":550,"time":1783352188512,"data":{"turn":1,"step":7,"content":[{"type":"reasoning","text":"The policy is blocking the output \"HELLO\" - it seems like the word \"HELLO\" (which might be a misspelling of \"HELLO\" that looks like \"HELL\" with \"O\") could be triggering some content filter. Let me try a completely different word to see if the tool works at all."},{"type":"text","text":"Let me try a different word to verify the tool works:"},{"type":"tool-call","id":"call_00_Y371DzUR0Pz6IrkO8qgB9050","name":"bash","arguments":"{\"description\": \"Echo test message\", \"command\": \"echo \\\"TEST\\\"\"}"}],"usage":{"inputTokens":287,"outputTokens":146,"cacheReadTokens":3328,"reasoningTokens":70}},"sourceEventSeqs":[436,437,438,439,440,441,442,443,444,445,446,447,448,449,450,451,452,453,454,455,456,457,458,459,460,461,462,463,464,465,466,467,468,469,470,471,472,473,474,475,476,477,478,479,480,481,482,483,484,485,486,487,488,489,490,491,492,493,494,495,496,497,498,499,500,501,502,503,504,505,506,507,508,509,510,511,512,513,514,515,516,517,518,519,520,521,522,523,524,525,526,527,528,529,530,531,532,533,534,535,536,537,538,539,540,541,542,543,544,545,546,547,548,549],"surfaceOp":"append"} +{"type":"assistant/message","seq":550,"time":1783352188512,"data":{"turn":1,"step":7,"content":[{"type":"reasoning","text":"The policy is blocking the output \"HELLO\" - it seems like the word \"HELLO\" (which might be a misspelling of \"HELLO\" that looks like \"HELL\" with \"O\") could be triggering some content filter. Let me try a completely different word to see if the tool works at all."},{"type":"text","text":"Let me try a different word to verify the tool works:"},{"type":"tool-call","id":"call_00_Y371DzUR0Pz6IrkO8qgB9050","name":"bash","arguments":"{\"description\": \"Echo test message\", \"command\": \"echo \\\"TEST\\\"\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":287,"outputTokens":146,"cacheReadTokens":3328,"reasoningTokens":70}},"sourceEventSeqs":[436,437,438,439,440,441,442,443,444,445,446,447,448,449,450,451,452,453,454,455,456,457,458,459,460,461,462,463,464,465,466,467,468,469,470,471,472,473,474,475,476,477,478,479,480,481,482,483,484,485,486,487,488,489,490,491,492,493,494,495,496,497,498,499,500,501,502,503,504,505,506,507,508,509,510,511,512,513,514,515,516,517,518,519,520,521,522,523,524,525,526,527,528,529,530,531,532,533,534,535,536,537,538,539,540,541,542,543,544,545,546,547,548,549],"surfaceOp":"append"} {"type":"tool/call","seq":551,"time":1783352188512,"data":{"turn":1,"step":7,"callId":"call_00_Y371DzUR0Pz6IrkO8qgB9050","name":"bash","arguments":"{\"description\": \"Echo test message\", \"command\": \"echo \\\"TEST\\\"\"}"}} {"type":"hook/invoked","seq":552,"time":1783352188524,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:7","matcher":"bash"}} {"type":"hook/result","seq":553,"time":1783352188532,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:7","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":7.573905000001105}} @@ -605,7 +605,7 @@ {"type":"assistant/chunk","seq":603,"time":1783352189858,"data":{"turn":1,"step":8,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_S2XENjVanaHtBn3RZfhO7965","name":"bash","arguments":"{\"description\": \"Print working directory\", \"command\": \"pwd\"}"}}}} {"type":"assistant/chunk","seq":604,"time":1783352189858,"data":{"turn":1,"step":8,"chunk":{"type":"usage","usage":{"inputTokens":201,"outputTokens":84,"cacheReadTokens":3584,"reasoningTokens":22}}}} {"type":"assistant/chunk","seq":605,"time":1783352189858,"data":{"turn":1,"step":8,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":606,"time":1783352189859,"data":{"turn":1,"step":8,"content":[{"type":"reasoning","text":"Even \"TEST\" is rejected. Let me try a simpler command like `pwd` or `ls`."},{"type":"tool-call","id":"call_00_S2XENjVanaHtBn3RZfhO7965","name":"bash","arguments":"{\"description\": \"Print working directory\", \"command\": \"pwd\"}"}],"usage":{"inputTokens":201,"outputTokens":84,"cacheReadTokens":3584,"reasoningTokens":22}},"sourceEventSeqs":[557,558,559,560,561,562,563,564,565,566,567,568,569,570,571,572,573,574,575,576,577,578,579,580,581,582,583,584,585,586,587,588,589,590,591,592,593,594,595,596,597,598,599,600,601,602,603,604,605],"surfaceOp":"append"} +{"type":"assistant/message","seq":606,"time":1783352189859,"data":{"turn":1,"step":8,"content":[{"type":"reasoning","text":"Even \"TEST\" is rejected. Let me try a simpler command like `pwd` or `ls`."},{"type":"tool-call","id":"call_00_S2XENjVanaHtBn3RZfhO7965","name":"bash","arguments":"{\"description\": \"Print working directory\", \"command\": \"pwd\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":201,"outputTokens":84,"cacheReadTokens":3584,"reasoningTokens":22}},"sourceEventSeqs":[557,558,559,560,561,562,563,564,565,566,567,568,569,570,571,572,573,574,575,576,577,578,579,580,581,582,583,584,585,586,587,588,589,590,591,592,593,594,595,596,597,598,599,600,601,602,603,604,605],"surfaceOp":"append"} {"type":"tool/call","seq":607,"time":1783352189859,"data":{"turn":1,"step":8,"callId":"call_00_S2XENjVanaHtBn3RZfhO7965","name":"bash","arguments":"{\"description\": \"Print working directory\", \"command\": \"pwd\"}"}} {"type":"hook/invoked","seq":608,"time":1783352189876,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:8","matcher":"bash"}} {"type":"hook/result","seq":609,"time":1783352189883,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:8","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":7.748225999999704}} @@ -747,6 +747,6 @@ {"type":"assistant/chunk","seq":745,"time":1783352192246,"data":{"turn":1,"step":9,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"I'm unable to run the `echo HELLO` command via the bash tool — every invocation is being rejected by the policy with the message \"tool output rejected by policy: rerun with a summary instead\". This appears to be a systemic policy restriction on the bash tool in this environment, as even simple commands like `pwd` and `echo \"TEST\"` are blocked.\n\nI cannot produce the tool result you asked for because the bash tool is not currently available for use."}}}} {"type":"assistant/chunk","seq":746,"time":1783352192246,"data":{"turn":1,"step":9,"chunk":{"type":"usage","usage":{"inputTokens":181,"outputTokens":130,"cacheReadTokens":3712,"reasoningTokens":31}}}} {"type":"assistant/chunk","seq":747,"time":1783352192246,"data":{"turn":1,"step":9,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":748,"time":1783352192247,"data":{"turn":1,"step":9,"content":[{"type":"reasoning","text":"All bash commands are being rejected. This seems like a system-level policy issue where the bash tool is blocked entirely. Let me report this to the user."},{"type":"text","text":"I'm unable to run the `echo HELLO` command via the bash tool — every invocation is being rejected by the policy with the message \"tool output rejected by policy: rerun with a summary instead\". This appears to be a systemic policy restriction on the bash tool in this environment, as even simple commands like `pwd` and `echo \"TEST\"` are blocked.\n\nI cannot produce the tool result you asked for because the bash tool is not currently available for use."}],"usage":{"inputTokens":181,"outputTokens":130,"cacheReadTokens":3712,"reasoningTokens":31}},"sourceEventSeqs":[613,614,615,616,617,618,619,620,621,622,623,624,625,626,627,628,629,630,631,632,633,634,635,636,637,638,639,640,641,642,643,644,645,646,647,648,649,650,651,652,653,654,655,656,657,658,659,660,661,662,663,664,665,666,667,668,669,670,671,672,673,674,675,676,677,678,679,680,681,682,683,684,685,686,687,688,689,690,691,692,693,694,695,696,697,698,699,700,701,702,703,704,705,706,707,708,709,710,711,712,713,714,715,716,717,718,719,720,721,722,723,724,725,726,727,728,729,730,731,732,733,734,735,736,737,738,739,740,741,742,743,744,745,746,747],"surfaceOp":"append"} +{"type":"assistant/message","seq":748,"time":1783352192247,"data":{"turn":1,"step":9,"content":[{"type":"reasoning","text":"All bash commands are being rejected. This seems like a system-level policy issue where the bash tool is blocked entirely. Let me report this to the user."},{"type":"text","text":"I'm unable to run the `echo HELLO` command via the bash tool — every invocation is being rejected by the policy with the message \"tool output rejected by policy: rerun with a summary instead\". This appears to be a systemic policy restriction on the bash tool in this environment, as even simple commands like `pwd` and `echo \"TEST\"` are blocked.\n\nI cannot produce the tool result you asked for because the bash tool is not currently available for use."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":181,"outputTokens":130,"cacheReadTokens":3712,"reasoningTokens":31}},"sourceEventSeqs":[613,614,615,616,617,618,619,620,621,622,623,624,625,626,627,628,629,630,631,632,633,634,635,636,637,638,639,640,641,642,643,644,645,646,647,648,649,650,651,652,653,654,655,656,657,658,659,660,661,662,663,664,665,666,667,668,669,670,671,672,673,674,675,676,677,678,679,680,681,682,683,684,685,686,687,688,689,690,691,692,693,694,695,696,697,698,699,700,701,702,703,704,705,706,707,708,709,710,711,712,713,714,715,716,717,718,719,720,721,722,723,724,725,726,727,728,729,730,731,732,733,734,735,736,737,738,739,740,741,742,743,744,745,746,747],"surfaceOp":"append"} {"type":"step/end","seq":749,"time":1783352192247,"data":{"turn":1,"step":9}} {"type":"turn/end","seq":750,"time":1783352192247,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl index 6c98868284..2e167db28c 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352196662,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352196662,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352196664,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352196664,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352196664,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352197315,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352197315,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352197457,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -57,7 +57,7 @@ {"type":"assistant/chunk","seq":55,"time":1783352197953,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_HbCMzTslWBZTSphWN0z97382","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":56,"time":1783352197953,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":23}}}} {"type":"assistant/chunk","seq":57,"time":1783352197954,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":58,"time":1783352197956,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `echo HELLO` using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_HbCMzTslWBZTSphWN0z97382","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"usage":{"inputTokens":2878,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"surfaceOp":"append"} +{"type":"assistant/message","seq":58,"time":1783352197956,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `echo HELLO` using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_HbCMzTslWBZTSphWN0z97382","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2878,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"surfaceOp":"append"} {"type":"tool/call","seq":59,"time":1783352197956,"data":{"turn":1,"step":1,"callId":"call_00_HbCMzTslWBZTSphWN0z97382","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}} {"type":"hook/invoked","seq":60,"time":1783352197968,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":61,"time":1783352197976,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:1","decision":"pass","exitCode":0,"durationMs":7.404540999999881}} @@ -121,6 +121,6 @@ {"type":"assistant/chunk","seq":119,"time":1783352199410,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result was:\n\n```\nHELLO\n```\n\nIt completed successfully with exit code 0."}}}} {"type":"assistant/chunk","seq":120,"time":1783352199411,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":188,"outputTokens":51,"cacheReadTokens":2816,"reasoningTokens":30}}}} {"type":"assistant/chunk","seq":121,"time":1783352199411,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":122,"time":1783352199411,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user asked me to report the tool result verbatim. The result was \"HELLO\" with an exit code of 0 (success)."},{"type":"text","text":"The tool result was:\n\n```\nHELLO\n```\n\nIt completed successfully with exit code 0."}],"usage":{"inputTokens":188,"outputTokens":51,"cacheReadTokens":2816,"reasoningTokens":30}},"sourceEventSeqs":[66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121],"surfaceOp":"append"} +{"type":"assistant/message","seq":122,"time":1783352199411,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user asked me to report the tool result verbatim. The result was \"HELLO\" with an exit code of 0 (success)."},{"type":"text","text":"The tool result was:\n\n```\nHELLO\n```\n\nIt completed successfully with exit code 0."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":188,"outputTokens":51,"cacheReadTokens":2816,"reasoningTokens":30}},"sourceEventSeqs":[66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121],"surfaceOp":"append"} {"type":"step/end","seq":123,"time":1783352199411,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":124,"time":1783352199412,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl index 46a5e135a6..18c5510b8a 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352171519,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352171520,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352171527,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352171528,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352171528,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352171991,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352171991,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352172088,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -51,7 +51,7 @@ {"type":"assistant/chunk","seq":49,"time":1783352172555,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":50,"time":1783352172555,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":51,"time":1783352172555,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":52,"time":1783352172557,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."},{"type":"tool-call","id":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}],"usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} +{"type":"assistant/message","seq":52,"time":1783352172557,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."},{"type":"tool-call","id":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} {"type":"tool/call","seq":53,"time":1783352172557,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}} {"type":"hook/invoked","seq":54,"time":1783352172558,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":55,"time":1783352172573,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"ask","exitCode":0,"durationMs":14.113374999999905}} @@ -108,6 +108,6 @@ {"type":"assistant/chunk","seq":106,"time":1783352173964,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash requires manual approval in this session\n```"}}}} {"type":"assistant/chunk","seq":107,"time":1783352173964,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":166,"outputTokens":45,"cacheReadTokens":2816,"reasoningTokens":22}}}} {"type":"assistant/chunk","seq":108,"time":1783352173964,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":109,"time":1783352173964,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The bash tool returned an error saying it requires manual approval in this session. I'll report this verbatim."},{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash requires manual approval in this session\n```"}],"usage":{"inputTokens":166,"outputTokens":45,"cacheReadTokens":2816,"reasoningTokens":22}},"sourceEventSeqs":[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} +{"type":"assistant/message","seq":109,"time":1783352173964,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The bash tool returned an error saying it requires manual approval in this session. I'll report this verbatim."},{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash requires manual approval in this session\n```"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":166,"outputTokens":45,"cacheReadTokens":2816,"reasoningTokens":22}},"sourceEventSeqs":[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} {"type":"step/end","seq":110,"time":1783352173964,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":111,"time":1783352173965,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl index b8f30ee327..9633075e5b 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352165195,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352165196,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352165198,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352165199,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352165199,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352165899,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352165899,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352166048,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -51,7 +51,7 @@ {"type":"assistant/chunk","seq":49,"time":1783352166512,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":50,"time":1783352166512,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":51,"time":1783352166512,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":52,"time":1783352166514,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."},{"type":"tool-call","id":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} +{"type":"assistant/message","seq":52,"time":1783352166514,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."},{"type":"tool-call","id":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} {"type":"tool/call","seq":53,"time":1783352166514,"data":{"turn":1,"step":1,"callId":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}} {"type":"hook/invoked","seq":54,"time":1783352166515,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":55,"time":1783352166528,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"block","exitCode":2,"stderrSummary":"bash is disabled by policy in this session","durationMs":12.367074000000684}} @@ -115,6 +115,6 @@ {"type":"assistant/chunk","seq":113,"time":1783352167933,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool returned:\n\n> Error: bash is disabled by policy in this session\n\nI cannot run the command because the bash tool is disabled by policy."}}}} {"type":"assistant/chunk","seq":114,"time":1783352167933,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":167,"outputTokens":52,"cacheReadTokens":2816,"reasoningTokens":21}}}} {"type":"assistant/chunk","seq":115,"time":1783352167933,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":116,"time":1783352167934,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The bash tool is disabled by policy. I need to report this error verbatim back to the user."},{"type":"text","text":"The tool returned:\n\n> Error: bash is disabled by policy in this session\n\nI cannot run the command because the bash tool is disabled by policy."}],"usage":{"inputTokens":167,"outputTokens":52,"cacheReadTokens":2816,"reasoningTokens":21}},"sourceEventSeqs":[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115],"surfaceOp":"append"} +{"type":"assistant/message","seq":116,"time":1783352167934,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The bash tool is disabled by policy. I need to report this error verbatim back to the user."},{"type":"text","text":"The tool returned:\n\n> Error: bash is disabled by policy in this session\n\nI cannot run the command because the bash tool is disabled by policy."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":167,"outputTokens":52,"cacheReadTokens":2816,"reasoningTokens":21}},"sourceEventSeqs":[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115],"surfaceOp":"append"} {"type":"step/end","seq":117,"time":1783352167934,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":118,"time":1783352167934,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl index 3e07124e41..886761da18 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl @@ -5,7 +5,7 @@ {"type":"user/message","seq":3,"time":1783352160564,"data":{"content":[{"type":"text","text":"What is my favorite color? Reply with just the color and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"context/message","seq":4,"time":1783352160564,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-claude"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783352160565,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":6,"time":1783352160566,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783352160566,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":7,"time":1783352161228,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":8,"time":1783352161229,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":9,"time":1783352161335,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -33,6 +33,6 @@ {"type":"assistant/chunk","seq":31,"time":1783352161512,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"teal"}}}} {"type":"assistant/chunk","seq":32,"time":1783352161512,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2892,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}}}} {"type":"assistant/chunk","seq":33,"time":1783352161512,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":34,"time":1783352161515,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user's favorite color is teal, as stated in the context provided by the plugin."},{"type":"text","text":"teal"}],"usage":{"inputTokens":2892,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"surfaceOp":"append"} +{"type":"assistant/message","seq":34,"time":1783352161515,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user's favorite color is teal, as stated in the context provided by the plugin."},{"type":"text","text":"teal"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2892,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"surfaceOp":"append"} {"type":"step/end","seq":35,"time":1783352161516,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":36,"time":1783352161516,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl index 2bed8d839a..5f6b0e6e9e 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352203369,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352203370,"data":{"content":[{"type":"text","text":"Reply with the single word FIRST and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352203371,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352203372,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352203372,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352204036,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352204036,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352204247,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -28,7 +28,7 @@ {"type":"assistant/chunk","seq":26,"time":1783352204393,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"FIRST"}}}} {"type":"assistant/chunk","seq":27,"time":1783352204393,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2862,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":28,"time":1783352204393,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":29,"time":1783352204396,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with the single word \"FIRST\" and stop."},{"type":"text","text":"FIRST"}],"usage":{"inputTokens":2862,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28],"surfaceOp":"append"} +{"type":"assistant/message","seq":29,"time":1783352204396,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with the single word \"FIRST\" and stop."},{"type":"text","text":"FIRST"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2862,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28],"surfaceOp":"append"} {"type":"step/end","seq":30,"time":1783352204396,"data":{"turn":1,"step":1}} {"type":"hook/invoked","seq":31,"time":1783352204396,"data":{"turn":1,"point":"Stop","dialect":"claude","handlerId":"claude:Stop:1"}} {"type":"hook/result","seq":32,"time":1783352204443,"data":{"turn":1,"point":"Stop","handlerId":"claude:Stop:1","decision":"block","exitCode":2,"stderrSummary":"Also reply with the single word SECOND, then stop.","durationMs":47.01462700000047}} @@ -185,7 +185,7 @@ {"type":"assistant/chunk","seq":183,"time":1783352206162,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"FIRST"}}}} {"type":"assistant/chunk","seq":184,"time":1783352206162,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":73,"outputTokens":146,"cacheReadTokens":2816,"reasoningTokens":143}}}} {"type":"assistant/chunk","seq":185,"time":1783352206162,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":186,"time":1783352206162,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user wants me to reply with \"FIRST\" only, but there's a steering input telling me to also reply with \"SECOND\". However, the user's explicit instruction is to reply with the single word FIRST and stop. The steering is from a plugin, not the user themselves. I should follow the user's original instruction.\n\nWait, let me re-read. The user said \"Reply with the single word FIRST and stop.\" Then there's a steering from \"plugin\" saying \"Also reply with the single word SECOND, then stop.\"\n\nThe user's instruction is clear: reply with FIRST and stop. The steering is from a plugin source, not the user. I'll follow the user's instruction."},{"type":"text","text":"FIRST"}],"usage":{"inputTokens":73,"outputTokens":146,"cacheReadTokens":2816,"reasoningTokens":143}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185],"surfaceOp":"append"} +{"type":"assistant/message","seq":186,"time":1783352206162,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user wants me to reply with \"FIRST\" only, but there's a steering input telling me to also reply with \"SECOND\". However, the user's explicit instruction is to reply with the single word FIRST and stop. The steering is from a plugin, not the user themselves. I should follow the user's original instruction.\n\nWait, let me re-read. The user said \"Reply with the single word FIRST and stop.\" Then there's a steering from \"plugin\" saying \"Also reply with the single word SECOND, then stop.\"\n\nThe user's instruction is clear: reply with FIRST and stop. The steering is from a plugin source, not the user. I'll follow the user's instruction."},{"type":"text","text":"FIRST"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":73,"outputTokens":146,"cacheReadTokens":2816,"reasoningTokens":143}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185],"surfaceOp":"append"} {"type":"step/end","seq":187,"time":1783352206163,"data":{"turn":1,"step":2}} {"type":"hook/invoked","seq":188,"time":1783352206163,"data":{"turn":1,"point":"Stop","dialect":"claude","handlerId":"claude:Stop:2"}} {"type":"hook/result","seq":189,"time":1783352206190,"data":{"turn":1,"point":"Stop","handlerId":"claude:Stop:2","decision":"pass","exitCode":0,"durationMs":26.904655000000275}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl index 0936881298..4272fe6a94 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352220747,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352220748,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352220749,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352220750,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352220750,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352221451,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352221451,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352221651,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -60,7 +60,7 @@ {"type":"assistant/chunk","seq":58,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}}}} {"type":"assistant/chunk","seq":59,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":25}}}} {"type":"assistant/chunk","seq":60,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":61,"time":1783352222124,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run the command \"echo HELLO\" using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}],"usage":{"inputTokens":2878,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":25}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} +{"type":"assistant/message","seq":61,"time":1783352222124,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run the command \"echo HELLO\" using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2878,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":25}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} {"type":"tool/call","seq":62,"time":1783352222124,"data":{"turn":1,"step":1,"callId":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}} {"type":"hook/invoked","seq":63,"time":1783352222138,"data":{"turn":1,"point":"PostToolUse","dialect":"codex","handlerId":"codex:PostToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":64,"time":1783352222148,"data":{"turn":1,"point":"PostToolUse","handlerId":"codex:PostToolUse:1","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by codex policy: summarize instead","durationMs":9.571565000000192}} @@ -217,6 +217,6 @@ {"type":"assistant/chunk","seq":215,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result I got back is:\n\n> `tool output rejected by codex policy: summarize instead`\n\nThis is the verbatim result from the tool — it was not the expected `\"HELLO\"` output because the codex policy blocked it and instructed me to summarize instead."}}}} {"type":"assistant/chunk","seq":216,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":176,"outputTokens":145,"cacheReadTokens":2816,"reasoningTokens":86}}}} {"type":"assistant/chunk","seq":217,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":218,"time":1783352224655,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output was rejected by the codex policy with the instruction to \"summarize instead\". This means I cannot show the raw output verbatim as the user requested. Let me try to comply but report what happened.\n\nActually, the user asked me to report the tool result verbatim. The tool result I got back is:\n\n\"tool output rejected by codex policy: summarize instead\"\n\nSo I should report that verbatim."},{"type":"text","text":"The tool result I got back is:\n\n> `tool output rejected by codex policy: summarize instead`\n\nThis is the verbatim result from the tool — it was not the expected `\"HELLO\"` output because the codex policy blocked it and instructed me to summarize instead."}],"usage":{"inputTokens":176,"outputTokens":145,"cacheReadTokens":2816,"reasoningTokens":86}},"sourceEventSeqs":[68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217],"surfaceOp":"append"} +{"type":"assistant/message","seq":218,"time":1783352224655,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output was rejected by the codex policy with the instruction to \"summarize instead\". This means I cannot show the raw output verbatim as the user requested. Let me try to comply but report what happened.\n\nActually, the user asked me to report the tool result verbatim. The tool result I got back is:\n\n\"tool output rejected by codex policy: summarize instead\"\n\nSo I should report that verbatim."},{"type":"text","text":"The tool result I got back is:\n\n> `tool output rejected by codex policy: summarize instead`\n\nThis is the verbatim result from the tool — it was not the expected `\"HELLO\"` output because the codex policy blocked it and instructed me to summarize instead."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":176,"outputTokens":145,"cacheReadTokens":2816,"reasoningTokens":86}},"sourceEventSeqs":[68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217],"surfaceOp":"append"} {"type":"step/end","seq":219,"time":1783352224655,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":220,"time":1783352224655,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl index 6932a1f47e..d60858ee0a 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352228441,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352228442,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352228443,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352228443,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352228443,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352228985,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352228985,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352229106,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -57,7 +57,7 @@ {"type":"assistant/chunk","seq":55,"time":1783352229598,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_Q6wHtakaip2QNfIXaVJY5458","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":56,"time":1783352229598,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":23}}}} {"type":"assistant/chunk","seq":57,"time":1783352229598,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":58,"time":1783352229601,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `echo HELLO` using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_Q6wHtakaip2QNfIXaVJY5458","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"usage":{"inputTokens":2878,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"surfaceOp":"append"} +{"type":"assistant/message","seq":58,"time":1783352229601,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `echo HELLO` using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_Q6wHtakaip2QNfIXaVJY5458","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2878,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"surfaceOp":"append"} {"type":"tool/call","seq":59,"time":1783352229601,"data":{"turn":1,"step":1,"callId":"call_00_Q6wHtakaip2QNfIXaVJY5458","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}} {"type":"hook/invoked","seq":60,"time":1783352229622,"data":{"turn":1,"point":"PostToolUse","dialect":"codex","handlerId":"codex:PostToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":61,"time":1783352229632,"data":{"turn":1,"point":"PostToolUse","handlerId":"codex:PostToolUse:1","decision":"pass","exitCode":0,"durationMs":9.27664199999981}} @@ -111,6 +111,6 @@ {"type":"assistant/chunk","seq":109,"time":1783352231379,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result I received is:\n\n```\nHELLO\n```"}}}} {"type":"assistant/chunk","seq":110,"time":1783352231379,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":188,"outputTokens":41,"cacheReadTokens":2816,"reasoningTokens":27}}}} {"type":"assistant/chunk","seq":111,"time":1783352231379,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":112,"time":1783352231380,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user asked me to report the tool result verbatim. The result I got back is:\n\nHELLO\n\nThat's it."},{"type":"text","text":"The tool result I received is:\n\n```\nHELLO\n```"}],"usage":{"inputTokens":188,"outputTokens":41,"cacheReadTokens":2816,"reasoningTokens":27}},"sourceEventSeqs":[66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111],"surfaceOp":"append"} +{"type":"assistant/message","seq":112,"time":1783352231380,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user asked me to report the tool result verbatim. The result I got back is:\n\nHELLO\n\nThat's it."},{"type":"text","text":"The tool result I received is:\n\n```\nHELLO\n```"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":188,"outputTokens":41,"cacheReadTokens":2816,"reasoningTokens":27}},"sourceEventSeqs":[66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111],"surfaceOp":"append"} {"type":"step/end","seq":113,"time":1783352231380,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":114,"time":1783352231380,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl index a2022d9d6d..812998aad5 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352214604,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352214605,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352214607,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352214608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352214608,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352215181,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352215181,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352215351,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -51,7 +51,7 @@ {"type":"assistant/chunk","seq":49,"time":1783352215801,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_tv0SMeLXaTuyuVrOxnV97085","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":50,"time":1783352215801,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2880,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":51,"time":1783352215801,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":52,"time":1783352215804,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."},{"type":"tool-call","id":"call_00_tv0SMeLXaTuyuVrOxnV97085","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"usage":{"inputTokens":2880,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} +{"type":"assistant/message","seq":52,"time":1783352215804,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."},{"type":"tool-call","id":"call_00_tv0SMeLXaTuyuVrOxnV97085","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2880,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} {"type":"tool/call","seq":53,"time":1783352215804,"data":{"turn":1,"step":1,"callId":"call_00_tv0SMeLXaTuyuVrOxnV97085","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}} {"type":"hook/invoked","seq":54,"time":1783352215805,"data":{"turn":1,"point":"PreToolUse","dialect":"codex","handlerId":"codex:PreToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":55,"time":1783352215832,"data":{"turn":1,"point":"PreToolUse","handlerId":"codex:PreToolUse:1","decision":"block","exitCode":2,"stderrSummary":"bash is disabled by codex policy in this session","durationMs":26.08518500000082}} @@ -112,6 +112,6 @@ {"type":"assistant/chunk","seq":110,"time":1783352217214,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash is disabled by codex policy in this session\n```"}}}} {"type":"assistant/chunk","seq":111,"time":1783352217214,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":171,"outputTokens":49,"cacheReadTokens":2816,"reasoningTokens":23}}}} {"type":"assistant/chunk","seq":112,"time":1783352217214,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":113,"time":1783352217214,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The bash tool is disabled by policy in this session. I need to report this result verbatim to the user."},{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash is disabled by codex policy in this session\n```"}],"usage":{"inputTokens":171,"outputTokens":49,"cacheReadTokens":2816,"reasoningTokens":23}},"sourceEventSeqs":[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} +{"type":"assistant/message","seq":113,"time":1783352217214,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The bash tool is disabled by policy in this session. I need to report this result verbatim to the user."},{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash is disabled by codex policy in this session\n```"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":171,"outputTokens":49,"cacheReadTokens":2816,"reasoningTokens":23}},"sourceEventSeqs":[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} {"type":"step/end","seq":114,"time":1783352217215,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":115,"time":1783352217215,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl index e9efd04100..1c710ff8e1 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl @@ -5,7 +5,7 @@ {"type":"user/message","seq":3,"time":1783352209707,"data":{"content":[{"type":"text","text":"What is my favorite color? Reply with just the color and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"context/message","seq":4,"time":1783352209707,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-codex"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783352209709,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":6,"time":1783352209710,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783352209710,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":7,"time":1783352210353,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":8,"time":1783352210353,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":9,"time":1783352210470,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -52,6 +52,6 @@ {"type":"assistant/chunk","seq":50,"time":1783352210788,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"teal"}}}} {"type":"assistant/chunk","seq":51,"time":1783352210788,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2891,"outputTokens":41,"cacheReadTokens":0,"reasoningTokens":38}}}} {"type":"assistant/chunk","seq":52,"time":1783352210788,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":53,"time":1783352210790,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user asked about their favorite color, and the context tells me they previously stated it's teal. They asked me to reply with just the color and stop, without using any tools."},{"type":"text","text":"teal"}],"usage":{"inputTokens":2891,"outputTokens":41,"cacheReadTokens":0,"reasoningTokens":38}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52],"surfaceOp":"append"} +{"type":"assistant/message","seq":53,"time":1783352210790,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user asked about their favorite color, and the context tells me they previously stated it's teal. They asked me to reply with just the color and stop, without using any tools."},{"type":"text","text":"teal"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2891,"outputTokens":41,"cacheReadTokens":0,"reasoningTokens":38}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52],"surfaceOp":"append"} {"type":"step/end","seq":54,"time":1783352210790,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":55,"time":1783352210790,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl index 252ff8e262..bba879203d 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352235020,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352235020,"data":{"content":[{"type":"text","text":"Reply with the single word FIRST and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352235022,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352235023,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352235023,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352235669,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352235670,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352235879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -30,7 +30,7 @@ {"type":"assistant/chunk","seq":28,"time":1783352236041,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"FIRST"}}}} {"type":"assistant/chunk","seq":29,"time":1783352236041,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2862,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}}}} {"type":"assistant/chunk","seq":30,"time":1783352236041,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":31,"time":1783352236043,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with only the single word \"FIRST\" and then stop."},{"type":"text","text":"FIRST"}],"usage":{"inputTokens":2862,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30],"surfaceOp":"append"} +{"type":"assistant/message","seq":31,"time":1783352236043,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with only the single word \"FIRST\" and then stop."},{"type":"text","text":"FIRST"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2862,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30],"surfaceOp":"append"} {"type":"step/end","seq":32,"time":1783352236043,"data":{"turn":1,"step":1}} {"type":"hook/invoked","seq":33,"time":1783352236043,"data":{"turn":1,"point":"Stop","dialect":"codex","handlerId":"codex:Stop:1"}} {"type":"hook/result","seq":34,"time":1783352236059,"data":{"turn":1,"point":"Stop","handlerId":"codex:Stop:1","decision":"block","exitCode":2,"stderrSummary":"Also reply with the single word SECOND, then stop.","durationMs":14.77945499999987}} @@ -60,7 +60,7 @@ {"type":"assistant/chunk","seq":58,"time":1783352236876,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"SECOND"}}}} {"type":"assistant/chunk","seq":59,"time":1783352236876,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":73,"outputTokens":19,"cacheReadTokens":2816,"reasoningTokens":16}}}} {"type":"assistant/chunk","seq":60,"time":1783352236877,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":61,"time":1783352236877,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user is asking me to reply with the single word SECOND, then stop."},{"type":"text","text":"SECOND"}],"usage":{"inputTokens":73,"outputTokens":19,"cacheReadTokens":2816,"reasoningTokens":16}},"sourceEventSeqs":[37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} +{"type":"assistant/message","seq":61,"time":1783352236877,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user is asking me to reply with the single word SECOND, then stop."},{"type":"text","text":"SECOND"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":73,"outputTokens":19,"cacheReadTokens":2816,"reasoningTokens":16}},"sourceEventSeqs":[37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} {"type":"step/end","seq":62,"time":1783352236877,"data":{"turn":1,"step":2}} {"type":"hook/invoked","seq":63,"time":1783352236877,"data":{"turn":1,"point":"Stop","dialect":"codex","handlerId":"codex:Stop:2"}} {"type":"hook/result","seq":64,"time":1783352236908,"data":{"turn":1,"point":"Stop","handlerId":"codex:Stop:2","decision":"pass","exitCode":0,"durationMs":30.947317000000112}} diff --git a/examples/acp-agent/tests/snapshots/multi-turn/session.jsonl b/examples/acp-agent/tests/snapshots/multi-turn/session.jsonl index 3b8c470ded..cd32072eaa 100644 --- a/examples/acp-agent/tests/snapshots/multi-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/multi-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352113765,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352113765,"data":{"content":[{"type":"text","text":"Reply with exactly the word: ONE. No tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352113767,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352113768,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352113768,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352114428,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352114428,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352114542,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -28,7 +28,7 @@ {"type":"assistant/chunk","seq":26,"time":1783352114687,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ONE"}}}} {"type":"assistant/chunk","seq":27,"time":1783352114687,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2864,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":18}}}} {"type":"assistant/chunk","seq":28,"time":1783352114687,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":29,"time":1783352114690,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ONE\" and use no tools."},{"type":"text","text":"ONE"}],"usage":{"inputTokens":2864,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28],"surfaceOp":"append"} +{"type":"assistant/message","seq":29,"time":1783352114690,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ONE\" and use no tools."},{"type":"text","text":"ONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2864,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28],"surfaceOp":"append"} {"type":"step/end","seq":30,"time":1783352114690,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":31,"time":1783352114690,"data":{"turn":1,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":32,"time":1783352114699,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} @@ -60,6 +60,6 @@ {"type":"assistant/chunk","seq":58,"time":1783352115610,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"TWO"}}}} {"type":"assistant/chunk","seq":59,"time":1783352115610,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":64,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}}}} {"type":"assistant/chunk","seq":60,"time":1783352115610,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":61,"time":1783352115611,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"TWO\" and no tools."},{"type":"text","text":"TWO"}],"usage":{"inputTokens":64,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} +{"type":"assistant/message","seq":61,"time":1783352115611,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"TWO\" and no tools."},{"type":"text","text":"TWO"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":64,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} {"type":"step/end","seq":62,"time":1783352115611,"data":{"turn":2,"step":1}} {"type":"turn/end","seq":63,"time":1783352115611,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl b/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl index 7e50e71b3b..20d18973d9 100644 --- a/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl +++ b/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl @@ -2,13 +2,13 @@ {"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Write the todo list 'watch the kettle boil' five times in a row without changing it, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_1","name":"todo_write","argumentsDelta":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}} {"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_1","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}}} {"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_1","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_1","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} {"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"call_1","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}} {"type":"todo/write","seq":11,"time":0,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}} {"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_1","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"} @@ -19,7 +19,7 @@ {"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_2","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}}} {"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_2","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"} +{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_2","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"} {"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"call_2","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}} {"type":"todo/write","seq":22,"time":0,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}} {"type":"tool/result","seq":23,"time":0,"data":{"turn":1,"step":2,"callId":"call_2","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"} @@ -30,7 +30,7 @@ {"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_3","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}}} {"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":30,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":31,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"call_3","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[26,27,28,29,30],"surfaceOp":"append"} +{"type":"assistant/message","seq":31,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"call_3","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[26,27,28,29,30],"surfaceOp":"append"} {"type":"tool/call","seq":32,"time":0,"data":{"turn":1,"step":3,"callId":"call_3","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}} {"type":"todo/write","seq":33,"time":0,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}} {"type":"tool/result","seq":34,"time":0,"data":{"turn":1,"step":3,"callId":"call_3","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[32],"surfaceOp":"append"} @@ -42,7 +42,7 @@ {"type":"assistant/chunk","seq":40,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_4","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}}} {"type":"assistant/chunk","seq":41,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":42,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":43,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"call_4","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[38,39,40,41,42],"surfaceOp":"append"} +{"type":"assistant/message","seq":43,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"call_4","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[38,39,40,41,42],"surfaceOp":"append"} {"type":"tool/call","seq":44,"time":0,"data":{"turn":1,"step":4,"callId":"call_4","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}} {"type":"todo/write","seq":45,"time":0,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}} {"type":"tool/result","seq":46,"time":0,"data":{"turn":1,"step":4,"callId":"call_4","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[44],"surfaceOp":"append"} @@ -53,7 +53,7 @@ {"type":"assistant/chunk","seq":51,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_5","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}}} {"type":"assistant/chunk","seq":52,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":53,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":54,"time":0,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"call_5","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[49,50,51,52,53],"surfaceOp":"append"} +{"type":"assistant/message","seq":54,"time":0,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"call_5","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[49,50,51,52,53],"surfaceOp":"append"} {"type":"tool/call","seq":55,"time":0,"data":{"turn":1,"step":5,"callId":"call_5","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}} {"type":"todo/write","seq":56,"time":0,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}} {"type":"tool/result","seq":57,"time":0,"data":{"turn":1,"step":5,"callId":"call_5","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[55],"surfaceOp":"append"} @@ -65,6 +65,6 @@ {"type":"assistant/chunk","seq":63,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE."}}}} {"type":"assistant/chunk","seq":64,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":3}}}} {"type":"assistant/chunk","seq":65,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":66,"time":0,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"DONE."}],"usage":{"inputTokens":10,"outputTokens":3}},"sourceEventSeqs":[61,62,63,64,65],"surfaceOp":"append"} +{"type":"assistant/message","seq":66,"time":0,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"DONE."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":3}},"sourceEventSeqs":[61,62,63,64,65],"surfaceOp":"append"} {"type":"step/end","seq":67,"time":0,"data":{"turn":1,"step":6}} {"type":"turn/end","seq":68,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 645671709e..9b5bdfa503 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} @@ -11,7 +11,7 @@ {"type":"assistant/chunk","seq":9,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}}}} {"type":"assistant/chunk","seq":10,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}}}} {"type":"assistant/chunk","seq":11,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":12,"time":1783654655609,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"Load the requested skill."},{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}],"usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}},"sourceEventSeqs":[4,5,6,7,8,9,10,11],"surfaceOp":"append"} +{"type":"assistant/message","seq":12,"time":1783654655609,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"Load the requested skill."},{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}},"sourceEventSeqs":[4,5,6,7,8,9,10,11],"surfaceOp":"append"} {"type":"tool/call","seq":13,"time":1783654655609,"data":{"turn":1,"step":1,"callId":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}} {"type":"tool/result","seq":14,"time":1783654655610,"data":{"turn":1,"step":1,"callId":"call_skill_load","content":[{"type":"text","text":"\n\nBase directory for this skill: /var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-DhYwNW/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n\n\n\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n\n"}],"isError":false},"sourceEventSeqs":[13],"surfaceOp":"append"} {"type":"step/end","seq":15,"time":1783654655610,"data":{"turn":1,"step":1}} @@ -24,6 +24,6 @@ {"type":"assistant/chunk","seq":22,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":23,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":180,"outputTokens":10,"cacheReadTokens":0,"reasoningTokens":4}}}} {"type":"assistant/chunk","seq":24,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":25,"time":1783654655611,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The skill is loaded."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":180,"outputTokens":10,"cacheReadTokens":0,"reasoningTokens":4}},"sourceEventSeqs":[17,18,19,20,21,22,23,24],"surfaceOp":"append"} +{"type":"assistant/message","seq":25,"time":1783654655611,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The skill is loaded."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":180,"outputTokens":10,"cacheReadTokens":0,"reasoningTokens":4}},"sourceEventSeqs":[17,18,19,20,21,22,23,24],"surfaceOp":"append"} {"type":"step/end","seq":26,"time":1783654655611,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":27,"time":1783654655611,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl index 409fa1428d..4ecb61b60f 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352134837,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352134838,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is MARMALADE. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352134840,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352134840,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352134840,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352135465,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352135465,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352135621,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -33,13 +33,13 @@ {"type":"assistant/chunk","seq":31,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} {"type":"assistant/chunk","seq":32,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}}}} {"type":"assistant/chunk","seq":33,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":34,"time":1783352135773,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember the codeword \"MARMALADE\" and reply with just \"OK\"."},{"type":"text","text":"OK"}],"usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"surfaceOp":"append"} +{"type":"assistant/message","seq":34,"time":1783352135773,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember the codeword \"MARMALADE\" and reply with just \"OK\"."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"surfaceOp":"append"} {"type":"step/end","seq":35,"time":1783352135773,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":36,"time":1783352135773,"data":{"turn":1,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":37,"time":1783352137162,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":38,"time":1783352137163,"data":{"content":[{"type":"text","text":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":39,"time":1783352137163,"data":{"turn":2,"step":1}} -{"type":"request/header","seq":40,"time":1783352137163,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}} +{"type":"request/header","seq":40,"time":1783352137163,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}} {"type":"assistant/chunk","seq":41,"time":1783352137783,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":42,"time":1783352137783,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":43,"time":1783352137961,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -84,6 +84,6 @@ {"type":"assistant/chunk","seq":82,"time":1783352138307,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"MARMALADE"}}}} {"type":"assistant/chunk","seq":83,"time":1783352138307,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":97,"outputTokens":39,"cacheReadTokens":2816,"reasoningTokens":34}}}} {"type":"assistant/chunk","seq":84,"time":1783352138307,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":85,"time":1783352138308,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user asked me to remember the project codeword \"MARMALADE\" and now they're asking what it is. I should just reply with that word."},{"type":"text","text":"MARMALADE"}],"usage":{"inputTokens":97,"outputTokens":39,"cacheReadTokens":2816,"reasoningTokens":34}},"sourceEventSeqs":[41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84],"surfaceOp":"append"} +{"type":"assistant/message","seq":85,"time":1783352138308,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user asked me to remember the project codeword \"MARMALADE\" and now they're asking what it is. I should just reply with that word."},{"type":"text","text":"MARMALADE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":97,"outputTokens":39,"cacheReadTokens":2816,"reasoningTokens":34}},"sourceEventSeqs":[41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84],"surfaceOp":"append"} {"type":"step/end","seq":86,"time":1783352138308,"data":{"turn":2,"step":1}} {"type":"turn/end","seq":87,"time":1783352138308,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl index d61503ffbb..64da6e60e5 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352134837,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352134838,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is MARMALADE. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352134840,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352134840,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352134840,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352135465,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352135465,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352135621,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -33,7 +33,7 @@ {"type":"assistant/chunk","seq":31,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} {"type":"assistant/chunk","seq":32,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}}}} {"type":"assistant/chunk","seq":33,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":34,"time":1783352135773,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember the codeword \"MARMALADE\" and reply with just \"OK\"."},{"type":"text","text":"OK"}],"usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"surfaceOp":"append"} +{"type":"assistant/message","seq":34,"time":1783352135773,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember the codeword \"MARMALADE\" and reply with just \"OK\"."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"surfaceOp":"append"} {"type":"step/end","seq":35,"time":1783352135773,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":36,"time":1783352135773,"data":{"turn":1,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":37,"time":1783352135780,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} @@ -149,7 +149,7 @@ {"type":"assistant/chunk","seq":147,"time":1783352137158,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":148,"time":1783352137158,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":158,"outputTokens":147,"cacheReadTokens":2816,"reasoningTokens":59}}}} {"type":"assistant/chunk","seq":149,"time":1783352137159,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":150,"time":1783352137159,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use subagent_fork to delegate a question to a child agent. The child agent inherits this conversation and should be able to answer: the project codeword is MARMALADE. After the subagent returns, I should reply with PARENT_DONE."},{"type":"tool-call","id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}],"usage":{"inputTokens":158,"outputTokens":147,"cacheReadTokens":2816,"reasoningTokens":59}},"sourceEventSeqs":[40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"surfaceOp":"append"} +{"type":"assistant/message","seq":150,"time":1783352137159,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use subagent_fork to delegate a question to a child agent. The child agent inherits this conversation and should be able to answer: the project codeword is MARMALADE. After the subagent returns, I should reply with PARENT_DONE."},{"type":"tool-call","id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":158,"outputTokens":147,"cacheReadTokens":2816,"reasoningTokens":59}},"sourceEventSeqs":[40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"surfaceOp":"append"} {"type":"tool/call","seq":151,"time":1783352137159,"data":{"turn":2,"step":1,"callId":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}} {"type":"tool/result","seq":152,"time":1783352138315,"data":{"turn":2,"step":1,"callId":"call_00_sAtKUseRzHRBvL4CF7XF1334","content":[{"type":"text","text":"MARMALADE"}],"isError":false},"sourceEventSeqs":[151],"surfaceOp":"append"} {"type":"step/end","seq":153,"time":1783352138316,"data":{"turn":2,"step":1}} @@ -189,6 +189,6 @@ {"type":"assistant/chunk","seq":187,"time":1783352139274,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} {"type":"assistant/chunk","seq":188,"time":1783352139274,"data":{"turn":2,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":65,"outputTokens":30,"cacheReadTokens":3072,"reasoningTokens":25}}}} {"type":"assistant/chunk","seq":189,"time":1783352139274,"data":{"turn":2,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":190,"time":1783352139274,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"The forked child agent correctly returned \"MARMALADE\". Now I need to reply with \"PARENT_DONE\"."},{"type":"text","text":"PARENT_DONE"}],"usage":{"inputTokens":65,"outputTokens":30,"cacheReadTokens":3072,"reasoningTokens":25}},"sourceEventSeqs":[155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189],"surfaceOp":"append"} +{"type":"assistant/message","seq":190,"time":1783352139274,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"The forked child agent correctly returned \"MARMALADE\". Now I need to reply with \"PARENT_DONE\"."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":65,"outputTokens":30,"cacheReadTokens":3072,"reasoningTokens":25}},"sourceEventSeqs":[155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189],"surfaceOp":"append"} {"type":"step/end","seq":191,"time":1783352139274,"data":{"turn":2,"step":2}} {"type":"turn/end","seq":192,"time":1783352139274,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl index 85a6405535..c99a5681e2 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352145224,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352145224,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352145224,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352145224,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352145224,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352145820,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352145821,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352145985,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -31,6 +31,6 @@ {"type":"assistant/chunk","seq":29,"time":1783352146129,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ALPHA"}}}} {"type":"assistant/chunk","seq":30,"time":1783352146129,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":48,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}}}} {"type":"assistant/chunk","seq":31,"time":1783352146129,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":32,"time":1783352146130,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user asked me to reply with exactly the word \"ALPHA\" and nothing else."},{"type":"text","text":"ALPHA"}],"usage":{"inputTokens":48,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} +{"type":"assistant/message","seq":32,"time":1783352146130,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user asked me to reply with exactly the word \"ALPHA\" and nothing else."},{"type":"text","text":"ALPHA"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":48,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} {"type":"step/end","seq":33,"time":1783352146130,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":34,"time":1783352146130,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl index b9b6b48a9a..adfcb6f60e 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352142834,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352142834,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is SAFFRON. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352142835,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352142836,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352142836,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352143493,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352143494,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352143621,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -27,13 +27,13 @@ {"type":"assistant/chunk","seq":25,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} {"type":"assistant/chunk","seq":26,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":27,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":28,"time":1783352143771,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember a codeword and just reply with \"OK\"."},{"type":"text","text":"OK"}],"usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27],"surfaceOp":"append"} +{"type":"assistant/message","seq":28,"time":1783352143771,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember a codeword and just reply with \"OK\"."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27],"surfaceOp":"append"} {"type":"step/end","seq":29,"time":1783352143771,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":30,"time":1783352143771,"data":{"turn":1,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":31,"time":1783352147508,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":32,"time":1783352147509,"data":{"content":[{"type":"text","text":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":33,"time":1783352147509,"data":{"turn":2,"step":1}} -{"type":"request/header","seq":34,"time":1783352147509,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}} +{"type":"request/header","seq":34,"time":1783352147509,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}} {"type":"assistant/chunk","seq":35,"time":1783352147925,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":36,"time":1783352147925,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":37,"time":1783352148019,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -74,6 +74,6 @@ {"type":"assistant/chunk","seq":72,"time":1783352148345,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"SAFFRON"}}}} {"type":"assistant/chunk","seq":73,"time":1783352148345,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":95,"outputTokens":35,"cacheReadTokens":2816,"reasoningTokens":31}}}} {"type":"assistant/chunk","seq":74,"time":1783352148345,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":75,"time":1783352148345,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user is asking me to recall the project codeword that was mentioned earlier in the conversation. I was told to remember it: SAFFRON."},{"type":"text","text":"SAFFRON"}],"usage":{"inputTokens":95,"outputTokens":35,"cacheReadTokens":2816,"reasoningTokens":31}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74],"surfaceOp":"append"} +{"type":"assistant/message","seq":75,"time":1783352148345,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user is asking me to recall the project codeword that was mentioned earlier in the conversation. I was told to remember it: SAFFRON."},{"type":"text","text":"SAFFRON"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":95,"outputTokens":35,"cacheReadTokens":2816,"reasoningTokens":31}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74],"surfaceOp":"append"} {"type":"step/end","seq":76,"time":1783352148345,"data":{"turn":2,"step":1}} {"type":"turn/end","seq":77,"time":1783352148345,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl index ff5cfda975..1ea4f541e1 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352142834,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352142834,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is SAFFRON. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352142835,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352142836,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352142836,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352143493,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352143494,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352143621,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -27,7 +27,7 @@ {"type":"assistant/chunk","seq":25,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} {"type":"assistant/chunk","seq":26,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":27,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":28,"time":1783352143771,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember a codeword and just reply with \"OK\"."},{"type":"text","text":"OK"}],"usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27],"surfaceOp":"append"} +{"type":"assistant/message","seq":28,"time":1783352143771,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember a codeword and just reply with \"OK\"."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27],"surfaceOp":"append"} {"type":"step/end","seq":29,"time":1783352143771,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":30,"time":1783352143771,"data":{"turn":1,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":31,"time":1783352143779,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} @@ -108,7 +108,7 @@ {"type":"assistant/chunk","seq":106,"time":1783352145221,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","arguments":"{\"description\": \"Reply ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":107,"time":1783352145221,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":185,"outputTokens":110,"cacheReadTokens":2816,"reasoningTokens":35}}}} {"type":"assistant/chunk","seq":108,"time":1783352145221,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":109,"time":1783352145221,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"Let me do these two delegations one at a time as requested.\n\nFirst, I'll use the subagent tool (fresh child) to reply with \"ALPHA\"."},{"type":"tool-call","id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","arguments":"{\"description\": \"Reply ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}],"usage":{"inputTokens":185,"outputTokens":110,"cacheReadTokens":2816,"reasoningTokens":35}},"sourceEventSeqs":[34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} +{"type":"assistant/message","seq":109,"time":1783352145221,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"Let me do these two delegations one at a time as requested.\n\nFirst, I'll use the subagent tool (fresh child) to reply with \"ALPHA\"."},{"type":"tool-call","id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","arguments":"{\"description\": \"Reply ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":185,"outputTokens":110,"cacheReadTokens":2816,"reasoningTokens":35}},"sourceEventSeqs":[34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} {"type":"tool/call","seq":110,"time":1783352145222,"data":{"turn":2,"step":1,"callId":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","arguments":"{\"description\": \"Reply ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}} {"type":"tool/result","seq":111,"time":1783352146133,"data":{"turn":2,"step":1,"callId":"call_00_YvHr2bGomk5HhpgDTvE81896","content":[{"type":"text","text":"ALPHA"}],"isError":false},"sourceEventSeqs":[110],"surfaceOp":"append"} {"type":"step/end","seq":112,"time":1783352146134,"data":{"turn":2,"step":1}} @@ -204,7 +204,7 @@ {"type":"assistant/chunk","seq":202,"time":1783352147502,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":203,"time":1783352147502,"data":{"turn":2,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":54,"outputTokens":128,"cacheReadTokens":3072,"reasoningTokens":40}}}} {"type":"assistant/chunk","seq":204,"time":1783352147502,"data":{"turn":2,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":205,"time":1783352147503,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"The first subagent returned \"ALPHA\". Now I need to use the subagent_fork tool (forked child that inherits this conversation) to ask about the project codeword."},{"type":"tool-call","id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}],"usage":{"inputTokens":54,"outputTokens":128,"cacheReadTokens":3072,"reasoningTokens":40}},"sourceEventSeqs":[114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204],"surfaceOp":"append"} +{"type":"assistant/message","seq":205,"time":1783352147503,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"The first subagent returned \"ALPHA\". Now I need to use the subagent_fork tool (forked child that inherits this conversation) to ask about the project codeword."},{"type":"tool-call","id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":54,"outputTokens":128,"cacheReadTokens":3072,"reasoningTokens":40}},"sourceEventSeqs":[114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204],"surfaceOp":"append"} {"type":"tool/call","seq":206,"time":1783352147503,"data":{"turn":2,"step":2,"callId":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}} {"type":"tool/result","seq":207,"time":1783352148348,"data":{"turn":2,"step":2,"callId":"call_00_JSr5rhREq23wSmwSkCP77184","content":[{"type":"text","text":"SAFFRON"}],"isError":false},"sourceEventSeqs":[206],"surfaceOp":"append"} {"type":"step/end","seq":208,"time":1783352148348,"data":{"turn":2,"step":2}} @@ -283,6 +283,6 @@ {"type":"assistant/chunk","seq":281,"time":1783352149821,"data":{"turn":2,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} {"type":"assistant/chunk","seq":282,"time":1783352149821,"data":{"turn":2,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":69,"outputTokens":69,"cacheReadTokens":3200,"reasoningTokens":64}}}} {"type":"assistant/chunk","seq":283,"time":1783352149821,"data":{"turn":2,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":284,"time":1783352149822,"data":{"turn":2,"step":3,"content":[{"type":"reasoning","text":"Both subagents returned:\n1. First (fresh child): \"ALPHA\"\n2. Second (forked child): \"SAFFRON\" - correctly inherited the conversation context where I was asked to remember the codeword \"SAFFRON\".\n\nNow I reply with \"PARENT_DONE\" as instructed."},{"type":"text","text":"PARENT_DONE"}],"usage":{"inputTokens":69,"outputTokens":69,"cacheReadTokens":3200,"reasoningTokens":64}},"sourceEventSeqs":[210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280,281,282,283],"surfaceOp":"append"} +{"type":"assistant/message","seq":284,"time":1783352149822,"data":{"turn":2,"step":3,"content":[{"type":"reasoning","text":"Both subagents returned:\n1. First (fresh child): \"ALPHA\"\n2. Second (forked child): \"SAFFRON\" - correctly inherited the conversation context where I was asked to remember the codeword \"SAFFRON\".\n\nNow I reply with \"PARENT_DONE\" as instructed."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":69,"outputTokens":69,"cacheReadTokens":3200,"reasoningTokens":64}},"sourceEventSeqs":[210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280,281,282,283],"surfaceOp":"append"} {"type":"step/end","seq":285,"time":1783352149822,"data":{"turn":2,"step":3}} {"type":"turn/end","seq":286,"time":1783352149822,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl index e046c226d0..86c481c5ff 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352127670,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352127670,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352127671,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352127671,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352127671,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352128125,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352128125,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352128240,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -31,6 +31,6 @@ {"type":"assistant/chunk","seq":29,"time":1783352128365,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ALPHA"}}}} {"type":"assistant/chunk","seq":30,"time":1783352128365,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":49,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}}}} {"type":"assistant/chunk","seq":31,"time":1783352128365,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":32,"time":1783352128365,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ALPHA\" and nothing else."},{"type":"text","text":"ALPHA"}],"usage":{"inputTokens":49,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} +{"type":"assistant/message","seq":32,"time":1783352128365,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ALPHA\" and nothing else."},{"type":"text","text":"ALPHA"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":49,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} {"type":"step/end","seq":33,"time":1783352128365,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":34,"time":1783352128366,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl index e113159d39..483e687a14 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352129662,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352129662,"data":{"content":[{"type":"text","text":"Reply with exactly the word BETA and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352129663,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352129663,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352129663,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352130236,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352130236,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352130375,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -29,6 +29,6 @@ {"type":"assistant/chunk","seq":27,"time":1783352130527,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"BETA"}}}} {"type":"assistant/chunk","seq":28,"time":1783352130527,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}}}} {"type":"assistant/chunk","seq":29,"time":1783352130527,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":30,"time":1783352130528,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"BETA\" and nothing else."},{"type":"text","text":"BETA"}],"usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} +{"type":"assistant/message","seq":30,"time":1783352130528,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"BETA\" and nothing else."},{"type":"text","text":"BETA"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} {"type":"step/end","seq":31,"time":1783352130528,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":32,"time":1783352130528,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl index c7a079391f..a8093fba04 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352126251,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352126251,"data":{"content":[{"type":"text","text":"Use the subagent tool TWICE, once at a time, to delegate two subtasks to child agents. First subtask: 'Reply with exactly the word ALPHA and nothing else.' Second subtask (after the first returns): 'Reply with exactly the word BETA and nothing else.' After both subagents return, reply with the single word PARENT_DONE and stop. Do not use the bash tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352126252,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352126253,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352126253,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352126729,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352126729,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352126848,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -92,7 +92,7 @@ {"type":"assistant/chunk","seq":90,"time":1783352127665,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":91,"time":1783352127665,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2938,"outputTokens":124,"cacheReadTokens":0,"reasoningTokens":49}}}} {"type":"assistant/chunk","seq":92,"time":1783352127665,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":93,"time":1783352127668,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the subagent tool twice, sequentially (one at a time). First subagent should reply with \"ALPHA\", second with \"BETA\". After both return, I reply with \"PARENT_DONE\"."},{"type":"tool-call","id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}],"usage":{"inputTokens":2938,"outputTokens":124,"cacheReadTokens":0,"reasoningTokens":49}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92],"surfaceOp":"append"} +{"type":"assistant/message","seq":93,"time":1783352127668,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the subagent tool twice, sequentially (one at a time). First subagent should reply with \"ALPHA\", second with \"BETA\". After both return, I reply with \"PARENT_DONE\"."},{"type":"tool-call","id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2938,"outputTokens":124,"cacheReadTokens":0,"reasoningTokens":49}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92],"surfaceOp":"append"} {"type":"tool/call","seq":94,"time":1783352127668,"data":{"turn":1,"step":1,"callId":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}} {"type":"tool/result","seq":95,"time":1783352128371,"data":{"turn":1,"step":1,"callId":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","content":[{"type":"text","text":"ALPHA"}],"isError":false},"sourceEventSeqs":[94],"surfaceOp":"append"} {"type":"step/end","seq":96,"time":1783352128371,"data":{"turn":1,"step":1}} @@ -158,7 +158,7 @@ {"type":"assistant/chunk","seq":156,"time":1783352129661,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":157,"time":1783352129661,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":133,"outputTokens":96,"cacheReadTokens":2944,"reasoningTokens":23}}}} {"type":"assistant/chunk","seq":158,"time":1783352129661,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":159,"time":1783352129661,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"First subagent returned \"ALPHA\". Now I'll call the second subagent to return \"BETA\"."},{"type":"tool-call","id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\"}"}],"usage":{"inputTokens":133,"outputTokens":96,"cacheReadTokens":2944,"reasoningTokens":23}},"sourceEventSeqs":[98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158],"surfaceOp":"append"} +{"type":"assistant/message","seq":159,"time":1783352129661,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"First subagent returned \"ALPHA\". Now I'll call the second subagent to return \"BETA\"."},{"type":"tool-call","id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":133,"outputTokens":96,"cacheReadTokens":2944,"reasoningTokens":23}},"sourceEventSeqs":[98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158],"surfaceOp":"append"} {"type":"tool/call","seq":160,"time":1783352129661,"data":{"turn":1,"step":2,"callId":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\"}"}} {"type":"tool/result","seq":161,"time":1783352130531,"data":{"turn":1,"step":2,"callId":"call_00_FudNKuJ0fchSptGy3Scw1411","content":[{"type":"text","text":"BETA"}],"isError":false},"sourceEventSeqs":[160],"surfaceOp":"append"} {"type":"step/end","seq":162,"time":1783352130531,"data":{"turn":1,"step":2}} @@ -203,6 +203,6 @@ {"type":"assistant/chunk","seq":201,"time":1783352131242,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} {"type":"assistant/chunk","seq":202,"time":1783352131242,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":115,"outputTokens":35,"cacheReadTokens":3072,"reasoningTokens":30}}}} {"type":"assistant/chunk","seq":203,"time":1783352131242,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":204,"time":1783352131243,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"Both subagents have returned: first with \"ALPHA\", second with \"BETA\". Now I should reply with \"PARENT_DONE\"."},{"type":"text","text":"PARENT_DONE"}],"usage":{"inputTokens":115,"outputTokens":35,"cacheReadTokens":3072,"reasoningTokens":30}},"sourceEventSeqs":[164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203],"surfaceOp":"append"} +{"type":"assistant/message","seq":204,"time":1783352131243,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"Both subagents have returned: first with \"ALPHA\", second with \"BETA\". Now I should reply with \"PARENT_DONE\"."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":115,"outputTokens":35,"cacheReadTokens":3072,"reasoningTokens":30}},"sourceEventSeqs":[164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203],"surfaceOp":"append"} {"type":"step/end","seq":205,"time":1783352131243,"data":{"turn":1,"step":3}} {"type":"turn/end","seq":206,"time":1783352131243,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl index fedd7cbfb4..8dd26c4e70 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352120856,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352120856,"data":{"content":[{"type":"text","text":"Reply with exactly the word CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352120856,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352120856,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352120856,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352121437,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352121438,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352121635,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -29,6 +29,6 @@ {"type":"assistant/chunk","seq":27,"time":1783352121777,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"CHILD_OK"}}}} {"type":"assistant/chunk","seq":28,"time":1783352121777,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":29,"time":1783352121777,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":30,"time":1783352121777,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word CHILD_OK and nothing else."},{"type":"text","text":"CHILD_OK"}],"usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} +{"type":"assistant/message","seq":30,"time":1783352121777,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word CHILD_OK and nothing else."},{"type":"text","text":"CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} {"type":"step/end","seq":31,"time":1783352121778,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":32,"time":1783352121778,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl index b550a8cb19..6a87cfabb5 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352119273,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352119274,"data":{"content":[{"type":"text","text":"Use the subagent tool exactly once to delegate this subtask to a child agent: 'Reply with exactly the word CHILD_OK and nothing else.' After the subagent returns, reply with the single word PARENT_DONE and stop. Do not use the bash tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352119275,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352119281,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352119281,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352119925,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352119925,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352120053,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -110,7 +110,7 @@ {"type":"assistant/chunk","seq":108,"time":1783352120851,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","arguments":"{\"description\": \"Reply with CHILD_OK\", \"prompt\": \"Reply with exactly the word CHILD_OK and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":109,"time":1783352120852,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2907,"outputTokens":142,"cacheReadTokens":0,"reasoningTokens":67}}}} {"type":"assistant/chunk","seq":110,"time":1783352120852,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":111,"time":1783352120854,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Use the subagent tool exactly once to delegate the task: \"Reply with exactly the word CHILD_OK and nothing else.\"\n2. After the subagent returns, reply with the single word PARENT_DONE and stop.\n3. Do not use the bash tool.\n\nLet me do this."},{"type":"tool-call","id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","arguments":"{\"description\": \"Reply with CHILD_OK\", \"prompt\": \"Reply with exactly the word CHILD_OK and nothing else.\"}"}],"usage":{"inputTokens":2907,"outputTokens":142,"cacheReadTokens":0,"reasoningTokens":67}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110],"surfaceOp":"append"} +{"type":"assistant/message","seq":111,"time":1783352120854,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Use the subagent tool exactly once to delegate the task: \"Reply with exactly the word CHILD_OK and nothing else.\"\n2. After the subagent returns, reply with the single word PARENT_DONE and stop.\n3. Do not use the bash tool.\n\nLet me do this."},{"type":"tool-call","id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","arguments":"{\"description\": \"Reply with CHILD_OK\", \"prompt\": \"Reply with exactly the word CHILD_OK and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2907,"outputTokens":142,"cacheReadTokens":0,"reasoningTokens":67}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110],"surfaceOp":"append"} {"type":"tool/call","seq":112,"time":1783352120854,"data":{"turn":1,"step":1,"callId":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","arguments":"{\"description\": \"Reply with CHILD_OK\", \"prompt\": \"Reply with exactly the word CHILD_OK and nothing else.\"}"}} {"type":"tool/result","seq":113,"time":1783352121784,"data":{"turn":1,"step":1,"callId":"call_00_gVbLWC12Qu8JheZpVRRz8749","content":[{"type":"text","text":"CHILD_OK"}],"isError":false},"sourceEventSeqs":[112],"surfaceOp":"append"} {"type":"step/end","seq":114,"time":1783352121784,"data":{"turn":1,"step":1}} @@ -155,6 +155,6 @@ {"type":"assistant/chunk","seq":153,"time":1783352122731,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} {"type":"assistant/chunk","seq":154,"time":1783352122732,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":120,"outputTokens":35,"cacheReadTokens":2944,"reasoningTokens":30}}}} {"type":"assistant/chunk","seq":155,"time":1783352122732,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":156,"time":1783352122732,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The subagent returned \"CHILD_OK\" as expected. Now I need to reply with the single word \"PARENT_DONE\" and stop."},{"type":"text","text":"PARENT_DONE"}],"usage":{"inputTokens":120,"outputTokens":35,"cacheReadTokens":2944,"reasoningTokens":30}},"sourceEventSeqs":[116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155],"surfaceOp":"append"} +{"type":"assistant/message","seq":156,"time":1783352122732,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The subagent returned \"CHILD_OK\" as expected. Now I need to reply with the single word \"PARENT_DONE\" and stop."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":120,"outputTokens":35,"cacheReadTokens":2944,"reasoningTokens":30}},"sourceEventSeqs":[116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155],"surfaceOp":"append"} {"type":"step/end","seq":157,"time":1783352122732,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":158,"time":1783352122732,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index 324ef8d4eb..b8afff45de 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -31,6 +31,6 @@ {"type":"assistant/chunk","seq":29,"time":1783600631009,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PONG"}}}} {"type":"assistant/chunk","seq":30,"time":1783600631009,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3091,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":20}}}} {"type":"assistant/chunk","seq":31,"time":1783600631009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":32,"time":1783600631011,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"PONG\" and not use any tools."},{"type":"text","text":"PONG"}],"usage":{"inputTokens":3091,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":20}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} +{"type":"assistant/message","seq":32,"time":1783600631011,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"PONG\" and not use any tools."},{"type":"text","text":"PONG"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3091,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":20}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} {"type":"step/end","seq":33,"time":1783600631011,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":34,"time":1783600631011,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/todo-plan/session.jsonl b/examples/acp-agent/tests/snapshots/todo-plan/session.jsonl index 8e93132d30..909afc44cd 100644 --- a/examples/acp-agent/tests/snapshots/todo-plan/session.jsonl +++ b/examples/acp-agent/tests/snapshots/todo-plan/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352057655,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352057655,"data":{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352057657,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352057657,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352057657,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352058320,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352058320,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352058426,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -94,7 +94,7 @@ {"type":"assistant/chunk","seq":92,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}}}} {"type":"assistant/chunk","seq":93,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2913,"outputTokens":121,"cacheReadTokens":0,"reasoningTokens":31}}}} {"type":"assistant/chunk","seq":94,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":95,"time":1783352059099,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the todo_write tool to record a plan with exactly three todos in the specified statuses, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}],"usage":{"inputTokens":2913,"outputTokens":121,"cacheReadTokens":0,"reasoningTokens":31}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94],"surfaceOp":"append"} +{"type":"assistant/message","seq":95,"time":1783352059099,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the todo_write tool to record a plan with exactly three todos in the specified statuses, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2913,"outputTokens":121,"cacheReadTokens":0,"reasoningTokens":31}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94],"surfaceOp":"append"} {"type":"tool/call","seq":96,"time":1783352059099,"data":{"turn":1,"step":1,"callId":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}} {"type":"todo/write","seq":97,"time":1783352059100,"data":{"todos":[{"content":"read the code","status":"in_progress"},{"content":"write the fix","status":"pending"},{"content":"run the tests","status":"pending"}]}} {"type":"tool/result","seq":98,"time":1783352059101,"data":{"turn":1,"step":1,"callId":"call_00_fjAnBThbDjxepBtp3hDt3264","content":[{"type":"text","text":"Updated todo list: 2 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[96],"surfaceOp":"append"} @@ -129,6 +129,6 @@ {"type":"assistant/chunk","seq":127,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":128,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":237,"outputTokens":24,"cacheReadTokens":2816,"reasoningTokens":21}}}} {"type":"assistant/chunk","seq":129,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":130,"time":1783352059981,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The todos have been written successfully. Now I just need to reply with the single word \"DONE\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":237,"outputTokens":24,"cacheReadTokens":2816,"reasoningTokens":21}},"sourceEventSeqs":[101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} +{"type":"assistant/message","seq":130,"time":1783352059981,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The todos have been written successfully. Now I just need to reply with the single word \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":237,"outputTokens":24,"cacheReadTokens":2816,"reasoningTokens":21}},"sourceEventSeqs":[101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} {"type":"step/end","seq":131,"time":1783352059981,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":132,"time":1783352059981,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl b/examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl index 20a11443a7..f631c9bf54 100644 --- a/examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352044771,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352044771,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo SNAPSHOT_OK. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352044773,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352044773,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352044773,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352045294,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352045294,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352045396,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -57,7 +57,7 @@ {"type":"assistant/chunk","seq":55,"time":1783352045866,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_Rn2Mz1y8uZN62ukEXiNO2077","name":"bash","arguments":"{\"command\": \"echo SNAPSHOT_OK\", \"description\": \"Run echo SNAPSHOT_OK\"}"}}}} {"type":"assistant/chunk","seq":56,"time":1783352045866,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2879,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":57,"time":1783352045866,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":58,"time":1783352045867,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific bash command and then reply with DONE."},{"type":"tool-call","id":"call_00_Rn2Mz1y8uZN62ukEXiNO2077","name":"bash","arguments":"{\"command\": \"echo SNAPSHOT_OK\", \"description\": \"Run echo SNAPSHOT_OK\"}"}],"usage":{"inputTokens":2879,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"surfaceOp":"append"} +{"type":"assistant/message","seq":58,"time":1783352045867,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific bash command and then reply with DONE."},{"type":"tool-call","id":"call_00_Rn2Mz1y8uZN62ukEXiNO2077","name":"bash","arguments":"{\"command\": \"echo SNAPSHOT_OK\", \"description\": \"Run echo SNAPSHOT_OK\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2879,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"surfaceOp":"append"} {"type":"tool/call","seq":59,"time":1783352045867,"data":{"turn":1,"step":1,"callId":"call_00_Rn2Mz1y8uZN62ukEXiNO2077","name":"bash","arguments":"{\"command\": \"echo SNAPSHOT_OK\", \"description\": \"Run echo SNAPSHOT_OK\"}"}} {"type":"tool/result","seq":60,"time":1783352045879,"data":{"turn":1,"step":1,"callId":"call_00_Rn2Mz1y8uZN62ukEXiNO2077","content":[{"type":"text","text":"SNAPSHOT_OK\n"}],"isError":false},"sourceEventSeqs":[59],"surfaceOp":"append"} {"type":"step/end","seq":61,"time":1783352045880,"data":{"turn":1,"step":1}} @@ -95,6 +95,6 @@ {"type":"assistant/chunk","seq":93,"time":1783352047156,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":94,"time":1783352047156,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":170,"outputTokens":28,"cacheReadTokens":2816,"reasoningTokens":25}}}} {"type":"assistant/chunk","seq":95,"time":1783352047156,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":96,"time":1783352047158,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command executed successfully and printed SNAPSHOT_OK. Now I need to reply with the single word DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":170,"outputTokens":28,"cacheReadTokens":2816,"reasoningTokens":25}},"sourceEventSeqs":[63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95],"surfaceOp":"append"} +{"type":"assistant/message","seq":96,"time":1783352047158,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command executed successfully and printed SNAPSHOT_OK. Now I need to reply with the single word DONE."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":170,"outputTokens":28,"cacheReadTokens":2816,"reasoningTokens":25}},"sourceEventSeqs":[63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95],"surfaceOp":"append"} {"type":"step/end","seq":97,"time":1783352047158,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":98,"time":1783352047158,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl index a8c1d6018b..3d89428bbd 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600636316,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600636316,"data":{"content":[{"type":"text","text":"Reply with exactly the word WF_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600636316,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600636317,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600636317,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600638073,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600638073,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600638173,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -31,6 +31,6 @@ {"type":"assistant/chunk","seq":29,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"WF_CHILD_OK"}}}} {"type":"assistant/chunk","seq":30,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":17,"outputTokens":23,"cacheReadTokens":3072,"reasoningTokens":18}}}} {"type":"assistant/chunk","seq":31,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":32,"time":1783600638281,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly \"WF_CHILD_OK\" and nothing else."},{"type":"text","text":"WF_CHILD_OK"}],"usage":{"inputTokens":17,"outputTokens":23,"cacheReadTokens":3072,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} +{"type":"assistant/message","seq":32,"time":1783600638281,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly \"WF_CHILD_OK\" and nothing else."},{"type":"text","text":"WF_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":17,"outputTokens":23,"cacheReadTokens":3072,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} {"type":"step/end","seq":33,"time":1783600638281,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":34,"time":1783600638281,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl index ab53f20550..3e0ae3da73 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600631838,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600631838,"data":{"content":[{"type":"text","text":"Use the workflow tool exactly once, with args omitted, meta set to { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }, and this EXACT script body (copy it verbatim):\nphase('Run')\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\nreturn { reply }\nAfter the workflow returns, reply with the single word WORKFLOW_DONE and stop. Do not use any other tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600631839,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600631839,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600631839,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600634643,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600634643,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -158,7 +158,7 @@ {"type":"assistant/chunk","seq":156,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}}}} {"type":"assistant/chunk","seq":157,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3174,"outputTokens":191,"cacheReadTokens":0,"reasoningTokens":88}}}} {"type":"assistant/chunk","seq":158,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":159,"time":1783600636247,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the workflow tool exactly once with specific parameters. Let me carefully follow the instructions:\n\n1. args omitted (so I don't include it)\n2. meta = { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }\n3. script = as given verbatim\n4. After it returns, reply with \"WORKFLOW_DONE\"\n\nLet me do exactly that."},{"type":"tool-call","id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}],"usage":{"inputTokens":3174,"outputTokens":191,"cacheReadTokens":0,"reasoningTokens":88}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158],"surfaceOp":"append"} +{"type":"assistant/message","seq":159,"time":1783600636247,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the workflow tool exactly once with specific parameters. Let me carefully follow the instructions:\n\n1. args omitted (so I don't include it)\n2. meta = { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }\n3. script = as given verbatim\n4. After it returns, reply with \"WORKFLOW_DONE\"\n\nLet me do exactly that."},{"type":"tool-call","id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3174,"outputTokens":191,"cacheReadTokens":0,"reasoningTokens":88}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158],"surfaceOp":"append"} {"type":"tool/call","seq":160,"time":1783600636247,"data":{"turn":1,"step":1,"callId":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}} {"type":"tool/result","seq":161,"time":1783600638304,"data":{"turn":1,"step":1,"callId":"call_00_dD2BLuNeJCTh2iiYC1QR3449","content":[{"type":"text","text":"workflow \"snapshot-flow\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WF_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[160],"surfaceOp":"append"} {"type":"step/end","seq":162,"time":1783600638304,"data":{"turn":1,"step":1}} @@ -204,6 +204,6 @@ {"type":"assistant/chunk","seq":202,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"WORKFLOW_DONE"}}}} {"type":"assistant/chunk","seq":203,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":328,"outputTokens":36,"cacheReadTokens":3072,"reasoningTokens":30}}}} {"type":"assistant/chunk","seq":204,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":205,"time":1783600640865,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The workflow returned successfully with the reply \"WF_CHILD_OK\". Now I need to reply with exactly \"WORKFLOW_DONE\" and stop."},{"type":"text","text":"WORKFLOW_DONE"}],"usage":{"inputTokens":328,"outputTokens":36,"cacheReadTokens":3072,"reasoningTokens":30}},"sourceEventSeqs":[164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204],"surfaceOp":"append"} +{"type":"assistant/message","seq":205,"time":1783600640865,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The workflow returned successfully with the reply \"WF_CHILD_OK\". Now I need to reply with exactly \"WORKFLOW_DONE\" and stop."},{"type":"text","text":"WORKFLOW_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":328,"outputTokens":36,"cacheReadTokens":3072,"reasoningTokens":30}},"sourceEventSeqs":[164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204],"surfaceOp":"append"} {"type":"step/end","seq":206,"time":1783600640865,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":207,"time":1783600640865,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl index 9a908f24a3..6b9b03a95e 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352264080,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352264081,"data":{"content":[{"type":"text","text":"A file named greeting.txt in the current directory contains one word. Use the bash tool to append a second line containing the word WORLD to it (so it has two lines), then read the file back with `cat greeting.txt` to confirm, and reply with the single word DONE. Use a single bash call per action."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352264082,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352264083,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352264083,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352264544,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352264544,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352264642,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -77,7 +77,7 @@ {"type":"assistant/chunk","seq":75,"time":1783352265489,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_OjRFB4zvxu6UALDjytZD0978","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}}}} {"type":"assistant/chunk","seq":76,"time":1783352265489,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2918,"outputTokens":101,"cacheReadTokens":0,"reasoningTokens":55}}}} {"type":"assistant/chunk","seq":77,"time":1783352265489,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":78,"time":1783352265491,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read the file greeting.txt\n2. Append the word WORLD as a second line\n3. Read the file back with cat to confirm\n4. Reply with DONE\n\nLet me start by reading the file to see its contents."},{"type":"tool-call","id":"call_00_OjRFB4zvxu6UALDjytZD0978","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}],"usage":{"inputTokens":2918,"outputTokens":101,"cacheReadTokens":0,"reasoningTokens":55}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77],"surfaceOp":"append"} +{"type":"assistant/message","seq":78,"time":1783352265491,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read the file greeting.txt\n2. Append the word WORLD as a second line\n3. Read the file back with cat to confirm\n4. Reply with DONE\n\nLet me start by reading the file to see its contents."},{"type":"tool-call","id":"call_00_OjRFB4zvxu6UALDjytZD0978","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2918,"outputTokens":101,"cacheReadTokens":0,"reasoningTokens":55}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77],"surfaceOp":"append"} {"type":"tool/call","seq":79,"time":1783352265491,"data":{"turn":1,"step":1,"callId":"call_00_OjRFB4zvxu6UALDjytZD0978","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}} {"type":"tool/result","seq":80,"time":1783352265504,"data":{"turn":1,"step":1,"callId":"call_00_OjRFB4zvxu6UALDjytZD0978","content":[{"type":"text","text":"/tmp/acp-snap-cwd-rxbEpP/greeting.txt\nfile\n\n1: hello\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[79],"surfaceOp":"append"} {"type":"step/end","seq":81,"time":1783352265504,"data":{"turn":1,"step":1}} @@ -154,7 +154,7 @@ {"type":"assistant/chunk","seq":152,"time":1783352267302,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_IUUvbNiPcnwhVL8ErEFS4806","name":"bash","arguments":"{\"command\": \"printf '\\\\nWORLD' >> greeting.txt\", \"description\": \"Append newline and WORLD to greeting.txt\"}"}}}} {"type":"assistant/chunk","seq":153,"time":1783352267302,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":261,"outputTokens":107,"cacheReadTokens":2816,"reasoningTokens":32}}}} {"type":"assistant/chunk","seq":154,"time":1783352267302,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":155,"time":1783352267302,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file contains \"hello\" on one line. Now I need to append a second line with \"WORLD\" to it. Then cat it to confirm."},{"type":"tool-call","id":"call_00_IUUvbNiPcnwhVL8ErEFS4806","name":"bash","arguments":"{\"command\": \"printf '\\\\nWORLD' >> greeting.txt\", \"description\": \"Append newline and WORLD to greeting.txt\"}"}],"usage":{"inputTokens":261,"outputTokens":107,"cacheReadTokens":2816,"reasoningTokens":32}},"sourceEventSeqs":[83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154],"surfaceOp":"append"} +{"type":"assistant/message","seq":155,"time":1783352267302,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file contains \"hello\" on one line. Now I need to append a second line with \"WORLD\" to it. Then cat it to confirm."},{"type":"tool-call","id":"call_00_IUUvbNiPcnwhVL8ErEFS4806","name":"bash","arguments":"{\"command\": \"printf '\\\\nWORLD' >> greeting.txt\", \"description\": \"Append newline and WORLD to greeting.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":261,"outputTokens":107,"cacheReadTokens":2816,"reasoningTokens":32}},"sourceEventSeqs":[83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154],"surfaceOp":"append"} {"type":"tool/call","seq":156,"time":1783352267302,"data":{"turn":1,"step":2,"callId":"call_00_IUUvbNiPcnwhVL8ErEFS4806","name":"bash","arguments":"{\"command\": \"printf '\\\\nWORLD' >> greeting.txt\", \"description\": \"Append newline and WORLD to greeting.txt\"}"}} {"type":"tool/result","seq":157,"time":1783352267330,"data":{"turn":1,"step":2,"callId":"call_00_IUUvbNiPcnwhVL8ErEFS4806","content":[{"type":"text","text":"(no output)"}],"isError":false},"sourceEventSeqs":[156],"surfaceOp":"append"} {"type":"step/end","seq":158,"time":1783352267330,"data":{"turn":1,"step":2}} @@ -201,7 +201,7 @@ {"type":"assistant/chunk","seq":199,"time":1783352268414,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_Wo4H7tFNheZJWKVDrAHK5851","name":"bash","arguments":"{\"command\": \"cat greeting.txt\", \"description\": \"Read greeting.txt to confirm\"}"}}}} {"type":"assistant/chunk","seq":200,"time":1783352268414,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":126,"outputTokens":77,"cacheReadTokens":3072,"reasoningTokens":12}}}} {"type":"assistant/chunk","seq":201,"time":1783352268414,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":202,"time":1783352268415,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"Good, now let me read the file back with cat."},{"type":"tool-call","id":"call_00_Wo4H7tFNheZJWKVDrAHK5851","name":"bash","arguments":"{\"command\": \"cat greeting.txt\", \"description\": \"Read greeting.txt to confirm\"}"}],"usage":{"inputTokens":126,"outputTokens":77,"cacheReadTokens":3072,"reasoningTokens":12}},"sourceEventSeqs":[160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201],"surfaceOp":"append"} +{"type":"assistant/message","seq":202,"time":1783352268415,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"Good, now let me read the file back with cat."},{"type":"tool-call","id":"call_00_Wo4H7tFNheZJWKVDrAHK5851","name":"bash","arguments":"{\"command\": \"cat greeting.txt\", \"description\": \"Read greeting.txt to confirm\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":126,"outputTokens":77,"cacheReadTokens":3072,"reasoningTokens":12}},"sourceEventSeqs":[160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201],"surfaceOp":"append"} {"type":"tool/call","seq":203,"time":1783352268415,"data":{"turn":1,"step":3,"callId":"call_00_Wo4H7tFNheZJWKVDrAHK5851","name":"bash","arguments":"{\"command\": \"cat greeting.txt\", \"description\": \"Read greeting.txt to confirm\"}"}} {"type":"tool/result","seq":204,"time":1783352268429,"data":{"turn":1,"step":3,"callId":"call_00_Wo4H7tFNheZJWKVDrAHK5851","content":[{"type":"text","text":"hello\n\nWORLD"}],"isError":false},"sourceEventSeqs":[203],"surfaceOp":"append"} {"type":"step/end","seq":205,"time":1783352268429,"data":{"turn":1,"step":3}} @@ -236,6 +236,6 @@ {"type":"assistant/chunk","seq":234,"time":1783352269538,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":235,"time":1783352269538,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":219,"outputTokens":25,"cacheReadTokens":3072,"reasoningTokens":22}}}} {"type":"assistant/chunk","seq":236,"time":1783352269538,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":237,"time":1783352269538,"data":{"turn":1,"step":4,"content":[{"type":"reasoning","text":"The file now has two lines:\n1. hello\n2. WORLD\n\nI can reply with DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":219,"outputTokens":25,"cacheReadTokens":3072,"reasoningTokens":22}},"sourceEventSeqs":[207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236],"surfaceOp":"append"} +{"type":"assistant/message","seq":237,"time":1783352269538,"data":{"turn":1,"step":4,"content":[{"type":"reasoning","text":"The file now has two lines:\n1. hello\n2. WORLD\n\nI can reply with DONE."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":219,"outputTokens":25,"cacheReadTokens":3072,"reasoningTokens":22}},"sourceEventSeqs":[207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236],"surfaceOp":"append"} {"type":"step/end","seq":238,"time":1783352269538,"data":{"turn":1,"step":4}} {"type":"turn/end","seq":239,"time":1783352269539,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/coding-agent/code-mode.cordis.yml b/examples/coding-agent/code-mode.cordis.yml index ac4ce03570..87075b1d85 100644 --- a/examples/coding-agent/code-mode.cordis.yml +++ b/examples/coding-agent/code-mode.cordis.yml @@ -16,6 +16,7 @@ - id: stdio-agent name: '@deepseek-ai/dsh-stdio-agent' config: + provider: deepseek model: deepseek-v4-flash resumeSessionId: !!js process.env.RESUME_SESSION_ID persistenceRoot: './.sessions' diff --git a/examples/coding-agent/cordis.yml b/examples/coding-agent/cordis.yml index cf2e267e06..74318aea4f 100644 --- a/examples/coding-agent/cordis.yml +++ b/examples/coding-agent/cordis.yml @@ -17,16 +17,12 @@ config: root: ['.'] -# The DeepSeek adapter. Swap to '@deepseek-ai/dsh-llm-pi-ai' for the pi-ai-backed -# twin (same config shape; `reasoning: high` replaces thinking/reasoningEffort). +# The native DeepSeek adapter. - id: llm-deepseek name: '@deepseek-ai/dsh-llm-deepseek' config: apiKey: !!js process.env.DEEPSEEK_API_KEY baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: - - deepseek-v4-pro - - deepseek-v4-flash # Local bash executor for agent-core's tool-bash schema (one of several tool # stacks in this tree: filesystem, subagent, and todo_write load below). @@ -40,6 +36,7 @@ - id: stdio-agent name: '@deepseek-ai/dsh-stdio-agent' config: + provider: deepseek model: deepseek-v4-flash # Set RESUME_SESSION_ID to continue a prior persisted session (the ids live # under ./.sessions); unset starts a fresh session each run. @@ -66,6 +63,7 @@ contextWindow: 128000 thresholdRatio: 0.8 retainTokens: 20480 + summarizationProvider: '' summarizationModel: '' maxTokens: 8192 compactionRetries: 1 diff --git a/examples/coding-agent/tests/code-mode.e2e.ts b/examples/coding-agent/tests/code-mode.e2e.ts index 512688d88d..b8209e119d 100644 --- a/examples/coding-agent/tests/code-mode.e2e.ts +++ b/examples/coding-agent/tests/code-mode.e2e.ts @@ -50,7 +50,7 @@ async function codeModeHarness(cwd: string): Promise { await harness.plugin(ToolRegistry, { mode: 'code' }) await harness.plugin(AgentRegistry) await harness.plugin(AgentLoop, { agents: [] }) - await harness.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) + await harness.plugin(LlmDeepSeek) await harness.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 }) await harness.plugin(ToolBash) await harness.plugin(WorkerCodeRuntime, {}) @@ -72,7 +72,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p it('collapses the wire tool list to [run_code], bridges sub-calls, and returns curated output', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-e2e-')) ctx = await codeModeHarness(workdir) - const agent = ctx.agentLoop.create(AgentId('e2e-code-mode'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('e2e-code-mode'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/coding-task.e2e.ts b/examples/coding-agent/tests/coding-task.e2e.ts index ce716bdb2c..d53688835e 100644 --- a/examples/coding-agent/tests/coding-task.e2e.ts +++ b/examples/coding-agent/tests/coding-task.e2e.ts @@ -54,7 +54,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test expect(before.status).not.toBe(0) ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-task'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('e2e-task'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/compaction.e2e.ts b/examples/coding-agent/tests/compaction.e2e.ts index 854cf49d2a..ab32e7f8a8 100644 --- a/examples/coding-agent/tests/compaction.e2e.ts +++ b/examples/coding-agent/tests/compaction.e2e.ts @@ -58,13 +58,14 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa contextWindow: 2000, thresholdRatio: 0.5, retainTokens: 400, + summarizationProvider: '', summarizationModel: '', maxTokens: 1024, compactionRetries: 1, }, persistenceRoot: join(workdir, '.sessions'), }) - const agent = ctx.agentLoop.create(AgentId('e2e-compaction'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('e2e-compaction'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/full-loop.e2e.ts b/examples/coding-agent/tests/full-loop.e2e.ts index 8718139ced..7314b7ab21 100644 --- a/examples/coding-agent/tests/full-loop.e2e.ts +++ b/examples/coding-agent/tests/full-loop.e2e.ts @@ -28,7 +28,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bas it('runs a bash command on request and reports its output', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-full-loop-e2e-')) ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-loop'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('e2e-loop'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }]) await waitForIdle(ctx, agent) diff --git a/examples/coding-agent/tests/harness.ts b/examples/coding-agent/tests/harness.ts index dd0bc42a1b..378414a6be 100644 --- a/examples/coding-agent/tests/harness.ts +++ b/examples/coding-agent/tests/harness.ts @@ -56,7 +56,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) - await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) + await ctx.plugin(LlmDeepSeek) await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 }) await ctx.plugin(ToolBash) await ctx.plugin(ToolTodo) diff --git a/examples/coding-agent/tests/resume.e2e.ts b/examples/coding-agent/tests/resume.e2e.ts index 70382b4beb..c9081c659f 100644 --- a/examples/coding-agent/tests/resume.e2e.ts +++ b/examples/coding-agent/tests/resume.e2e.ts @@ -42,7 +42,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses const first = (await ctx.agents.create({ agentId: AgentId('resume-1'), sessionId: SESSION_ID, - agentOptions: { model: 'deepseek-v4-flash' }, + agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' }, })).agent as ReactLoopAgent first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }]) await waitForIdle(ctx, first) @@ -56,7 +56,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses const resumed = (await ctx.agents.resume({ agentId: AgentId('resume-2'), resumeSessionId: SESSION_ID, - agentOptions: { model: 'deepseek-v4-flash' }, + agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' }, })).agent as ReactLoopAgent expect(resumed.session.id).toBe(SESSION_ID) // The prior user turn is in the rehydrated log before the model is asked. diff --git a/examples/coding-agent/tests/todo-write.e2e.ts b/examples/coding-agent/tests/todo-write.e2e.ts index 698fbd9e9e..a16f15528d 100644 --- a/examples/coding-agent/tests/todo-write.e2e.ts +++ b/examples/coding-agent/tests/todo-write.e2e.ts @@ -26,7 +26,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a it('appends a todo/write event with the model-produced task list', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-todo-write-e2e-')) ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-todo'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('e2e-todo'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Use the todo_write tool to record a plan of exactly two steps: first ' diff --git a/examples/cordis-agent/cordis.yml b/examples/cordis-agent/cordis.yml index 65d5e6eb36..2fd88199ab 100644 --- a/examples/cordis-agent/cordis.yml +++ b/examples/cordis-agent/cordis.yml @@ -25,9 +25,6 @@ config: apiKey: !!js process.env.DEEPSEEK_API_KEY baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: - - deepseek-v4-pro - - deepseek-v4-flash # Local bash executor for agent-core's tool-bash schema — gives the agent an # ordinary tool whose calls make the mounted listeners observably fire. @@ -58,6 +55,7 @@ - id: stdio-agent name: '@deepseek-ai/dsh-stdio-agent' config: + provider: deepseek model: deepseek-v4-flash resumeSessionId: !!js process.env.RESUME_SESSION_ID persistenceRoot: './.sessions' diff --git a/examples/cordis-agent/tests/cordis-tools.e2e.ts b/examples/cordis-agent/tests/cordis-tools.e2e.ts index 388fcb0058..5b742d8830 100644 --- a/examples/cordis-agent/tests/cordis-tools.e2e.ts +++ b/examples/cordis-agent/tests/cordis-tools.e2e.ts @@ -38,7 +38,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('mounts a status listener whose tagged output actually fires, then unmounts it', async () => { ctx = await cordisHarness() const log = vi.spyOn(console, 'log').mockImplementation(() => {}) - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-listener'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('cordis-e2e-listener'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', @@ -66,7 +66,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('builds itself a reverse_text tool and actually calls it', async () => { ctx = await cordisHarness() - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-selftool'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('cordis-e2e-selftool'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', @@ -114,7 +114,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('composes two mounts through provide/inject, and unmounting the provider parks the consumer', async () => { ctx = await cordisHarness() - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-compose'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('cordis-e2e-compose'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/cordis-agent/tests/harness.ts b/examples/cordis-agent/tests/harness.ts index 78e5b0bb93..062e643ca8 100644 --- a/examples/cordis-agent/tests/harness.ts +++ b/examples/cordis-agent/tests/harness.ts @@ -29,7 +29,7 @@ export async function cordisHarness(): Promise { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) - await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) + await ctx.plugin(LlmDeepSeek) await ctx.plugin(ToolCordis) return ctx } diff --git a/examples/echo-agent/cordis.yml b/examples/echo-agent/cordis.yml index b66c5e8163..bbe6c78b7c 100644 --- a/examples/echo-agent/cordis.yml +++ b/examples/echo-agent/cordis.yml @@ -32,6 +32,7 @@ - id: stdio-agent name: '@deepseek-ai/dsh-stdio-agent' config: + provider: mock model: mock-echo persona: 'You are echo-agent, a demo agent.' welcome: 'echo-agent ready. Type a message ("echo " triggers the tool).' diff --git a/examples/echo-agent/src/mock-llm.ts b/examples/echo-agent/src/mock-llm.ts index 93132711de..1f61dc4ee3 100644 --- a/examples/echo-agent/src/mock-llm.ts +++ b/examples/echo-agent/src/mock-llm.ts @@ -55,5 +55,5 @@ export const name = 'mock-llm' export const inject = ['llm'] export function apply(ctx: Context) { - ctx.llm.registerAdapter(['mock-echo'], new MockEchoAdapter()) + ctx.llm.registerAdapter(['mock'], new MockEchoAdapter()) } diff --git a/examples/sandbox-acp-agent/cordis.yml b/examples/sandbox-acp-agent/cordis.yml index d02253342e..5ab8becd69 100644 --- a/examples/sandbox-acp-agent/cordis.yml +++ b/examples/sandbox-acp-agent/cordis.yml @@ -18,8 +18,6 @@ config: apiKey: !!js process.env.DEEPSEEK_API_KEY baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: - - deepseek-v4-flash # The sandbox stack: the platform-runner provider (bwrap → per-platform # Landlock launcher → Seatbelt, functionally probed), then the confined bash executor. @@ -49,6 +47,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash # Persistence root: $DSH_SNAPSHOT_SESSIONS_ROOT when the snapshot harness # sets it (so a record run's logs land where the harness harvests them), diff --git a/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl b/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl index 2ac9d27044..526524e870 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl +++ b/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783486769426,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783486769426,"data":{"content":[{"type":"text","text":"The sandbox already denied writing escalated.txt in this workspace earlier. Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > escalated.txt && cat escalated.txt, with sandbox_permissions set to workspace-write and the justification 'the user asked to write escalated.txt in the workspace'. Do not run it without sandbox_permissions first. I will approve the permission prompt. After the result, reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783486769427,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783486769427,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783486769427,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783486770051,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783486770052,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783486770179,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -112,7 +112,7 @@ {"type":"assistant/chunk","seq":110,"time":1783486771232,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}}}} {"type":"assistant/chunk","seq":111,"time":1783486771232,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1255,"outputTokens":160,"cacheReadTokens":0,"reasoningTokens":34}}}} {"type":"assistant/chunk","seq":112,"time":1783486771232,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":113,"time":1783486771236,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the command with sandbox_permissions set to workspace-write. They explicitly said they will approve the permission prompt. Let me proceed."},{"type":"tool-call","id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"usage":{"inputTokens":1255,"outputTokens":160,"cacheReadTokens":0,"reasoningTokens":34}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} +{"type":"assistant/message","seq":113,"time":1783486771236,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the command with sandbox_permissions set to workspace-write. They explicitly said they will approve the permission prompt. Let me proceed."},{"type":"tool-call","id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1255,"outputTokens":160,"cacheReadTokens":0,"reasoningTokens":34}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} {"type":"tool/call","seq":114,"time":1783486771236,"data":{"turn":1,"step":1,"callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}} {"type":"approval/asked","seq":115,"time":1783486771238,"data":{"id":"3ec45405-5add-4929-a755-e8c077ec7a7e","toolName":"bash","callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}} {"type":"approval/decided","seq":116,"time":1783486771243,"data":{"id":"3ec45405-5add-4929-a755-e8c077ec7a7e","outcome":"allowed-once"}} @@ -144,6 +144,6 @@ {"type":"assistant/chunk","seq":142,"time":1783486772229,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":143,"time":1783486772229,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":23,"outputTokens":20,"cacheReadTokens":1408,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":144,"time":1783486772229,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":145,"time":1783486772230,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command succeeded. The user asked me to reply with the single word DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":23,"outputTokens":20,"cacheReadTokens":1408,"reasoningTokens":17}},"sourceEventSeqs":[120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144],"surfaceOp":"append"} +{"type":"assistant/message","seq":145,"time":1783486772230,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command succeeded. The user asked me to reply with the single word DONE."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":23,"outputTokens":20,"cacheReadTokens":1408,"reasoningTokens":17}},"sourceEventSeqs":[120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144],"surfaceOp":"append"} {"type":"step/end","seq":146,"time":1783486772230,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":147,"time":1783486772230,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl b/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl index ee2586bc34..cca88b26c9 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl +++ b/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783486772551,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783486772551,"data":{"content":[{"type":"text","text":"The sandbox already denied writing escalated.txt in this workspace earlier. Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > escalated.txt && cat escalated.txt, with sandbox_permissions set to workspace-write and the justification 'the user asked to write escalated.txt in the workspace'. Do not run it without sandbox_permissions first. I will reject the permission prompt; after the rejection, do not retry and do not work around it — explain in one short sentence that the escalation was rejected, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783486772552,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783486772552,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783486772552,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783486773136,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783486773136,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783486773275,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -149,7 +149,7 @@ {"type":"assistant/chunk","seq":147,"time":1783486774569,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}}}} {"type":"assistant/chunk","seq":148,"time":1783486774569,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1269,"outputTokens":197,"cacheReadTokens":0,"reasoningTokens":70}}}} {"type":"assistant/chunk","seq":149,"time":1783486774569,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":150,"time":1783486774572,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the exact command `printf 'escalated\\n' > escalated.txt && cat escalated.txt` with `sandbox_permissions` set to `workspace-write` and the justification they specified. They explicitly say they will reject the permission prompt, so after rejection I should explain in one short sentence and stop."},{"type":"tool-call","id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"usage":{"inputTokens":1269,"outputTokens":197,"cacheReadTokens":0,"reasoningTokens":70}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"surfaceOp":"append"} +{"type":"assistant/message","seq":150,"time":1783486774572,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the exact command `printf 'escalated\\n' > escalated.txt && cat escalated.txt` with `sandbox_permissions` set to `workspace-write` and the justification they specified. They explicitly say they will reject the permission prompt, so after rejection I should explain in one short sentence and stop."},{"type":"tool-call","id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1269,"outputTokens":197,"cacheReadTokens":0,"reasoningTokens":70}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"surfaceOp":"append"} {"type":"tool/call","seq":151,"time":1783486774572,"data":{"turn":1,"step":1,"callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}} {"type":"approval/asked","seq":152,"time":1783486774574,"data":{"id":"ed977255-38a3-4c1d-9f4e-0e258ef86e94","toolName":"bash","callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}} {"type":"approval/decided","seq":153,"time":1783486774578,"data":{"id":"ed977255-38a3-4c1d-9f4e-0e258ef86e94","outcome":"rejected"}} @@ -197,6 +197,6 @@ {"type":"assistant/chunk","seq":195,"time":1783486776185,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The escalation request to write to the workspace was rejected, so the command was not executed."}}}} {"type":"assistant/chunk","seq":196,"time":1783486776185,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":341,"outputTokens":36,"cacheReadTokens":1152,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":197,"time":1783486776185,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":198,"time":1783486776186,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user rejected the escalation. I need to explain in one short sentence and stop."},{"type":"text","text":"The escalation request to write to the workspace was rejected, so the command was not executed."}],"usage":{"inputTokens":341,"outputTokens":36,"cacheReadTokens":1152,"reasoningTokens":17}},"sourceEventSeqs":[157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197],"surfaceOp":"append"} +{"type":"assistant/message","seq":198,"time":1783486776186,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user rejected the escalation. I need to explain in one short sentence and stop."},{"type":"text","text":"The escalation request to write to the workspace was rejected, so the command was not executed."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":341,"outputTokens":36,"cacheReadTokens":1152,"reasoningTokens":17}},"sourceEventSeqs":[157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197],"surfaceOp":"append"} {"type":"step/end","seq":199,"time":1783486776186,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":200,"time":1783486776186,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl b/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl index ef287390aa..18aa91c7a0 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl +++ b/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783613224997,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783613224997,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: cat notes.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783613224997,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783613224997,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783613224997,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783613225437,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783613225438,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783613225658,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -49,7 +49,7 @@ {"type":"assistant/chunk","seq":47,"time":1783613226061,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","arguments":"{\"command\": \"cat notes.txt\", \"description\": \"Show contents of notes.txt\"}"}}}} {"type":"assistant/chunk","seq":48,"time":1783613226061,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1202,"outputTokens":81,"cacheReadTokens":0,"reasoningTokens":16}}}} {"type":"assistant/chunk","seq":49,"time":1783613226061,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":50,"time":1783613226064,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `cat notes.txt` using the bash tool."},{"type":"tool-call","id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","arguments":"{\"command\": \"cat notes.txt\", \"description\": \"Show contents of notes.txt\"}"}],"usage":{"inputTokens":1202,"outputTokens":81,"cacheReadTokens":0,"reasoningTokens":16}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"surfaceOp":"append"} +{"type":"assistant/message","seq":50,"time":1783613226064,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `cat notes.txt` using the bash tool."},{"type":"tool-call","id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","arguments":"{\"command\": \"cat notes.txt\", \"description\": \"Show contents of notes.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1202,"outputTokens":81,"cacheReadTokens":0,"reasoningTokens":16}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"surfaceOp":"append"} {"type":"tool/call","seq":51,"time":1783613226064,"data":{"turn":1,"step":1,"callId":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","arguments":"{\"command\": \"cat notes.txt\", \"description\": \"Show contents of notes.txt\"}"}} {"type":"tool/result","seq":52,"time":1783613226148,"data":{"turn":1,"step":1,"callId":"call_00_I9sT0gKlfz9YP4dlf2pA3899","content":[{"type":"text","text":"hello from the sandboxed workspace\n"}],"isError":false},"sourceEventSeqs":[51],"surfaceOp":"append"} {"type":"step/end","seq":53,"time":1783613226148,"data":{"turn":1,"step":1}} @@ -80,7 +80,7 @@ {"type":"assistant/chunk","seq":78,"time":1783613227141,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":79,"time":1783613227141,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":23,"outputTokens":21,"cacheReadTokens":1280,"reasoningTokens":18}}}} {"type":"assistant/chunk","seq":80,"time":1783613227141,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":81,"time":1783613227142,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command ran successfully. The user asked me to reply with the single word DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":23,"outputTokens":21,"cacheReadTokens":1280,"reasoningTokens":18}},"sourceEventSeqs":[55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80],"surfaceOp":"append"} +{"type":"assistant/message","seq":81,"time":1783613227142,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command ran successfully. The user asked me to reply with the single word DONE."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":23,"outputTokens":21,"cacheReadTokens":1280,"reasoningTokens":18}},"sourceEventSeqs":[55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80],"surfaceOp":"append"} {"type":"step/end","seq":82,"time":1783613227142,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":83,"time":1783613227142,"data":{"turn":1,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":84,"time":1783613227169,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} @@ -142,7 +142,7 @@ {"type":"assistant/chunk","seq":140,"time":1783613228325,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","arguments":"{\"description\": \"Write and read out.txt\", \"command\": \"printf 'switched\\\\n' > out.txt && cat out.txt\"}"}}}} {"type":"assistant/chunk","seq":141,"time":1783613228325,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":70,"outputTokens":90,"cacheReadTokens":1280,"reasoningTokens":15}}}} {"type":"assistant/chunk","seq":142,"time":1783613228325,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":143,"time":1783613228325,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command. Let me execute it."},{"type":"tool-call","id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","arguments":"{\"description\": \"Write and read out.txt\", \"command\": \"printf 'switched\\\\n' > out.txt && cat out.txt\"}"}],"usage":{"inputTokens":70,"outputTokens":90,"cacheReadTokens":1280,"reasoningTokens":15}},"sourceEventSeqs":[88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"surfaceOp":"append"} +{"type":"assistant/message","seq":143,"time":1783613228325,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command. Let me execute it."},{"type":"tool-call","id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","arguments":"{\"description\": \"Write and read out.txt\", \"command\": \"printf 'switched\\\\n' > out.txt && cat out.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":70,"outputTokens":90,"cacheReadTokens":1280,"reasoningTokens":15}},"sourceEventSeqs":[88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"surfaceOp":"append"} {"type":"tool/call","seq":144,"time":1783613228325,"data":{"turn":2,"step":1,"callId":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","arguments":"{\"description\": \"Write and read out.txt\", \"command\": \"printf 'switched\\\\n' > out.txt && cat out.txt\"}"}} {"type":"tool/result","seq":145,"time":1783613228412,"data":{"turn":2,"step":1,"callId":"call_00_htXcbtvwTFK0NqfclLWL7784","content":[{"type":"text","text":"switched\n"}],"isError":false},"sourceEventSeqs":[144],"surfaceOp":"append"} {"type":"step/end","seq":146,"time":1783613228412,"data":{"turn":2,"step":1}} @@ -166,7 +166,7 @@ {"type":"assistant/chunk","seq":164,"time":1783613229048,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":165,"time":1783613229048,"data":{"turn":2,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":47,"outputTokens":14,"cacheReadTokens":1408,"reasoningTokens":11}}}} {"type":"assistant/chunk","seq":166,"time":1783613229048,"data":{"turn":2,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":167,"time":1783613229049,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"Command executed successfully. The output is \"switched\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":47,"outputTokens":14,"cacheReadTokens":1408,"reasoningTokens":11}},"sourceEventSeqs":[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166],"surfaceOp":"append"} +{"type":"assistant/message","seq":167,"time":1783613229049,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"Command executed successfully. The output is \"switched\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":47,"outputTokens":14,"cacheReadTokens":1408,"reasoningTokens":11}},"sourceEventSeqs":[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166],"surfaceOp":"append"} {"type":"step/end","seq":168,"time":1783613229049,"data":{"turn":2,"step":2}} {"type":"turn/end","seq":169,"time":1783613229049,"data":{"turn":2,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":170,"time":1783613229056,"data":{"turn":3,"trigger":{"kind":"message","source":{"kind":"user"}}}} @@ -240,6 +240,6 @@ {"type":"assistant/chunk","seq":238,"time":1783613230689,"data":{"turn":3,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"Approvals are never asked; any action requiring approval is automatically rejected."}}}} {"type":"assistant/chunk","seq":239,"time":1783613230689,"data":{"turn":3,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1530,"outputTokens":60,"cacheReadTokens":0,"reasoningTokens":45}}}} {"type":"assistant/chunk","seq":240,"time":1783613230689,"data":{"turn":3,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":241,"time":1783613230690,"data":{"turn":3,"step":1,"content":[{"type":"reasoning","text":"The user wants me to state my current approval policy without using any tools. From the context, the approval policy is \"never\" — meaning actions that require approval are rejected automatically, and I should not request sandbox escalation."},{"type":"text","text":"Approvals are never asked; any action requiring approval is automatically rejected."}],"usage":{"inputTokens":1530,"outputTokens":60,"cacheReadTokens":0,"reasoningTokens":45}},"sourceEventSeqs":[176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240],"surfaceOp":"append"} +{"type":"assistant/message","seq":241,"time":1783613230690,"data":{"turn":3,"step":1,"content":[{"type":"reasoning","text":"The user wants me to state my current approval policy without using any tools. From the context, the approval policy is \"never\" — meaning actions that require approval are rejected automatically, and I should not request sandbox escalation."},{"type":"text","text":"Approvals are never asked; any action requiring approval is automatically rejected."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1530,"outputTokens":60,"cacheReadTokens":0,"reasoningTokens":45}},"sourceEventSeqs":[176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240],"surfaceOp":"append"} {"type":"step/end","seq":242,"time":1783613230690,"data":{"turn":3,"step":1}} {"type":"turn/end","seq":243,"time":1783613230690,"data":{"turn":3,"reason":{"kind":"completed"}}} diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index a22e86bd99..bc65ae799b 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -74,7 +74,7 @@ describe('bash tool through the agent loop', () => { textResponse('The command printed integration-ok.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-fg'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('it-fg'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'run echo integration-ok' }]) await waitForIdle(ctx, agent) @@ -106,7 +106,7 @@ describe('bash tool through the agent loop', () => { textResponse('It failed with code 9.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-exit'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('it-exit'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'run exit 9' }]) await waitForIdle(ctx, agent) @@ -128,7 +128,7 @@ describe('bash tool through the agent loop', () => { let taskId = '' const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-bg'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('it-bg'), { provider: 'mock', model: 'mock' }) // Capture the generated id so the deterministic fixture is checked against // the real executor instead of silently assuming it. diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index a06e74b818..ce8067dbb3 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -11,13 +11,13 @@ The abstract contract states only WHAT compaction does; this backend owns every - **Token estimation** — `estimateContentTokens()`: chars divided by the `charsPerToken` config (default 4) with per-block structural overhead (`text`/`reasoning` = `ceil(len/charsPerToken) + 4`, `tool-call` from name + arguments, `tool-result` recursive, unknown blocks via JSON length). The pressure gate estimates the NEXT request via `estimatePressure()`: the session prefix (the `agent/session-prefix` product — composed by the loop BEFORE the pre-step seam and handed through it, so the gate counts the prefix this instance will actually send in front of the history, never a stale logged one) + the derived history + the system prompt. - **Retention policy** — `compactIfNeeded()` walks the surface nodes tail→head summing per-node token estimates, and retains the smallest tail-run of WHOLE units (a closed step, or a single no-step node such as a pre-step `user/message` or inter-step `steering/message`) whose total reaches `retainTokens`; everything older is compacted. Retention is **turn-agnostic** — turn boundaries play no role, so a single runaway turn that alone exceeds the window compacts its OWN early closed steps rather than being retained verbatim (the failure mode that motivated dropping turn-protection: a tool-heavy turn must stay compactable or the harness dies exactly when compaction is needed). The only structural guard is **tool-pairing balance**: the compacted region's edges are balanced cuts on the surface (no unanswered tool-call crosses either edge), so it never splits a step's `assistant/message` tool-calls from their `tool/result`s. When the only compactable content left is an un-splittable open tail step, it declines (returns `null`) and retries once an older step closes. **Single-unit overflow is out of scope, by design**: if one retained unit (a single closed step, or a large pasted `user/message`) ALONE exceeds the budget, compaction cannot help and the call may go out over-budget — bounding an individual unit's size is a separate concern. `compactRegion()` enforces tool-pairing balance strictly, throwing on a boundary that would split a step. `dsh-session` exports `isToolPairingBalanced` for the check. - **Dynamic convergence** — no static summary-length config pretends to bound what the model will write. If framing/estimator/system overhead leaves the compacted surface above threshold, `compactIfNeeded()` re-compacts the head checkpoint up to `compactionRetries` extra times; if it still cannot get below threshold, it throws. A summary whose estimated stored size is not smaller than the shadowed content fails closed before it mutates the surface. -- **Summarization** — `summarize()`: a `GenerateOptions` request assembled via `BlockAssembler` with a fixed system prompt that asks for a structured checkpoint (Primary Request and Intent · Key Technical Concepts · Files and Code · Errors and Fixes · Pending Tasks · Current Work · Next Step · Critical Context), every section mandatory, exact paths/commands/identifiers preserved. The request is a direct one-shot `ctx.llm.stream()` call — NOT a loop step, so it does not run `agent/request` (that seam shapes the loop's conversation requests); the model comes from `summarizationModel` falling back to the agent's own, and per-call routing happens at `llm/stream` like any other direct call. `maxTokens` is the provider-side generation cap; only text blocks from the model's reply are kept before the checkpoint is stored (reasoning is dropped so private chain-of-thought never leaks into the durable summary, and a stray `tool-call` is dropped so the synthesized `user/message` summary cannot land an orphaned call with no matching `tool-result`). The compacted region is flattened to a plain-text transcript first: text and reasoning contribute their text, and every non-text block (tool-call, tool-result, plugin-added types) contributes a type-tagged placeholder (`[tool-call: name(args)]`, `[tool-result: …]`, …) so the summarizer is told what existed rather than silently dropping it. +- **Summarization** — `summarize()`: a `GenerateOptions` request assembled via `BlockAssembler` with a fixed system prompt that asks for a structured checkpoint (Primary Request and Intent · Key Technical Concepts · Files and Code · Errors and Fixes · Pending Tasks · Current Work · Next Step · Critical Context), every section mandatory, exact paths/commands/identifiers preserved. The request is a direct one-shot `ctx.llm.stream()` call — NOT a loop step, so it does not run `agent/request` (that seam shapes the loop's conversation requests); the target comes from the explicit `summarizationProvider`+`summarizationModel` pair, otherwise the latest logged request pair, otherwise the agent pair. Per-call routing happens at `llm/stream` like any other direct call. `maxTokens` is the provider-side generation cap; only text blocks from the model's reply are kept before the checkpoint is stored (reasoning is dropped so private chain-of-thought never leaks into the durable summary, and a stray `tool-call` is dropped so the synthesized `user/message` summary cannot land an orphaned call with no matching `tool-result`). The compacted region is flattened to a plain-text transcript first: text and reasoning contribute their text, and every non-text block (tool-call, tool-result, plugin-added types) contributes a type-tagged placeholder (`[tool-call: name(args)]`, `[tool-result: …]`, …) so the summarizer is told what existed rather than silently dropping it. - **Checkpoint framing** — the raw summary is not landed directly. `compactRegion()` wraps it in a checkpoint preamble (so a resuming model reads it as a checkpoint, not a fresh user request, and builds on the captured context rather than restating it) plus `…` tags. Because region compaction can be invoked manually, a surface may hold several checkpoints, so the framing does not claim everything after it is recent or verbatim. The tags make a prior checkpoint detectable in the transcript on the next compaction cycle: the summarization prompt then instructs the model to merge it in place (preserve still-true facts, drop stale ones) rather than re-summarize it verbatim — a cheap incremental merge that needs no extra log/event machinery. The unframed summary stays on the `compact/summary` provenance event. - **Surface mutation** — `compactRegion()` appends the `compact/start` → `compact/summary` → `compact/end` log records and the single `user/message` replace node carrying the framed summary (see the interface README). - **Auto-compaction** — an `agent/pre-step` listener delegates to `compactIfNeeded()` before every step (not just a turn's first — a tool-heavy turn grows the surface mid-turn, so a runaway turn still compacts, and per-step firing is the only moment to rescue it before overflow). `agent/pre-step` is a serial (awaited, in-order) surface-mutation checkpoint that fires after `turn/start` and BEFORE the step opens (`step/start`) and its request history is derived, so compaction mutates the surface — with its log-only `compact/*` records landing cleanly outside any step — and the loop derives once from the result: no double-derive, and the listener cannot see (or need to rewrite) an already-assembled `messages` array. The listener owns no threshold logic of its own (the single token-pressure check lives in `compactIfNeeded()`); because Cordis `serial` bails early on non-void return values, the listener returns `void` and does not use the dispatcher's bail channel as a veto surface. - **Failure handling** — the `compact/start … compact/end` bracket is a log-recorded lock: it makes a crash mid-summarization a detectable orphan (a `compact/start` with no `compact/end`), records provenance, and prevents a concurrent compaction. Two failure paths: a **crash** (the loop dies mid-summarization) leaves a dangling `compact/start` that is inert — `compact/*` events are log-only, the surface replacement never landed, so the full history derives fine and generic turn-repair closes the turn; a **recoverable** failure (summarization throws but the loop survives) appends `compact/end` with its `error` field set, leaving the surface untouched so the call proceeds with full history. Core session repair stays compaction-agnostic by design — it never learns about `compact/*`. -`estimateContentTokens()` and `summarize()` are overridable hooks: a tokenizer-based or template-based backend can subclass `BasicCompactService` and override just those, reusing the retention walk and surface plumbing. `summarize()` returns the summary blocks together with the call envelope it actually used (`{ summary, model, maxTokens? }`) — the caller logs that envelope on the `compact/summary` provenance event, so an overriding backend reports its own envelope honestly. +`estimateContentTokens()` and `summarize()` are overridable hooks: a tokenizer-based or template-based backend can subclass `BasicCompactService` and override just those, reusing the retention walk and surface plumbing. `summarize()` returns the summary blocks together with the call envelope it actually used (`{ summary, provider, model, maxTokens? }`) — the caller logs that envelope on the `compact/summary` provenance event, so an overriding backend reports its own envelope honestly. ## Config (`BasicCompactConfig`) @@ -28,7 +28,8 @@ Every knob is **required** except `auto` — there is no concrete data yet to ju | `contextWindow` | yes | Context window size in tokens. | | `thresholdRatio` | yes | Compact when estimated usage exceeds this fraction of the window. | | `retainTokens` | yes | Tokens of recent context to keep intact. | -| `summarizationModel` | yes | Model for summarization (`''` → use the agent's model). | +| `summarizationProvider` | yes | Provider for summarization (`''` together with an empty model → use the latest logged request pair, then the agent pair). | +| `summarizationModel` | yes | Model for summarization (`''` together with an empty provider → use the latest logged request pair, then the agent pair). | | `maxTokens` | yes | Provider generation cap for the summarization call; may include reasoning tokens. | | `compactionRetries` | yes | Extra compaction attempts after the first if the compacted surface remains over threshold. | | `auto` | no (default `true`) | Register the `agent/pre-step` auto-compaction listener. Set `false` for manual-only. | @@ -48,6 +49,7 @@ export function apply(ctx: Context): void { contextWindow: 128000, thresholdRatio: 0.8, retainTokens: 20480, + summarizationProvider: '', summarizationModel: '', maxTokens: 8192, compactionRetries: 1, diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index c0d4ff483a..32dc8bf9aa 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -294,8 +294,8 @@ export class BasicCompactService extends CompactService { * loop step: it does not run the `agent/request` waterfall (that seam shapes * the loop's conversation requests); per-call * interception happens at `llm/stream` like any other direct call. The model - * comes from `BasicCompactConfig.summarizationModel`, falling back to the - * agent's own model. + * target comes from the explicit summarization provider/model pair, falling + * back to the last logged request target and then the agent's creation options. * Override in a subclass for a template or remote summarizer. * * Honors the adapter failure contract: an adapter may report a model failure @@ -307,23 +307,27 @@ export class BasicCompactService extends CompactService { * down the in-flight summarization rather than orphaning the model call. * * Returns the summary blocks TOGETHER with the call envelope it actually - * used (`model`, `maxTokens`) — the caller logs the envelope on the + * used (`provider`, `model`, `maxTokens`) — the caller logs the envelope on the * `compact/summary` provenance event, so an overriding subclass (template * or remote summarizer) reports its own envelope honestly. * * @param text - plain-text rendering of the conversation region to condense. - * @param agent - supplies the fallback model and the session id stamped on - * the call; throws when neither it nor the config names a model. + * @param agent - supplies the request-header/creation fallback target and the + * session id stamped on the call; throws when no complete target exists. * @param signal - optional abort signal, forwarded into the model call. * @returns the text-only summary blocks plus the call envelope used - * (`model`, and `maxTokens` when the summarizer has a cap). + * (`provider`, `model`, and `maxTokens` when the summarizer has a cap). */ async summarize( text: string, agent: Agent, signal?: AbortSignal, - ): Promise<{ summary: ContentBlock[]; model: string; maxTokens?: number }> { + ): Promise<{ summary: ContentBlock[]; provider: string; model: string; maxTokens?: number }> { const assembler = new BlockAssembler() + const logged = agent.session.requestHeader()?.config + const provider = this.config.summarizationProvider || logged?.provider || agent.options.provider || '' + const model = this.config.summarizationModel || logged?.model || agent.options.model || '' const options: GenerateOptions = { - model: this.config.summarizationModel || agent.options.model || '', + provider, + model, messages: [{ role: 'user', content: [{ type: 'text', text: `Summarize this conversation history:\n\n${text}\n\nSummary:` }], @@ -335,8 +339,8 @@ export class BasicCompactService extends CompactService { // exactOptionalPropertyTypes: only set `signal` when present — assigning // `undefined` to an optional `signal?: AbortSignal` is a type error. if (signal) options.signal = signal - if (!options.model) { - throw new Error('no model available for summarization: set BasicCompactConfig.summarizationModel or AgentOptions.model') + if (!options.provider || !options.model) { + throw new Error('no provider/model available for summarization: set both summarization fields or provide a logged/agent target') } for await (const chunk of this.ctx.llm.stream(options)) { assembler.push(chunk) @@ -353,7 +357,7 @@ export class BasicCompactService extends CompactService { // config.maxTokens is required and validated positive, so this backend's // envelope always carries the cap; the return type's optionality exists // for overriding subclasses whose summarizer has none. - return { summary, model: options.model, maxTokens: this.config.maxTokens } + return { summary, provider: options.provider, model: options.model, maxTokens: this.config.maxTokens } } // ---- Core API (implements the abstract contract) ---- @@ -511,7 +515,7 @@ export class BasicCompactService extends CompactService { try { // --- Extract text and summarize --- const text = renderTranscript(session.events, shadowedSeqs) - const { summary, model, maxTokens } = await this.summarize(text, agent, signal) + const { summary, provider, model, maxTokens } = await this.summarize(text, agent, signal) // Estimate token count of the shadowed content for provenance. let shadowedTokenCount = 0 @@ -533,6 +537,7 @@ export class BasicCompactService extends CompactService { shadowedRange: { start, end }, shadowedSeqs, shadowedTokenCount, + provider, model, ...maxTokens !== undefined ? { maxTokens } : {}, }) diff --git a/packages/compact/compact-basic/src/types.ts b/packages/compact/compact-basic/src/types.ts index a590c01431..741412f421 100644 --- a/packages/compact/compact-basic/src/types.ts +++ b/packages/compact/compact-basic/src/types.ts @@ -24,7 +24,9 @@ export interface BasicCompactConfig { thresholdRatio: number /** Number of tokens of recent context to retain during compaction. */ retainTokens: number - /** Model to use for summarization (`''` — uses the agent's model). */ + /** Provider to use for summarization (`''` with an empty model inherits the conversation target). */ + summarizationProvider: string + /** Model to use for summarization (`''` with an empty provider inherits the conversation target). */ summarizationModel: string /** Provider generation cap for the summarization call. */ maxTokens: number @@ -70,6 +72,12 @@ export function resolveConfig(config: BasicCompactConfig): ResolvedConfig { if (typeof resolved.summarizationModel !== 'string') { throw new Error('BasicCompactConfig: summarizationModel must be a string.') } + if (typeof resolved.summarizationProvider !== 'string') { + throw new Error('BasicCompactConfig: summarizationProvider must be a string.') + } + if ((resolved.summarizationProvider.length === 0) !== (resolved.summarizationModel.length === 0)) { + throw new Error('BasicCompactConfig: summarizationProvider and summarizationModel must both be empty or both be set.') + } if (typeof resolved.auto !== 'boolean') { throw new Error('BasicCompactConfig: auto must be a boolean.') } diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index e47ca434e3..71193f6c7f 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -21,6 +21,7 @@ const TEST_CONFIG: BasicCompactConfig = { contextWindow: 128000, thresholdRatio: 0.8, retainTokens: 20480, + summarizationProvider: '', summarizationModel: '', maxTokens: 8192, compactionRetries: 1, @@ -58,13 +59,17 @@ class TestCompactService extends BasicCompactService { return blocks.length * 10 } - override async summarize(text: string, agent: Agent): Promise<{ summary: ContentBlock[]; model: string; maxTokens?: number }> { + override async summarize( + text: string, + agent: Agent, + ): Promise<{ summary: ContentBlock[]; provider: string; model: string; maxTokens?: number }> { + const provider = this.config.summarizationProvider || agent.options.provider || '' const model = this.config.summarizationModel || agent.options.model || '' this.summarizeCalls.push({ text, model }) if (this.summarizeError) throw this.summarizeError const summary = this.mockSummaryQueue.shift() ?? this.mockSummary this.summaryOutputs.add(summary) - return { summary, model } + return { summary, provider, model } } } @@ -102,7 +107,7 @@ function multiTurnSession(turns: number, messagesPerTurn: number = 2, opts: { le content: [{ type: 'text', text: `turn ${t} user message ${m + 1}.${LONG_FIXTURE_TEXT}` }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: t, step: 1, content: [{ type: 'text', text: `turn ${t} assistant response ${m + 1}.${LONG_FIXTURE_TEXT}` }], }, { surfaceOp: 'append' }) @@ -127,7 +132,7 @@ function sessionWithTools(): Session { content: [{ type: 'text', text: 'read file x' }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [ { type: 'text', text: 'Let me read that file.' }, @@ -140,7 +145,7 @@ function sessionWithTools(): Session { content: [{ type: 'text', text: 'hello world' }], isError: false, }, { surfaceOp: 'append' }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'The file contains: hello world' }], }, { surfaceOp: 'append' }) @@ -169,7 +174,7 @@ function toolTurnSession(turns: number): Session { source: { kind: 'user' }, }, { surfaceOp: 'append' }) s.append('step/start', { turn: t, step: 1 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: t, step: 1, content: [ { type: 'text', text: `turn ${t} calling tool` }, @@ -240,7 +245,7 @@ describe('BasicCompactService step-alignment (never split a tool-call/result pai const s = new Session(SessionId('one-step')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'calling' }, { type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], }, { surfaceOp: 'append' }) @@ -286,7 +291,7 @@ describe('BasicCompactService step-alignment (never split a tool-call/result pai s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('user/message', { content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], }, { surfaceOp: 'append' }) @@ -348,7 +353,7 @@ describe('BasicCompactService.estimateEventTokens', () => { const userEvent: SessionEvent = { type: 'user/message', seq: 0, time: 1, data: { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } } } expect(svc.estimateEventTokens(userEvent)).toBe(10) - const asstEvent: SessionEvent = { type: 'assistant/message', seq: 1, time: 2, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }, { type: 'text', text: 'b' }] } } + const asstEvent: SessionEvent = { type: 'assistant/message', seq: 1, time: 2, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }, { type: 'text', text: 'b' }], provenance: { provider: 'mock', model: 'mock' } } } expect(svc.estimateEventTokens(asstEvent)).toBe(20) const toolEvent: SessionEvent = { type: 'tool/result', seq: 2, time: 3, data: { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'output' }], isError: false } } @@ -633,7 +638,7 @@ describe('BasicCompactService.compactIfNeeded', () => { s.append('user/message', { content: [{ type: 'text', text: 'do a big multi-step task' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) for (let step = 1; step <= 5; step++) { s.append('step/start', { turn: 1, step }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step, content: [{ type: 'text', text: `step ${step}` }, { type: 'tool-call', id: CallId(`c${step}`), name: 'bash', arguments: '{}' }], }, { surfaceOp: 'append' }) @@ -686,7 +691,7 @@ describe('BasicCompactService.compactIfNeeded', () => { // the fresh nodes are retained. s.append('step/start', { turn: 5, step: 1 }) s.append('user/message', { content: [{ type: 'text', text: 'turn 5 work' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 5, step: 1, content: [{ type: 'text', text: 'reply 5' }] }, { surfaceOp: 'append' }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 5, step: 1, content: [{ type: 'text', text: 'reply 5' }] }, { surfaceOp: 'append' }) s.append('step/end', { turn: 5, step: 1 }) const second = await compactIfNeeded(svc, s, '', 'm', SIGNAL) @@ -785,7 +790,7 @@ describe('BasicCompactService blocking (compaction in progress)', () => { s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) s.append('user/message', { content: [{ type: 'text', text: 'turn 1' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'reply 1' }] }, { surfaceOp: 'append' }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'reply 1' }] }, { surfaceOp: 'append' }) s.append('compact/start', { turn: 1 }) // ← orphaned: no matching compact/end s.append('step/end', { turn: 1, step: 1 }) s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) // repair closed the turn @@ -991,7 +996,7 @@ async function ctxWithFinish(reason: (StreamChunk & { type: 'finish' })['reason' /** A minimal Agent stub carrying just session + options (enough for the listeners). */ function stubAgent(session: Session, model?: string): Agent { - return { session, options: { model } } as unknown as Agent + return { session, options: { provider: model, model } } as unknown as Agent } function compactIfNeeded( @@ -1076,7 +1081,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { it('throws when no model is provided', async () => { const { ctx } = await ctxWithModel('x') const svc = new BasicCompactService(ctx, cfg({ auto: false })) - await expect(summarize(svc, 'text', '')).rejects.toThrow(/no model available/) + await expect(summarize(svc, 'text', '')).rejects.toThrow(/no provider\/model available/) }) it('rethrows when the stream ends with a finish-error chunk', async () => { @@ -1153,7 +1158,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) session.append('user/message', { content: [{ type: 'text', text: 'tiny user' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'tiny assistant' }] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'tiny assistant' }] }, { surfaceOp: 'append' }) session.append('step/end', { turn: 1, step: 1 }) session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) @@ -1262,9 +1267,10 @@ describe('BasicCompactService auto-compaction (agent/pre-step listener)', () => // The summarize call is a direct one-shot model call, not a loop step: it // does not run agent/request (that seam shapes the loop's conversation // requests). llm/stream is its interception surface, and a hand-built - // request is not frozen, so mutate-then-next model routing works — the - // adapter resolves AFTER the waterfall, so the rewrite picks the adapter. + // request is not frozen, so mutate-then-next provider/model routing works — + // the adapter resolves AFTER the waterfall, so the rewrite picks it. ctx.on('llm/stream', (options, next) => { + options.provider = 'routed-model' options.model = 'routed-model' return next() }) @@ -1307,7 +1313,7 @@ describe('BasicCompactService transcript rendering (delegated to dsh-compact)', content: [{ type: 'text', text: 'project context here' }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'reasoning', text: 'thinking hard' }, { type: 'text', text: 'answer' }], }, { surfaceOp: 'append' }) @@ -1335,7 +1341,7 @@ describe('BasicCompactService transcript rendering (delegated to dsh-compact)', s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) s.append('user/message', { content: [{ type: 'text', text: 'run it' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c9'), name: 'bash', arguments: '{}' }], }, { surfaceOp: 'append' }) @@ -1364,7 +1370,7 @@ describe('BasicCompactService edge cases', () => { // assistant/message carrying a nested tool-result block, an unknown block, // and the tool-call that the following tool/result answers (so the surface // is tool-pairing balanced). - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [ { type: 'tool-result', toolCallId: CallId('n1'), content: [{ type: 'chart', data: 'x' } as unknown as ContentBlock] }, @@ -1427,7 +1433,7 @@ describe('BasicCompactService edge cases', () => { s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) s.append('user/message', { content: [{ type: 'text', text: 'orphan' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'reply' }] }, { surfaceOp: 'append' }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'reply' }] }, { surfaceOp: 'append' }) s.append('step/end', { turn: 1, step: 1 }) s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) const nodes = s.surface.nodes @@ -1522,7 +1528,7 @@ describe('BasicCompactService edge cases', () => { // nothing and are skipped. s.append('step/start', { turn: 1, step: 1 }) s.append('user/message', { content: [{ type: 'text', text: '' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'reasoning', text: '' }] }, { surfaceOp: 'append' }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'reasoning', text: '' }] }, { surfaceOp: 'append' }) s.append('context/message', { content: [], source: { kind: 'user' } }, { surfaceOp: 'append' }) s.append('steering/message', { turn: 1, content: [{ type: 'text', text: '' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) s.append('step/end', { turn: 1, step: 1 }) @@ -1531,7 +1537,7 @@ describe('BasicCompactService edge cases', () => { // surface stays tool-pairing balanced; its text extracts to the tool-call // placeholder (the one surviving line). s.append('step/start', { turn: 1, step: 2 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 2, content: [{ type: 'tool-call', id: CallId('z1'), name: 'bash', arguments: '{}' }], }, { surfaceOp: 'append' }) @@ -1562,7 +1568,7 @@ describe('BasicCompactService edge cases', () => { s.append('user/message', { content: [chart('y')], source: { kind: 'user' } }, { surfaceOp: 'append' }) // assistant/message with a plugin-added block AND the tool-call its // tool/result answers (so the surface is tool-pairing balanced). - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [ chart('z'), @@ -1713,7 +1719,7 @@ describe('BasicCompactService under the real invariants plugin', () => { session.append('turn/start', { turn, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn, step: 1 }) session.append('user/message', { content: [{ type: 'text', text: `turn ${turn} user.${LONG_FIXTURE_TEXT}` }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - session.append('assistant/message', { turn, step: 1, content: [{ type: 'text', text: `turn ${turn} assistant.${LONG_FIXTURE_TEXT}` }] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn, step: 1, content: [{ type: 'text', text: `turn ${turn} assistant.${LONG_FIXTURE_TEXT}` }] }, { surfaceOp: 'append' }) session.append('step/end', { turn, step: 1 }) session.append('turn/end', { turn, reason: { kind: 'completed' } }) } diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index 1efb417b48..acee9036ed 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -41,8 +41,8 @@ class ReproCompactService extends BasicCompactService { return blocks.length * TOKENS_PER_BLOCK } - override async summarize(): Promise<{ summary: ContentBlock[]; model: string }> { - return { summary: [{ type: 'text', text: 'CHECKPOINT SUMMARY' }], model: 'stub' } + override async summarize(): Promise<{ summary: ContentBlock[]; provider: string; model: string }> { + return { summary: [{ type: 'text', text: 'CHECKPOINT SUMMARY' }], provider: 'mock', model: 'stub' } } } @@ -97,6 +97,7 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr contextWindow: 64, thresholdRatio: 0.5, retainTokens: 20, + summarizationProvider: '', summarizationModel: '', maxTokens: 8192, compactionRetries: 1, @@ -119,7 +120,7 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () it('the head checkpoint the loop lands is a balanced cut on both sides', async () => { const { ctx } = await harness(8) try { - const agent = ctx.agentLoop.create(AgentId('repro'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('repro'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'do a long multi-step task' }]) await waitForIdle(ctx, agent) diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index e98f00899f..4c45ec2d6f 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -29,7 +29,7 @@ Both methods are **abstract** — the backend owns the entire strategy (token es 1. appends `compact/start` (log-only) — acquires the lock, 2. summarizes the range, -3. appends `compact/summary` (log-only) — provenance: summary, range, shadowed seqs, token count, +3. appends `compact/summary` (log-only) — provenance: summary, range, shadowed seqs, token count, and provider/model call envelope, 4. appends a single `user/message` with `surfaceOp: { op: 'replace', start, end }` carrying the summary — **the only surface mutation**, 5. appends `compact/end` (log-only) — releases the lock. diff --git a/packages/compact/compact/src/types.ts b/packages/compact/compact/src/types.ts index ba9834910f..0ef28a4ff6 100644 --- a/packages/compact/compact/src/types.ts +++ b/packages/compact/compact/src/types.ts @@ -32,6 +32,8 @@ declare module '@deepseek-ai/dsh-session' { shadowedRange: { start: number; end: number } shadowedSeqs: number[] shadowedTokenCount: number + /** The provider route that wrote the summary. */ + provider: string /** * The model that wrote the summary — the summarize call's envelope, * reported by the backend that made the call, logged so the one-shot diff --git a/packages/compact/compact/tests/compact.spec.ts b/packages/compact/compact/tests/compact.spec.ts index c4daa8cc5a..f272b1fe85 100644 --- a/packages/compact/compact/tests/compact.spec.ts +++ b/packages/compact/compact/tests/compact.spec.ts @@ -41,6 +41,7 @@ class StubCompactService extends CompactService { shadowedRange: { start, end }, shadowedSeqs: [], shadowedTokenCount: 0, + provider: 'mock', model: 'stub', }) const endEvent = session.append('compact/end', { turn: 0 }) diff --git a/packages/compact/compact/tests/render.spec.ts b/packages/compact/compact/tests/render.spec.ts index 1a22296565..3b4bb41ac2 100644 --- a/packages/compact/compact/tests/render.spec.ts +++ b/packages/compact/compact/tests/render.spec.ts @@ -54,7 +54,7 @@ describe('renderTranscript', () => { content: [{ type: 'text', text: 'fix the bug' }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - const assistant = s.append('assistant/message', { + const assistant = s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 0, step: 0, content: [{ type: 'text', text: 'looking' }], }, { surfaceOp: 'append' }) @@ -111,7 +111,7 @@ describe('renderTranscript', () => { content: [{ type: 'text', text: '' }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - const emptyAssistant = s.append('assistant/message', { + const emptyAssistant = s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 0, step: 0, content: [{ type: 'text', text: '' }], }, { surfaceOp: 'append' }) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index b4420e80c7..e3d7665ea6 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -129,8 +129,8 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ key: 'llm', summary: 'The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall.', methods: [ - 'registerAdapter(models: string[], adapter: LlmAdapter): () => void', - 'models(): string[]', + 'registerAdapter(providers: string[], adapter: LlmAdapter): () => void', + 'providers(): string[]', 'stream(options: GenerateOptions): AsyncIterable', ], }, @@ -504,7 +504,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'AgentOptions', - declaration: 'export interface AgentOptions {\n model?: string;\n}', + declaration: 'export interface AgentOptions {\n provider?: string;\n model?: string;\n}', }, { name: 'AgentStatus', @@ -546,6 +546,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'AssembledSection', declaration: 'export interface AssembledSection {\n name: string;\n order: number;\n text: string;\n}', }, + { + name: 'AssistantProvenance', + declaration: 'export interface AssistantProvenance {\n provider: string;\n model: string;\n replayState?: unknown;\n}', + }, { name: 'BashExecRequest', declaration: 'export interface BashExecRequest {\n command: string;\n workdir?: string | undefined;\n timeoutMs?: number | undefined;\n signal?: AbortSignal | undefined;\n stdin?: string | undefined;\n env?: Record | undefined;\n owner?: OwnerToken | undefined;\n sandboxMode?: SandboxMode | undefined;\n}', @@ -712,7 +716,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'GenerateOptions', - declaration: 'export interface GenerateOptions {\n model: string;\n messages: Message[];\n system?: string;\n tools?: ToolSchema[];\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n signal?: AbortSignal;\n sessionId?: Branded<\'SessionId\'>;\n}', + declaration: 'export interface GenerateOptions {\n provider: string;\n model: string;\n messages: Message[];\n system?: string;\n tools?: ToolSchema[];\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n signal?: AbortSignal;\n sessionId?: Branded<\'SessionId\'>;\n}', }, { name: 'GenericCallView', @@ -728,7 +732,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'Message', - declaration: 'export interface Message {\n role: \'system\' | \'user\' | \'assistant\';\n content: ContentBlock[];\n}', + declaration: 'export interface Message {\n role: \'system\' | \'user\' | \'assistant\';\n content: ContentBlock[];\n provenance?: AssistantProvenance;\n}', }, { name: 'MessageSource', @@ -784,7 +788,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SessionEventMap', - declaration: 'export interface SessionEventMap {\n \'turn/start\': {\n turn: number;\n trigger: TurnTrigger;\n };\n \'turn/end\': {\n turn: number;\n reason: TurnEndReason;\n };\n \'step/start\': {\n turn: number;\n step: number;\n };\n \'step/end\': {\n turn: number;\n step: number;\n };\n \'user/message\': {\n content: ContentBlock[];\n source: MessageSource;\n };\n \'prompt/blocked\': {\n content: ContentBlock[];\n source: MessageSource;\n reason: string;\n };\n \'context/message\': {\n content: ContentBlock[];\n source: MessageSource;\n };\n \'assistant/chunk\': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n \'assistant/message\': {\n turn: number;\n step: number;\n content: ContentBlock[];\n usage?: TokenUsage;\n };\n \'tool/call\': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n \'tool/result\': {\n turn: number;\n step: number;\n callId: CallId;\n content: ContentBlock[];\n isError: boolean;\n error?: {\n name: string;\n code: string;\n };\n meta?: unknown;\n };\n \'steering/message\': {\n turn: number;\n content: ContentBlock[];\n source: MessageSource;\n };\n \'todo/write\': {\n todos: TodoItem[];\n };\n \'request/header\': {\n header: E /* …truncated — full shape in source */', + declaration: 'export interface SessionEventMap {\n \'turn/start\': {\n turn: number;\n trigger: TurnTrigger;\n };\n \'turn/end\': {\n turn: number;\n reason: TurnEndReason;\n };\n \'step/start\': {\n turn: number;\n step: number;\n };\n \'step/end\': {\n turn: number;\n step: number;\n };\n \'user/message\': {\n content: ContentBlock[];\n source: MessageSource;\n };\n \'prompt/blocked\': {\n content: ContentBlock[];\n source: MessageSource;\n reason: string;\n };\n \'context/message\': {\n content: ContentBlock[];\n source: MessageSource;\n };\n \'assistant/chunk\': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n \'assistant/message\': {\n turn: number;\n step: number;\n content: ContentBlock[];\n provenance: AssistantProvenance;\n usage?: TokenUsage;\n };\n \'tool/call\': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n \'tool/result\': {\n turn: number;\n step: number;\n callId: CallId;\n content: ContentBlock[];\n isError: boolean;\n error?: {\n name: string;\n code: string;\n };\n meta?: unknown;\n };\n \'steering/message\': {\n turn: number;\n content: ContentBlock[];\n source: MessageSource;\n };\n \'todo/write\': {\n todos: TodoItem[];\n };\n /* …truncated — full shape in source */', }, { name: 'SessionEventType', @@ -836,7 +840,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'StreamChunk', - declaration: 'export type StreamChunk = {\n type: \'block-start\';\n index: number;\n blockType: ContentBlockType;\n} | {\n type: \'text-delta\';\n index: number;\n text: string;\n} | {\n type: \'reasoning-delta\';\n index: number;\n text: string;\n} | {\n type: \'tool-call-delta\';\n index: number;\n id: CallId;\n name?: string;\n argumentsDelta: string;\n} | {\n type: \'block-end\';\n index: number;\n block: ContentBlock;\n} | {\n type: \'usage\';\n usage: TokenUsage;\n} | {\n type: \'finish\';\n reason: FinishReason;\n};', + declaration: 'export type StreamChunk = {\n type: \'block-start\';\n index: number;\n blockType: ContentBlockType;\n} | {\n type: \'text-delta\';\n index: number;\n text: string;\n} | {\n type: \'reasoning-delta\';\n index: number;\n text: string;\n} | {\n type: \'tool-call-delta\';\n index: number;\n id: CallId;\n name?: string;\n argumentsDelta: string;\n} | {\n type: \'block-end\';\n index: number;\n block: ContentBlock;\n} | {\n type: \'usage\';\n usage: TokenUsage;\n} | {\n type: \'finish\';\n reason: FinishReason;\n replayState?: unknown;\n};', }, { name: 'StructuredOutputSchema', @@ -1040,7 +1044,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'WorkflowPhase', - declaration: 'export interface WorkflowPhase {\n title: string;\n detail?: string;\n model?: string;\n}', + declaration: 'export interface WorkflowPhase {\n title: string;\n detail?: string;\n provider?: string;\n model?: string;\n}', }, { name: 'WorkflowResult', diff --git a/packages/cordis/tool-cordis/tests/integration.spec.ts b/packages/cordis/tool-cordis/tests/integration.spec.ts index 94331df7c0..540339bc93 100644 --- a/packages/cordis/tool-cordis/tests/integration.spec.ts +++ b/packages/cordis/tool-cordis/tests/integration.spec.ts @@ -51,7 +51,7 @@ describe('cordis tools through the agent loop', () => { textResponse('Done.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-cordis'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('it-cordis'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'give yourself reverse_text, use it, clean up' }]) await waitForIdle(ctx, agent) diff --git a/packages/core/agent-core/tests/agent-core.spec.ts b/packages/core/agent-core/tests/agent-core.spec.ts index 855bb28d49..54eb102a54 100644 --- a/packages/core/agent-core/tests/agent-core.spec.ts +++ b/packages/core/agent-core/tests/agent-core.spec.ts @@ -108,7 +108,7 @@ describe('dsh-agent-core bundle', () => { it('forwards a pre-created agent to the loop and the persona to system-prompt', async () => { const ctx = await mount({ - agents: [{ id: AgentId('main'), model: 'mock' }], + agents: [{ id: AgentId('main'), provider: 'mock', model: 'mock' }], persona: 'You are main.', }) expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 6832800d2e..0d9e09c687 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -33,6 +33,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo interface Config { agents: Array<{ id: string // required + provider?: string model?: string resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session @@ -40,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` applies only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. A model call requires both `provider` and `model`; a request-waterfall listener may supply the pair before dispatch when they are absent from creation options. `cwd` applies only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `provider`/`model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 4ad4779176..6ecde4f088 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -342,6 +342,7 @@ export class AgentLoop extends Service implements AgentFactory { static Config = z.object({ agents: z.array(z.object({ id: z.string().required(), + provider: z.string(), model: z.string(), cwd: z.string(), resumeSessionId: z.string(), @@ -358,6 +359,7 @@ export class AgentLoop extends Service implements AgentFactory { this.runtime = { ctx } ctx.effect(() => () => this.ownership.dispose(), 'agentLoop.transactions()') ctx.effect(() => ctx.agents.setFactory(this), 'agentLoop.setFactory()') + ctx.systemPrompt.variable('provider', context => context.agent?.options.provider) ctx.systemPrompt.variable('model', context => context.agent?.options.model) ctx.systemPrompt.variable('cwd', context => context.agent?.session.header.cwd) diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 7a7ca2e28c..5c4ab89f05 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -9,6 +9,7 @@ import type { Context } from 'cordis' import type { FinishReason, GenerateOptions, LlmCallConfig, Message } from '@deepseek-ai/dsh-llm' +import { isDeepStrictEqual } from 'node:util' import { BlockAssembler, HarnessError, deepFreeze } from '@deepseek-ai/dsh-llm' import { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' import type { AgentEventDispatch, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' @@ -757,7 +758,7 @@ async function runStep( const seedConfig: LlmCallConfig = deepFreeze(structuredClone(transmission.loggedHeader // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- loggedHeader ⟹ a snapshot is in the log ? session.requestHeader()!.config - : { model: options.model ?? '' })) + : { provider: options.provider ?? '', model: options.model ?? '' })) // Shape the call config: listeners return a replacement to switch model or // sampling (the seed is frozen — content shaping is not expressible here; @@ -765,8 +766,8 @@ async function runStep( // below records whatever the request ACTUALLY uses, so a listener's switch // is a logged, reconstructable fact, never silent drift. const config = await events.waterfall('agent/request', turn, step, seedConfig, () => Promise.resolve(seedConfig)) - if (!config.model) { - throw new Error(`agent "${agent.id}" has no model: set AgentOptions.model or supply one via the agent/request waterfall`) + if (!config.provider || !config.model) { + throw new Error(`agent "${agent.id}" has no provider/model: set AgentOptions.provider and AgentOptions.model or supply both via the agent/request waterfall`) } // The session prefix was composed (once per instance) before this step's @@ -791,6 +792,7 @@ async function runStep( // keys on. Message order: header.messagePrefix, then the boundary // snapshot — the reconstruction equation the invariant recomputes. const request: GenerateOptions = deepFreeze({ + provider: header.config.provider, model: header.config.model, messages: [...header.messagePrefix ?? [], ...boundaryMessages], ...header.system !== undefined ? { system: header.system } : {}, @@ -822,7 +824,8 @@ async function runStep( if (stepError) throw stepError if (assembler.finish.kind === 'max-tokens') { - let message: Message = withoutToolCalls(assembler.message()) + const assembled = assembler.message() + let message: Message = withoutToolCalls(assembled) message = withoutToolCalls(await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message))) // Fire the assistant/message when there is content OR usage: a max-tokens // step can be cut off with empty content but still carry token accounting, @@ -830,22 +833,15 @@ async function runStep( // usage event). An empty-content assistant/message is skipped by // deriveMessages(), so hosting usage on it never injects a spurious assistant // turn into derived history. - if (message.content.length > 0 || assembler.usage) { - // A max-tokens finish is itself a streamed `finish` chunk, so chunkSeqs is - // never empty here — pass the provenance unconditionally. - session.append( - 'assistant/message', - { turn, step, content: message.content, ...(assembler.usage ? { usage: assembler.usage } : {}) }, - { surfaceOp: 'append', sourceEventSeqs: chunkSeqs }, - ) - } + recordAssistantMessage(session, turn, step, header.config, assembled, message, assembler, chunkSeqs) return { hadToolCalls: false, finish: assembler.finish } } // The step-result waterfall runs BEFORE the session append so the log (the // source of truth for derived history and replay) records the message that // tool dispatch actually uses. - let message: Message = assembler.message() + const assembled = assembler.message() + let message: Message = assembled message = await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message)) // Same content-or-usage guard as the max-tokens branch: a step that finishes @@ -856,13 +852,7 @@ async function runStep( // // sourceEventSeqs records the assistant/chunk provenance, but is omitted when // no chunks streamed (the surface invariant rejects an empty sourceEventSeqs). - if (message.content.length > 0 || assembler.usage) { - session.append( - 'assistant/message', - { turn, step, content: message.content, ...(assembler.usage ? { usage: assembler.usage } : {}) }, - { surfaceOp: 'append', ...(chunkSeqs.length > 0 ? { sourceEventSeqs: chunkSeqs } : {}) }, - ) - } + recordAssistantMessage(session, turn, step, header.config, assembled, message, assembler, chunkSeqs) // --- Tool execution (sequential; parallel execution is a TODO) --- // ToolRegistry.execute converts tool failures (including aborts) into @@ -933,6 +923,44 @@ async function runStep( return { hadToolCalls: toolCalls.length > 0, finish: assembler.finish } } +/** Record one content-or-usage assistant message with replay-safe provenance. */ +function recordAssistantMessage( + session: Session, + turn: number, + step: number, + config: LlmCallConfig, + assembled: Message, + message: Message, + assembler: BlockAssembler, + chunkSeqs: number[], +): void { + if (message.content.length === 0 && assembler.usage === undefined) return + session.append( + 'assistant/message', + { + turn, + step, + content: message.content, + provenance: assistantProvenance( + config, + assembler.replayState, + isDeepStrictEqual(message.content, assembled.content), + ), + ...assembler.usage === undefined ? {} : { usage: assembler.usage }, + }, + { surfaceOp: 'append', ...chunkSeqs.length > 0 ? { sourceEventSeqs: chunkSeqs } : {} }, + ) +} + +/** Build durable assistant provenance, dropping replay state after any content rewrite. */ +function assistantProvenance(config: LlmCallConfig, replayState: unknown, contentUnchanged: boolean): NonNullable { + return { + provider: config.provider, + model: config.model, + ...contentUnchanged && replayState !== undefined ? { replayState } : {}, + } +} + function withoutToolCalls(message: Message): Message { return { ...message, content: message.content.filter(block => block.type !== 'tool-call') } } diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 7f65bbc5f3..3d42e8e088 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -53,10 +53,10 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('exclusive-driver')) - const prepared = prepareReactLoopAgent(ctx, AgentId('first-driver'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, AgentId('first-driver'), { provider: 'mock', model: 'mock' }, session) expect(() => prepared.agent.ctx).toThrow('context is not bound') - expect(() => prepareReactLoopAgent(ctx, AgentId('second-driver'), { model: 'mock' }, session)) + expect(() => prepareReactLoopAgent(ctx, AgentId('second-driver'), { provider: 'mock', model: 'mock' }, session)) .toThrow('already has a concrete agent driver') await prepared.dispose() @@ -65,7 +65,7 @@ describe('ReactLoopAgent', () => { it('borrows caller options and binds its scoped context exactly once', async () => { const ctx = await harness(new MockAdapter([textResponse('unused')])) - const options = { model: 'mock' } + const options = { provider: 'mock', model: 'mock' } const agent = ctx.agentLoop.create(AgentId('owned-bindings'), options) expect(agent.options).toBe(options) @@ -81,7 +81,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -96,7 +96,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -111,7 +111,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -124,7 +124,7 @@ describe('ReactLoopAgent', () => { it('inject() decides enclosure from the LOG (open turn), not agent status', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Simulate an OPEN turn in the log while the agent is idle (status is not a // reliable open-turn signal). inject must append into that open turn, NOT @@ -150,7 +150,7 @@ describe('ReactLoopAgent', () => { // A persistence-like listener whose flush rejects. ctx.on('session/flush', () => { throw new Error('disk gone') }) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // inject() is synchronous and fires a fire-and-forget flush; a rejecting // flush must be contained (logged), never thrown into the caller. @@ -163,7 +163,7 @@ describe('ReactLoopAgent', () => { it('idle inject() closes its one-shot turn AND still checkpoints even if the append throws', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) @@ -183,7 +183,7 @@ describe('ReactLoopAgent', () => { it('idle inject() still checkpoints when a listener throws on the synthetic turn/end', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) // Session contains a throwing post-commit turn/end observer. The accepted @@ -206,7 +206,7 @@ describe('ReactLoopAgent', () => { // A non-Error rejection exercises the String() normalization branch. ctx.on('session/flush', () => { throw 'disk gone' }) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const errors: { turn: number; step: number; message: string }[] = [] ctx.on('agent/error', (_a, turn, step, error) => void errors.push({ turn, step, message: error.message })) @@ -225,7 +225,7 @@ describe('ReactLoopAgent', () => { it('idle inject() with a non-serializable source opens no turn (nothing to close)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // A non-serializable source makes the turn/start append throw BEFORE the // event is pushed (Session.append validates before push), so NO turn opens. @@ -240,7 +240,7 @@ describe('ReactLoopAgent', () => { it('steer() when idle falls through to send() and starts a turn', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // steer while idle delegates to send agent.steer([{ type: 'text', text: 'steer idle' }], { source: { kind: 'plugin', plugin: 'test' } }) @@ -258,7 +258,7 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('test')) - const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session) const { agent } = prepared // Start the loop to get the disposer; the agent waits for messages @@ -280,7 +280,7 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('pre-start-dispose')) - const prepared = prepareReactLoopAgent(ctx, AgentId('pre-start-dispose'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, AgentId('pre-start-dispose'), { provider: 'mock', model: 'mock' }, session) await prepared.dispose() expect(prepared.agent.status).toBe('disposed') @@ -294,7 +294,7 @@ describe('ReactLoopAgent', () => { it('setting the same status does not emit agent/status again', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const statuses: string[] = [] ctx.on('agent/status', (subject, status) => { @@ -313,7 +313,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() resolves immediately when the agent is not running', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Fresh agent is idle — whenIdle() takes the not-running fast path and // resolves without subscribing. await must not hang. @@ -324,7 +324,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() waits for queued work that has not flipped status yet', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'queued') let settled = false @@ -342,8 +342,8 @@ describe('ReactLoopAgent', () => { it('whenIdle() awaits the running→idle transition, ignoring other subjects/running events', async () => { const adapter = new MockAdapter([textResponse('ok'), textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - const other = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const other = ctx.agentLoop.create(AgentId('a2'), { provider: 'mock', model: 'mock' }) // Drive `agent` into `running`, then await whenIdle() — it subscribes to // agent/status and resolves on the first transition out of running. @@ -379,7 +379,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter(['hang']) ctx.llm.registerAdapter(['mock'], adapter) const session = ctx.sessions.create(SessionId('bare')) - const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session) const { agent } = prepared prepared.markPublished() const dispose = prepared.startDriver() @@ -404,7 +404,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -425,7 +425,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -446,7 +446,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/status', (_subject, status) => { if (status === 'running') throw new Error('bad running listener') }) @@ -464,7 +464,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/status', (_subject, status) => { if (status === 'idle') throw new Error('bad idle listener') }) diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index 56376b69a7..25e90326cf 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -57,7 +57,7 @@ describe('Agent.cancel()', () => { it('cancel() on an idle agent with nothing queued is a no-op; the next prompt runs (F2 leak guard)', async () => { const adapter = new MockAdapter([textResponse('reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // The loop is parked at the idle wait with nothing queued. A cancel here must // NOT arm the marker — otherwise the next legitimate prompt would be dropped. @@ -74,7 +74,7 @@ describe('Agent.cancel()', () => { it('pre-step cancel drops the about-to-start turn (no turn is opened)', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // send() queues synchronously (status still idle, loop microtask not yet // resumed). Cancel in that pre-step window: the queued turn must not run. @@ -93,7 +93,7 @@ describe('Agent.cancel()', () => { it('a whenIdle() waiter registered BEFORE a pre-step cancel resolves (F1 hang guard)', async () => { const adapter = new MockAdapter([textResponse('x')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Queue work, then register a whenIdle() waiter while in the pre-step window // (status idle, hasQueued true) — it does NOT take the fast path. Then cancel. @@ -114,7 +114,7 @@ describe('Agent.cancel()', () => { it('cancel() mid-step aborts the in-flight model call; the turn ends aborted', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -131,7 +131,7 @@ describe('Agent.cancel()', () => { it('cancel() with no reason defaults to "cancelled" when aborting an in-flight step', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -147,7 +147,7 @@ describe('Agent.cancel()', () => { it('a prompt sent AFTER a cancelled turn settles runs normally (marker reset)', async () => { const adapter = new MockAdapter(['hang', textResponse('second reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // First turn hangs; cancel it mid-step. send(agent, 'first') @@ -169,7 +169,7 @@ describe('Agent.cancel()', () => { it('cancel from inside the agent/session-prefix waterfall drops the step (prefix-composition window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Prefix composition runs before the pre-step seam on the instance's first // step; a cancel landing inside it must drop the about-to-start step @@ -205,7 +205,7 @@ describe('Agent.cancel()', () => { const handle = await ctx.agents.create({ agentId: AgentId('a-dispose-prefix'), sessionId: SessionId('dispose-prefix-session'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const agent = handle.agent as ReactLoopAgent @@ -232,7 +232,7 @@ describe('Agent.cancel()', () => { it('a cancel-interrupted prefix composition is discarded: the next send recomposes and ships the fresh prefix (stale-cache guard)', async () => { const adapter = new MockAdapter([textResponse('reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // The first composition is interrupted mid-waterfall and — like an // abort-aware listener bailing on a firing signal — contributes nothing. @@ -266,7 +266,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous turn/start session-event listener drops the step (step-start window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // A turn/start listener fires right after turn/start is appended, BEFORE any // AbortController is installed for the step. Cancelling there must still drop @@ -295,7 +295,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous step/start session-event listener drops the step (post-step-start window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // A step/start session-event listener fires AFTER step/start is appended // (and after the pre-step seam), so cancelling there lands in the SECOND @@ -336,7 +336,7 @@ describe('Agent.cancel()', () => { const handle = await ctx.agents.create({ agentId: AgentId('a-dispose-step-start'), sessionId: SessionId('dispose-step-start-session'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const agent = handle.agent as ReactLoopAgent @@ -366,7 +366,7 @@ describe('Agent.cancel()', () => { // `aborted` and run NO second step. const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let steps = 0 const reasons: TurnEndReason[] = [] @@ -398,7 +398,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous agent/status(running) listener drops the turn (window 2)', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // setStatus('running') emits agent/status SYNCHRONOUSLY, so a running // listener can cancel in the gap between the loop's pre-step check and @@ -428,7 +428,7 @@ describe('Agent.cancel()', () => { // so whenIdle() resolves on the replacement turn's running→idle, not before. const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let replaced = false const dispose = ctx.on('agent/status', (subject, status) => { @@ -458,7 +458,7 @@ describe('Agent.cancel()', () => { // settle (the quiescence contract), not resolve before B's first event. const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'A') // queues A (status still idle, loop microtask pending) const idle = agent.whenIdle() // registers a waiter (idle + hasQueued → no fast path) @@ -478,7 +478,7 @@ describe('Agent.cancel()', () => { it("cancel clears the turn's steering — it is not re-enqueued as a fresh turn", async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 07d6cd9e9b..cc30906707 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -32,7 +32,7 @@ describe('config-driven session id', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) const loopFiber = await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('deferred') }], + agents: [{ id: AgentId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('deferred') }], }) const resumeEffect = loopFiber.getEffects().find(effect => effect.label === 'agentLoop.resume(main)') @@ -53,7 +53,7 @@ describe('config-driven session id', () => { await ctx1.plugin(SystemPrompt) await ctx1.plugin(ToolRegistry) await ctx1.plugin(AgentRegistry) - await ctx1.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] }) + await ctx1.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), provider: 'mock', model: 'mock' }] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg')])) const a1 = ctx1.agents.get(AgentId('cfg')) as ReactLoopAgent @@ -70,7 +70,7 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] }) + await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), provider: 'mock', model: 'mock' }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg2')])) const a2 = ctx2.agents.get(AgentId('cfg')) as ReactLoopAgent @@ -110,7 +110,7 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) + await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')])) @@ -138,7 +138,7 @@ describe('config-driven session id', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) + await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) const warn = vi.spyOn((ctx.agentLoop as unknown as { ctx: { logger: { warn: (...a: unknown[]) => void } } }).ctx.logger, 'warn') .mockImplementation(() => undefined) await ctx.plugin(SessionPersistenceJsonl, { root }) diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index 23e5670f85..bd1e528f0a 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -40,7 +40,7 @@ describe('inbox acceptance', () => { it('rejects non-serializable content or source synchronously before notification or enqueue', async () => { const adapter = new MockAdapter([textResponse('turn 1')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let queued = 0 ctx.on('agent/queued', () => { queued += 1 }) @@ -80,7 +80,7 @@ describe('tool JSON parse', () => { return [{ type: 'text', text: typeof args === 'string' ? `raw: ${args}` : JSON.stringify(args) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -113,7 +113,7 @@ describe('tool JSON parse', () => { return [{ type: 'text', text: 'ran with empty args' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -126,7 +126,7 @@ describe('toError normalization', () => { it('normalizes non-Error throws from pre-commit dispatch validation via the runLoop backstop', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let threwOnce = false ctx.on('internal/dispatch', (_mode, name, args) => { @@ -152,7 +152,7 @@ describe('toError normalization', () => { it('normalizes non-Error throws from agent/request waterfall via inline toError in runStep catch', async () => { const adapter = new MockAdapter([textResponse('irrelevant')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let threwOnce = false ctx.on('agent/request', async (_agent, _turn, _step, _options, _next) => { @@ -180,7 +180,7 @@ describe('coded error data emission', () => { it('errorData includes code when a coded error (LlmError) is thrown from a plugin', async () => { const adapter = new MockAdapter([textResponse('turn 1')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let threwOnce = false ctx.on('agent/request', async (_agent, _turn, _step, _options, next) => { @@ -214,7 +214,7 @@ describe('disposed vs aborted branching', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -242,7 +242,7 @@ describe('structured tool error propagation (the runtime-validation RFC, part 2) textResponse('done'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'boom', description: 'always fails', diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index d4ec6312ba..6ba2b02b41 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -57,7 +57,7 @@ describe('agent/prompt-submit', () => { it('allow (default via next) records the user/message unchanged', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const seen: string[] = [] ctx.on('agent/prompt-submit', async (_agent, content, _source, next) => { @@ -76,7 +76,7 @@ describe('agent/prompt-submit', () => { it('allow with content REWRITES the prompt before it is recorded', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ kind: 'allow', content: [{ type: 'text', text: 'REWRITTEN' }] })) @@ -94,7 +94,7 @@ describe('agent/prompt-submit', () => { it('allow with additionalContext injects a separate context/message into the turn', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ @@ -127,7 +127,7 @@ describe('agent/prompt-submit', () => { // elsewhere; this asserts they see each other's effects on the same turn). const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ @@ -157,7 +157,7 @@ describe('agent/prompt-submit', () => { it('block drops the (only) prompt → zero-step turn ends rejected, model never called', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ kind: 'block', reason: 'blocked by policy' })) @@ -194,7 +194,7 @@ describe('agent/prompt-submit', () => { // vetoed prompt and its reason would vanish from the log entirely. const adapter = new MockAdapter([textResponse('ran once')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/prompt-submit', async (_agent, content, _source, next): Promise => { const text = content.map(b => (b.type === 'text' ? b.text : '')).join('') @@ -230,7 +230,7 @@ describe('agent/prompt-submit', () => { it('a throwing prompt-submit listener ends the turn balanced (error), loop survives', async () => { const adapter = new MockAdapter([textResponse('after')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('agent/prompt-submit', async () => { @@ -263,7 +263,7 @@ describe('agent/session-start', () => { const sources: SessionStartSource[] = [] ctx.on('agent/session-start', (_agent, source) => void sources.push(source)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // fires synchronously at create, before any turn expect(sources).toEqual(['startup']) expect(events(agent).some(e => e.type === 'turn/start')).toBe(false) @@ -282,7 +282,7 @@ describe('agent/session-start', () => { agent.inject([{ type: 'text', text: 'session preamble' }], { source: { kind: 'plugin', plugin: 'test' } }) }) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -300,7 +300,7 @@ describe('agent/session-start', () => { ctx.on('agent/session-start', () => { throw new Error('session-start hook broke') }) // create must not throw — the listener error is contained/logged - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) expect(agent.id).toBe(AgentId('a1')) // and the agent still runs @@ -314,8 +314,8 @@ describe('agent/session-prefix', () => { it('dispatches to global and matching agent-scope listeners only', async () => { const adapter = new MockAdapter([textResponse('a done'), textResponse('b done')]) const ctx = await harness(adapter) - const agentA = ctx.agentLoop.create(AgentId('prefix-a'), { model: 'mock' }) - const agentB = ctx.agentLoop.create(AgentId('prefix-b'), { model: 'mock' }) + const agentA = ctx.agentLoop.create(AgentId('prefix-a'), { provider: 'mock', model: 'mock' }) + const agentB = ctx.agentLoop.create(AgentId('prefix-b'), { provider: 'mock', model: 'mock' }) const seen: string[] = [] ctx.on('agent/session-prefix', async (agent, _prefix, _signal, next) => { seen.push(`global:${agent.id}`) @@ -352,7 +352,7 @@ describe('agent/session-prefix', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'catalog' }] } let composed = 0 @@ -385,7 +385,7 @@ describe('agent/session-prefix', () => { it('composes before the first pre-step and hands the prefix to the seam (pressure gates see the real value)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'opener' }] } const order: string[] = [] @@ -412,7 +412,7 @@ describe('agent/session-prefix', () => { it('the canonical prepend pattern composes contributions in registration order', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Both listeners use the canonical `[mine, ...await next()]` prepend: the // waterfall unwinds innermost-first (the second listener's array is built @@ -434,7 +434,7 @@ describe('agent/session-prefix', () => { it('with no contributions the header omits messagePrefix and the request is the bare derivation', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // A listener that delegates without contributing — the canonical no-op. ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => next()) @@ -450,7 +450,7 @@ describe('agent/session-prefix', () => { it('the frozen seed rejects in-place mutation — a contribution is a returned extension', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let mutationError: unknown ctx.on('agent/session-prefix', async (_agent, prefix, _signal, next): Promise => { @@ -479,7 +479,7 @@ describe('agent/session-prefix', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const held: Message = { role: 'user', content: [{ type: 'text', text: 'v1' }] } ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise => [...await next(), held]) @@ -500,7 +500,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => { it('a continue decision with a reason records next-step steering in the same turn', async () => { const adapter = new MockAdapter([textResponse('step 1 no tools'), textResponse('step 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let forced = false ctx.on('agent/turn-continuation', async (_agent, _turn, _default, next): Promise => { @@ -533,7 +533,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/turn-continuation', async (): Promise => ({ action: 'stop' })) @@ -563,7 +563,7 @@ describe('tools/post-execute additionalContext buffering across a multi-call ste name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Each call attaches additionalContext naming itself. ctx.on('tools/post-execute', async (exec, _result): Promise => @@ -599,7 +599,7 @@ describe('tools/pre-execute gate (native-plugin permission pattern, end-to-end t name: 'danger', description: 'danger', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('tools/pre-execute', async (exec, next): Promise => { if (exec.name === 'danger') return { kind: 'deny', reason: 'blocked dangerous tool' } @@ -663,7 +663,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'please echo hi') await waitForIdle(ctx, agent) @@ -686,7 +686,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) await ctx.plugin(NativeGuard) - const agent = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a2'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event: SessionEvent) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -705,7 +705,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se await fiber.dispose() // After disposal, a destructive prompt is NOT blocked (the listener is gone). - const agent = ctx.agentLoop.create(AgentId('a3'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a3'), { provider: 'mock', model: 'mock' }) send(agent, 'run rm -rf /') await waitForIdle(ctx, agent) // the prompt ran (not rejected) — proving the prompt-submit listener was disposed diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index 71be5b339e..0e9ce85ac9 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -44,7 +44,7 @@ describe('agent loop', () => { it('runs a simple turn: queued message → model → idle, with ordered events', async () => { const adapter = new MockAdapter([textResponse('hello there')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // All boundaries — turn and step — are durable session events on the // session/event feed (no agent/* mirror). Record them in fire order to @@ -92,7 +92,7 @@ describe('agent loop', () => { return [{ type: 'text', text: `echo: ${args.text}` }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -131,7 +131,7 @@ describe('agent loop', () => { return { content: [{ type: 'text', text: 'ok' }], meta: { diffs: [{ path: 'a.txt', oldText: null, newText: 'x' }] } } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -155,7 +155,7 @@ describe('agent loop', () => { return [] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -172,7 +172,7 @@ describe('agent loop', () => { agentId: AgentId('a-cwd'), sessionId: SessionId('s-cwd'), meta: { cwd: '/work/space' }, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const agent = handle.agent as ReactLoopAgent @@ -192,7 +192,7 @@ describe('agent loop', () => { const ctx = await harness(adapter, 'In {{cwd}}.') const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -227,11 +227,12 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter, 'You run on {{model}}.') ctx.on('system-prompt/assemble', async (assembly, _context, next) => { + assembly.variables['provider'] = 'mock' assembly.variables['model'] = 'mock' return next() }) ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { - return { ...config, model: 'mock' } + return { ...config, provider: 'mock', model: 'mock' } }) const agent = ctx.agentLoop.create(AgentId('a-late-model'), {}) @@ -259,7 +260,7 @@ describe('agent loop', () => { parameters: {}, execute: () => Promise.resolve({ content: [{ type: 'text' as const, text: 'apparent success' }], meta }), })) - const agent = ctx.agentLoop.create(AgentId('bad-meta-agent'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('bad-meta-agent'), { provider: 'mock', model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -288,7 +289,7 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) ctx.on('system-prompt/assemble', async () => ({ sections: [], tools: [], variables: {} })) - const agent = ctx.agentLoop.create(AgentId('a-no-system'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-no-system'), { provider: 'mock', model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -300,7 +301,7 @@ describe('agent loop', () => { it('records raw chunks for replay as assistant/chunk session events', async () => { const adapter = new MockAdapter([textResponse('abc')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -324,7 +325,7 @@ describe('agent loop', () => { ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'slow', description: '', @@ -356,7 +357,7 @@ describe('agent loop', () => { it('steering while idle behaves like send (starts a turn)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.steer([{ type: 'text', text: 'hello' }]) await waitForIdle(ctx, agent) @@ -366,7 +367,7 @@ describe('agent loop', () => { it('inject() while idle wraps context in a one-shot turn, visible to the next request', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.inject([{ type: 'text', text: 'file changed: a.ts' }], { source: { kind: 'plugin', plugin: 'watcher' } }) // The idle inject records a self-contained turn (turn/start → context/message @@ -393,7 +394,7 @@ describe('agent loop', () => { textResponse('done'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // A tool that injects mid-execution: at this point the agent is running, so // inject must append the context/message into the ALREADY-open turn rather // than wrap it in its own one-shot turn. @@ -427,7 +428,7 @@ describe('agent loop', () => { textResponse('step 3'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let steps = 0 ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ }) @@ -453,7 +454,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/turn-continuation', async () => ({ action: 'stop' }) as const) @@ -468,8 +469,7 @@ describe('agent loop', () => { it('agent/request waterfall switches models by returning a replacement config; the switch is logged', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - ctx.llm.registerAdapter(['other-model'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { // The seed is frozen — config is not a mutable per-call knob; a switch @@ -502,7 +502,7 @@ describe('agent loop', () => { name: 'echo', description: 'echo', parameters: {}, async execute() { return [{ type: 'text', text: 'echoed' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const fires: { turn: number; step: number; fullSystemPrompt: string }[] = [] ctx.on('agent/pre-step', (subject, turn, step, fullSystemPrompt) => { @@ -527,7 +527,7 @@ describe('agent loop', () => { // the derived request for that step (derive happens after step/start). const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let injected = false ctx.on('agent/pre-step', (subject) => { @@ -563,7 +563,7 @@ describe('agent loop', () => { // The loop survives and a follow-up prompt still runs. const adapter = new MockAdapter([textResponse('second turn ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let throwOnce = true ctx.on('agent/pre-step', () => { @@ -597,7 +597,7 @@ describe('agent loop', () => { it('cancel() mid-stream ends the turn with reason aborted', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -617,7 +617,7 @@ describe('agent loop', () => { // turn stops by default and ends max-tokens, not completed. const adapter = new MockAdapter([maxTokensResponse('truncat')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -642,7 +642,7 @@ describe('agent loop', () => { textResponse('second half'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let steps = 0 ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ }) @@ -663,7 +663,7 @@ describe('agent loop', () => { expect(adapter.requests).toHaveLength(2) expect(adapter.requests[1]!.messages).toEqual([ { role: 'user', content: [{ type: 'text', text: 'go' }] }, - { role: 'assistant', content: [{ type: 'text', text: 'first half' }] }, + { role: 'assistant', content: [{ type: 'text', text: 'first half' }], provenance: { provider: 'mock', model: 'mock' } }, ]) expect(reasons).toEqual([{ kind: 'max-tokens' }]) }) @@ -673,7 +673,7 @@ describe('agent loop', () => { // stop. The per-turn reason must be independent — turn 2 ends completed. const adapter = new MockAdapter([maxTokensResponse('cut'), textResponse('clean')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -706,7 +706,7 @@ describe('agent loop', () => { return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -725,7 +725,7 @@ describe('agent loop', () => { // the derived history above is NOT corrupted by a spurious assistant turn. const assistantMessage = agent.session.events.find(e => e.type === 'assistant/message') expect(assistantMessage?.type === 'assistant/message' && assistantMessage.data).toEqual({ - turn: 1, step: 1, content: [], usage: { inputTokens: 10, outputTokens: 5 }, + turn: 1, step: 1, content: [], provenance: { provider: 'mock', model: 'mock' }, usage: { inputTokens: 10, outputTokens: 5 }, }) }) @@ -748,7 +748,7 @@ describe('agent loop', () => { parameters: { text: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -767,7 +767,7 @@ describe('agent loop', () => { // on the normal step path suppresses a pure trace-only empty assistant/message. const adapter = new MockAdapter([[{ type: 'finish', reason: { kind: 'stop' } }]]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -797,7 +797,7 @@ describe('agent loop', () => { expect(message.content).toEqual([{ type: 'text', text: 'partial text' }]) return next() }) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -806,7 +806,7 @@ describe('agent loop', () => { expect(agent.session.events.some(e => e.type === 'tool/call')).toBe(false) expect(agent.session.deriveMessages()).toEqual([ { role: 'user', content: [{ type: 'text', text: 'go' }] }, - { role: 'assistant', content: [{ type: 'text', text: 'partial text' }] }, + { role: 'assistant', content: [{ type: 'text', text: 'partial text' }], provenance: { provider: 'mock', model: 'mock' } }, ]) }) @@ -824,7 +824,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let threw = false // Post-commit session observers cannot control the loop. The tool call still // drives the second model request, and the turn completes normally. @@ -843,7 +843,7 @@ describe('agent loop', () => { it('chains queued messages into consecutive turns', async () => { const adapter = new MockAdapter([textResponse('first'), textResponse('second')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const turns: number[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/start') turns.push(event.data.turn) }) @@ -868,7 +868,7 @@ describe('agent loop', () => { it('awaits session/flush at turn end (persistence checkpoint)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let flushed = 0 let flushedBeforeIdle = false @@ -888,7 +888,7 @@ describe('agent loop', () => { it('errors from the model surface as agent/error and end the turn', async () => { const adapter = new MockAdapter([]) // script exhausted → throws const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const errors: Error[] = [] const reasons: TurnEndReason[] = [] @@ -913,7 +913,7 @@ describe('agent loop', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) expect(ctx.agents.get(AgentId('scoped'))).toBe(agent) @@ -938,7 +938,7 @@ describe('agent loop', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('config-agent'), model: 'mock' }], + agents: [{ id: AgentId('config-agent'), provider: 'mock', model: 'mock' }], }) ctx.llm.registerAdapter(['mock'], adapter) @@ -961,7 +961,7 @@ describe('agent loop', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('config-agent'), model: 'mock', cwd: '/work/project' }], + agents: [{ id: AgentId('config-agent'), provider: 'mock', model: 'mock', cwd: '/work/project' }], }) const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent @@ -982,7 +982,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'run') await waitForIdle(ctx, agent) diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index 1e603a1cc4..ddb401ea08 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -95,7 +95,7 @@ describe('agent loop scheduling properties', () => { async (texts) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' }) const { seen: trace } = recordStatus(ctx, agent) const idle = nextIdle(ctx, agent) // Send all in one synchronous tick: they queue before the loop wakes. @@ -120,7 +120,7 @@ describe('agent loop scheduling properties', () => { async (texts) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' }) for (const text of texts) { const idle = nextIdle(ctx, agent) agent.send([{ type: 'text', text }]) @@ -145,7 +145,7 @@ describe('agent loop scheduling properties', () => { async (steps) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' }) // Capture an idle waiter before EACH send; the last one is guaranteed // to resolve because the final send always triggers (or joins) a turn // that ends idle. Awaiting an already-resolved waiter is a no-op, so a diff --git a/packages/core/agent-loop/tests/request-cache.e2e.ts b/packages/core/agent-loop/tests/request-cache.e2e.ts index 5ccaa7e797..08b6491cc0 100644 --- a/packages/core/agent-loop/tests/request-cache.e2e.ts +++ b/packages/core/agent-loop/tests/request-cache.e2e.ts @@ -45,7 +45,7 @@ async function loopHarness(): Promise { await created.plugin(ToolRegistry) await created.plugin(AgentRegistry) await created.plugin(AgentLoop, { agents: [] }) - await created.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) + await created.plugin(LlmDeepSeek) created.tools.register(defineTool({ name: 'lookup', description: 'Look up the stored value for a key.', @@ -71,7 +71,7 @@ function waitForIdle(context: Context, agent: Agent): Promise { describe.skipIf(!process.env.DEEPSEEK_API_KEY)('log-derived request cache hits (real API)', () => { it('every request after the first hits the provider prefix cache', async () => { ctx = await loopHarness() - const agent = ctx.agentLoop.create(AgentId('cache-e2e'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('cache-e2e'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) // Turn 1: forces a tool call → at least two steps (two model requests). agent.send([{ type: 'text', text: 'Look up the key "deploy-color" with the lookup tool and tell me the value.' }]) diff --git a/packages/core/agent-loop/tests/request-log.spec.ts b/packages/core/agent-loop/tests/request-log.spec.ts index a6befde84e..912a13892c 100644 --- a/packages/core/agent-loop/tests/request-log.spec.ts +++ b/packages/core/agent-loop/tests/request-log.spec.ts @@ -30,7 +30,7 @@ describe('recordRequestHeader', () => { it("anchors a new conversation with an 'initial' snapshot, then logs nothing while unchanged", () => { const session = openSession('rl-initial') const state = createTransmissionLog() - const header = canonicalHeader({ config: { model: 'm' }, system: 's', tools: [tool('t')] }) + const header = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 's', tools: [tool('t')] }) recordRequestHeader(session, state, header) const [first] = headerEvents(session) @@ -42,7 +42,7 @@ describe('recordRequestHeader', () => { it("anchors a fresh loop instance over an anchored log with a 'resume' snapshot, even unchanged", () => { const session = openSession('rl-resume') - const header = canonicalHeader({ config: { model: 'm' }, system: 's' }) + const header = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 's' }) recordRequestHeader(session, createTransmissionLog(), header) // A second instance (process restart / fork): the boundary itself is a @@ -56,10 +56,10 @@ describe('recordRequestHeader', () => { it('logs a round-tripping delta for a mid-run change, and the fold reproduces the header', () => { const session = openSession('rl-delta') const state = createTransmissionLog() - const first = canonicalHeader({ config: { model: 'm' }, system: 'a\nb', tools: [tool('t')] }) + const first = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 'a\nb', tools: [tool('t')] }) recordRequestHeader(session, state, first) - const second = canonicalHeader({ config: { model: 'm' }, system: 'a\nc', tools: [tool('t'), tool('u')] }) + const second = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 'a\nc', tools: [tool('t'), tool('u')] }) recordRequestHeader(session, state, second) const events = headerEvents(session) expect(events).toHaveLength(2) @@ -70,10 +70,10 @@ describe('recordRequestHeader', () => { it("records a change the delta cannot express (pure reordering) as a 'fallback' snapshot", () => { const session = openSession('rl-fallback') const state = createTransmissionLog() - const first = canonicalHeader({ config: { model: 'm' }, tools: [tool('a'), tool('b')] }) + const first = canonicalHeader({ config: { provider: 'mock', model: 'm' }, tools: [tool('a'), tool('b')] }) recordRequestHeader(session, state, first) - const reordered = canonicalHeader({ config: { model: 'm' }, tools: [tool('b'), tool('a')] }) + const reordered = canonicalHeader({ config: { provider: 'mock', model: 'm' }, tools: [tool('b'), tool('a')] }) recordRequestHeader(session, state, reordered) const events = headerEvents(session) expect(events).toHaveLength(2) diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index bb6d613954..7600117b58 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -74,7 +74,7 @@ describe('request stability across the loop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -95,7 +95,7 @@ describe('request stability across the loop', () => { it('a later turn append-extends the previous turn (one conversation, one log)', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -109,7 +109,7 @@ describe('request stability across the loop', () => { it('a compaction replace rewrites the resend, and the log explains it', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -142,7 +142,7 @@ describe('request stability across the loop', () => { it('a real system-prompt change is a logged header delta; a stable prompt logs nothing', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two'), textResponse('three')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -165,7 +165,7 @@ describe('request stability across the loop', () => { it('an inject() during the agent/request waterfall joins the NEXT request (the step/start boundary)', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let injected = false ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => { @@ -193,7 +193,7 @@ describe('request stability across the loop', () => { it('a mutation attempt on the frozen request content throws into the step (loud, not silent)', async () => { const adapter = new MockAdapter([textResponse('one')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) @@ -214,7 +214,7 @@ describe('request stability across the loop', () => { it('a fresh loop instance over a seeded log anchors with a resume snapshot and stays cache-aligned', async () => { const adapter = new MockAdapter([textResponse('one')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('gen1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('gen1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -226,7 +226,7 @@ describe('request stability across the loop', () => { agentId: AgentId('gen2'), sessionId: SessionId('gen2-session'), seed: [...agent.session.events], - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const agent2 = handle.agent as ReactLoopAgent send(agent2, 'second') @@ -243,7 +243,7 @@ describe('request stability across the loop', () => { it('a delegating listener cannot mutate the seed through next() — the fold stays log-true', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => { const config = await next() @@ -277,7 +277,7 @@ describe('request stability across the loop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) diff --git a/packages/core/agent-loop/tests/resume.spec.ts b/packages/core/agent-loop/tests/resume.spec.ts index 93605008ec..67f91addee 100644 --- a/packages/core/agent-loop/tests/resume.spec.ts +++ b/packages/core/agent-loop/tests/resume.spec.ts @@ -201,7 +201,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { const resuming = ctx.agents.resume({ agentId: AgentId('resumed-atomic'), resumeSessionId: sessionId, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async (agentCtx) => { expect(agentCtx.agent?.id).toBe(AgentId('resumed-atomic')) expect(agentCtx.agent?.session.events).toHaveLength(2) @@ -242,7 +242,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { const handle = await ctx.agents.resume({ agentId, resumeSessionId: sessionId, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const transactionLabels = [ `agentLoop.owner(${agentId})`, @@ -267,7 +267,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await expect(ctx.agents.resume({ agentId: AgentId('resume-reject'), resumeSessionId: sessionId, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async () => { await Promise.resolve() throw new Error('resume setup failed') @@ -280,7 +280,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { const retry = await ctx.agents.resume({ agentId: AgentId('resume-reject'), resumeSessionId: sessionId, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) await retry.dispose() await ctx.fiber.dispose() @@ -301,7 +301,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { resuming = inner.agents.resume({ agentId: AgentId('resume-owner-race'), resumeSessionId: sessionId, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async () => { setupStarted.resolve(undefined) await gate.promise @@ -348,7 +348,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { let resuming!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { - resuming = inner.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) + resuming = inner.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } }) }, { inject: ['agents'] })) await loadStarted.promise @@ -360,7 +360,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // owner.dispose() awaited transaction settlement, so the same identities // can be reused before awaiting the public rejection. - const retry = await promptly(ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } })) + const retry = await promptly(ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } })) await rejection expect(loads).toBe(2) expect(published).toEqual(['session/created', 'agent/created', 'agent/session-start']) @@ -404,7 +404,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('session/created', () => void published.push('session/created')) ctx.on('agent/created', () => void published.push('agent/created')) - const resuming = ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) + const resuming = ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } }) await loadStarted.promise const rejection = expect(promptly(resuming)).rejects.toThrow(/agent loop is not active/) await promptly(loopFiber.dispose()) diff --git a/packages/core/agent-loop/tests/review-fixes.spec.ts b/packages/core/agent-loop/tests/review-fixes.spec.ts index 5898a82ee2..467a9aecd6 100644 --- a/packages/core/agent-loop/tests/review-fixes.spec.ts +++ b/packages/core/agent-loop/tests/review-fixes.spec.ts @@ -41,7 +41,9 @@ function send(agent: ReactLoopAgent, text: string) { describe('HIGH: session log records what agent/step-result actually produced', () => { it('a step-result rewrite is what the log, derived history, and tool dispatch all see', async () => { - const adapter = new MockAdapter([textResponse('original'), textResponse('done')]) + const original = textResponse('original') + original[original.length - 1] = { type: 'finish', reason: { kind: 'stop' }, replayState: { private: 'original-state' } } + const adapter = new MockAdapter([original, textResponse('done')]) const ctx = await harness(adapter) const executed: string[] = [] ctx.tools.register(defineTool({ @@ -53,7 +55,7 @@ describe('HIGH: session log records what agent/step-result actually produced', ( return [{ type: 'text', text: 'ran' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Plugin rewrites the message: replaces the text AND adds a tool call. let rewritten = false @@ -78,6 +80,7 @@ describe('HIGH: session log records what agent/step-result actually produced', ( const recorded = agent.session.events.find(e => e.type === 'assistant/message')! expect(JSON.stringify(recorded.data)).toContain('rewritten') expect(JSON.stringify(recorded.data)).not.toContain('original') + expect(recorded.type === 'assistant/message' && recorded.data.provenance.replayState).toBeUndefined() // tool/call + tool/result correlate with the injected call id const callEvent = agent.session.events.find(e => e.type === 'tool/call')! if (callEvent.type !== 'tool/call') throw new Error('wrong event type') @@ -87,6 +90,26 @@ describe('HIGH: session log records what agent/step-result actually produced', ( expect(JSON.stringify(derived)).toContain('rewritten') expect(JSON.stringify(derived)).not.toContain('original') }) + + it('records adapter replay state when step-result preserves the assembled content', async () => { + const response = textResponse('unchanged') + const replayState = { private: 'state' } + response[response.length - 1] = { type: 'finish', reason: { kind: 'stop' }, replayState } + const adapter = new MockAdapter([response]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('replay-state'), { provider: 'mock', model: 'next-model' }) + + send(agent, 'go') + await waitForIdle(ctx, agent) + + const recorded = agent.session.events.find(e => e.type === 'assistant/message') + expect(recorded?.type === 'assistant/message' && recorded.data.provenance).toEqual({ + provider: 'mock', model: 'next-model', replayState, + }) + expect(agent.session.deriveMessages().at(-1)?.provenance).toEqual({ + provider: 'mock', model: 'next-model', replayState, + }) + }) }) describe('HIGH: abort during tool execution ends the turn', () => { @@ -104,7 +127,7 @@ describe('HIGH: abort during tool execution ends the turn', () => { ]) const ctx = await harness(adapter) const executed: string[] = [] - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'aborter', description: '', @@ -148,7 +171,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { textResponse('continued because of steering'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let steeredOnce = false ctx.on('agent/turn-continuation', async (_agent, _turn, _decision, next) => { @@ -188,7 +211,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { textResponse('after goal reminder'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let steeredOnce = false ctx.on('session/event', (subject, event) => { @@ -218,7 +241,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { it('steer() from a turn/end session-event listener becomes a queued message for the next turn', async () => { const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const turns: number[] = [] let steeredOnce = false @@ -244,7 +267,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { it('steering queued during an aborted step is re-delivered, not silently consumed', async () => { const adapter = new MockAdapter(['hang', textResponse('recovered')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -267,7 +290,7 @@ describe('HIGH: plugin exceptions are contained', () => { it('a throwing agent/turn-continuation listener ends the turn with an error, loop survives', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let threwOnce = false ctx.on('agent/turn-continuation', async (): Promise => { @@ -295,7 +318,7 @@ describe('HIGH: plugin exceptions are contained', () => { it('a rejecting session/flush listener is reported but does not kill the agent', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let rejectedOnce = false ctx.on('session/flush', async () => { @@ -325,7 +348,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const statuses: string[] = [] @@ -348,7 +371,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) ctx.on('agent/status', (_agent, status) => { @@ -374,7 +397,7 @@ describe('MEDIUM: misc registry and config fixes', () => { expect(() => ctx.llm.registerAdapter(['m1'], new MockAdapter([]))) .toThrow('already registered') // the original registration survives the failed attempt - expect(ctx.llm.models()).toEqual(['m1']) + expect(ctx.llm.providers()).toEqual(['m1']) }) it('an agent without a model fails the step with a clear error (not NO_ADAPTER for "default")', async () => { @@ -388,7 +411,7 @@ describe('MEDIUM: misc registry and config fixes', () => { send(agent, 'go') await waitForIdle(ctx, agent) expect(errors).toHaveLength(1) - expect(errors[0]!.message).toContain('has no model') + expect(errors[0]!.message).toContain('has no provider/model') expect(errors[0]!.message).toContain('agent/request') }) @@ -398,7 +421,7 @@ describe('MEDIUM: misc registry and config fixes', () => { const agent = ctx.agentLoop.create(AgentId('a1'), {}) // no model — router plugin decides ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { - return { ...config, model: 'mock' } + return { ...config, provider: 'mock', model: 'mock' } }) send(agent, 'go') @@ -410,7 +433,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('agent/queued carries the resolved source; steering/message records its source', async () => { const adapter = new MockAdapter([toolCallResponse('c1', 'noop', {}), textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'noop', description: '', @@ -438,7 +461,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('send() owns content and source before notification and delivery', async () => { const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('owned-send'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('owned-send'), { provider: 'mock', model: 'mock' }) const content = [{ type: 'text' as const, text: 'accepted-send' }] const source = { kind: 'plugin' as const, plugin: 'accepted-source' } let notifiedContent: ContentBlock[] | undefined @@ -474,7 +497,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('running steer() owns content and source before notification and delivery', async () => { const adapter = new MockAdapter([toolCallResponse('c1', 'gate', {}), textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('owned-steer'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('owned-steer'), { provider: 'mock', model: 'mock' }) const entered = Promise.withResolvers() const release = Promise.withResolvers() ctx.tools.register(defineTool({ @@ -528,7 +551,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () it('a forked agent continues turn numbers after the seed log', async () => { const first = new MockAdapter([textResponse('turn one')]) const ctx = await harness(first) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -544,7 +567,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () ctx2.llm.registerAdapter(['mock'], second) const seeded = ctx2.sessions.create(SessionId('forked'), { seed: [...agent.session.events] }) - const prepared = prepareReactLoopAgent(ctx2, AgentId('forked-agent'), { model: 'mock' }, seeded) + const prepared = prepareReactLoopAgent(ctx2, AgentId('forked-agent'), { provider: 'mock', model: 'mock' }, seeded) const forked = prepared.agent prepared.markPublished() ctx2.effect(() => prepared.startDriver()) @@ -591,7 +614,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([errorStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-error'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-finish-error'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -616,7 +639,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([abortedStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-aborted'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-finish-aborted'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -634,7 +657,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([errorStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-error-nocode'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-finish-error-nocode'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -650,7 +673,7 @@ describe('step boundary publication order', () => { it('the step/start event is in session.events when its session/event listener fires', async () => { const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-step-order'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-step-order'), { provider: 'mock', model: 'mock' }) // Session.append pushes the event BEFORE notifying session/event listeners, // so a step/start listener always finds the matching event already in the @@ -711,7 +734,7 @@ describe('turn and step boundary recovery', () => { it('a throwing step/start observer cannot change a successful turn', async () => { const adapter = new MockAdapter([textResponse('request completed')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepstart'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-stepstart'), { provider: 'mock', model: 'mock' }) // Session owns post-commit containment. The loop sees a successful append, // runs the request, and balances the ordinary step and turn boundaries. @@ -740,7 +763,7 @@ describe('turn and step boundary recovery', () => { it('a pre-commit step/start validation failure does not invent a step boundary', async () => { const adapter = new MockAdapter([textResponse('never reached')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepstart-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-stepstart-veto'), { provider: 'mock', model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -771,7 +794,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider failed' } }] const adapter = new MockAdapter([errorStream]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-turnend-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-turnend-veto'), { provider: 'mock', model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -805,7 +828,7 @@ describe('turn and step boundary recovery', () => { it('a one-shot step/end validation failure keeps the step open until retry succeeds', async () => { const adapter = new MockAdapter([textResponse('completed before close validation')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepend-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-stepend-veto'), { provider: 'mock', model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -839,7 +862,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }] const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-errorlistener'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-errorlistener'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('agent/error', () => { if (!threw) { threw = true; throw new Error('boom error-listener') } }) @@ -872,7 +895,7 @@ describe('turn and step boundary recovery', () => { const ctx = await balancedHarness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('a-dispose'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -901,7 +924,7 @@ describe('turn and step boundary recovery', () => { const ctx = await balancedHarness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-prestep-dispose-throw'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('a-prestep-dispose-throw'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) let threw = false @@ -935,7 +958,7 @@ describe('turn and step boundary recovery', () => { it('a throwing turn/start observer cannot starve the loop or later turns', async () => { const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-preturn'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-preturn'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('session/event', (_session, event) => { @@ -966,7 +989,7 @@ describe('turn and step boundary recovery', () => { it('a throwing step/end observer cannot rewrite the turn outcome', async () => { const adapter = new MockAdapter([textResponse('all good'), textResponse('turn 2 ok')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepend-throw'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-stepend-throw'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1008,7 +1031,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }] const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stependthrow'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-stependthrow'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1038,7 +1061,7 @@ describe('turn and step boundary recovery', () => { // boundary stays authoritative and the loop continues normally. const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-turnendappend'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-turnendappend'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1085,7 +1108,7 @@ describe('tool result call identity', () => { return Promise.resolve({ kind: 'accept', content: [{ type: 'text', text: 'ok' }] }) }, { prepend: true }) - const agent = ctx.agentLoop.create(AgentId('a-callid'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-callid'), { provider: 'mock', model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -1120,7 +1143,7 @@ describe('surface: assistant/message omits sourceEventSeqs when no chunks stream const adapter = new MockAdapter([[]]) const ctx = await harness(adapter) await ctx.plugin(Invariants) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/step-result', async (_agent, _turn, _step, _message, _next) => ({ role: 'assistant' as const, @@ -1171,7 +1194,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-assemble'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('a-dispose-assemble'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1227,7 +1250,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-cancel-assemble'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('a-cancel-assemble'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1282,7 +1305,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-prestep'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('a-dispose-prestep'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1334,7 +1357,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-cancel-prestep'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('a-cancel-prestep'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1384,7 +1407,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-no-leak'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('a-dispose-no-leak'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index 2c478ad1f0..e07ba84e8d 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -144,7 +144,7 @@ describe('agent scope lifecycle', () => { it('wires agent.ctx: tagged with the agent, DX field set, ctx.agent safe elsewhere', async () => { const ctx = await harness() - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) expect(scopeOf(agent.ctx)).toBe(agent) expect(agent.ctx.agent).toBe(agent) // The root accessor default: a plain context answers undefined, not a throw. @@ -154,7 +154,7 @@ describe('agent scope lifecycle', () => { it('scoped registrations live in the agent world and die with the agent', async () => { const ctx = await harness() - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { provider: 'mock', model: 'mock' } }) const { agent } = handle agent.ctx.systemPrompt.section({ name: 'deployment:persona', order: 0, text: 'You run tests.' }) agent.ctx.tools.register({ @@ -179,8 +179,8 @@ describe('agent scope lifecycle', () => { it('agent.ctx listeners hear only their own agent (scoped dispatch end to end)', async () => { const ctx = await harness(new MockAdapter([textResponse('one'), textResponse('two')])) - const a = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) - const b = ctx.agentLoop.create(AgentId('b'), { model: 'mock' }) + const a = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' }) + const b = ctx.agentLoop.create(AgentId('b'), { provider: 'mock', model: 'mock' }) const heard: string[] = [] a.ctx.on('agent/status', (subject, status) => void heard.push(`a-sees:${subject.id}:${status}`)) @@ -212,7 +212,7 @@ describe('agent scope lifecycle', () => { const handle = await ctx.agents.create({ agentId: AgentId('child'), sessionId: SessionId('child-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async (agentCtx) => { order.push('setup') await Promise.resolve() @@ -236,7 +236,7 @@ describe('agent scope lifecycle', () => { }) ctx.on('agent/created', () => void order.push('agent/created')) ctx.on('agent/session-start', () => void order.push('agent/session-start')) - const acceptedOptions = { model: 'mock' } + const acceptedOptions = { provider: 'mock', model: 'mock' } const creating = ctx.agents.create({ agentId: AgentId('atomic'), @@ -285,13 +285,13 @@ describe('agent scope lifecycle', () => { const first = ctx.agents.create({ agentId, sessionId: SessionId('concurrent-final-enter-a'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup, }) const second = ctx.agents.create({ agentId, sessionId: SessionId('concurrent-final-enter-b'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup, }) await bothStarted.promise @@ -320,7 +320,7 @@ describe('agent scope lifecycle', () => { const pending = ctx.agents.create({ agentId: AgentId('signal-pending'), sessionId: SessionId('signal-pending-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, signal: pendingController.signal, setup: async () => { setupStarted.resolve(undefined) @@ -337,7 +337,7 @@ describe('agent scope lifecycle', () => { const live = await ctx.agents.create({ agentId: AgentId('signal-live'), sessionId: SessionId('signal-live-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, signal: liveController.signal, }) liveController.abort(new Error('too late')) @@ -360,7 +360,7 @@ describe('agent scope lifecycle', () => { creating = inner.agents.create({ agentId: AgentId('owner-race'), sessionId: SessionId('owner-race-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async () => { setupStarted.resolve(undefined) await gate.promise @@ -388,7 +388,7 @@ describe('agent scope lifecycle', () => { creating2 = inner.agents.create({ agentId: AgentId('owner-race-2'), sessionId: SessionId('owner-race-s-2'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async () => { setupStarted2.resolve(undefined) await gate2.promise @@ -415,7 +415,7 @@ describe('agent scope lifecycle', () => { const creating = ctx.agents.create({ agentId: AgentId('factory-setup-race'), sessionId: SessionId('factory-setup-race-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async () => { setupStarted.resolve(undefined) await gate.promise @@ -446,7 +446,7 @@ describe('agent scope lifecycle', () => { const creating = ctx.agents.create({ agentId: AgentId('factory-scope-race'), sessionId: SessionId('factory-scope-race-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: () => { setupCalls += 1 }, }) await expect(creating).rejects.toThrow(/agent loop is not active/) @@ -481,7 +481,7 @@ describe('agent scope lifecycle', () => { creating = inner.agents.create({ agentId: AgentId('caller-scope-race'), sessionId: SessionId('caller-scope-race-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) }, { inject: ['agents'] })) @@ -511,7 +511,7 @@ describe('agent scope lifecycle', () => { void loopFiber.dispose() }) - expect(() => ctx.agentLoop.create(AgentId('config-scope-race'), { model: 'mock' })) + expect(() => ctx.agentLoop.create(AgentId('config-scope-race'), { provider: 'mock', model: 'mock' })) .toThrow(/agent loop is not active/) await loopFiber.dispose() expect(ctx.agents.get(AgentId('config-scope-race'))).toBeUndefined() @@ -523,9 +523,9 @@ describe('agent scope lifecycle', () => { const ctx = await harness() const id = AgentId('config-prepare-failure') - expect(() => ctx.agentLoop.create(id, { model: 'mock' }, { cwd: 'relative' })) + expect(() => ctx.agentLoop.create(id, { provider: 'mock', model: 'mock' }, { cwd: 'relative' })) .toThrow(/absolute path/) - const replacement = ctx.agentLoop.create(id, { model: 'mock' }, { cwd: '/recovered' }) + const replacement = ctx.agentLoop.create(id, { provider: 'mock', model: 'mock' }, { cwd: '/recovered' }) expect(ctx.agents.get(id)).toBe(replacement) await replacement.whenIdle() await ctx.fiber.dispose() @@ -544,7 +544,7 @@ describe('agent scope lifecycle', () => { await expect(ctx.agents.create({ agentId: AgentId('factory-scope-throw'), sessionId: SessionId('factory-scope-throw-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, })).rejects.toThrow('scope preparation failed') await loopFiber.dispose() expect(ctx.agents.get(AgentId('factory-scope-throw'))).toBeUndefined() @@ -560,7 +560,7 @@ describe('agent scope lifecycle', () => { const handle = await ctx.agents.create({ agentId, sessionId: SessionId('factory-live-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) await loopFiber.dispose() @@ -585,7 +585,7 @@ describe('agent scope lifecycle', () => { creating = inner.agents.create({ agentId: AgentId('dependency-origin'), sessionId: SessionId('dependency-origin-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: (agentCtx) => { agentCtx.tools.register({ name: 'dependency-origin-tool', @@ -640,7 +640,7 @@ describe('agent scope lifecycle', () => { creating = inner.agents.create({ agentId: AgentId('session-created-barrier'), sessionId: SessionId('session-created-barrier-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) }, { inject: ['agents'] })) @@ -689,7 +689,7 @@ describe('agent scope lifecycle', () => { creating = inner.agents.create({ agentId: AgentId('agent-created-barrier'), sessionId: SessionId('agent-created-barrier-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) }, { inject: ['agents'] })) @@ -723,7 +723,7 @@ describe('agent scope lifecycle', () => { creating = inner.agents.create({ agentId: AgentId('listener-dispose'), sessionId: SessionId('listener-dispose-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) }, { inject: ['agents'] })) @@ -764,7 +764,7 @@ describe('agent scope lifecycle', () => { creating = inner.agents.create({ agentId: AgentId('session-start-dispose'), sessionId: SessionId('session-start-dispose-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) }, { inject: ['agents'] })) @@ -789,7 +789,7 @@ describe('agent scope lifecycle', () => { await expect(ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async () => { await Promise.resolve() throw new Error('boom setup') @@ -800,7 +800,7 @@ describe('agent scope lifecycle', () => { expect(published).toEqual([]) expect(ctx.agents.get(AgentId('bad'))).toBeUndefined() expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined() - const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) + const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' } }) await retry.dispose() }) @@ -819,7 +819,7 @@ describe('agent scope lifecycle', () => { await expect(ctx.agents.create({ agentId: AgentId('exotic-seed'), sessionId: SessionId('exotic-seed-session'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, seed, })).rejects.toThrow(/seed event at index 0 is not losslessly JSON-serializable/) @@ -829,7 +829,7 @@ describe('agent scope lifecycle', () => { const retry = await ctx.agents.create({ agentId: AgentId('exotic-seed'), sessionId: SessionId('exotic-seed-session'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) await retry.dispose() }) @@ -843,13 +843,13 @@ describe('agent scope lifecycle', () => { if (boom) { boom = false; throw new Error('boom created') } }) await expect(ctx.agents.create({ - agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' }, + agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' }, })).rejects.toThrow('boom created') expect(ctx.agents.get(AgentId('bad'))).toBeUndefined() expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined() expect(disposed).toEqual([]) // inserted but never announced: no impossible disposed edge // The rollback also disposed the scope fiber: re-creating works cleanly. - const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) + const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' } }) expect(scopeOf(retry.agent.ctx)).toBe(retry.agent) await retry.dispose() }) @@ -868,7 +868,7 @@ describe('agent scope lifecycle', () => { await expect(ctx.agents.create({ agentId: AgentId('partial-agent'), sessionId: SessionId('partial-session'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, })).rejects.toThrow('agent observer failed') expect(lifecycle).toEqual([ @@ -892,7 +892,7 @@ describe('agent scope lifecycle', () => { } }) - expect(() => ctx.agentLoop.create(AgentId('config-bad'), { model: 'mock' })) + expect(() => ctx.agentLoop.create(AgentId('config-bad'), { provider: 'mock', model: 'mock' })) .toThrow('config publish failed') expect(ctx.agents.get(AgentId('config-bad'))).toBeUndefined() expect(ctx.sessions.list()).toHaveLength(sessionsBefore) @@ -900,15 +900,15 @@ describe('agent scope lifecycle', () => { it('registrations through a disposed agent ctx throw INACTIVE_EFFECT', async () => { const ctx = await harness() - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { provider: 'mock', model: 'mock' } }) await handle.dispose() expect(() => handle.agent.ctx.on('agent/status', () => {})).toThrow(/inactive context/) }) it('agentEvents fuses carrier and subject for custom drivers', async () => { const ctx = await harness() - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - const other = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const other = ctx.agentLoop.create(AgentId('a2'), { provider: 'mock', model: 'mock' }) const heard: string[] = [] agent.ctx.on('agent/error', (subject: Agent, turn: number) => void heard.push(`${subject.id}:${turn}`)) @@ -921,7 +921,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { - handle = await inner.agents.create({ agentId: AgentId('o1'), sessionId: SessionId('o1-s'), agentOptions: { model: 'mock' } }) + handle = await inner.agents.create({ agentId: AgentId('o1'), sessionId: SessionId('o1-s'), agentOptions: { provider: 'mock', model: 'mock' } }) }, { inject: ['agents'] })) const { agent } = handle @@ -955,7 +955,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { - handle = await inner.agents.create({ agentId: AgentId('h1'), sessionId: SessionId('h1-s'), agentOptions: { model: 'mock' } }) + handle = await inner.agents.create({ agentId: AgentId('h1'), sessionId: SessionId('h1-s'), agentOptions: { provider: 'mock', model: 'mock' } }) }, { inject: ['agents'] })) const teardownDone: string[] = [] @@ -978,7 +978,7 @@ describe('agent scope lifecycle', () => { const handle = await ctx.agents.create({ agentId, sessionId: SessionId('retired-owner-effect-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${agentId})`) @@ -996,7 +996,7 @@ describe('agent scope lifecycle', () => { handle = await inner.agents.create({ agentId: AgentId('manual-first'), sessionId: SessionId('manual-first-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup(agentCtx) { agentCtx.effect(() => async () => { cleanupStarted.resolve(undefined) @@ -1032,7 +1032,7 @@ describe('agent scope lifecycle', () => { const first = await ctx.agents.create({ agentId, sessionId, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup(agentCtx) { agentCtx.effect(() => async () => { cleanupStarted.resolve(undefined) @@ -1045,7 +1045,7 @@ describe('agent scope lifecycle', () => { await Promise.all([sessionDisposed.promise, cleanupStarted.promise]) expect(ctx.agents.get(agentId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() - const replacement = await ctx.agents.create({ agentId, sessionId, agentOptions: { model: 'mock' } }) + const replacement = await ctx.agents.create({ agentId, sessionId, agentOptions: { provider: 'mock', model: 'mock' } }) expect(ctx.agents.get(agentId)).toBe(replacement.agent) expect(ctx.sessions.get(sessionId)).toBe(replacement.agent.session) @@ -1060,7 +1060,7 @@ describe('agent scope lifecycle', () => { const handle = await ctx.agents.create({ agentId: AgentId('idle-flush'), sessionId: SessionId('idle-flush-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const gate = Promise.withResolvers() let flushStarted = false diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index d9b0a87e1d..e34ec918d1 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -57,7 +57,7 @@ async function runTurn(registrationOrder: string[], toolOrder?: SystemPromptConf const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter, toolOrder) for (const name of registrationOrder) registerNamed(ctx, name) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) return { ctx, agent, adapter } @@ -103,7 +103,7 @@ describe('loop-level canonical tool order', () => { registerNamed(ctx, 'alpha') const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) diff --git a/packages/core/agent-loop/tests/turn-stop.spec.ts b/packages/core/agent-loop/tests/turn-stop.spec.ts index c275fee88c..5e979988d7 100644 --- a/packages/core/agent-loop/tests/turn-stop.spec.ts +++ b/packages/core/agent-loop/tests/turn-stop.spec.ts @@ -45,7 +45,7 @@ describe('agent/turn-stop', () => { textResponse('must not be requested'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-steering'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('terminal-steering'), { provider: 'mock', model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let steered = false @@ -72,7 +72,7 @@ describe('agent/turn-stop', () => { textResponse('must not become a late-steering turn'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-flush-steering'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('terminal-flush-steering'), { provider: 'mock', model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let injected = false @@ -98,7 +98,7 @@ describe('agent/turn-stop', () => { textResponse('queued follow-up answer'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-flush-send'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('terminal-flush-send'), { provider: 'mock', model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let queued = false @@ -124,8 +124,8 @@ describe('agent/turn-stop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const stopped = ctx.agentLoop.create(AgentId('stopped'), { model: 'mock' }) - const ordinary = ctx.agentLoop.create(AgentId('ordinary'), { model: 'mock' }) + const stopped = ctx.agentLoop.create(AgentId('stopped'), { provider: 'mock', model: 'mock' }) + const ordinary = ctx.agentLoop.create(AgentId('ordinary'), { provider: 'mock', model: 'mock' }) stopped.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) await send(stopped) @@ -145,7 +145,7 @@ describe('agent/turn-stop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('owned-listener'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('owned-listener'), { provider: 'mock', model: 'mock' }) const disposeStop = agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) await send(agent, 'first turn') @@ -162,7 +162,7 @@ describe('agent/turn-stop', () => { textResponse('healthy later turn'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('bad-policy'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('bad-policy'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] const errors: string[] = [] ctx.on('session/event', (session, event) => { diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index 7a046dcc82..218c15727c 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -88,7 +88,9 @@ declare module '@deepseek-ai/dsh-system-prompt' { * Merge-extensible: plugins declare extra fields via declaration merging. */ export interface AgentOptions { - /** Model name (must have a registered adapter at call time). */ + /** Provider route (must have a registered adapter at call time). */ + provider?: string + /** Model id interpreted by the selected provider adapter. */ model?: string } diff --git a/packages/core/session/README.md b/packages/core/session/README.md index 97b18b0504..cea12cfd7d 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -33,7 +33,7 @@ The store pairs announced creation with disposal, publishes each append, and pro Plain class (not a Cordis Service). Create via `ctx.sessions.create()`. - `session.append(type, data, opts?): SessionEvent` — synchronous, never blocks on I/O. At this durable boundary, data and surface metadata are lossless-JSON snapshotted and deep-frozen. For an attached session, a reentrant append during dispatch/observer publication rejects, and detach waits for that publication to unwind. Callbacks resolve before the log push; the push is the commit point, after which each observer failure is contained independently. Runtime surface validation covers widened unions and raw seed/load logs. -- `session.deriveMessages(): Message[]` — the LLM message history, CACHED: each surface node is projected exactly once, when first seen (O(new nodes) per call; a surface rewrite rebuilds via `surface.replaceGeneration`). Returns a fresh array per call over shared, deep-frozen `Message` objects. Each projection reuses the already deep-frozen content in its durable log event, so no second deep clone is needed and a consumer still cannot mutate logged data. The surface is the single source of derived history — there is no raw-log fallback. +- `session.deriveMessages(): Message[]` — the LLM message history, CACHED: each surface node is projected exactly once, when first seen (O(new nodes) per call; a surface rewrite rebuilds via `surface.replaceGeneration`). Returns a fresh array per call over shared, deep-frozen `Message` objects. Assistant projections preserve the event's provider/model provenance and optional adapter-private replay state. Each projection reuses the already deep-frozen content in its durable log event, so no second deep clone is needed and a consumer still cannot mutate logged data. The surface is the single source of derived history — there is no raw-log fallback. - `session.deriveEventMessage(event): Message | null` — the per-event projection `deriveMessages()` folds: a fresh message wrapper that reuses the event's already frozen content, or `null` when the event produces none (a non-surface event, or an empty-content `assistant/message` hosting only usage). External reconstructors and the dev invariant fold the same function over a log prefix's surface, so no two paths can disagree about what a request's messages were (the reconstructability RFC). - `session.surface: SurfaceManager` — the derived surface, lazily rebuilt from `surfaceOp` markers in the log. Processes only new events (delta) on each access — the log is append-only, so prior events never change. `surface.replaceGeneration` is the rewrite signal: bumped by every folded `replace` and by `invalidate()`, never reset, so an incremental consumer comparing generations cannot be fooled. - `session.events` — a cached, frozen array snapshot over deep-frozen events. Repeated reads without an append return the same array; an append invalidates the cache and the next read returns a new snapshot, while earlier snapshots stay unchanged. Neither a cast nor a retained reference can push into the live log or rewrite an accepted event. @@ -57,7 +57,7 @@ The `request/header` (full `EpochHeader` snapshot with a `RequestHeaderReason`) ### Session event vocabulary (`types.ts`) -The append-only log's event types, enumerated member by member — payloads, surface badges, provenance — in the generated [persistence log event catalog](../../../docs/persistence-catalog.md). Token usage rides on `assistant/message.usage`; an operational error's step is on `turn/end.reason` for `kind: 'error'`. +The append-only log's event types, enumerated member by member — payloads, surface badges, provenance — in the generated [persistence log event catalog](../../../docs/persistence-catalog.md). Token usage and provider/model/replay provenance ride on `assistant/message`; an operational error's step is on `turn/end.reason` for `kind: 'error'`. Merge-extensible via `SessionEventMap` — a plugin declaration-merges its own types (the compaction seam's `compact/*`, the hook bridges' `hook/*`); merged members appear in the same catalog. @@ -75,7 +75,7 @@ Every `SessionEvent` carries two optional top-level fields (structural metadata) ### Extension points - Persistence plugins: subscribe to `session/event` (write-behind) and drain on `session/flush` (awaited) and fiber dispose. A durable backend reads the log and reloads it into a live session; the metadata seam (`SessionHeader`, `session.header`) is what such a backend stores beside the log. -- Replay/fork: `ctx.sessions.create(id, { seed })` seeds a new session with an existing event log. The surface rebuilds deterministically from `surfaceOp` markers in the seeded events. The constructor reads each seed entry once and uses the same one-pass lossless-JSON snapshot and exact surface-metadata shape checks as `append`, then enforces contiguous seqs and deep-freezes every accepted record; a stateful caller, exotic nested value, marker-less or malformed surface event, metadata on a non-surface event, or retained seed reference therefore cannot silently change the reconstructed history. Broader turn-enclosure checks stay in `dsh-invariants` and persistence repair. Ordinary live-session forks use `ctx.sessions.fork(source, boundary?, childSessionId?)`, where `boundary` is the inclusive source event seq to fork through. +- Replay/fork: `ctx.sessions.create(id, { seed })` seeds a new session with an existing event log. The surface rebuilds deterministically from `surfaceOp` markers in the seeded events. The constructor reads each seed entry once and uses the same one-pass lossless-JSON snapshot and exact surface-metadata shape checks as `append`, then enforces contiguous seqs and deep-freezes every accepted record; a stateful caller, exotic nested value, marker-less or malformed surface event, metadata on a non-surface event, or retained seed reference therefore cannot silently change the reconstructed history. In the unreleased pinned-v0 format, request headers without provider/model and assistant messages without provider/model provenance are rejected rather than migrated or guessed. Broader turn-enclosure checks stay in `dsh-invariants` and persistence repair. Ordinary live-session forks use `ctx.sessions.fork(source, boundary?, childSessionId?)`, where `boundary` is the inclusive source event seq to fork through. - Compaction: the `dsh-compact-basic` plugin appends a `user/message` with `surfaceOp: { op: 'replace', start, end }` to shadow old surface nodes behind a summary checkpoint. ### What is NOT here (TODO) diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index a6dff5cd27..1e590c8e08 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -207,6 +207,33 @@ function assertSessionEventEnvelope(value: Record, index: numbe || !Object.hasOwn(event, 'data')) { throw new Error(`seed event at index ${index} has an invalid event envelope`) } + assertCurrentLlmShape(event, index) +} + +/** Reject pre-provider request headers and assistant messages at the seed/load boundary. */ +function assertCurrentLlmShape(event: Record, index: number): void { + const data = event['data'] + if (typeof data !== 'object' || data === null) return + const record = data as Record + if (event['type'] === 'request/header') { + const header = record['header'] + const config = typeof header === 'object' && header !== null ? (header as Record)['config'] : undefined + if (!hasProviderModel(config)) throw new Error(`seed request/header at index ${index} lacks provider/model`) + } + if (event['type'] === 'request/header-delta' && record['config'] !== undefined && !hasProviderModel(record['config'])) { + throw new Error(`seed request/header-delta at index ${index} lacks provider/model`) + } + if (event['type'] === 'assistant/message' && !hasProviderModel(record['provenance'])) { + throw new Error(`seed assistant/message at index ${index} lacks provider/model provenance`) + } +} + +/** Whether an unknown value carries the current provider/model pair. */ +function hasProviderModel(value: unknown): boolean { + if (typeof value !== 'object' || value === null) return false + const pair = value as Record + return typeof pair['provider'] === 'string' && pair['provider'].length > 0 + && typeof pair['model'] === 'string' && pair['model'].length > 0 } type SessionCallback = (...args: unknown[]) => unknown @@ -530,7 +557,7 @@ export class Session { // max-tokens step's usage and must not inject a content-less assistant // turn into the provider transcript. if (event.data.content.length === 0) return null - return { role: 'assistant', content: event.data.content } + return { role: 'assistant', content: event.data.content, provenance: event.data.provenance } } case 'tool/result': { const { callId, content, isError } = event.data diff --git a/packages/core/session/src/types.ts b/packages/core/session/src/types.ts index c4838808c1..74e77dc0fd 100644 --- a/packages/core/session/src/types.ts +++ b/packages/core/session/src/types.ts @@ -1,5 +1,5 @@ import type { Branded } from '@deepseek-ai/dsh-brand' -import type { CallId, ContentBlock, LlmCallConfig, Message, MessageSource, StreamChunk, TokenUsage, ToolSchema } from '@deepseek-ai/dsh-llm' +import type { AssistantProvenance, CallId, ContentBlock, LlmCallConfig, Message, MessageSource, StreamChunk, TokenUsage, ToolSchema } from '@deepseek-ai/dsh-llm' /** Identifies one session in the store (and its persistence artifacts). */ export type SessionId = Branded<'SessionId'> @@ -203,7 +203,7 @@ export interface TodoItem { * prefix are ABSENT fields, matching how requests are built. */ export interface EpochHeader { - /** The conversation's call configuration (model + sampling scalars). */ + /** The conversation's call configuration (provider, model, and sampling scalars). */ config: LlmCallConfig /** Rendered system prompt text; absent for a system-less request. */ system?: string @@ -326,7 +326,7 @@ export interface SessionEventMap { * the model output and its accounting travel together (there is no separate * usage record). `usage` is absent when the adapter reported none. */ - 'assistant/message': { turn: number; step: number; content: ContentBlock[]; usage?: TokenUsage } + 'assistant/message': { turn: number; step: number; content: ContentBlock[]; provenance: AssistantProvenance; usage?: TokenUsage } /** * The model requested one tool invocation: `name` with the raw `arguments` * JSON string exactly as the model produced it (unparsed). `callId` pairs the @@ -375,7 +375,7 @@ export interface SessionEventMap { /** * Amendment to the folded {@link EpochHeader}: at least one of a * {@link SystemDelta}, a {@link ToolsDelta}, a whole replacement - * {@link LlmCallConfig} (four scalars — not worth diffing), or a whole + * {@link LlmCallConfig} (provider/model plus sampling scalars — not worth diffing), or a whole * replacement session prefix (`messagePrefix` — small advisory content, * replaced whole; an EMPTY array encodes the transition to "none", * mirroring the canonical form's absent field — the loop never produces diff --git a/packages/core/session/tests/derived-cache.spec.ts b/packages/core/session/tests/derived-cache.spec.ts index 46015106c8..5be127a84f 100644 --- a/packages/core/session/tests/derived-cache.spec.ts +++ b/packages/core/session/tests/derived-cache.spec.ts @@ -26,10 +26,10 @@ describe('derived-message cache', () => { userText(session, 'one') expect(session.deriveMessages()).toEqual(scratch(session)) userText(session, 'two') - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'reply' }] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'reply' }] }, { surfaceOp: 'append' }) expect(session.deriveMessages()).toEqual(scratch(session)) // An empty-content assistant/message (usage host) projects to nothing. - session.append('assistant/message', { turn: 1, step: 2, content: [], usage: { inputTokens: 1, outputTokens: 0 } }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 2, content: [], usage: { inputTokens: 1, outputTokens: 0 } }, { surfaceOp: 'append' }) expect(session.deriveMessages()).toEqual(scratch(session)) }) @@ -106,7 +106,7 @@ describe('Session.deriveEventMessage — the per-event projection', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) const boundary = session.append('step/start', { turn: 1, step: 1 }) expect(session.deriveEventMessage(boundary)).toBeNull() - const empty = session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append' }) + const empty = session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append' }) expect(session.deriveEventMessage(empty)).toBeNull() }) }) diff --git a/packages/core/session/tests/fork.spec.ts b/packages/core/session/tests/fork.spec.ts index af143ea5ee..5344449078 100644 --- a/packages/core/session/tests/fork.spec.ts +++ b/packages/core/session/tests/fork.spec.ts @@ -195,14 +195,14 @@ describe('SessionStore.fork', () => { ['assistant/message', (session) => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'partial' }] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'partial' }] }, { surfaceOp: 'append' }) return lastSeq(session) }], ['tool/call', (session) => { const callId = CallId('call-open') session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) - session.append('assistant/message', { + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'tool-call', id: callId, name: 'bash', arguments: '{}' }], diff --git a/packages/core/session/tests/properties.spec.ts b/packages/core/session/tests/properties.spec.ts index c3a887e14f..dd9a8cf0c2 100644 --- a/packages/core/session/tests/properties.spec.ts +++ b/packages/core/session/tests/properties.spec.ts @@ -30,8 +30,8 @@ const textContentArb = fc.array( // explicit `surfaceOp: 'append'` intent — the marker the real loop passes. const messageEventArb: fc.Arbitrary = fc.oneof( textContentArb.map((content): Appendable => ({ type: 'user/message', data: { content, source: { kind: 'user' } }, intent: { surfaceOp: 'append' } })), - textContentArb.map((content): Appendable => ({ type: 'assistant/message', data: { turn: 1, step: 1, content }, intent: { surfaceOp: 'append' } })), - textContentArb.map((content): Appendable => ({ type: 'assistant/message', data: { turn: 1, step: 1, content, usage: { inputTokens: 1, outputTokens: 1 } }, intent: { surfaceOp: 'append' } })), + textContentArb.map((content): Appendable => ({ type: 'assistant/message', data: { turn: 1, step: 1, content, provenance: { provider: 'mock', model: 'mock' } }, intent: { surfaceOp: 'append' } })), + textContentArb.map((content): Appendable => ({ type: 'assistant/message', data: { turn: 1, step: 1, content, provenance: { provider: 'mock', model: 'mock' }, usage: { inputTokens: 1, outputTokens: 1 } }, intent: { surfaceOp: 'append' } })), fc.record({ id: fc.string({ minLength: 1 }), content: textContentArb, isError: fc.boolean() }) .map((r): Appendable => ({ type: 'tool/result', data: { turn: 1, step: 1, callId: CallId(r.id), content: r.content, isError: r.isError }, intent: { surfaceOp: 'append' } })), ) diff --git a/packages/core/session/tests/repair.spec.ts b/packages/core/session/tests/repair.spec.ts index e94a9b437f..a8c3d1c309 100644 --- a/packages/core/session/tests/repair.spec.ts +++ b/packages/core/session/tests/repair.spec.ts @@ -56,7 +56,7 @@ describe('interruptedTurnClosers', () => { { type: 'assistant/message', seq: 2, time: 2, data: { turn: 2, step: 1, content: [ { type: 'text', text: 'calling a tool' }, { type: 'tool-call', id: CallId('call-1'), name: 'bash', arguments: '{}' }, - ] } }, + ], provenance: { provider: 'mock', model: 'mock' } } }, ] const closers = interruptedTurnClosers(events) // tool/result (for the orphaned call) → step/end → turn/end, contiguous seqs. @@ -74,7 +74,7 @@ describe('interruptedTurnClosers', () => { { type: 'step/start', seq: 1, time: 1, data: { turn: 2, step: 1 } }, { type: 'assistant/message', seq: 2, time: 2, data: { turn: 2, step: 1, content: [ { type: 'tool-call', id: CallId('call-1'), name: 'bash', arguments: '{}' }, - ] } }, + ], provenance: { provider: 'mock', model: 'mock' } } }, { type: 'tool/result', seq: 3, time: 3, data: { turn: 2, step: 1, callId: CallId('call-1'), content: [{ type: 'text', text: 'ok' }], isError: false } }, ] // The call is answered, so only the open step + turn need closing. @@ -88,7 +88,7 @@ describe('interruptedTurnClosers', () => { { type: 'step/start', seq: 1, time: 1, data: { turn: 2, step: 1 } }, { type: 'assistant/message', seq: 2, time: 2, data: { turn: 2, step: 1, content: [ { type: 'tool-call', id: CallId('call-1'), name: 'bash', arguments: '{}' }, - ] } }, + ], provenance: { provider: 'mock', model: 'mock' } } }, { type: 'step/end', seq: 3, time: 3, data: { turn: 2, step: 1 } }, ] @@ -105,7 +105,7 @@ describe('interruptedTurnClosers', () => { { type: 'step/start', seq: 1, time: 1, data: { turn: 1, step: 1 } }, { type: 'assistant/message', seq: 2, time: 2, data: { turn: 1, step: 1, content: [ { type: 'tool-call', id: CallId('old-call'), name: 'bash', arguments: '{}' }, - ] } }, + ], provenance: { provider: 'mock', model: 'mock' } } }, { type: 'tool/result', seq: 3, time: 3, data: { turn: 1, step: 1, callId: CallId('old-call'), content: [], isError: false } }, { type: 'step/end', seq: 4, time: 4, data: { turn: 1, step: 1 } }, { type: 'turn/end', seq: 5, time: 5, data: { turn: 1, reason: { kind: 'completed' } } }, @@ -113,7 +113,7 @@ describe('interruptedTurnClosers', () => { { type: 'step/start', seq: 7, time: 7, data: { turn: 2, step: 1 } }, { type: 'assistant/message', seq: 8, time: 8, data: { turn: 2, step: 1, content: [ { type: 'tool-call', id: CallId('new-call'), name: 'bash', arguments: '{}' }, - ] } }, + ], provenance: { provider: 'mock', model: 'mock' } } }, ] const closers = interruptedTurnClosers(events) expect(closers.map(e => e.type)).toEqual(['tool/result', 'step/end', 'turn/end']) @@ -128,7 +128,7 @@ describe('interruptedTurnClosers', () => { { type: 'assistant/message', seq: 2, time: 2, data: { turn: 1, step: 1, content: [ { type: 'tool-call', id: CallId('call-a'), name: 'bash', arguments: '{}' }, { type: 'tool-call', id: CallId('call-b'), name: 'bash', arguments: '{}' }, - ] } }, + ], provenance: { provider: 'mock', model: 'mock' } } }, // call-a got answered before the crash; call-b did not. { type: 'tool/result', seq: 3, time: 3, data: { turn: 1, step: 1, callId: CallId('call-a'), content: [], isError: false } }, ] @@ -144,7 +144,7 @@ describe('interruptedTurnClosers', () => { { type: 'step/start', seq: 1, time: 1, data: { turn: 1, step: 1 } }, { type: 'assistant/message', seq: 2, time: 2, data: { turn: 1, step: 1, content: [ { type: 'tool-call', id: CallId('call-1'), name: 'bash', arguments: '{}' }, - ] } }, + ], provenance: { provider: 'mock', model: 'mock' } } }, { type: 'tool/call', seq: 3, time: 3, data: { turn: 1, step: 1, callId: CallId('call-1'), name: 'bash', arguments: '{}' } }, ] const closers = interruptedTurnClosers(events) diff --git a/packages/core/session/tests/request-header.spec.ts b/packages/core/session/tests/request-header.spec.ts index 8a5af819c3..6cd2e2c7fb 100644 --- a/packages/core/session/tests/request-header.spec.ts +++ b/packages/core/session/tests/request-header.spec.ts @@ -12,7 +12,7 @@ import { Session, SessionId, applyHeaderDelta, canonicalHeader, diffHeader, fold import type { EpochHeader, SessionEvent } from '@deepseek-ai/dsh-session' import type { Message, ToolSchema } from '@deepseek-ai/dsh-llm' -const CONFIG = { model: 'm' } +const CONFIG = { provider: 'mock', model: 'm' } function tool(name: string, description = 'd'): ToolSchema { return { name, description, parameters: { type: 'object' } } @@ -100,10 +100,10 @@ describe('diffHeader / applyHeaderDelta', () => { }) it('replaces the config whole and leaves untouched parts alone', () => { - const prev = canonicalHeader({ config: { model: 'm' }, system: 's', tools: [tool('t')] }) - const next = canonicalHeader({ config: { model: 'm2', temperature: 0.1 }, system: 's', tools: [tool('t')] }) + const prev = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 's', tools: [tool('t')] }) + const next = canonicalHeader({ config: { provider: 'mock', model: 'm2', temperature: 0.1 }, system: 's', tools: [tool('t')] }) const delta = roundTrip(prev, next) - expect(delta).toEqual({ config: { model: 'm2', temperature: 0.1 } }) + expect(delta).toEqual({ config: { provider: 'mock', model: 'm2', temperature: 0.1 } }) }) }) @@ -163,16 +163,16 @@ describe('foldRequestHeader', () => { it('folds snapshot then deltas into the header in force, skipping unrelated events', () => { const session = new Session(SessionId('fold')) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - const first = canonicalHeader({ config: { model: 'm' }, system: 'a\nb', tools: [tool('t')] }) + const first = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 'a\nb', tools: [tool('t')] }) session.append('request/header', { header: first, reason: 'initial' }) session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - const second = canonicalHeader({ config: { model: 'm' }, system: 'a\nc', tools: [tool('t')] }) + const second = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 'a\nc', tools: [tool('t')] }) session.append('request/header-delta', diffHeader(first, second)!) expect(foldRequestHeader(headerEvents(session))).toEqual(second) // A later snapshot replaces the state wholesale (the 'resume'/'fallback' anchor). - const third = canonicalHeader({ config: { model: 'other' } }) + const third = canonicalHeader({ config: { provider: 'mock', model: 'other' } }) session.append('request/header', { header: third, reason: 'resume' }) expect(foldRequestHeader(headerEvents(session))).toEqual(third) }) @@ -180,7 +180,7 @@ describe('foldRequestHeader', () => { it('throws on a delta before any snapshot (corrupt log)', () => { const session = new Session(SessionId('fold-corrupt')) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - session.append('request/header-delta', { config: { model: 'x' } }) + session.append('request/header-delta', { config: { provider: 'mock', model: 'x' } }) expect(() => foldRequestHeader(headerEvents(session))).toThrow(/before any request\/header snapshot/) }) }) diff --git a/packages/core/session/tests/session.spec.ts b/packages/core/session/tests/session.spec.ts index 2204fc9027..e80f1b1373 100644 --- a/packages/core/session/tests/session.spec.ts +++ b/packages/core/session/tests/session.spec.ts @@ -10,7 +10,7 @@ describe('Session', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('user/message', { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) session.append('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'hi' } }) - session.append('assistant/message', { + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [ { type: 'text', text: 'let me check' }, @@ -63,7 +63,7 @@ describe('Session', () => { const original = new Session(SessionId('s3')) original.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) original.append('user/message', { content: [{ type: 'text', text: 'q' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - original.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, { surfaceOp: 'append' }) + original.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, { surfaceOp: 'append' }) original.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) const replayed = new Session(SessionId('s3-replay'), [...original.events]) @@ -71,6 +71,43 @@ describe('Session', () => { expect(replayed.seq).toBe(original.seq) }) + it('rejects pre-provider request headers and assistant messages on seed/load', () => { + const requestHeader = { + type: 'request/header', seq: 0, time: 1, + data: { header: { config: { model: 'old-model' } }, reason: 'initial' }, + } as unknown as SessionEvent + expect(() => new Session(SessionId('old-header'), [requestHeader])) + .toThrow('seed request/header at index 0 lacks provider/model') + + const requestDelta = { + type: 'request/header-delta', seq: 0, time: 1, + data: { config: { model: 'old-model' } }, + } as unknown as SessionEvent + expect(() => new Session(SessionId('old-delta'), [requestDelta])) + .toThrow('seed request/header-delta at index 0 lacks provider/model') + + const assistantMessage = { + type: 'assistant/message', seq: 0, time: 1, + data: { turn: 1, step: 1, content: [{ type: 'text', text: 'old' }] }, + surfaceOp: 'append', + } as unknown as SessionEvent + expect(() => new Session(SessionId('old-assistant'), [assistantMessage])) + .toThrow('seed assistant/message at index 0 lacks provider/model provenance') + + const malformedHeader = { + type: 'request/header', seq: 0, time: 1, + data: { header: 'old-header' }, + } as unknown as SessionEvent + expect(() => new Session(SessionId('malformed-header'), [malformedHeader])) + .toThrow('seed request/header at index 0 lacks provider/model') + + const unrelatedPrimitiveData = { + type: 'plugin/event', seq: 0, time: 1, data: null, + } as unknown as SessionEvent + expect(new Session(SessionId('primitive-plugin-data'), [unrelatedPrimitiveData]).events) + .toEqual([unrelatedPrimitiveData]) + }) + it('isolates the log from mutation through a derived message (append-only contract)', () => { const session = new Session(SessionId('s4')) session.append('user/message', { content: [{ type: 'text', text: 'original' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) diff --git a/packages/core/session/tests/surface.spec.ts b/packages/core/session/tests/surface.spec.ts index 257828e466..ec06eba5c2 100644 --- a/packages/core/session/tests/surface.spec.ts +++ b/packages/core/session/tests/surface.spec.ts @@ -8,7 +8,7 @@ function surfaceSession(): Session { const s = new Session(SessionId('ss')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('user/message', { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'hi' }] }, { surfaceOp: 'append' }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'hi' }] }, { surfaceOp: 'append' }) s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) return s } @@ -74,7 +74,7 @@ describe('SurfaceManager', () => { // Surface nodes: seq 1 (user), seq 2 (assistant). // Replace both with a compaction marker. Both 1 and 2 are valid surface seqs. s.append('assistant/message', - { turn: 2, step: 1, content: [{ type: 'text', text: 'summary' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 2, step: 1, content: [{ type: 'text', text: 'summary' }] }, { surfaceOp: { op: 'replace', start: 1, end: 2 }, sourceEventSeqs: [1, 2] }, ) // Now the surface should have just the compaction node. @@ -91,7 +91,7 @@ describe('SurfaceManager', () => { s.append('user/message', { content: [{ type: 'text', text: 'c' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2 // Replace seq 0 through 1 inclusive: shadow a and b, keep c. s.append('assistant/message', - { turn: 1, step: 1, content: [{ type: 'text', text: 'summary' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'summary' }] }, { surfaceOp: { op: 'replace', start: 0, end: 1 }, sourceEventSeqs: [0, 1] }, ) // seq 3 expect(s.surface.nodes.map(n => n.seq)).toEqual([3, 2]) @@ -108,7 +108,7 @@ describe('SurfaceManager', () => { s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 1 // Replace only seq 1 (single node). s.append('assistant/message', - { turn: 1, step: 1, content: [{ type: 'text', text: 'x' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'x' }] }, { surfaceOp: { op: 'replace', start: 1, end: 1 }, sourceEventSeqs: [1] }, ) // seq 2 expect(s.surface.nodes.map(n => n.seq)).toEqual([0, 2]) @@ -120,7 +120,7 @@ describe('SurfaceManager', () => { const s = new Session(SessionId('bad-start')) s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 0 s.append('assistant/message', - { turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, { surfaceOp: { op: 'replace', start: 5, end: 0 }, sourceEventSeqs: [5, 0] }, ) expect(() => s.surface.nodes).toThrow(/surface replace: start seq 5 not found/) @@ -130,7 +130,7 @@ describe('SurfaceManager', () => { const s = new Session(SessionId('bad-end')) s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 0 s.append('assistant/message', - { turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, { surfaceOp: { op: 'replace', start: 0, end: 99 }, sourceEventSeqs: [0] }, ) expect(() => s.surface.nodes).toThrow(/surface replace: end seq 99 not found/) @@ -142,7 +142,7 @@ describe('SurfaceManager', () => { s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 1 // start=1, end=0 would be reversed order. s.append('assistant/message', - { turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, { surfaceOp: { op: 'replace', start: 1, end: 0 }, sourceEventSeqs: [1, 0] }, ) expect(() => s.surface.nodes).toThrow(/start seq 1.*after end seq 0/) @@ -151,7 +151,7 @@ describe('SurfaceManager', () => { it('sourceEventSeqs is snapshot so caller mutation does not affect logged event', () => { const s = new Session(SessionId('immutable')) const sources = [10, 20] - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'h' }] }, { surfaceOp: 'append', sourceEventSeqs: sources }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'h' }] }, { surfaceOp: 'append', sourceEventSeqs: sources }) // Mutate caller's array after append. sources.push(30) sources[0] = 99 @@ -166,7 +166,7 @@ describe('SurfaceManager', () => { s.append('user/message', { content: [{ type: 'text', text: 'c' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2 // Replace the middle node (seq 1) only, keeping seq 0 and seq 2. s.append('assistant/message', - { turn: 1, step: 1, content: [{ type: 'text', text: 'x' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'x' }] }, { surfaceOp: { op: 'replace', start: 1, end: 1 }, sourceEventSeqs: [1] }, ) // seq 3 expect(s.surface.nodes.map(n => n.seq)).toEqual([0, 3, 2]) @@ -183,7 +183,7 @@ describe('SurfaceManager', () => { const s = new Session(SessionId('immutable-op')) s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) const op = { op: 'replace' as const, start: 0, end: 0 } - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: op, sourceEventSeqs: [0] }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: op, sourceEventSeqs: [0] }) // Mutate caller's object after append. op.start = 99 const logged = s.events[1]! as SurfaceEvent @@ -208,7 +208,7 @@ describe('deriveMessages with surface', () => { s.append('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'h' } }) s.append('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'text-delta', index: 1, text: 'i' } }) s.append('user/message', { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'hi' }] }, { surfaceOp: 'append' }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'hi' }] }, { surfaceOp: 'append' }) s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) // Chunks and boundaries are NOT in the surface, so only 2 messages. expect(s.deriveMessages()).toHaveLength(2) @@ -217,7 +217,7 @@ describe('deriveMessages with surface', () => { it('deriveMessages via surface respects replace (shadowed nodes are excluded)', () => { const s = new Session(SessionId('compacted')) s.append('user/message', { content: [{ type: 'text', text: 'original' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'compacted' }] }, { surfaceOp: { op: 'replace', start: 0, end: 0 }, sourceEventSeqs: [0] }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'compacted' }] }, { surfaceOp: { op: 'replace', start: 0, end: 0 }, sourceEventSeqs: [0] }) // Only the compaction node is visible. const messages = s.deriveMessages() expect(messages).toHaveLength(1) @@ -239,7 +239,7 @@ describe('Session.append surface opts', () => { it('records sourceEventSeqs and surfaceOp on the event', () => { const s = new Session(SessionId('opts')) const event = s.append('assistant/message', - { turn: 1, step: 1, content: [{ type: 'text', text: 'h' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'h' }] }, { surfaceOp: 'append', sourceEventSeqs: [3, 5, 7] }, ) expect(event.sourceEventSeqs).toEqual([3, 5, 7]) @@ -256,7 +256,7 @@ describe('Session.append surface opts', () => { const seed: SessionEvent[] = [ { type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } }, { type: 'step/start', seq: 1, time: 2, data: { turn: 1, step: 1 } }, - { type: 'assistant/message', seq: 2, time: 3, data: { turn: 1, step: 1, content: [] }, surfaceOp: 'append' }, + { type: 'assistant/message', seq: 2, time: 3, data: { turn: 1, step: 1, content: [], provenance: { provider: 'mock', model: 'mock' } }, surfaceOp: 'append' }, { type: 'step/end', seq: 3, time: 4, data: { turn: 1, step: 1 } }, { type: 'turn/end', seq: 4, time: 5, data: { turn: 1, reason: { kind: 'completed' } } }, ] @@ -274,7 +274,7 @@ describe('Session.append surface opts', () => { it('surfaceOp primitives are not cloned (they are immutable)', () => { const s = new Session(SessionId('prim')) - const event = s.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append' }) + const event = s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append' }) // The string 'append' is a primitive — identity-preserving is fine. expect(event.surfaceOp).toBe('append') }) diff --git a/packages/core/session/tests/tool-pairing.spec.ts b/packages/core/session/tests/tool-pairing.spec.ts index 307b0d8658..9765abbd01 100644 --- a/packages/core/session/tests/tool-pairing.spec.ts +++ b/packages/core/session/tests/tool-pairing.spec.ts @@ -56,7 +56,7 @@ function toolStepSession(): Session { s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('user/message', { content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }, SURFACE) s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [ { type: 'text', text: 'calling' }, @@ -122,7 +122,7 @@ describe('isToolPairingBalanced — region END (cut after a node)', () => { const s = new Session(SessionId('open-step')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], }, SURFACE) @@ -135,7 +135,7 @@ describe('isToolPairingBalanced — region END (cut after a node)', () => { const s = new Session(SessionId('trailing-steer')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, SURFACE) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, SURFACE) s.append('step/end', { turn: 1, step: 1 }) s.append('steering/message', { turn: 1, content: [{ type: 'text', text: 's' }], source: { kind: 'user' } }, SURFACE) expect(endBalanced(s, seqOf(s, 'steering/message'))).toBe(true) @@ -156,7 +156,7 @@ describe('isToolPairingBalanced — multiple tool calls in one assistant message const s = new Session(SessionId('two-call')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [ { type: 'tool-call', id: CallId('c1'), name: 'a', arguments: '{}' }, @@ -190,7 +190,7 @@ describe('isToolPairingBalanced — a mid-step injection context/message', () => const s = new Session(SessionId('mid-inject')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], }, SURFACE) @@ -247,7 +247,7 @@ describe('isToolPairingBalanced — CBR-001: a head checkpoint left by a replace s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) s.append('user/message', { content: [{ type: 'text', text: 'u1' }], source: { kind: 'user' } }, SURFACE) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], }, SURFACE) @@ -267,7 +267,7 @@ describe('isToolPairingBalanced — CBR-001: a head checkpoint left by a replace }, { surfaceOp: { op: 'replace', start: u1, end: result } }) // The step's own assistant/message lands AFTER the checkpoint in the log, // still inside the open step. - s.append('assistant/message', { turn: 2, step: 1, content: [{ type: 'text', text: 'a2' }] }, SURFACE) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 2, step: 1, content: [{ type: 'text', text: 'a2' }] }, SURFACE) return s } diff --git a/packages/fs/tool-fs/tests/fs-tools.e2e.ts b/packages/fs/tool-fs/tests/fs-tools.e2e.ts index a270e7c6d8..ca93bad63d 100644 --- a/packages/fs/tool-fs/tests/fs-tools.e2e.ts +++ b/packages/fs/tool-fs/tests/fs-tools.e2e.ts @@ -35,7 +35,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => ctx = await fsHarness(workdir, SYSTEM) // agentLoop.create prepares a session with no cwd, so the provider default // (config.cwd = workdir) is the workspace. - const agent = ctx.agentLoop.create(AgentId('fs-e2e'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('fs-e2e'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Create a file named note.txt containing exactly the line: status: draft. ' @@ -68,7 +68,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => agentId: AgentId('fs-e2e-cwd'), sessionId: SessionId(`fs-e2e-cwd-${Date.now()}`), meta: { cwd: sessionDir }, - agentOptions: { model: 'deepseek-v4-flash' }, + agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' }, }) handle.agent.send([{ type: 'text', text: 'Use the write tool to create a file named where.txt containing exactly the line: here. Tell me when done.' }]) diff --git a/packages/fs/tool-fs/tests/harness.ts b/packages/fs/tool-fs/tests/harness.ts index 61c163c28b..1bab80baaa 100644 --- a/packages/fs/tool-fs/tests/harness.ts +++ b/packages/fs/tool-fs/tests/harness.ts @@ -29,7 +29,7 @@ export async function fsHarness(fsCwd: string, persona = ''): Promise { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) - await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) + await ctx.plugin(LlmDeepSeek) await ctx.plugin(LocalFileSystem, { cwd: fsCwd }) await ctx.plugin(FsPolicy) await ctx.plugin(ToolFs) diff --git a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts index 565f1076b5..89c18a5221 100644 --- a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts +++ b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts @@ -57,7 +57,7 @@ describe('threshold escalation', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -78,7 +78,7 @@ describe('threshold escalation', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -100,7 +100,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -124,7 +124,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -142,7 +142,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -163,7 +163,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -179,7 +179,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -195,7 +195,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -215,8 +215,8 @@ describe('chain semantics', () => { toolCallResponse('b3', 'probe', { q: 1 }), textResponse('done'), ])) - const agentA = ctx.agentLoop.create(AgentId('a'), { model: 'mock-a' }) - const agentB = ctx.agentLoop.create(AgentId('b'), { model: 'mock-b' }) + const agentA = ctx.agentLoop.create(AgentId('a'), { provider: 'mock-a', model: 'model-a' }) + const agentB = ctx.agentLoop.create(AgentId('b'), { provider: 'mock-b', model: 'model-b' }) agentA.send([{ type: 'text', text: 'go' }]) agentB.send([{ type: 'text', text: 'go' }]) await Promise.all([waitForIdle(ctx, agentA), waitForIdle(ctx, agentB)]) @@ -235,7 +235,7 @@ describe('chain semantics', () => { textResponse('turn two done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) agent.send([{ type: 'text', text: 'again' }]) @@ -256,14 +256,14 @@ describe('chain semantics', () => { // (the loop.spec pattern): a child plugin fiber owns `first`. let first!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - first = inner.agentLoop.create(AgentId('reused'), { model: 'mock' }) + first = inner.agentLoop.create(AgentId('reused'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) first.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, first) await fiber.dispose() await first.done - const second = ctx.agentLoop.create(AgentId('reused'), { model: 'mock' }) + const second = ctx.agentLoop.create(AgentId('reused'), { provider: 'mock', model: 'mock' }) second.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, second) @@ -279,7 +279,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -295,7 +295,7 @@ describe('chain semantics', () => { toolCallResponse('c1', 'probe', { q: 1 }), // if the direct call had counted, this would be #2 textResponse('done'), ])) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -317,7 +317,7 @@ describe('fold onto the downstream decision', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -348,7 +348,7 @@ describe('fold onto the downstream decision', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 2cbc995ce3..ef2bf1087c 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -95,7 +95,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'do something' }]) await waitForIdle(ctx, agent) @@ -118,7 +118,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -143,7 +143,7 @@ describe('hooks-claude bridge — PreToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'danger', description: 'd', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'use danger' }]) await waitForIdle(ctx, agent) @@ -166,7 +166,7 @@ describe('hooks-claude bridge — PreToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'safe', description: 's', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ran ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'use safe' }]) await waitForIdle(ctx, agent) @@ -188,7 +188,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(dir, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'raw output' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -209,7 +209,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(dir, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -233,7 +233,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -257,7 +257,7 @@ describe('hooks-claude bridge — SessionStart', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // session-start fires async (detached .then → agent.inject); wait for the // injected context/message to actually land before sending, rather than a // fixed sleep that flakes under load. @@ -359,7 +359,7 @@ describe('hooks-claude bridge — load resilience', () => { await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksClaude, { configPath: '/nonexistent/hooks.json' }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The turn ran normally — no hooks, no crash. @@ -385,7 +385,7 @@ describe('hooks-claude bridge — load resilience', () => { const fiber = await ctx.plugin(HooksClaude, { configPath: join(dir, 'hooks.json') }) await fiber.dispose() ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index 7feb46df05..af9b6e9289 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -72,7 +72,7 @@ describe('hooks-claude coverage — config option arms + substitution + skip war const ctx = await harness(path, adapter, { pluginRoot: d, projectDir: d }) ctx.logger.warn = warn as never ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) // substituted command ran @@ -88,7 +88,7 @@ describe('hooks-claude coverage — config option arms + substitution + skip war ctx.logger.warn = warn as never let sawArgs: unknown ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: { command: { type: 'string' } }, async execute(args) { sawArgs = args; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // updatedInput is NOT honored — the tool ran with the ORIGINAL args. @@ -104,7 +104,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ran')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The prompt proceeded unchanged; no context/message injected. @@ -134,7 +134,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -159,7 +159,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter, { stderrSummaryMaxChars: 40 }) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -175,7 +175,7 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) @@ -192,7 +192,7 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // A second model request ran → the empty-reason block forced continuation. @@ -240,7 +240,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -254,7 +254,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -283,7 +283,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('no')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const turnEnd = events(agent).findLast(e => e.type === 'turn/end') @@ -298,7 +298,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // ask (no reason) → degrades to deny with the registry's generic message. @@ -313,7 +313,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -342,7 +342,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () // the protocol lib's reference default, not a config knob). HooksClaude.apply(ctx, { configPath: join(d, 'hooks.json') }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) @@ -357,7 +357,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) @@ -372,7 +372,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -393,7 +393,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -410,7 +410,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -430,7 +430,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) // the mismatched deny was discarded → the tool ran @@ -448,7 +448,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) // NB: no projectDir // The factory create() path honors meta.cwd (the plain agentLoop.create() does not). const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { provider: 'mock', model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) expect(events(handle.agent as ReactLoopAgent).some(e => e.type === 'context/message' @@ -468,7 +468,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => // A later listener that blocks every prompt (registered AFTER the bridge). const { AgentId: AId } = await import('@deepseek-ai/dsh-agent') ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) - const agent = ctx.agentLoop.create(AId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // the downstream block won: the model was never called, no user/message was @@ -492,7 +492,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => content: [{ type: 'text' as const, text: 'rewritten-prompt' }], additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) @@ -514,7 +514,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -533,7 +533,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -557,7 +557,7 @@ describe('hooks-claude coverage — executor reject + no-open-turn', () => { const bash = ctx.bash bash.run = (() => Promise.reject(new Error('executor down'))) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -573,7 +573,7 @@ describe('hooks-claude coverage — detached-listener catch handlers', () => { const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Make inject throw, forcing the SessionStart .catch path. const original = agent.inject.bind(agent) let threw = false @@ -613,7 +613,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { provider: 'mock', model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) @@ -649,7 +649,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server // Register a live child on its own session cwd; emit subagent/end with its id. const { SessionId } = await import('@deepseek-ai/dsh-session') - const childHandle = await ctx.agents.create({ agentId: AgentId('child-stop'), sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { model: 'mock' } }) + const childHandle = await ctx.agents.create({ agentId: AgentId('child-stop'), sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { provider: 'mock', model: 'mock' } }) ctx.emit('subagent/end', { provider: 'inproc', id: childHandle.agent.id, stopReason: 'completed' }) await waitFor(() => existsSync(marker)) @@ -670,7 +670,7 @@ describe('hooks-claude coverage — systemMessage is warned, not surfaced', () = const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) @@ -691,7 +691,7 @@ describe('hooks-claude coverage — SessionStart timing is best-effort (no-wait) const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Send immediately — do NOT wait for the session-start inject. agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) diff --git a/packages/hooks/hooks-codex/tests/bridge.spec.ts b/packages/hooks/hooks-codex/tests/bridge.spec.ts index e0677306b0..6cdfd2f81f 100644 --- a/packages/hooks/hooks-codex/tests/bridge.spec.ts +++ b/packages/hooks/hooks-codex/tests/bridge.spec.ts @@ -82,7 +82,7 @@ describe('hooks-codex bridge', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'no' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'run ls' }]) await waitForIdle(ctx, agent) @@ -107,7 +107,7 @@ describe('hooks-codex bridge', () => { // Step 1 has no tool calls → would stop; the Stop hook forces step 2. const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer after goal')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -124,7 +124,7 @@ describe('hooks-codex bridge', () => { const adapter = new MockAdapter([textResponse('fine')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // Ran normally; the unknown event was dropped at parse. @@ -135,7 +135,7 @@ describe('hooks-codex bridge', () => { const dir = configDir() // no hooks.json written const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) @@ -161,7 +161,7 @@ describe('hooks-codex bridge', () => { const fiber = await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'm' }) await fiber.dispose() ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone @@ -190,7 +190,7 @@ describe('hooks-codex bridge', () => { ctx.llm.registerAdapter(['mock'], new MockAdapter([])) const warn = vi.fn() ctx.logger.warn = warn as never - ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) // fires agent/session-start + ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // fires agent/session-start await waitFor(() => existsSync(marker)) const pid = Number(readFileSync(pidFile, 'utf8').trim()) await fiber.dispose() diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index 774b308fa1..95d02e40a0 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -52,7 +52,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) const adapter = new MockAdapter([textResponse('no')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) const te = events(agent).findLast(e => e.type === 'turn/end') @@ -64,7 +64,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"ctx-x"}}\'\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('ctx-x') }) @@ -78,7 +78,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) expect(events(agent).some(e => e.type === 'user/message')).toBe(false) @@ -96,7 +96,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { content: [{ type: 'text' as const, text: 'rewritten-prompt' }], additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) expect(req).toContain('from-bridge') @@ -111,7 +111,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true) @@ -125,7 +125,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.isError).toBe(true) @@ -138,7 +138,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"start-ctx"}}\'\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) await waitFor(() => events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('start-ctx')))) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) @@ -151,7 +151,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.isError).toBe(true) @@ -164,7 +164,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('post-ctx')))).toBe(true) }) @@ -176,7 +176,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // clean-exit hook allows; commandOf returned '' }) @@ -187,7 +187,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0) @@ -200,7 +200,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true) @@ -223,7 +223,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter, { stderrSummaryMaxChars: 40 }) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary).toBe('x'.repeat(40) + '…') @@ -246,7 +246,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { // Direct apply (schema bypass) → the `model ?? ''` fallback is exercised. HooksCodex.apply(ctx, { configPath: join(d, 'hooks.json') }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) expect(warn).toHaveBeenCalledWith(expect.stringContaining('async hook')) @@ -259,7 +259,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -273,7 +273,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\ntouch "${marker}"\nexit 0\n`) }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) await waitFor(() => existsSync(marker)) // the clean no-output hook has finished agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(events(agent).some(e => e.type === 'context/message')).toBe(false) @@ -285,7 +285,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.inject = (() => { throw new Error('inject boom') }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SessionStart hook failed'))) expect(warn).toHaveBeenCalledWith(expect.stringContaining('SessionStart hook failed')) @@ -298,7 +298,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -311,7 +311,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // matcher didn't match → no hook ran → tool proceeded expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) @@ -327,7 +327,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded @@ -340,7 +340,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true) @@ -352,7 +352,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.isError).toBe(true) @@ -369,7 +369,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 7 }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'number' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_input: { command: string } } expect(payload.tool_input.command).toBe('') @@ -405,7 +405,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.bash.run = (() => Promise.reject(new Error('executor down'))) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false) @@ -419,7 +419,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { Stop: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\nexit 2\n`) }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) // empty-reason block forced continuation expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('blocked by Stop hook') @@ -432,7 +432,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho "extra guidance from a plain hook"\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('extra guidance from a plain hook') }) @@ -448,7 +448,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', `#!/usr/bin/env bash\ntouch "${marker}"\necho "stale"\nexit 2\n`) }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) await waitFor(() => existsSync(marker)) // the exit-2 hook has finished expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('stale')))).toBe(false) @@ -462,7 +462,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'e.sh', '#!/usr/bin/env bash\necho "stale"\nexit 1\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // exit 1 is non-blocking → the turn ran expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('stale') @@ -473,7 +473,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'ss.sh', '#!/usr/bin/env bash\necho "session preamble"\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) await waitFor(() => events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('session preamble')))) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) @@ -487,7 +487,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'j.sh', '#!/usr/bin/env bash\necho \'{"unrelated":"json"}\'\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('unrelated') }) @@ -502,7 +502,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'shell', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_name: string; tool_input: { command: string } } expect(payload.tool_name).toBe('shell') @@ -518,7 +518,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(false) // the matcher fired → the hook denied the tool expect(events(agent).some(e => e.type === 'hook/invoked' && e.data.point === 'PreToolUse')).toBe(true) @@ -530,7 +530,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('heads up') @@ -553,7 +553,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { ctx.llm.registerAdapter(['mock'], adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { provider: 'mock', model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) expect(existsSync(marker)).toBe(true) diff --git a/packages/llm/README.md b/packages/llm/README.md index 3fc5c9cf9e..d971fc830c 100644 --- a/packages/llm/README.md +++ b/packages/llm/README.md @@ -6,6 +6,6 @@ The LLM seam and its provider adapters. The interface package (`llm`) owns the a |---|---|---| | `llm/` | Abstract LLM service + content-block vocabulary + chunk assembler | `ctx.llm` | | `llm-deepseek/` | DeepSeek API adapter (hand-rolled fetch/SSE) | (registers on `ctx.llm`) | -| `llm-pi-ai/` | DeepSeek adapter via `@earendil-works/pi-ai` (design twin) | (registers on `ctx.llm`) | +| `llm-pi-ai/` | Multi-provider adapter via `@earendil-works/pi-ai` | (registers on `ctx.llm`) | -The interface lives at `llm/llm/`; adapters are flat siblings under the group. A new provider adapter joins here and registers on `ctx.llm` without touching the interface. See [twin LLM adapters](../../docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md) for why two adapters exist. +The interface lives at `llm/llm/`; adapters are flat siblings under the group. Requests route by `provider`, while `model` is passed through to the selected adapter. A new provider adapter joins here and registers one or more provider routes on `ctx.llm` without touching the interface. See [twin LLM adapters](../../docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md) for the contract-validation origin of the two shipping implementations. diff --git a/packages/llm/llm-deepseek/README.md b/packages/llm/llm-deepseek/README.md index 15fad9f881..77b62426e6 100644 --- a/packages/llm/llm-deepseek/README.md +++ b/packages/llm/llm-deepseek/README.md @@ -2,7 +2,7 @@ DeepSeek chat-completions adapter for the harness LLM seam: hand-rolled `fetch` + SSE translation from the official wire format (source of truth: the API docs — guides/thinking_mode, guides/tool_calls, api/create-chat-completion) into the `StreamChunk` protocol. -A second, independent implementation of the same seam exists in `@deepseek-ai/dsh-llm-pi-ai` (library-backed). Same Config shape — pick one per context (registering both for the same model names throws by design). +A second, library-backed implementation of the same seam exists in `@deepseek-ai/dsh-llm-pi-ai`. This package always owns the `deepseek` provider route; mounting a pi-ai profile with `provider: deepseek` in the same context throws `LlmError('DUPLICATE_ADAPTER')` by design. ## Config @@ -12,12 +12,11 @@ A second, independent implementation of the same seam exists in `@deepseek-ai/ds config: apiKey: !!js process.env.DEEPSEEK_API_KEY # or rely on the env fallback baseURL: !!js process.env.DEEPSEEK_BASE_URL # default: https://api.deepseek.com - models: [deepseek-v4-flash, deepseek-v4-pro] # one adapter, registered for each name thinking: enabled # optional; provider default is enabled reasoningEffort: high # optional; high | max — omitted ⇒ not sent ``` -`models` lists every model name this one adapter instance serves: the adapter registers itself for each (the harness model name IS the wire `model` string), so a `generate`/`stream` call routes to it whenever `options.model` is any of them. Registering a second adapter for a name already taken throws `LlmError('DUPLICATE_ADAPTER')` (the LLM service enforces one adapter per model, all-or-nothing). +The plugin registers the single provider route `deepseek`. A request selects it with `provider: deepseek`; its `model` is passed through as the wire `model` string, so changing DeepSeek models does not require lifecycle-time registration. Registering another adapter for `deepseek` throws `LlmError('DUPLICATE_ADAPTER')`. `reasoningEffort` is **omitted by default** — when unset, the `reasoning_effort` wire field is not sent and the server applies its own default for the model. The only accepted values are `high` and `max` (DeepSeek's official effort levels). It is meaningful only with thinking enabled (the provider default). diff --git a/packages/llm/llm-deepseek/src/index.ts b/packages/llm/llm-deepseek/src/index.ts index 3a3d7bb4a1..b5c5758e01 100644 --- a/packages/llm/llm-deepseek/src/index.ts +++ b/packages/llm/llm-deepseek/src/index.ts @@ -1,6 +1,6 @@ /** * DeepSeek LLM adapter plugin: registers a {@link DeepSeekAdapter} for the - * configured model names on `ctx.llm`. + * `deepseek` provider route on `ctx.llm`. * * Config is cordis-native (schemastery). Secrets flow per the repo policy: * `apiKey` from cordis.yml via the `!!js` tag (`!!js process.env.DEEPSEEK_API_KEY`) @@ -12,7 +12,6 @@ * config: * apiKey: !!js process.env.DEEPSEEK_API_KEY * baseURL: !!js process.env.DEEPSEEK_BASE_URL - * models: [deepseek-v4-flash, deepseek-v4-pro] * ``` * * @module @deepseek-ai/dsh-llm-deepseek @@ -45,8 +44,6 @@ export interface Config { apiKey?: string /** Endpoint base; falls back to $DEEPSEEK_BASE_URL, then the public API. */ baseURL?: string - /** Model names to register (sent verbatim on the wire). */ - models?: string[] /** Thinking-mode default for every request (provider default: enabled). */ thinking?: 'enabled' | 'disabled' /** Thinking effort (only meaningful with thinking enabled). */ @@ -56,7 +53,6 @@ export interface Config { export const Config: z = z.object({ apiKey: z.string(), baseURL: z.string(), - models: z.array(z.string()).default(['deepseek-v4-flash', 'deepseek-v4-pro']), thinking: z.union(['enabled', 'disabled']), reasoningEffort: z.union(['high', 'max']), }) @@ -70,10 +66,7 @@ export function apply(ctx: Context, config: Config): void { throw new Error('llm-deepseek: an API key is required (Config.apiKey or $DEEPSEEK_API_KEY)') } const baseURL = config.baseURL ?? process.env.DEEPSEEK_BASE_URL ?? PUBLIC_BASE_URL - // schemastery's .default() guarantees models is set after validation. - const models = config.models as string[] - - ctx.llm.registerAdapter(models, new DeepSeekAdapter({ + ctx.llm.registerAdapter(['deepseek'], new DeepSeekAdapter({ apiKey, baseURL, defaults: { diff --git a/packages/llm/llm-deepseek/tests/adapter.e2e.ts b/packages/llm/llm-deepseek/tests/adapter.e2e.ts index b01b498dff..e02476eaef 100644 --- a/packages/llm/llm-deepseek/tests/adapter.e2e.ts +++ b/packages/llm/llm-deepseek/tests/adapter.e2e.ts @@ -16,11 +16,11 @@ const FLASH = 'deepseek-v4-flash' const PRO = 'deepseek-v4-pro' const contexts: Context[] = [] -async function harness(model: string, config: Partial = {}) { +async function harness(_model: string, config: Partial = {}) { const ctx = new Context() contexts.push(ctx) await ctx.plugin(LlmService) - await ctx.plugin(LlmDeepSeek, { models: [model], ...config }) + await ctx.plugin(LlmDeepSeek, config) return ctx } @@ -134,6 +134,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-deepseek e2e (real API)', () const ctx = await harness(FLASH, { thinking: 'disabled' }) const kinds: string[] = [] for await (const chunk of ctx.llm.stream({ + provider: 'deepseek', model: FLASH, messages: ask('Count from 1 to 5, digits only.'), maxTokens: 50, diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 46f123a1c7..e31b1c2e41 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -86,7 +86,7 @@ const textEvents = [ async function harness(baseURL: string, config: object = {}) { const ctx = new Context() await ctx.plugin(LlmService) - await ctx.plugin(LlmDeepSeek, { apiKey: 'test-key', baseURL, models: ['deepseek-v4-flash'], ...config }) + await ctx.plugin(LlmDeepSeek, { apiKey: 'test-key', baseURL, ...config }) return ctx } @@ -123,6 +123,7 @@ describe('DeepSeekAdapter against a mock server', () => { const kinds: string[] = [] for await (const chunk of ctx.llm.stream({ + provider: 'deepseek', model: 'deepseek-v4-flash', messages: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }], })) { @@ -198,7 +199,7 @@ describe('DeepSeekAdapter against a mock server', () => { ) try { const iterate = async (): Promise => { - for await (const _chunk of adapter.stream({ model: 'm', messages: [] })) { /* drain */ } + for await (const _chunk of adapter.stream({ provider: 'deepseek', model: 'm', messages: [] })) { /* drain */ } } await expect(iterate()).rejects.toThrow(/no response body/) } finally { @@ -224,6 +225,7 @@ describe('DeepSeekAdapter against a mock server', () => { const pending = (async () => { const chunks = [] for await (const chunk of ctx.llm.stream({ + provider: 'deepseek', model: 'deepseek-v4-flash', messages: [], signal: controller.signal, @@ -239,25 +241,24 @@ describe('DeepSeekAdapter against a mock server', () => { }) describe('plugin registration and config', () => { - it('registers the configured models and unregisters on dispose (HMR safety)', async () => { + it('registers the deepseek provider and unregisters on dispose (HMR safety)', async () => { const server = await mockServer([]) const ctx = new Context() await ctx.plugin(LlmService) const fiber = await ctx.plugin(LlmDeepSeek, { apiKey: 'k', baseURL: server.url, - models: ['deepseek-v4-flash', 'deepseek-v4-pro'], }) - expect(ctx.llm.models().sort()).toEqual(['deepseek-v4-flash', 'deepseek-v4-pro']) + expect(ctx.llm.providers()).toEqual(['deepseek']) await fiber.dispose() - expect(ctx.llm.models()).toEqual([]) + expect(ctx.llm.providers()).toEqual([]) }) - it('defaults the model list', async () => { + it('always owns the deepseek provider', async () => { const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(LlmDeepSeek, { apiKey: 'k', baseURL: 'http://127.0.0.1:1' }) - expect(ctx.llm.models().sort()).toEqual(['deepseek-v4-flash', 'deepseek-v4-pro']) + expect(ctx.llm.providers()).toEqual(['deepseek']) }) it('falls back to DEEPSEEK_API_KEY and DEEPSEEK_BASE_URL env vars', async () => { @@ -266,7 +267,7 @@ describe('plugin registration and config', () => { const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(LlmDeepSeek, {}) - expect(ctx.llm.models().length).toBeGreaterThan(0) + expect(ctx.llm.providers()).toEqual(['deepseek']) }) it('throws a clear error when no API key is available', async () => { @@ -275,7 +276,7 @@ describe('plugin registration and config', () => { await ctx.plugin(LlmService) await expect(ctx.plugin(LlmDeepSeek, {})) .rejects.toThrow(/an API key is required/) - expect(ctx.llm.models()).toEqual([]) + expect(ctx.llm.providers()).toEqual([]) }) it('prefers explicit config over env for key and base URL', async () => { @@ -292,7 +293,7 @@ describe('plugin registration and config', () => { vi.stubEnv('DEEPSEEK_BASE_URL', server.url) const ctx = new Context() await ctx.plugin(LlmService) - await ctx.plugin(LlmDeepSeek, { apiKey: 'k', models: ['deepseek-v4-flash'] }) + await ctx.plugin(LlmDeepSeek, { apiKey: 'k' }) await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) expect(server.requests).toHaveLength(1) }) @@ -304,7 +305,7 @@ describe('plugin registration and config', () => { await ctx.plugin(LlmService) // Registration succeeds; no call is made (would hit api.deepseek.com). await ctx.plugin(LlmDeepSeek, {}) - expect(ctx.llm.models().length).toBeGreaterThan(0) + expect(ctx.llm.providers()).toEqual(['deepseek']) }) it('adapter is constructible directly for embedding', () => { diff --git a/packages/llm/llm-deepseek/tests/assemble.ts b/packages/llm/llm-deepseek/tests/assemble.ts index b0182615e0..494eeac494 100644 --- a/packages/llm/llm-deepseek/tests/assemble.ts +++ b/packages/llm/llm-deepseek/tests/assemble.ts @@ -15,11 +15,19 @@ export interface AssembledResult { finish: FinishReason } -export async function assemble(ctx: Context, options: GenerateOptions): Promise { +export async function assemble(ctx: Context, options: Omit & { provider?: string }): Promise { const assembler = new BlockAssembler() - for await (const chunk of ctx.llm.stream(options)) assembler.push(chunk) + const request = { provider: 'deepseek', ...options } + for await (const chunk of ctx.llm.stream(request)) assembler.push(chunk) return { - message: assembler.message(), + message: { + ...assembler.message(), + provenance: { + provider: request.provider, + model: request.model, + ...assembler.replayState === undefined ? {} : { replayState: assembler.replayState }, + }, + }, ...assembler.usage !== undefined ? { usage: assembler.usage } : {}, finish: assembler.finish, } diff --git a/packages/llm/llm-deepseek/tests/serialize.spec.ts b/packages/llm/llm-deepseek/tests/serialize.spec.ts index 3e533f8e7c..a7d5cc7e2a 100644 --- a/packages/llm/llm-deepseek/tests/serialize.spec.ts +++ b/packages/llm/llm-deepseek/tests/serialize.spec.ts @@ -4,7 +4,7 @@ import type { ContentBlock, GenerateOptions, Message } from '@deepseek-ai/dsh-ll import { serializeMessages, serializeRequest } from '@deepseek-ai/dsh-llm-deepseek' function request(overrides: Partial = {}): GenerateOptions { - return { model: 'deepseek-v4-flash', messages: [], ...overrides } + return { provider: 'deepseek', model: 'deepseek-v4-flash', messages: [], ...overrides } } describe('serializeMessages', () => { diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index f74ccd2246..ebf3fc98ed 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -1,42 +1,56 @@ # @deepseek-ai/dsh-llm-pi-ai -DeepSeek adapter for the harness LLM seam backed by [`@earendil-works/pi-ai`](https://www.npmjs.com/package/@earendil-works/pi-ai) (the LLM library behind the pi agent). - -## Why a second adapter exists - -`@deepseek-ai/dsh-llm-deepseek` already talks to the same endpoint. This package is its **design-verification twin**: same models, same wire protocol, completely different internals — a unified LLM library with its own event vocabulary versus hand-rolled fetch/SSE. Anything the harness `StreamChunk` protocol cannot express for BOTH implementations is a core-vocabulary bug. The differences it exercised on purpose: - -- pi-ai hands tool-call `arguments` around as **parsed objects**; the harness keeps raw JSON strings. The adapter patches replay payloads back to the original raw strings before sending them, and re-stringifies parsed output tool calls at `block-end`. -- pi-ai reports failures as **in-stream error events** (it never throws mid-stream); these map to `finish {kind:'error'|'aborted'}` chunks — the protocol's other sanctioned error path besides throwing (which llm-deepseek uses). -- pi-ai folds reasoning tokens into `usage.output`; there is no separate reasoning count to map. -- pi-ai's options omit some DeepSeek/OpenAI-compatible details; the adapter uses its `onPayload` hook to preserve the harness contract (`stop`, scrubbing pi-ai's own per-tool `strict` default — the hand-rolled twin sends no such field — omitted reasoning effort, raw replayed tool arguments). +Generic multi-provider adapter for the harness LLM seam backed by [`@earendil-works/pi-ai`](https://www.npmjs.com/package/@earendil-works/pi-ai). One plugin instance owns an explicit list of provider profiles; every request selects a profile with `GenerateOptions.provider` and resolves `GenerateOptions.model` dynamically from pi-ai's installed catalog. ## Config -Same shape as llm-deepseek (one-line swap in cordis.yml), with pi-ai's thinking-level vocabulary: +Configure credentials and deployment-specific transport settings per provider. Omitting `apiKey` delegates authentication to pi-ai's provider-native ambient discovery. `baseURL` overrides only the endpoint of the selected catalog model, preserving its API family and compatibility metadata, so private proxies such as `https://proxy.example.com:8443` remain supported. ```yaml - id: llm name: '@deepseek-ai/dsh-llm-pi-ai' config: - apiKey: !!js process.env.DEEPSEEK_API_KEY - baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: [deepseek-v4-flash, deepseek-v4-pro] - reasoning: high # off | high | xhigh (xhigh → wire 'max') + providers: + - provider: openai + apiKey: !!js process.env.OPENAI_API_KEY + baseURL: https://proxy.example.com:8443 + reasoning: high + - provider: anthropic + apiKey: !!js process.env.ANTHROPIC_API_KEY + maxRetries: 2 + - provider: openrouter + apiKey: !!js process.env.OPENROUTER_API_KEY + headers: + X-Deployment: production ``` +Each provider name must exist in pi-ai's installed catalog and may appear only once in this plugin instance. Registration with `ctx.llm` is atomic: a collision with any provider route already owned by another adapter fails plugin loading without registering the remaining routes. Model ids are not lifecycle config; an unknown model fails before any provider request with `LlmError('UNKNOWN_MODEL')`. + +Supported profile fields are `provider`, `apiKey`, `baseURL`, `headers`, `reasoning`, `thinkingBudgets`, `cacheRetention`, `transport`, `timeoutMs`, `websocketConnectTimeoutMs`, `maxRetries`, and `maxRetryDelayMs`. They map to pi-ai's common stream options. Harness app attribution wins a conflicting configured header name. + +## Provider/model routing and replay + +The selected pi-ai catalog descriptor supplies the protocol implementation. This includes native API differences such as OpenAI models whose descriptor uses the Responses API rather than Chat Completions; the harness adapter does not hardcode endpoint selection by model name. + +Successful assistant responses store a versioned, lossless-JSON replay state beside their durable provider/model provenance. At request time, `LlmService` passes replay state only when the historical provider route and target provider route are currently owned by this same `PiAiAdapter` instance. The adapter validates the state and restores pi-ai response ids and provider signatures even when the target provider or model changes; pi-ai then decides which metadata its target API can reuse. History without replay state is translated as foreign provider-neutral content and never impersonates a native pi-ai response. + +If a listener rewrites assembled assistant content, the loop drops replay state before logging the message because its provider metadata no longer describes the content. Invalid versions, malformed metadata, and content/block mismatches fail explicitly with `LlmError('INVALID_REPLAY_STATE')`. + +## Vocabulary differences + +- pi-ai tool-call arguments are parsed objects; the harness stores raw JSON strings. The adapter parses input and re-stringifies output. +- pi-ai reports failures as in-stream error events; these map to `finish {kind:'error'|'aborted'}` chunks. +- pi-ai folds reasoning tokens into output usage; there is no separate reasoning count to map. +- `GenerateOptions.stop` is rejected with `UNSUPPORTED_OPTION` because pi-ai's common streaming surface cannot guarantee it across providers. + ## App attribution -Every request carries the shared attribution header from dsh-llm's `attributionHeaders()`, passed through pi-ai's `headers` stream option (pi-ai merges caller headers last, so it always reaches the wire - the unit suite asserts arrival on the mock server, same as llm-deepseek). OpenRouter-specific app attribution headers are intentionally not sent by this adapter contract; they are deferred to a future explicit OpenRouter adapter or mode. See [dsh-llm § App attribution](../llm/README.md#app-attribution-attributionts). +Every request carries the shared attribution header from dsh-llm's `attributionHeaders()`, merged through pi-ai's `headers` stream option. Provider-specific app-attribution headers are not synthesized. See [dsh-llm § App attribution](../llm/README.md#app-attribution-attributionts). ## Dependency weight -pi-ai declares the openai/anthropic/google/mistral/AWS SDKs as install-time dependencies. They are lazy-loaded — only the openai SDK actually loads for this adapter — but they do land in `node_modules`. Accepted for a package whose purpose is design verification. - -## Limitations - -Same MVP contract as llm-deepseek: `tool_choice` is not mapped. +pi-ai installs several provider SDKs and lazy-loads the one selected by the catalog model. The dependency weight is isolated to this opt-in adapter package. ## Testing -Unit suites run against a local `node:http` mock SSE server (pi-ai's openai SDK happily talks to any base URL). Real-API coverage in `tests/adapter.e2e.ts` (`pnpm run test:e2e`, key-gated): V4 Flash + V4 Pro across all exposed reasoning levels (off/high/xhigh), the thinking+tools round trip, and a cross-adapter structural-equivalence check against llm-deepseek. +Unit tests use pi-ai catalog models redirected to local mock servers and cover provider/profile routing, native API selection, endpoint overrides, attribution, conversion, replay-state validation, and cross-provider/model replay within one adapter instance. Real-API coverage remains key-gated under `pnpm run test:e2e`. diff --git a/packages/llm/llm-pi-ai/src/adapter.ts b/packages/llm/llm-pi-ai/src/adapter.ts index 00107e8e1c..ae6cf21ec3 100644 --- a/packages/llm/llm-pi-ai/src/adapter.ts +++ b/packages/llm/llm-pi-ai/src/adapter.ts @@ -1,181 +1,98 @@ /** - * `PiAiAdapter`: the `@earendil-works/pi-ai`-backed implementation of the - * harness LLM seam, pointed at a DeepSeek (OpenAI-compatible) endpoint. - * - * This adapter exists as a design-verification twin of - * `@deepseek-ai/dsh-llm-deepseek`: same models, same wire protocol, - * completely different internals (a unified LLM library with its own event - * vocabulary vs hand-rolled fetch/SSE). Anything the StreamChunk protocol - * cannot express for BOTH implementations is a core-vocabulary bug. + * Generic pi-ai-backed implementation of the Harness LLM seam. * * @module dsh-llm-pi-ai/adapter */ -import { stream as piStream } from '@earendil-works/pi-ai' -import type { Model } from '@earendil-works/pi-ai' -import { attributionHeaders, LlmAdapter } from '@deepseek-ai/dsh-llm' -import { CallId } from '@deepseek-ai/dsh-llm' +import { + getModels, + streamSimple, +} from '@earendil-works/pi-ai' +import type { + Api, + KnownProvider, + Model, + SimpleStreamOptions, +} from '@earendil-works/pi-ai' +import { attributionHeaders, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm' import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' -import { toPiContext, toStreamChunks } from './convert.ts' +import type { PiAiProviderProfile } from './config.ts' +import { toPiContext } from './context.ts' +import { toStreamChunks } from './stream.ts' -/** Reasoning levels surfaced by this adapter (DeepSeek wire: high|max). */ -export type PiAiReasoning = 'off' | 'high' | 'xhigh' - -/** Constructor options for {@link PiAiAdapter}; the plugin's `apply` resolves them from Config + environment. */ +/** Constructor options for {@link PiAiAdapter}. */ export interface PiAiAdapterOptions { - /** Bearer token pi-ai sends on every request. */ - apiKey: string - /** Endpoint base; `/chat/completions` is appended. */ - baseURL: string - /** Thinking level applied to every request ('off' disables thinking). */ - reasoning?: PiAiReasoning | undefined + /** Validated provider profiles this adapter instance owns. */ + profiles: readonly PiAiProviderProfile[] } /** - * Build the inline pi-ai model descriptor for one DeepSeek model name. - * @param modelId - harness model name; sent verbatim on the wire. - * @param options - adapter options; only `baseURL` is read here (key and reasoning apply per request, not per descriptor). - * @returns a descriptor with every DeepSeek compat flag explicit — pi-ai's URL-based auto-detection is never relied on. + * Resolve a catalog model dynamically and apply only the configured endpoint + * override, preserving the catalog's API/capability/compatibility metadata. */ -export function buildModel(modelId: string, options: PiAiAdapterOptions): Model<'openai-completions'> { +function resolveModel(profile: PiAiProviderProfile, modelId: string): Model { + const model = getModels(profile.provider as KnownProvider).find(candidate => candidate.id === modelId) as Model | undefined + if (model === undefined) { + throw new LlmError(`pi-ai provider "${profile.provider}" has no catalog model "${modelId}"`, 'UNKNOWN_MODEL') + } + return profile.baseURL === undefined ? model : { ...model, baseUrl: profile.baseURL } +} + +/** Copy profile stream knobs into pi-ai's common option vocabulary. */ +function profileOptions(profile: PiAiProviderProfile): SimpleStreamOptions { return { - id: modelId, - name: modelId, - api: 'openai-completions', - provider: 'deepseek', - baseUrl: options.baseURL, - // Always true: pi-ai only emits the DeepSeek `thinking` field for - // reasoning-capable models, deriving enabled/disabled from whether a - // reasoningEffort option is passed. DeepSeek's provider default is - // ENABLED, so 'off' must send an explicit {type: 'disabled'} — which - // requires this flag to stay on. - reasoning: true, - // DeepSeek's official effort levels: high|max (xhigh maps to max). - thinkingLevelMap: { minimal: null, low: null, medium: null, high: 'high', xhigh: 'max' }, - input: ['text'], - cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }, - contextWindow: 128_000, - maxTokens: 64_000, - compat: { - // Auto-detection only fires for *.deepseek.com base URLs; the internal - // endpoint (and test mocks) need these set explicitly. - thinkingFormat: 'deepseek', - requiresReasoningContentOnAssistantMessages: true, - supportsReasoningEffort: true, - // DeepSeek documents max_tokens (not OpenAI's max_completion_tokens). - maxTokensField: 'max_tokens', - }, + ...profile.apiKey === undefined ? {} : { apiKey: profile.apiKey }, + ...profile.reasoning === undefined ? {} : { reasoning: profile.reasoning }, + ...profile.thinkingBudgets === undefined ? {} : { thinkingBudgets: profile.thinkingBudgets }, + ...profile.cacheRetention === undefined ? {} : { cacheRetention: profile.cacheRetention }, + ...profile.transport === undefined ? {} : { transport: profile.transport }, + ...profile.timeoutMs === undefined ? {} : { timeoutMs: profile.timeoutMs }, + ...profile.websocketConnectTimeoutMs === undefined ? {} : { websocketConnectTimeoutMs: profile.websocketConnectTimeoutMs }, + ...profile.maxRetries === undefined ? {} : { maxRetries: profile.maxRetries }, + ...profile.maxRetryDelayMs === undefined ? {} : { maxRetryDelayMs: profile.maxRetryDelayMs }, } } -type Payload = { - tools?: { function?: { strict?: unknown } }[] - messages?: { - role?: unknown - tool_calls?: { id?: unknown; function?: { arguments?: unknown } }[] - }[] - reasoning_effort?: unknown - stop?: unknown -} - -function rawToolArguments(options: GenerateOptions): Map { - const raw = new Map() - for (const message of options.messages) { - if (message.role !== 'assistant') continue - for (const block of message.content) { - if (block.type === 'tool-call') raw.set(block.id, block.arguments) - } - } - return raw -} - -function patchPayload(payload: unknown, options: GenerateOptions, reasoning: PiAiReasoning | undefined): unknown { - /* v8 ignore next -- pi-ai onPayload always receives an object; tolerate unusual future hooks defensively */ - if (typeof payload !== 'object' || payload === null) return payload - const body = payload as Payload - - if (reasoning === undefined) { - delete body.reasoning_effort - } - if (options.stop !== undefined) { - body.stop = options.stop - } - - // pi-ai stamps its own `strict` default on every serialized tool; the - // harness tool contract has no strict field and the hand-rolled twin sends - // none, so scrub it for wire parity. - for (const tool of body.tools ?? []) { - /* v8 ignore next -- malformed pi-ai payload guard: real tool entries always carry function */ - if (tool.function === undefined) continue - delete tool.function.strict - } - - const rawById = rawToolArguments(options) - /* v8 ignore next -- defensive for non-chat payloads; OpenAI chat payloads always carry messages */ - for (const message of body.messages ?? []) { - if (message.role !== 'assistant') continue - /* v8 ignore next -- assistant messages without tool_calls need no raw-argument patch */ - for (const call of message.tool_calls ?? []) { - /* v8 ignore next -- malformed pi-ai payload guard: real tool calls always carry a string id */ - if (typeof call.id !== 'string') continue - const raw = rawById.get(CallId(call.id)) - /* v8 ignore next -- pi-ai always emits a function object for assistant tool_calls; guard malformed payloads defensively */ - if (raw !== undefined && call.function !== undefined) call.function.arguments = raw - } - } - - return body -} - /** - * pi-ai-backed adapter. One instance serves every registered model name. - * - * Implementation notes: - * - `onPayload` patches provider payload details pi-ai cannot express directly: - * stop sequences, scrubbing pi-ai's own per-tool `strict` default (the - * hand-rolled twin sends no such field), omitted reasoning effort, and raw - * replayed tool-call arguments. - * - pi-ai reports request failures as in-stream error events; convert.ts - * maps them to `finish {kind:'error'|'aborted'}` chunks rather than - * throwing — both are sanctioned StreamChunk error paths. + * pi-ai-backed multi-provider adapter. Model descriptors are resolved for each + * request, so models need not be registered during the Cordis lifecycle. */ export class PiAiAdapter extends LlmAdapter { - constructor(private readonly options: PiAiAdapterOptions) { + private readonly profiles: ReadonlyMap + + constructor(options: PiAiAdapterOptions) { super() + this.profiles = new Map(options.profiles.map(profile => [profile.provider, profile])) } async * stream(options: GenerateOptions): AsyncIterable { - const model = buildModel(options.model, this.options) - // Undefined config means "provider default" (DeepSeek: thinking ENABLED), - // matching llm-deepseek's omission semantics. pi-ai derives the wire - // thinking toggle from whether reasoningEffort is passed, so undefined maps - // internally to 'high' to get `thinking: enabled`; patchPayload then removes - // `reasoning_effort` so the provider chooses its default effort. - const reasoning = this.options.reasoning ?? 'high' + if (options.stop !== undefined) { + throw new LlmError('llm-pi-ai does not support GenerateOptions.stop', 'UNSUPPORTED_OPTION') + } + const profile = this.profiles.get(options.provider) + if (profile === undefined) { + throw new LlmError(`pi-ai adapter does not own provider "${options.provider}"`, 'NO_ADAPTER') + } + const model = resolveModel(profile, options.model) - // pi-ai's event stream has no iterator-return cancellation hook: if our - // consumer stops early (break / loop abort), the underlying HTTP stream - // would keep draining. Chain an internal controller onto the caller's - // signal and abort it when this generator exits for any reason. + // pi-ai's event stream has no iterator-return cancellation hook: abort its + // provider stream when our consumer exits early as well as on caller abort. const controller = new AbortController() const onCallerAbort = (): void => { controller.abort(options.signal?.reason) } if (options.signal?.aborted) controller.abort(options.signal.reason) else options.signal?.addEventListener('abort', onCallerAbort, { once: true }) try { - const events = piStream(model, toPiContext(options), { - apiKey: this.options.apiKey, - // pi-ai merges caller headers last over its provider defaults, so the - // harness attribution always reaches the wire. - headers: attributionHeaders(), - ...options.temperature !== undefined ? { temperature: options.temperature } : {}, - ...options.maxTokens !== undefined ? { maxTokens: options.maxTokens } : {}, + const events = streamSimple(model, toPiContext(options), { + ...profileOptions(profile), + ...options.temperature === undefined ? {} : { temperature: options.temperature }, + ...options.maxTokens === undefined ? {} : { maxTokens: options.maxTokens }, + ...options.sessionId === undefined ? {} : { sessionId: String(options.sessionId) }, signal: controller.signal, - ...reasoning !== 'off' ? { reasoningEffort: reasoning } : {}, - onPayload: payload => patchPayload(payload, options, this.options.reasoning), - maxRetries: 0, + // Profile headers are deployment-owned; attribution names are + // Harness-owned and therefore win collisions. + headers: { ...profile.headers, ...attributionHeaders() }, }) - yield* toStreamChunks(events) } finally { options.signal?.removeEventListener('abort', onCallerAbort) diff --git a/packages/llm/llm-pi-ai/src/config.ts b/packages/llm/llm-pi-ai/src/config.ts new file mode 100644 index 0000000000..b41ca2dd61 --- /dev/null +++ b/packages/llm/llm-pi-ai/src/config.ts @@ -0,0 +1,99 @@ +/** + * Configuration schema and provider-profile validation for the pi-ai adapter. + * + * @module dsh-llm-pi-ai/config + */ + +import { getProviders } from '@earendil-works/pi-ai' +import type { CacheRetention, ThinkingBudgets, ThinkingLevel, Transport } from '@earendil-works/pi-ai' +import z from 'schemastery' + +/** Configuration for one pi-ai provider route. */ +export interface PiAiProviderProfile { + /** pi-ai provider catalog name and Harness route key. */ + provider: string + /** Provider credential; when absent pi-ai uses its provider-native ambient discovery. */ + apiKey?: string + /** Override the selected catalog model's endpoint without changing its protocol metadata. */ + baseURL?: string + /** Provider request headers; Harness attribution wins reserved names. */ + headers?: Record + /** Provider-neutral pi-ai reasoning level. */ + reasoning?: ThinkingLevel + /** Token budgets used by reasoning providers that support them. */ + thinkingBudgets?: ThinkingBudgets + /** Prompt-cache retention preference. */ + cacheRetention?: CacheRetention + /** Streaming transport preference. */ + transport?: Transport + /** HTTP/provider SDK timeout in milliseconds. */ + timeoutMs?: number + /** WebSocket connection timeout in milliseconds. */ + websocketConnectTimeoutMs?: number + /** Provider SDK retry count. */ + maxRetries?: number + /** Maximum provider-requested retry delay in milliseconds. */ + maxRetryDelayMs?: number +} + +/** Plugin configuration: the non-empty provider profiles this instance owns. */ +export interface Config { + /** Non-empty set of pi-ai provider routes this adapter instance owns. */ + providers: PiAiProviderProfile[] +} + +const thinkingBudgets = z.object({ + minimal: z.number(), + low: z.number(), + medium: z.number(), + high: z.number(), +}) + +const profile = z.object({ + provider: z.string().required(), + apiKey: z.string(), + baseURL: z.string(), + headers: z.dict(z.string()), + reasoning: z.union(['minimal', 'low', 'medium', 'high', 'xhigh']), + thinkingBudgets, + cacheRetention: z.union(['none', 'short', 'long']), + transport: z.union(['sse', 'websocket', 'websocket-cached', 'auto']), + timeoutMs: z.number(), + websocketConnectTimeoutMs: z.number(), + maxRetries: z.number(), + maxRetryDelayMs: z.number(), +}) + +/** Runtime schema for {@link Config}. */ +export const Config: z = z.object({ + providers: z.array(profile).required(), +}) + +/** + * Validate profiles against the installed pi-ai catalog and return a detached + * shallow copy suitable for adapter construction. + * @param profiles - configured provider profiles. + * @returns validated profiles in configuration order. + */ +export function resolveProfiles(profiles: readonly PiAiProviderProfile[]): PiAiProviderProfile[] { + if (profiles.length === 0) throw new Error('llm-pi-ai: providers must contain at least one profile') + const supported = new Set(getProviders()) + const seen = new Set() + return profiles.map((source) => { + if (source.provider.length === 0) throw new Error('llm-pi-ai: provider names must be non-empty') + if (!supported.has(source.provider)) throw new Error(`llm-pi-ai: unknown pi-ai provider "${source.provider}"`) + if (seen.has(source.provider)) throw new Error(`llm-pi-ai: duplicate provider profile "${source.provider}"`) + if (source.apiKey !== undefined && source.apiKey.length === 0) { + throw new Error(`llm-pi-ai: provider "${source.provider}" has an empty apiKey; omit it to use ambient authentication`) + } + if (source.baseURL !== undefined && source.baseURL.length === 0) { + throw new Error(`llm-pi-ai: provider "${source.provider}" has an empty baseURL`) + } + seen.add(source.provider) + return { + ...source, + ...source.headers === undefined ? {} : { headers: { ...source.headers } }, + ...source.thinkingBudgets === undefined ? {} : { thinkingBudgets: { ...source.thinkingBudgets } }, + } + }) +} diff --git a/packages/llm/llm-pi-ai/src/context.ts b/packages/llm/llm-pi-ai/src/context.ts new file mode 100644 index 0000000000..ddb8284448 --- /dev/null +++ b/packages/llm/llm-pi-ai/src/context.ts @@ -0,0 +1,85 @@ +/** + * Harness request-history conversion into pi-ai's Context vocabulary. + * + * @module dsh-llm-pi-ai/context + */ + +import { CallId } from '@deepseek-ai/dsh-llm' +import type { GenerateOptions, Message } from '@deepseek-ai/dsh-llm' +import type { Context as PiContext, Message as PiMessage, Tool as PiTool } from '@earendil-works/pi-ai' +import { toPiAssistant } from './replay.ts' + +/** Join the text blocks of a harness message. */ +function flattenText(message: Message): string { + return message.content + .filter(block => block.type === 'text') + .map(block => block.text) + .join('') +} + +/** + * Convert harness history to a pi-ai Context. Tool results need the tool + * NAME (pi-ai's `toolName`), which the harness doesn't carry on the result + * block — it is recovered from the preceding assistant tool-call with the + * same id. + * @param options - the harness request; `options.system` maps to pi-ai's single `systemPrompt` slot. + * @returns the pi-ai context; `tools` is omitted entirely when the request declares none. + */ +export function toPiContext(options: GenerateOptions): PiContext { + const toolNames = new Map() + const messages: PiMessage[] = [] + + for (const message of options.messages) { + if (message.role === 'system') { + // pi-ai has a single systemPrompt slot; in-history system messages are + // folded into user messages to preserve order (rare in practice — the + // harness sends the system prompt via options.system). + messages.push({ role: 'user', content: flattenText(message), timestamp: 0 }) + continue + } + if (message.role === 'assistant') { + const assistant = toPiAssistant(message) + for (const block of assistant.content) { + if (block.type === 'toolCall') toolNames.set(CallId(block.id), block.name) + } + messages.push(assistant) + continue + } + // user role: text + tool results (each result becomes its own message). + const text = flattenText(message) + const results = message.content.filter(block => block.type === 'tool-result') + if (text.length > 0 || results.length === 0) { + messages.push({ role: 'user', content: text, timestamp: 0 }) + } + for (const result of results) { + messages.push({ + role: 'toolResult', + toolCallId: result.toolCallId, + toolName: toolNames.get(result.toolCallId) ?? 'unknown', + content: [{ + type: 'text', + text: result.content + .filter(block => block.type === 'text') + .map(block => block.text) + .join('') || '(no output)', + }], + isError: result.isError ?? false, + timestamp: 0, + }) + } + } + + const tools: PiTool[] | undefined = options.tools?.map(tool => ({ + name: tool.name, + description: tool.description, + // ToolSchema.parameters is a JSON Schema object; pi-ai's TSchema + // (TypeBox) is structurally JSON Schema, so it assigns directly. + parameters: tool.parameters, + })) + + return { + ...options.system !== undefined ? { systemPrompt: options.system } : {}, + messages, + ...tools !== undefined && tools.length > 0 ? { tools } : {}, + } +} diff --git a/packages/llm/llm-pi-ai/src/convert.ts b/packages/llm/llm-pi-ai/src/convert.ts deleted file mode 100644 index 9652cb7d56..0000000000 --- a/packages/llm/llm-pi-ai/src/convert.ts +++ /dev/null @@ -1,289 +0,0 @@ -/** - * Bidirectional mapping between the harness vocabulary and pi-ai's: - * `GenerateOptions`/`Message[]` → pi-ai `Context`, and pi-ai - * `AssistantMessageEvent`s → harness `StreamChunk`s. - * - * Vocabulary differences worth knowing (they are exactly why this adapter - * exists — an independent implementation stress-tests the StreamChunk - * protocol): - * - pi-ai tool-call `arguments` are PARSED OBJECTS; the harness keeps the - * raw JSON string. We parse on the way into pi-ai, patch provider payloads - * back to the original raw string in the adapter, and re-stringify on output. - * - pi-ai reports errors as in-stream `error` events (it never throws - * mid-stream); the harness expresses those as `finish {kind:'error'}` / - * `{kind:'aborted'}` chunks. - * - pi-ai folds reasoning tokens into `usage.output`; there is no separate - * reasoning count to map. - * - * @module dsh-llm-pi-ai/convert - */ - -import { CallId, LlmError } from '@deepseek-ai/dsh-llm' -import type { FinishReason, GenerateOptions, Message, StreamChunk, TokenUsage } from '@deepseek-ai/dsh-llm' -import type { - AssistantMessage, - AssistantMessageEvent, - Context as PiContext, - Message as PiMessage, - Tool as PiTool, - Usage as PiUsage, -} from '@earendil-works/pi-ai' - -/** Join the text blocks of a harness message. */ -function flattenText(message: Message): string { - return message.content - .filter(block => block.type === 'text') - .map(block => block.text) - .join('') -} - -/** Parse tool-call argument JSON; tolerate model malformations with {}. */ -function parseArguments(raw: string): Record { - try { - const parsed: unknown = JSON.parse(raw) - if (typeof parsed === 'object' && parsed !== null && !Array.isArray(parsed)) { - return parsed as Record - } - } catch { - // fall through - } - return {} -} - -/** - * Convert harness history to a pi-ai Context. Tool results need the tool - * NAME (pi-ai's `toolName`), which the harness doesn't carry on the result - * block — it is recovered from the preceding assistant tool-call with the - * same id. - * @param options - the harness request; `options.system` maps to pi-ai's single `systemPrompt` slot. - * @returns the pi-ai context; `tools` is omitted entirely when the request declares none. - */ -export function toPiContext(options: GenerateOptions): PiContext { - const toolNames = new Map() - const messages: PiMessage[] = [] - - for (const message of options.messages) { - if (message.role === 'system') { - // pi-ai has a single systemPrompt slot; in-history system messages are - // folded into user messages to preserve order (rare in practice — the - // harness sends the system prompt via options.system). - messages.push({ role: 'user', content: flattenText(message), timestamp: 0 }) - continue - } - if (message.role === 'assistant') { - const content: AssistantMessage['content'] = [] - for (const block of message.content) { - switch (block.type) { - case 'text': - content.push({ type: 'text', text: block.text }) - break - case 'reasoning': - // thinkingSignature names the wire field pi-ai replays the CoT - // under. Without it pi-ai falls back to reasoning_content: "" - // (its requiresReasoningContentOnAssistantMessages shim), which - // violates DeepSeek's thinking-mode passback rule on tool-call - // turns (guides/thinking_mode.mdx § Tool Calls). - content.push({ type: 'thinking', thinking: block.text, thinkingSignature: 'reasoning_content' }) - break - case 'tool-call': - toolNames.set(block.id, block.name) - content.push({ - type: 'toolCall', - id: block.id, - name: block.name, - arguments: parseArguments(block.arguments), - }) - break - default: - // plugin-added block types: not representable here. - break - } - } - messages.push({ - role: 'assistant', - content, - api: 'openai-completions', - provider: 'deepseek', - model: options.model, - usage: emptyPiUsage(), - stopReason: content.some(piece => piece.type === 'toolCall') ? 'toolUse' : 'stop', - timestamp: 0, - }) - continue - } - // user role: text + tool results (each result becomes its own message). - const text = flattenText(message) - const results = message.content.filter(block => block.type === 'tool-result') - if (text.length > 0 || results.length === 0) { - messages.push({ role: 'user', content: text, timestamp: 0 }) - } - for (const result of results) { - messages.push({ - role: 'toolResult', - toolCallId: result.toolCallId, - toolName: toolNames.get(result.toolCallId) ?? 'unknown', - content: [{ - type: 'text', - text: result.content - .filter(block => block.type === 'text') - .map(block => block.text) - .join('') || '(no output)', - }], - isError: result.isError ?? false, - timestamp: 0, - }) - } - } - - const tools: PiTool[] | undefined = options.tools?.map(tool => ({ - name: tool.name, - description: tool.description, - // ToolSchema.parameters is a JSON Schema object; pi-ai's TSchema - // (TypeBox) is structurally JSON Schema, so it assigns directly. - parameters: tool.parameters, - })) - - return { - ...options.system !== undefined ? { systemPrompt: options.system } : {}, - messages, - ...tools !== undefined && tools.length > 0 ? { tools } : {}, - } -} - -function emptyPiUsage(): PiUsage { - return { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - totalTokens: 0, - cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 }, - } -} - -/** - * Map pi-ai usage (reasoning folded into output by pi-ai). - * @param usage - cumulative usage from the terminal pi-ai event. - * @returns harness counts; cache fields appear only when non-zero (pi-ai reports zeros, not absence). - */ -export function mapUsage(usage: PiUsage): TokenUsage { - return { - inputTokens: usage.input, - outputTokens: usage.output, - ...usage.cacheRead > 0 ? { cacheReadTokens: usage.cacheRead } : {}, - ...usage.cacheWrite > 0 ? { cacheWriteTokens: usage.cacheWrite } : {}, - } -} - -function classifyPiAiError(message: string): string { - if (/\b(?:401|403)\b/.test(message)) return 'AUTH' - if (/\b429\b|rate.?limit/i.test(message)) return 'RATE_LIMIT' - if (/\b400\b|invalid.?request/i.test(message)) return 'INVALID_REQUEST' - if (/\b5\d\d\b/.test(message)) return 'SERVER' - return 'PI_AI_ERROR' -} - -/** - * Map a terminal pi-ai event to the harness finish reason. - * @param message - the assistant message carried by the `done` or `error` event. - * @returns the harness reason; `error` yields `{kind: 'error'}` with a code classified from the error text. - */ -export function mapStopReason(message: AssistantMessage): FinishReason { - switch (message.stopReason) { - case 'stop': return { kind: 'stop' } - case 'length': return { kind: 'max-tokens' } - case 'toolUse': return { kind: 'tool-calls' } - case 'aborted': return { kind: 'aborted' } - case 'error': { - const text = message.errorMessage ?? 'pi-ai stream error' - return { kind: 'error', message: text, code: classifyPiAiError(text) } - } - } -} - -/** - * Translate the pi-ai event stream into StreamChunks. pi-ai never throws - * mid-stream — failures arrive as `error` events, which become error/aborted - * `finish` chunks (the harness protocol's other error-delivery style). - * @param events - one assistant turn's pi-ai event stream. - * @returns the harness chunks, ending with `usage` then `finish`; throws - * `LlmError` (`STREAM_CLOSED`) if the source ends without a terminal event. - */ -export async function* toStreamChunks(events: AsyncIterable): AsyncGenerator { - // pi-ai contentIndex ↔ our block index map 1:1 (both count blocks from 0 - // in stream order), but we track ids per index for tool calls. - const toolIds = new Map() - - for await (const event of events) { - switch (event.type) { - case 'start': - break - case 'text_start': - yield { type: 'block-start', index: event.contentIndex, blockType: 'text' } - break - case 'text_delta': - yield { type: 'text-delta', index: event.contentIndex, text: event.delta } - break - case 'text_end': - yield { type: 'block-end', index: event.contentIndex, block: { type: 'text', text: event.content } } - break - case 'thinking_start': - yield { type: 'block-start', index: event.contentIndex, blockType: 'reasoning' } - break - case 'thinking_delta': - yield { type: 'reasoning-delta', index: event.contentIndex, text: event.delta } - break - case 'thinking_end': - yield { type: 'block-end', index: event.contentIndex, block: { type: 'reasoning', text: event.content } } - break - case 'toolcall_start': { - // The id/name live on the partial's content at this index. - const partial = event.partial.content[event.contentIndex] - const id = partial?.type === 'toolCall' ? partial.id : '' - const name = partial?.type === 'toolCall' ? partial.name : '' - toolIds.set(event.contentIndex, { id, name }) - yield { type: 'block-start', index: event.contentIndex, blockType: 'tool-call' } - break - } - case 'toolcall_delta': { - const known = toolIds.get(event.contentIndex) - yield { - type: 'tool-call-delta', - index: event.contentIndex, - id: CallId(known?.id ?? ''), - ...known?.name !== undefined && known.name.length > 0 ? { name: known.name } : {}, - argumentsDelta: event.delta, - } - break - } - case 'toolcall_end': - yield { - type: 'block-end', - index: event.contentIndex, - block: { - type: 'tool-call', - id: CallId(event.toolCall.id), - name: event.toolCall.name, - // pi-ai hands back the PARSED arguments; the harness vocabulary - // keeps the raw string. - arguments: JSON.stringify(event.toolCall.arguments), - }, - } - break - case 'done': - yield { type: 'usage', usage: mapUsage(event.message.usage) } - yield { type: 'finish', reason: mapStopReason(event.message) } - return - case 'error': - // In-stream error delivery (pi-ai's style) → error finish chunk - // (the harness's other sanctioned error path besides throwing). - yield { type: 'usage', usage: mapUsage(event.error.usage) } - yield { type: 'finish', reason: mapStopReason(event.error) } - return - // no default: AssistantMessageEvent is pi-ai's closed union; a new - // event type should fail compilation here via tsc's exhaustiveness - // when one is added (switch covers all current variants). - } - } - throw new LlmError('pi-ai event stream ended without done/error', 'STREAM_CLOSED') -} diff --git a/packages/llm/llm-pi-ai/src/index.ts b/packages/llm/llm-pi-ai/src/index.ts index 43468ba507..cbd0dcd435 100644 --- a/packages/llm/llm-pi-ai/src/index.ts +++ b/packages/llm/llm-pi-ai/src/index.ts @@ -1,76 +1,45 @@ /** - * pi-ai-backed DeepSeek adapter plugin. Same Config shape as - * `@deepseek-ai/dsh-llm-deepseek` (one-line swap in cordis.yml), different - * implementation underneath — see `./adapter.ts` for why both exist. + * Generic pi-ai-backed LLM adapter plugin. One plugin instance registers an + * explicit set of provider profiles; requests select a profile by provider and + * resolve the model dynamically from pi-ai's installed catalog. * * ```yaml * - id: llm * name: '@deepseek-ai/dsh-llm-pi-ai' * config: - * apiKey: !!js process.env.DEEPSEEK_API_KEY - * baseURL: !!js process.env.DEEPSEEK_BASE_URL - * models: [deepseek-v4-flash, deepseek-v4-pro] - * reasoning: high + * providers: + * - provider: openai + * apiKey: !!js process.env.OPENAI_API_KEY + * - provider: anthropic + * apiKey: !!js process.env.ANTHROPIC_API_KEY + * - provider: openrouter + * apiKey: !!js process.env.OPENROUTER_API_KEY + * baseURL: https://proxy.example.com/v1 * ``` * * @module @deepseek-ai/dsh-llm-pi-ai */ import type { Context } from 'cordis' -import z from 'schemastery' import type {} from '@deepseek-ai/dsh-llm' import { PiAiAdapter } from './adapter.ts' -import type { PiAiReasoning } from './adapter.ts' +import { Config, resolveProfiles } from './config.ts' -export { buildModel, PiAiAdapter } from './adapter.ts' -export type { PiAiAdapterOptions, PiAiReasoning } from './adapter.ts' -export { mapStopReason, mapUsage, toPiContext, toStreamChunks } from './convert.ts' +export { PiAiAdapter } from './adapter.ts' +export type { PiAiAdapterOptions } from './adapter.ts' +export { Config, resolveProfiles } from './config.ts' +export type { PiAiProviderProfile } from './config.ts' +export { toPiContext } from './context.ts' +export { toPiReplayState } from './replay.ts' +export type { PiAiReplayState } from './replay.ts' +export { mapStopReason, mapUsage, toStreamChunks } from './stream.ts' export const name = 'llm-pi-ai' export const inject = ['llm'] -/** - * Plugin config, validated by the same-named schemastery schema. Every field - * is optional in yml: credentials/endpoint fall back to the environment (a - * missing API key fails plugin load, not the first call). - */ -export interface Config { - /** API key; falls back to $DEEPSEEK_API_KEY. Required one way or the other. */ - apiKey?: string - /** Endpoint base; falls back to $DEEPSEEK_BASE_URL, then the public API. */ - baseURL?: string - /** Model names to register (sent verbatim on the wire). */ - models?: string[] - /** - * Thinking level for every request: 'off' disables thinking mode; 'high' - * and 'xhigh' (wire 'max') set the effort. Omitted = provider default - * (thinking enabled), matching llm-deepseek's omission semantics. - */ - reasoning?: PiAiReasoning -} - -export const Config: z = z.object({ - apiKey: z.string(), - baseURL: z.string(), - models: z.array(z.string()).default(['deepseek-v4-flash', 'deepseek-v4-pro']), - reasoning: z.union(['off', 'high', 'xhigh']), -}) - -/** Public API default; the internal endpoint comes from $DEEPSEEK_BASE_URL. */ -export const PUBLIC_BASE_URL = 'https://api.deepseek.com' - +/** Register one generic pi-ai adapter for all configured provider routes. */ export function apply(ctx: Context, config: Config): void { - const apiKey = config.apiKey ?? process.env.DEEPSEEK_API_KEY - if (apiKey === undefined || apiKey.length === 0) { - throw new Error('llm-pi-ai: an API key is required (Config.apiKey or $DEEPSEEK_API_KEY)') - } - const baseURL = config.baseURL ?? process.env.DEEPSEEK_BASE_URL ?? PUBLIC_BASE_URL - // schemastery's .default() guarantees models is set after validation. - const models = config.models as string[] - - ctx.llm.registerAdapter(models, new PiAiAdapter({ - apiKey, - baseURL, - reasoning: config.reasoning, - })) + const profiles = resolveProfiles(config.providers) + const adapter = new PiAiAdapter({ profiles }) + ctx.llm.registerAdapter(profiles.map(entry => entry.provider), adapter) } diff --git a/packages/llm/llm-pi-ai/src/replay.ts b/packages/llm/llm-pi-ai/src/replay.ts new file mode 100644 index 0000000000..665b236bfe --- /dev/null +++ b/packages/llm/llm-pi-ai/src/replay.ts @@ -0,0 +1,208 @@ +/** + * Durable pi-ai replay metadata and assistant-history reconstruction. + * + * Harness content remains the durable source for text and tool calls. This + * module stores only the provider-native metadata needed to reconstruct a + * pi-ai assistant message on a later request. + * + * @module dsh-llm-pi-ai/replay + */ + +import { LlmError } from '@deepseek-ai/dsh-llm' +import type { Message } from '@deepseek-ai/dsh-llm' +import type { Api, AssistantMessage, Usage as PiUsage } from '@earendil-works/pi-ai' + +type PiAiReplayBlock = + | { type: 'text'; textSignature?: string } + | { type: 'reasoning'; thinkingSignature?: string; redacted?: boolean } + | { type: 'tool-call'; thoughtSignature?: string } + +/** Versioned adapter-private projection required to replay a pi-ai response. */ +export interface PiAiReplayState { + kind: 'pi-ai' + version: 1 + api: Api + provider: string + model: string + responseModel?: string + responseId?: string + stopReason: AssistantMessage['stopReason'] + blocks: PiAiReplayBlock[] +} + +/** Parse tool-call argument JSON; tolerate model malformations with {}. */ +function parseArguments(raw: string): Record { + try { + const parsed: unknown = JSON.parse(raw) + if (typeof parsed === 'object' && parsed !== null && !Array.isArray(parsed)) { + return parsed as Record + } + } catch { + // fall through + } + return {} +} + +/** Construct the zero usage value required by historical pi-ai messages. */ +function emptyPiUsage(): PiUsage { + return { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + totalTokens: 0, + cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 }, + } +} + +/** + * Project a successful pi-ai response into the minimal durable replay state. + * @param message - completed native pi-ai assistant response. + * @returns the versioned lossless-JSON replay projection. + */ +export function toPiReplayState(message: AssistantMessage): PiAiReplayState { + return { + kind: 'pi-ai', + version: 1, + api: message.api, + provider: message.provider, + model: message.model, + ...message.responseModel === undefined ? {} : { responseModel: message.responseModel }, + ...message.responseId === undefined ? {} : { responseId: message.responseId }, + stopReason: message.stopReason, + blocks: message.content.map((block): PiAiReplayBlock => { + switch (block.type) { + case 'text': return { + type: 'text', + ...block.textSignature === undefined ? {} : { textSignature: block.textSignature }, + } + case 'thinking': return { + type: 'reasoning', + ...block.thinkingSignature === undefined ? {} : { thinkingSignature: block.thinkingSignature }, + ...block.redacted === undefined ? {} : { redacted: block.redacted }, + } + case 'toolCall': return { + type: 'tool-call', + ...block.thoughtSignature === undefined ? {} : { thoughtSignature: block.thoughtSignature }, + } + } + }), + } +} + +function invalidReplay(message: string): never { + throw new LlmError(`invalid pi-ai replay state: ${message}`, 'INVALID_REPLAY_STATE') +} + +/** Validate the adapter-private state before it reaches pi-ai. */ +function readReplayState(value: unknown): PiAiReplayState { + if (typeof value !== 'object' || value === null || Array.isArray(value)) return invalidReplay('expected an object') + const state = value as Record + if (state['kind'] !== 'pi-ai') return invalidReplay('unknown state kind') + if (state['version'] !== 1) return invalidReplay(`unsupported version ${String(state['version'])}`) + for (const key of ['api', 'provider', 'model'] as const) { + if (typeof state[key] !== 'string' || state[key].length === 0) return invalidReplay(`${key} must be a non-empty string`) + } + if (!['stop', 'length', 'toolUse', 'error', 'aborted'].includes(String(state['stopReason']))) { + return invalidReplay('unknown stopReason') + } + if (state['responseModel'] !== undefined && typeof state['responseModel'] !== 'string') return invalidReplay('responseModel must be a string') + if (state['responseId'] !== undefined && typeof state['responseId'] !== 'string') return invalidReplay('responseId must be a string') + if (!Array.isArray(state['blocks'])) return invalidReplay('blocks must be an array') + for (const [index, value] of state['blocks'].entries()) { + if (typeof value !== 'object' || value === null || Array.isArray(value)) return invalidReplay(`block ${index} must be an object`) + const block = value as Record + if (!['text', 'reasoning', 'tool-call'].includes(String(block['type']))) return invalidReplay(`block ${index} has an unknown type`) + for (const signature of ['textSignature', 'thinkingSignature', 'thoughtSignature'] as const) { + if (block[signature] !== undefined && typeof block[signature] !== 'string') return invalidReplay(`block ${index} ${signature} must be a string`) + } + if (block['redacted'] !== undefined && typeof block['redacted'] !== 'boolean') return invalidReplay(`block ${index} redacted must be boolean`) + } + return state as unknown as PiAiReplayState +} + +/** Convert provider-neutral blocks without trusting them as same-model replay. */ +function foreignAssistant(message: Message): AssistantMessage { + const content: AssistantMessage['content'] = [] + for (const block of message.content) { + switch (block.type) { + case 'text': content.push({ type: 'text', text: block.text }); break + case 'reasoning': content.push({ type: 'thinking', thinking: block.text }); break + case 'tool-call': content.push({ + type: 'toolCall', + id: block.id, + name: block.name, + arguments: parseArguments(block.arguments), + }); break + default: + // plugin-added block types are not representable in pi-ai. + break + } + } + return { + role: 'assistant', + content, + // Deliberately never equals a catalog API: absent replay state is foreign + // even if provenance names the same provider/model as this request. + api: 'dsh-foreign', + provider: message.provenance?.provider ?? 'dsh-foreign', + model: message.provenance?.model ?? 'dsh-foreign', + usage: emptyPiUsage(), + stopReason: content.some(piece => piece.type === 'toolCall') ? 'toolUse' : 'stop', + timestamp: 0, + } +} + +/** Recombine durable Harness content with validated pi-ai replay metadata. */ +function replayedAssistant(message: Message, rawState: unknown): AssistantMessage { + const state = readReplayState(rawState) + if (state.blocks.length !== message.content.length) return invalidReplay('block count does not match assistant content') + const content: AssistantMessage['content'] = message.content.map((block, index) => { + const replay = state.blocks[index] + if (replay === undefined || replay.type !== block.type) return invalidReplay(`block ${index} does not match assistant content`) + switch (block.type) { + case 'text': return { + type: 'text', + text: block.text, + ...replay.type === 'text' && replay.textSignature !== undefined ? { textSignature: replay.textSignature } : {}, + } + case 'reasoning': return { + type: 'thinking', + thinking: block.text, + ...replay.type === 'reasoning' && replay.thinkingSignature !== undefined ? { thinkingSignature: replay.thinkingSignature } : {}, + ...replay.type === 'reasoning' && replay.redacted !== undefined ? { redacted: replay.redacted } : {}, + } + case 'tool-call': return { + type: 'toolCall', + id: block.id, + name: block.name, + arguments: parseArguments(block.arguments), + ...replay.type === 'tool-call' && replay.thoughtSignature !== undefined ? { thoughtSignature: replay.thoughtSignature } : {}, + } + /* v8 ignore next -- readReplayState rejects unknown replay tags, so an equal plugin-added Harness tag cannot reach this switch */ + default: return invalidReplay(`block ${index} has an unsupported Harness type`) + } + }) + return { + role: 'assistant', + content, + api: state.api, + provider: state.provider, + model: state.model, + ...state.responseModel === undefined ? {} : { responseModel: state.responseModel }, + ...state.responseId === undefined ? {} : { responseId: state.responseId }, + usage: emptyPiUsage(), + stopReason: state.stopReason, + timestamp: 0, + } +} + +/** + * Convert one durable Harness assistant message into pi-ai history. + * @param message - assistant content with optional adapter-owned replay metadata. + * @returns a native pi-ai assistant message reconstructed from durable content. + */ +export function toPiAssistant(message: Message): AssistantMessage { + const replayState = message.provenance?.replayState + return replayState === undefined ? foreignAssistant(message) : replayedAssistant(message, replayState) +} diff --git a/packages/llm/llm-pi-ai/src/stream.ts b/packages/llm/llm-pi-ai/src/stream.ts new file mode 100644 index 0000000000..5bdce3c528 --- /dev/null +++ b/packages/llm/llm-pi-ai/src/stream.ts @@ -0,0 +1,141 @@ +/** + * pi-ai assistant event translation into the Harness streaming protocol. + * + * pi-ai tool-call arguments are parsed objects while the Harness keeps their + * raw JSON representation. pi-ai also reports failures as terminal stream + * events, which this module maps into Harness finish chunks. + * + * @module dsh-llm-pi-ai/stream + */ + +import { CallId, LlmError } from '@deepseek-ai/dsh-llm' +import type { FinishReason, StreamChunk, TokenUsage } from '@deepseek-ai/dsh-llm' +import type { AssistantMessage, AssistantMessageEvent, Usage as PiUsage } from '@earendil-works/pi-ai' +import { toPiReplayState } from './replay.ts' + +/** + * Map pi-ai usage (reasoning folded into output by pi-ai). + * @param usage - cumulative usage from the terminal pi-ai event. + * @returns harness counts; cache fields appear only when non-zero (pi-ai reports zeros, not absence). + */ +export function mapUsage(usage: PiUsage): TokenUsage { + return { + inputTokens: usage.input, + outputTokens: usage.output, + ...usage.cacheRead > 0 ? { cacheReadTokens: usage.cacheRead } : {}, + ...usage.cacheWrite > 0 ? { cacheWriteTokens: usage.cacheWrite } : {}, + } +} + +function classifyPiAiError(message: string): string { + if (/\b(?:401|403)\b/.test(message)) return 'AUTH' + if (/\b429\b|rate.?limit/i.test(message)) return 'RATE_LIMIT' + if (/\b400\b|invalid.?request/i.test(message)) return 'INVALID_REQUEST' + if (/\b5\d\d\b/.test(message)) return 'SERVER' + return 'PI_AI_ERROR' +} + +/** + * Map a terminal pi-ai event to the harness finish reason. + * @param message - the assistant message carried by the `done` or `error` event. + * @returns the harness reason; `error` yields `{kind: 'error'}` with a code classified from the error text. + */ +export function mapStopReason(message: AssistantMessage): FinishReason { + switch (message.stopReason) { + case 'stop': return { kind: 'stop' } + case 'length': return { kind: 'max-tokens' } + case 'toolUse': return { kind: 'tool-calls' } + case 'aborted': return { kind: 'aborted' } + case 'error': { + const text = message.errorMessage ?? 'pi-ai stream error' + return { kind: 'error', message: text, code: classifyPiAiError(text) } + } + } +} + +/** + * Translate the pi-ai event stream into StreamChunks. pi-ai never throws + * mid-stream — failures arrive as `error` events, which become error/aborted + * `finish` chunks (the harness protocol's other error-delivery style). + * @param events - one assistant turn's pi-ai event stream. + * @returns the harness chunks, ending with `usage` then `finish`; throws + * `LlmError` (`STREAM_CLOSED`) if the source ends without a terminal event. + */ +export async function* toStreamChunks(events: AsyncIterable): AsyncGenerator { + // pi-ai contentIndex ↔ our block index map 1:1 (both count blocks from 0 + // in stream order), but we track ids per index for tool calls. + const toolIds = new Map() + + for await (const event of events) { + switch (event.type) { + case 'start': + break + case 'text_start': + yield { type: 'block-start', index: event.contentIndex, blockType: 'text' } + break + case 'text_delta': + yield { type: 'text-delta', index: event.contentIndex, text: event.delta } + break + case 'text_end': + yield { type: 'block-end', index: event.contentIndex, block: { type: 'text', text: event.content } } + break + case 'thinking_start': + yield { type: 'block-start', index: event.contentIndex, blockType: 'reasoning' } + break + case 'thinking_delta': + yield { type: 'reasoning-delta', index: event.contentIndex, text: event.delta } + break + case 'thinking_end': + yield { type: 'block-end', index: event.contentIndex, block: { type: 'reasoning', text: event.content } } + break + case 'toolcall_start': { + // The id/name live on the partial's content at this index. + const partial = event.partial.content[event.contentIndex] + const id = partial?.type === 'toolCall' ? partial.id : '' + const name = partial?.type === 'toolCall' ? partial.name : '' + toolIds.set(event.contentIndex, { id, name }) + yield { type: 'block-start', index: event.contentIndex, blockType: 'tool-call' } + break + } + case 'toolcall_delta': { + const known = toolIds.get(event.contentIndex) + yield { + type: 'tool-call-delta', + index: event.contentIndex, + id: CallId(known?.id ?? ''), + ...known?.name !== undefined && known.name.length > 0 ? { name: known.name } : {}, + argumentsDelta: event.delta, + } + break + } + case 'toolcall_end': + yield { + type: 'block-end', + index: event.contentIndex, + block: { + type: 'tool-call', + id: CallId(event.toolCall.id), + name: event.toolCall.name, + // pi-ai hands back the PARSED arguments; the harness vocabulary + // keeps the raw string. + arguments: JSON.stringify(event.toolCall.arguments), + }, + } + break + case 'done': + yield { type: 'usage', usage: mapUsage(event.message.usage) } + yield { type: 'finish', reason: mapStopReason(event.message), replayState: toPiReplayState(event.message) } + return + case 'error': + // In-stream error delivery (pi-ai's style) → error finish chunk + // (the harness's other sanctioned error path besides throwing). + yield { type: 'usage', usage: mapUsage(event.error.usage) } + yield { type: 'finish', reason: mapStopReason(event.error) } + return + // no default: AssistantMessageEvent is pi-ai's closed union; a new + // event type should fail compilation here via tsc's exhaustiveness + // when one is added (switch covers all current variants). + } + } + throw new LlmError('pi-ai event stream ended without done/error', 'STREAM_CLOSED') +} diff --git a/packages/llm/llm-pi-ai/tests/adapter.e2e.ts b/packages/llm/llm-pi-ai/tests/adapter.e2e.ts index fa30226ddf..77d2cc81dd 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.e2e.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.e2e.ts @@ -3,26 +3,33 @@ import { Context } from 'cordis' import LlmService, { CallId } from '@deepseek-ai/dsh-llm' import type { Message, ToolSchema } from '@deepseek-ai/dsh-llm' import * as LlmPiAi from '@deepseek-ai/dsh-llm-pi-ai' -import type { Config } from '@deepseek-ai/dsh-llm-pi-ai' +import type { PiAiProviderProfile } from '@deepseek-ai/dsh-llm-pi-ai' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import { assemble, type AssembledResult } from './assemble.ts' /** - * Real-API e2e for the pi-ai-backed adapter: V4 Flash + V4 Pro across all - * reasoning levels the adapter exposes (off / high / xhigh→wire 'max'). - * Mirrors the llm-deepseek matrix so the two independent implementations - * verify the same StreamChunk contract. Key-gated. + * Real-API e2e for the pi-ai-backed adapter: V4 Flash + V4 Pro with provider + * defaults and representative high/xhigh reasoning. Mirrors the native + * adapter's StreamChunk contract and exercises a replayed tool follow-up. + * Key-gated. */ const FLASH = 'deepseek-v4-flash' const PRO = 'deepseek-v4-pro' const contexts: Context[] = [] -async function harness(model: string, config: Partial = {}) { +async function harness(_model: string, config: Partial = {}) { const ctx = new Context() contexts.push(ctx) await ctx.plugin(LlmService) - await ctx.plugin(LlmPiAi, { models: [model], ...config }) + await ctx.plugin(LlmPiAi, { + providers: [{ + provider: 'deepseek', + ...process.env.DEEPSEEK_API_KEY === undefined ? {} : { apiKey: process.env.DEEPSEEK_API_KEY }, + ...process.env.DEEPSEEK_BASE_URL === undefined ? {} : { baseURL: process.env.DEEPSEEK_BASE_URL }, + ...config, + }], + }) return ctx } @@ -56,8 +63,8 @@ const weatherTool: ToolSchema = { } describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-pi-ai e2e (real API)', () => { - it.each([FLASH, PRO])('%s + reasoning off: plain text generation', async (model) => { - const ctx = await harness(model, { reasoning: 'off' }) + it.each([FLASH, PRO])('%s + provider-default reasoning: plain text generation', async (model) => { + const ctx = await harness(model) const result = await assemble(ctx,{ model, messages: ask('Reply with exactly the word: pong'), @@ -65,7 +72,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-pi-ai e2e (real API)', () => }) expect(result.finish.kind).toBe('stop') expect(textOf(result).toLowerCase()).toContain('pong') - expect(result.message.content.some(block => block.type === 'reasoning')).toBe(false) }) it.each([FLASH, PRO])('%s + reasoning high: reasoning blocks present', async (model) => { @@ -99,7 +105,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-pi-ai e2e (real API)', () => model: PRO, messages: [ ...ask('What is the weather in Paris right now? Use the get_weather tool.'), - { role: 'assistant', content: first.message.content }, + first.message, { role: 'user', content: [{ @@ -123,9 +129,9 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-pi-ai e2e (real API)', () => const deepseekCtx = new Context() contexts.push(deepseekCtx) await deepseekCtx.plugin(LlmService) - await deepseekCtx.plugin(LlmDeepSeek, { models: [FLASH], thinking: 'disabled' }) + await deepseekCtx.plugin(LlmDeepSeek, { thinking: 'disabled' }) - const piCtx = await harness(FLASH, { reasoning: 'off' }) + const piCtx = await harness(FLASH) const prompt = ask('Reply with exactly the word: pong') const [fromDeepSeek, fromPiAi] = await Promise.all([ diff --git a/packages/llm/llm-pi-ai/tests/adapter.spec.ts b/packages/llm/llm-pi-ai/tests/adapter.spec.ts index cefaa9f745..6e6368611d 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.spec.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.spec.ts @@ -2,34 +2,35 @@ import { createServer } from 'node:http' import type { IncomingMessage, Server, ServerResponse } from 'node:http' import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import LlmService, { CallId, userAgent } from '@deepseek-ai/dsh-llm' +import LlmService, { LlmError, userAgent } from '@deepseek-ai/dsh-llm' import * as LlmPiAi from '@deepseek-ai/dsh-llm-pi-ai' -import { buildModel, PiAiAdapter } from '@deepseek-ai/dsh-llm-pi-ai' +import { PiAiAdapter, resolveProfiles } from '@deepseek-ai/dsh-llm-pi-ai' import { assemble } from './assemble.ts' -/** Scripted SSE responses, one per request (OpenAI chat-completions shape). */ interface MockServer { url: string + paths: string[] requests: unknown[] - /** Header bags of received requests, in order (parallel to `requests`). */ headers: IncomingMessage['headers'][] - close(): Promise } const servers: Server[] = [] afterEach(async () => { + vi.unstubAllEnvs() await Promise.all(servers.splice(0).map(server => new Promise(resolve => server.close(resolve)))) }) -async function mockServer(script: { status?: number; events?: string[]; body?: string }[]): Promise { +async function mockServer(script: { status?: number; events?: string[]; body?: string; delayMs?: number }[]): Promise { + const paths: string[] = [] const requests: unknown[] = [] const headers: IncomingMessage['headers'][] = [] const server = createServer((request: IncomingMessage, response: ServerResponse) => { let body = '' request.on('data', (chunk: Buffer) => { body += chunk.toString('utf8') }) request.on('end', () => { - requests.push(JSON.parse(body)) + paths.push(request.url ?? '') + requests.push(body.length === 0 ? undefined : JSON.parse(body)) headers.push(request.headers) const behavior = script.shift() ?? { status: 500, body: 'script exhausted' } if (behavior.status !== undefined && behavior.status !== 200) { @@ -38,20 +39,22 @@ async function mockServer(script: { status?: number; events?: string[]; body?: s return } response.writeHead(200, { 'content-type': 'text/event-stream' }) - for (const event of behavior.events ?? []) response.write(`data: ${event}\n\n`) - response.end() + let index = 0 + const writeNext = (): void => { + const event = behavior.events?.[index++] + if (event === undefined) { response.end(); return } + response.write(`data: ${event}\n\n`) + if (behavior.delayMs === undefined) writeNext() + else setTimeout(writeNext, behavior.delayMs) + } + writeNext() }) }) servers.push(server) await new Promise(resolve => server.listen(0, '127.0.0.1', resolve)) const address = server.address() if (address === null || typeof address === 'string') throw new Error('no port') - return { - url: `http://127.0.0.1:${address.port}`, - requests, - headers, - close: () => new Promise(resolve => server.close(() => { resolve() })), - } + return { url: `http://127.0.0.1:${address.port}`, paths, requests, headers } } const textEvents = [ @@ -61,347 +64,202 @@ const textEvents = [ '[DONE]', ] -const toolEvents = [ - '{"choices":[{"delta":{"role":"assistant","content":null},"index":0,"finish_reason":null}]}', - '{"choices":[{"delta":{"tool_calls":[{"index":0,"id":"call-1","type":"function","function":{"name":"get_weather","arguments":""}}]},"index":0,"finish_reason":null}]}', - '{"choices":[{"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\\"city\\":\\"Paris\\"}"}}]},"index":0,"finish_reason":null}]}', - '{"choices":[{"delta":{},"index":0,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":20,"completion_tokens":6}}', - '[DONE]', -] - -const thinkingEvents = [ - '{"choices":[{"delta":{"role":"assistant","content":null,"reasoning_content":""},"index":0,"finish_reason":null}]}', - '{"choices":[{"delta":{"reasoning_content":"pondering"},"index":0,"finish_reason":null}]}', - '{"choices":[{"delta":{"content":"answer","reasoning_content":null},"index":0,"finish_reason":null}]}', - '{"choices":[{"delta":{},"index":0,"finish_reason":"stop"}],"usage":{"prompt_tokens":5,"completion_tokens":9}}', - '[DONE]', -] - -async function harness(baseURL: string, config: object = {}) { +async function harness(baseURL: string, overrides: Record = {}): Promise { const ctx = new Context() await ctx.plugin(LlmService) - await ctx.plugin(LlmPiAi, { apiKey: 'test-key', baseURL, models: ['deepseek-v4-flash'], ...config }) + await ctx.plugin(LlmPiAi, { + providers: [{ provider: 'deepseek', apiKey: 'test-key', baseURL, ...overrides }], + }) return ctx } -describe('PiAiAdapter against a mock server', () => { - it('streams a text generation through the assembler', async () => { +describe('PiAiAdapter provider routing', () => { + it('resolves a catalog model dynamically and uses a private endpoint', async () => { const server = await mockServer([{ events: textEvents }]) const ctx = await harness(server.url) - const result = await assemble(ctx, { model: 'deepseek-v4-flash', messages: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }], }) expect(result.message.content).toEqual([{ type: 'text', text: 'hello' }]) expect(result.finish).toEqual({ kind: 'stop' }) - expect(result.usage).toMatchObject({ inputTokens: 3, outputTokens: 1 }) + expect(result.usage).toEqual({ inputTokens: 3, outputTokens: 1 }) + expect(server.paths).toEqual(['/chat/completions']) + }) - // Attribution reaches the wire through pi-ai's headers hook: the exact - // shared User-Agent, and no provider-specific headers under the - // User-Agent-only contract. + it('merges profile headers with Harness attribution winning', async () => { + const server = await mockServer([{ events: textEvents }]) + const ctx = await harness(server.url, { + headers: { 'x-company': 'private', 'user-agent': 'wrong' }, + }) + await assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }) + expect(server.headers[0]?.['x-company']).toBe('private') expect(server.headers[0]?.['user-agent']).toBe(userAgent()) - expect(server.headers[0]).not.toHaveProperty('http-referer') - expect(server.headers[0]).not.toHaveProperty('x-openrouter-title') - expect(server.headers[0]).not.toHaveProperty('x-openrouter-categories') }) - it('streams tool calls with re-stringified arguments', async () => { - const server = await mockServer([{ events: toolEvents }]) - const ctx = await harness(server.url) - - const result = await assemble(ctx,{ - model: 'deepseek-v4-flash', - messages: [{ role: 'user', content: [{ type: 'text', text: 'weather?' }] }], - tools: [{ - name: 'get_weather', - description: 'Get weather', - parameters: { type: 'object', properties: { city: { type: 'string' } } }, - }], + it('forwards common stream options and profile reasoning', async () => { + const server = await mockServer([{ events: textEvents }]) + const ctx = await harness(server.url, { + reasoning: 'xhigh', + cacheRetention: 'none', + transport: 'sse', + timeoutMs: 5000, + websocketConnectTimeoutMs: 3000, + maxRetries: 0, + maxRetryDelayMs: 10, + thinkingBudgets: { high: 2048 }, }) - expect(result.finish).toEqual({ kind: 'tool-calls' }) - const call = result.message.content.find(block => block.type === 'tool-call') - expect(call).toMatchObject({ name: 'get_weather', arguments: '{"city":"Paris"}' }) - }) - - it('maps reasoning_content streams to reasoning blocks', async () => { - const server = await mockServer([{ events: thinkingEvents }]) - const ctx = await harness(server.url, { reasoning: 'high' }) - - const result = await assemble(ctx,{ - model: 'deepseek-v4-flash', - messages: [{ role: 'user', content: [{ type: 'text', text: 'think' }] }], - }) - expect(result.message.content).toEqual([ - { type: 'reasoning', text: 'pondering' }, - { type: 'text', text: 'answer' }, - ]) - }) - - it('sends DeepSeek thinking fields when reasoning is configured', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url, { reasoning: 'xhigh' }) - await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - expect(server.requests[0]).toMatchObject({ - thinking: { type: 'enabled' }, - reasoning_effort: 'max', // xhigh maps to max via thinkingLevelMap - }) - }) - - it('disables thinking for reasoning: off', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url, { reasoning: 'off' }) - await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - expect(server.requests[0]).toMatchObject({ thinking: { type: 'disabled' } }) - }) - - it('injects stop sequences through onPayload', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url) - await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [], stop: ['END'] }) - expect(server.requests[0]).toMatchObject({ stop: ['END'] }) - }) - - it('scrubs pi-ai\'s own per-tool strict default through onPayload', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url) - await assemble(ctx,{ + await assemble(ctx, { model: 'deepseek-v4-flash', messages: [], - tools: [ - { name: 'alpha', description: 'a', parameters: {} }, - { name: 'beta', description: 'b', parameters: {} }, - ], + temperature: 0.2, + maxTokens: 77, + sessionId: 'session-for-pi' as never, }) - - // pi-ai stamps `strict` on every serialized tool function; the harness - // contract has none and the hand-rolled twin sends no such field, so the - // payload fixup must have deleted it from every tool. - const request = server.requests[0] as { tools: { function: { name: string; strict?: boolean } }[] } - expect(request.tools.map(tool => tool.function.name)).toEqual(['alpha', 'beta']) - for (const tool of request.tools) { - expect('strict' in tool.function).toBe(false) - } - }) - - it('preserves raw replayed tool-call arguments in the provider payload', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url) - await assemble(ctx,{ + expect(server.requests[0]).toMatchObject({ model: 'deepseek-v4-flash', - messages: [{ - role: 'assistant', - content: [{ type: 'tool-call', id: CallId('broken'), name: 'f', arguments: '{broken' }], - }], + temperature: 0.2, + max_completion_tokens: 77, + thinking: { type: 'enabled' }, + reasoning_effort: 'max', }) - - const request = server.requests[0] as { messages: { role: string; tool_calls?: { id: string; function: { arguments: string } }[] }[] } - const assistant = request.messages.find(message => message.role === 'assistant') - expect(assistant?.tool_calls?.[0]?.function.arguments).toBe('{broken') }) - it('maps HTTP errors to error finish chunks (pi-ai in-stream style)', async () => { - const server = await mockServer([{ - status: 401, - body: JSON.stringify({ error: { message: 'bad key' } }), - }]) + it('preserves omitted profile options when constructing the adapter directly', async () => { + const server = await mockServer([{ events: textEvents }]) + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['deepseek'], new PiAiAdapter({ + profiles: [{ provider: 'deepseek', apiKey: 'test-key', baseURL: server.url }], + })) + + const result = await assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }) + + expect(result.message.content).toEqual([{ type: 'text', text: 'hello' }]) + }) + + it('rejects stop sequences rather than silently ignoring them', async () => { + const server = await mockServer([]) const ctx = await harness(server.url) - const result = await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - expect(result.finish).toMatchObject({ kind: 'error', code: 'AUTH' }) - expect((result.finish as { message: string }).message).toMatch(/bad key|401/) + await expect(assemble(ctx, { model: 'deepseek-v4-flash', messages: [], stop: ['END'] })) + .rejects.toMatchObject({ code: 'UNSUPPORTED_OPTION' }) + expect(server.requests).toEqual([]) + }) + + it('rejects unknown catalog models before network I/O', async () => { + const server = await mockServer([]) + const ctx = await harness(server.url) + await expect(assemble(ctx, { model: 'not-in-the-catalog', messages: [] })) + .rejects.toMatchObject({ code: 'UNKNOWN_MODEL' }) + expect(server.requests).toEqual([]) + }) + + it('uses the catalog API implementation, including OpenAI Responses', async () => { + const server = await mockServer([{ status: 401, body: JSON.stringify({ error: { message: 'expected mock failure' } }) }]) + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(LlmPiAi, { + providers: [{ provider: 'openai', apiKey: 'test-key', baseURL: `${server.url}/v1`, maxRetries: 0 }], + }) + const result = await assemble(ctx, { provider: 'openai', model: 'gpt-4.1', messages: [] }) + expect(result.finish.kind).toBe('error') + expect(server.paths).toEqual(['/v1/responses']) }) it.each([ + [401, 'AUTH'], [400, 'INVALID_REQUEST'], [429, 'RATE_LIMIT'], [500, 'SERVER'], - ] as const)('maps HTTP %s to stable error code %s', async (status, code) => { + ] as const)('maps HTTP %s failures to %s', async (status, code) => { const server = await mockServer([{ status, body: JSON.stringify({ error: { message: `provider ${status}` } }) }]) - const ctx = await harness(server.url) - const result = await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) + const ctx = await harness(server.url, { maxRetries: 0 }) + const result = await assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }) expect(result.finish).toMatchObject({ kind: 'error', code }) }) +}) - it('registers/unregisters models on the llm service (HMR safety)', async () => { +describe('provider profile lifecycle', () => { + it('registers every profile atomically and unregisters on dispose', async () => { const ctx = new Context() await ctx.plugin(LlmService) - const fiber = await ctx.plugin(LlmPiAi, { apiKey: 'k', baseURL: 'http://127.0.0.1:1' }) - expect(ctx.llm.models().sort()).toEqual(['deepseek-v4-flash', 'deepseek-v4-pro']) + const fiber = await ctx.plugin(LlmPiAi, { + providers: [{ provider: 'openai' }, { provider: 'anthropic' }], + }) + expect(ctx.llm.providers()).toEqual(['openai', 'anthropic']) await fiber.dispose() - expect(ctx.llm.models()).toEqual([]) + expect(ctx.llm.providers()).toEqual([]) }) - it('throws a clear error when no API key is available', async () => { - const previous = process.env.DEEPSEEK_API_KEY - delete process.env.DEEPSEEK_API_KEY - try { - const ctx = new Context() - await ctx.plugin(LlmService) - await expect(ctx.plugin(LlmPiAi, {})).rejects.toThrow(/an API key is required/) - } finally { - if (previous !== undefined) process.env.DEEPSEEK_API_KEY = previous - } + it('accepts absent credentials for pi-ai ambient authentication', async () => { + vi.stubEnv('DEEPSEEK_API_KEY', 'ambient-key') + const server = await mockServer([{ events: textEvents }]) + const ctx = await harness(server.url, { apiKey: undefined }) + await assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }) + expect(server.headers[0]?.authorization).toBe('Bearer ambient-key') + }) + + it('validates empty, duplicate, unknown, and explicitly blank profiles', () => { + expect(() => resolveProfiles([])).toThrow(/at least one/) + expect(() => resolveProfiles([{ provider: '' }])).toThrow(/non-empty/) + expect(() => resolveProfiles([{ provider: 'not-real' }])).toThrow(/unknown/) + expect(() => resolveProfiles([{ provider: 'openai' }, { provider: 'openai' }])).toThrow(/duplicate/) + expect(() => resolveProfiles([{ provider: 'openai', apiKey: '' }])).toThrow(/empty apiKey/) + expect(() => resolveProfiles([{ provider: 'openai', baseURL: '' }])).toThrow(/empty baseURL/) + }) + + it('constructs the adapter directly and rejects routes it does not own', async () => { + const adapter = new PiAiAdapter({ profiles: [{ provider: 'openai' }] }) + await expect((async () => { + for await (const _chunk of adapter.stream({ provider: 'anthropic', model: 'claude-sonnet-4', messages: [] })) { /* drain */ } + })()).rejects.toMatchObject({ code: 'NO_ADAPTER' }) + expect(new LlmError('x', 'X')).toBeInstanceOf(Error) }) }) -describe('option spreads and env fallbacks', () => { - it('forwards temperature, maxTokens, and signal', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url) +describe('abort wiring', () => { + it('resolves catalog endpoints without an override before honoring pre-abort', async () => { + const adapter = new PiAiAdapter({ profiles: [{ provider: 'deepseek', apiKey: 'test-key', maxRetries: 0 }] }) const controller = new AbortController() - await assemble(ctx,{ - model: 'deepseek-v4-flash', - messages: [], - temperature: 0.5, - maxTokens: 40, - signal: controller.signal, - }) - expect(server.requests[0]).toMatchObject({ temperature: 0.5, max_tokens: 40 }) - }) - - it('falls back to DEEPSEEK_API_KEY / DEEPSEEK_BASE_URL env vars', async () => { - const server = await mockServer([{ events: textEvents }]) - vi.stubEnv('DEEPSEEK_API_KEY', 'env-key') - vi.stubEnv('DEEPSEEK_BASE_URL', server.url) - try { - const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(LlmPiAi, { models: ['deepseek-v4-flash'] }) - await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - expect(server.requests).toHaveLength(1) - } finally { - vi.unstubAllEnvs() - } - }) - - it('defaults to the public base URL without config or env', async () => { - vi.stubEnv('DEEPSEEK_API_KEY', 'k') - vi.stubEnv('DEEPSEEK_BASE_URL', undefined) - try { - const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(LlmPiAi, {}) - expect(ctx.llm.models().length).toBeGreaterThan(0) - } finally { - vi.unstubAllEnvs() - } - }) -}) - -describe('buildModel', () => { - it('builds a DeepSeek-compat openai-completions model descriptor', () => { - const model = buildModel('deepseek-v4-pro', { apiKey: 'k', baseURL: 'http://x', reasoning: 'high' }) - expect(model).toMatchObject({ - id: 'deepseek-v4-pro', - api: 'openai-completions', + controller.abort('already stopped') + const chunks = [] + for await (const chunk of adapter.stream({ provider: 'deepseek', - baseUrl: 'http://x', - reasoning: true, - compat: { thinkingFormat: 'deepseek', requiresReasoningContentOnAssistantMessages: true }, - }) - }) - - it('keeps reasoning true even for off (pi-ai gates the thinking field on it)', () => { - // 'off' yields {thinking: {type: 'disabled'}} on the wire — pi-ai only - // emits the field at all when model.reasoning is true. - expect(buildModel('m', { apiKey: 'k', baseURL: 'http://x', reasoning: 'off' }).reasoning).toBe(true) - }) - - it('adapter is constructible directly for embedding', () => { - expect(new PiAiAdapter({ apiKey: 'k', baseURL: 'http://x' })).toBeInstanceOf(PiAiAdapter) - }) -}) - -describe('review fixes', () => { - it('defaults omitted reasoning config to thinking ENABLED (provider default)', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url) // no reasoning key at all - await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - const request = server.requests[0] as Record - expect(request.thinking).toEqual({ type: 'enabled' }) - expect('reasoning_effort' in request).toBe(false) - }) - - it('replays reasoning_content on assistant tool-call turns (passback rule)', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url) - await assemble(ctx,{ - model: 'deepseek-v4-flash', - messages: [ - { role: 'user', content: [{ type: 'text', text: 'weather?' }] }, - { - role: 'assistant', - content: [ - { type: 'reasoning', text: 'I should check.' }, - { type: 'tool-call', id: CallId('c1'), name: 'get_weather', arguments: '{"city":"Paris"}' }, - ], - }, - { - role: 'user', - content: [{ type: 'tool-result', toolCallId: CallId('c1'), content: [{ type: 'text', text: 'Sunny' }] }], - }, - ], - }) - const request = server.requests[0] as { messages: { role: string; reasoning_content?: string }[] } - const assistant = request.messages.find(message => message.role === 'assistant') - expect(assistant?.reasoning_content).toBe('I should check.') - }) - - it('aborts the upstream request when the consumer stops streaming early', async () => { - // Slow server: write one chunk, then hold the connection open and record - // whether the socket closes (the adapter must cancel on early break). - let socketClosed = false - const server = createServer((request: IncomingMessage, response: ServerResponse) => { - request.on('data', () => undefined) - request.on('end', () => { - response.writeHead(200, { 'content-type': 'text/event-stream' }) - response.write(`data: ${textEvents[0]}\n\n`) - response.write(`data: ${textEvents[1]}\n\n`) - // never finish; rely on client abort - request.socket.on('close', () => { socketClosed = true }) - }) - }) - servers.push(server) - await new Promise(resolve => server.listen(0, '127.0.0.1', resolve)) - const address = server.address() - if (address === null || typeof address === 'string') throw new Error('no port') - const ctx = await harness(`http://127.0.0.1:${address.port}`) - - for await (const chunk of ctx.llm.stream({ model: 'deepseek-v4-flash', messages: [] })) { - if (chunk.type === 'text-delta') break // stop early mid-stream - } - // The finally-abort must reach the server as a closed socket. - await vi.waitFor(() => { expect(socketClosed).toBe(true) }, { timeout: 5_000 }) - }) -}) - -describe('review fixes: abort wiring', () => { - it('honors a pre-aborted caller signal', async () => { - const ctx = await harness('http://127.0.0.1:1') - const controller = new AbortController() - controller.abort('already cancelled') - // pi-ai surfaces the abort as an in-stream error event → aborted finish. - const result = await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [], signal: controller.signal, - }) + })) chunks.push(chunk) + expect(chunks.at(-1)).toMatchObject({ type: 'finish', reason: { kind: 'aborted' } }) + }) + + it('honors a pre-aborted caller signal', async () => { + const server = await mockServer([{ events: textEvents, delayMs: 20 }]) + const ctx = await harness(server.url) + const controller = new AbortController() + controller.abort('already stopped') + const result = await assemble(ctx, { model: 'deepseek-v4-flash', messages: [], signal: controller.signal }) expect(result.finish.kind).toBe('aborted') }) - it('propagates a mid-stream caller abort to the upstream request', async () => { - const server = await mockServer([{ events: textEvents }]) + it('forwards an abort that arrives while provider streaming is active', async () => { + const server = await mockServer([{ events: textEvents, delayMs: 30 }]) const ctx = await harness(server.url) const controller = new AbortController() - const pending = assemble(ctx,{ - model: 'deepseek-v4-flash', - messages: [], - signal: controller.signal, + const resultPromise = assemble(ctx, { + model: 'deepseek-v4-flash', messages: [], signal: controller.signal, }) - controller.abort() - const result = await pending - // Either the abort lands before any chunk (aborted) or after the tiny - // mock stream finished (stop) — both are valid races; never a hang. - expect(['aborted', 'stop']).toContain(result.finish.kind) + setTimeout(() => { controller.abort('stopped during stream') }, 10) + const result = await resultPromise + expect(result.finish.kind).toBe('aborted') + }) + + it('aborts upstream when a consumer stops early', async () => { + const server = await mockServer([{ events: textEvents, delayMs: 30 }]) + const ctx = await harness(server.url) + for await (const chunk of ctx.llm.stream({ provider: 'deepseek', model: 'deepseek-v4-flash', messages: [] })) { + if (chunk.type === 'block-start') break + } + await new Promise(resolve => setTimeout(resolve, 20)) + expect(server.requests).toHaveLength(1) }) }) diff --git a/packages/llm/llm-pi-ai/tests/assemble.ts b/packages/llm/llm-pi-ai/tests/assemble.ts index b0182615e0..494eeac494 100644 --- a/packages/llm/llm-pi-ai/tests/assemble.ts +++ b/packages/llm/llm-pi-ai/tests/assemble.ts @@ -15,11 +15,19 @@ export interface AssembledResult { finish: FinishReason } -export async function assemble(ctx: Context, options: GenerateOptions): Promise { +export async function assemble(ctx: Context, options: Omit & { provider?: string }): Promise { const assembler = new BlockAssembler() - for await (const chunk of ctx.llm.stream(options)) assembler.push(chunk) + const request = { provider: 'deepseek', ...options } + for await (const chunk of ctx.llm.stream(request)) assembler.push(chunk) return { - message: assembler.message(), + message: { + ...assembler.message(), + provenance: { + provider: request.provider, + model: request.model, + ...assembler.replayState === undefined ? {} : { replayState: assembler.replayState }, + }, + }, ...assembler.usage !== undefined ? { usage: assembler.usage } : {}, finish: assembler.finish, } diff --git a/packages/llm/llm-pi-ai/tests/convert.spec.ts b/packages/llm/llm-pi-ai/tests/convert.spec.ts index 078d2a4d3b..cf8e07de5c 100644 --- a/packages/llm/llm-pi-ai/tests/convert.spec.ts +++ b/packages/llm/llm-pi-ai/tests/convert.spec.ts @@ -1,8 +1,8 @@ import { describe, expect, it } from 'vitest' -import { CallId } from '@deepseek-ai/dsh-llm' +import { CallId, LlmError } from '@deepseek-ai/dsh-llm' import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm' import type { AssistantMessage, AssistantMessageEvent, Usage } from '@earendil-works/pi-ai' -import { mapStopReason, mapUsage, toPiContext, toStreamChunks } from '@deepseek-ai/dsh-llm-pi-ai' +import { mapStopReason, mapUsage, toPiContext, toPiReplayState, toStreamChunks } from '@deepseek-ai/dsh-llm-pi-ai' function usage(input = 0, output = 0, cacheRead = 0, cacheWrite = 0): Usage { return { @@ -42,6 +42,7 @@ async function collect(stream: AsyncIterable): Promise { it('maps system prompt, user text, and tools', () => { const context = toPiContext({ + provider: 'deepseek', model: 'deepseek-v4-flash', system: 'be helpful', messages: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }], @@ -55,13 +56,14 @@ describe('toPiContext', () => { }) it('omits empty tools and absent system prompt', () => { - const context = toPiContext({ model: 'm', messages: [], tools: [] }) + const context = toPiContext({ provider: 'deepseek', model: 'm', messages: [], tools: [] }) expect(context.systemPrompt).toBeUndefined() expect(context.tools).toBeUndefined() }) it('maps assistant text/reasoning/tool-call blocks', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [{ role: 'assistant', @@ -76,8 +78,7 @@ describe('toPiContext', () => { expect(message.role).toBe('assistant') expect(message.stopReason).toBe('toolUse') expect(message.content).toEqual([ - // thinkingSignature names the replay field — DeepSeek's passback rule. - { type: 'thinking', thinking: 'hmm', thinkingSignature: 'reasoning_content' }, + { type: 'thinking', thinking: 'hmm' }, { type: 'text', text: 'calling' }, { type: 'toolCall', id: 'c1', name: 'f', arguments: { a: 1 } }, ]) @@ -85,6 +86,7 @@ describe('toPiContext', () => { it('marks tool-call-free assistant messages with stopReason stop', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [{ role: 'assistant', content: [{ type: 'text', text: 'done' }] }], }) @@ -93,6 +95,7 @@ describe('toPiContext', () => { it('parses malformed tool-call arguments to {}', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [{ role: 'assistant', @@ -105,6 +108,7 @@ describe('toPiContext', () => { it('parses non-object argument JSON (arrays, scalars) to {}', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [{ role: 'assistant', @@ -116,6 +120,7 @@ describe('toPiContext', () => { it('recovers toolName for tool results from the preceding assistant call', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [ { @@ -140,6 +145,7 @@ describe('toPiContext', () => { it('labels unmatched tool results with toolName unknown and keeps isError', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [{ role: 'user', @@ -156,6 +162,7 @@ describe('toPiContext', () => { it('splits mixed user text + tool results and folds history system messages', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [ { role: 'system', content: [{ type: 'text', text: 'rule' }] }, @@ -173,6 +180,7 @@ describe('toPiContext', () => { it('skips plugin-added (unknown) blocks in assistant content', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [{ role: 'assistant', @@ -184,6 +192,173 @@ describe('toPiContext', () => { }) expect((context.messages[0] as AssistantMessage).content).toEqual([{ type: 'text', text: 'visible' }]) }) + + it('recombines durable content with pi-ai replay metadata across target providers and models', () => { + const state = toPiReplayState(assistant({ + api: 'openai-responses', + provider: 'openai', + model: 'gpt-5', + responseModel: 'gpt-5-2026-01-01', + responseId: 'resp_123', + stopReason: 'toolUse', + content: [ + { type: 'thinking', thinking: 'private reasoning', thinkingSignature: 'think-sig', redacted: true }, + { type: 'text', text: 'calling', textSignature: 'text-sig' }, + { type: 'toolCall', id: 'c1', name: 'f', arguments: { a: 1 }, thoughtSignature: 'tool-sig' }, + ], + })) + const context = toPiContext({ + provider: 'anthropic', + model: 'claude-next', + messages: [{ + role: 'assistant', + content: [ + { type: 'reasoning', text: 'private reasoning' }, + { type: 'text', text: 'calling' }, + { type: 'tool-call', id: CallId('c1'), name: 'f', arguments: '{"a":1}' }, + ], + provenance: { provider: 'openai', model: 'gpt-5', replayState: state }, + }], + }) + + expect(context.messages[0]).toMatchObject({ + role: 'assistant', + api: 'openai-responses', + provider: 'openai', + model: 'gpt-5', + responseModel: 'gpt-5-2026-01-01', + responseId: 'resp_123', + stopReason: 'toolUse', + content: [ + { type: 'thinking', thinking: 'private reasoning', thinkingSignature: 'think-sig', redacted: true }, + { type: 'text', text: 'calling', textSignature: 'text-sig' }, + { type: 'toolCall', id: 'c1', name: 'f', arguments: { a: 1 }, thoughtSignature: 'tool-sig' }, + ], + }) + }) + + it('replays all native block kinds when optional metadata is absent', () => { + const state = toPiReplayState(assistant({ + content: [ + { type: 'thinking', thinking: 'private reasoning' }, + { type: 'text', text: 'calling' }, + { type: 'toolCall', id: 'c1', name: 'f', arguments: { a: 1 } }, + ], + })) + const context = toPiContext({ + provider: 'deepseek', + model: 'new-model', + messages: [{ + role: 'assistant', + content: [ + { type: 'reasoning', text: 'private reasoning' }, + { type: 'text', text: 'calling' }, + { type: 'tool-call', id: CallId('c1'), name: 'f', arguments: '{"a":1}' }, + ], + provenance: { provider: 'deepseek', model: 'old-model', replayState: state }, + }], + }) + + expect(context.messages[0]).toMatchObject({ + role: 'assistant', + content: [ + { type: 'thinking', thinking: 'private reasoning' }, + { type: 'text', text: 'calling' }, + { type: 'toolCall', id: 'c1', name: 'f', arguments: { a: 1 } }, + ], + }) + expect(context.messages[0]).not.toHaveProperty('responseModel') + expect(context.messages[0]).not.toHaveProperty('responseId') + }) + + it('rejects unsupported replay-state versions with a stable error code', () => { + try { + toPiContext({ + provider: 'deepseek', + model: 'm', + messages: [{ + role: 'assistant', + content: [{ type: 'text', text: 'done' }], + provenance: { + provider: 'deepseek', + model: 'old', + replayState: { kind: 'pi-ai', version: 2 }, + }, + }], + }) + expect.fail('expected invalid replay state') + } catch (error: unknown) { + expect(error).toBeInstanceOf(LlmError) + expect((error as LlmError).code).toBe('INVALID_REPLAY_STATE') + expect((error as Error).message).toContain('unsupported version 2') + } + }) + + it('rejects replay metadata whose blocks do not match the durable content', () => { + const state = toPiReplayState(assistant({ content: [{ type: 'text', text: 'done' }] })) + expect(() => toPiContext({ + provider: 'deepseek', + model: 'm', + messages: [{ + role: 'assistant', + content: [{ type: 'reasoning', text: 'done' }], + provenance: { provider: 'deepseek', model: 'old', replayState: state }, + }], + })).toThrow(/block 0 does not match assistant content/) + }) + + it('rejects replay metadata whose block count differs from durable content', () => { + const state = toPiReplayState(assistant()) + expect(() => toPiContext({ + provider: 'deepseek', + model: 'm', + messages: [{ + role: 'assistant', + content: [{ type: 'text', text: 'done' }], + provenance: { provider: 'deepseek', model: 'old', replayState: state }, + }], + })).toThrow(/block count does not match assistant content/) + }) + + const validReplay = { + kind: 'pi-ai', + version: 1, + api: 'openai-completions', + provider: 'deepseek', + model: 'deepseek-v4-flash', + stopReason: 'stop', + blocks: [{ type: 'text' }], + } + + it.each([ + ['number state', 1, 'expected an object'], + ['null state', null, 'expected an object'], + ['array state', [], 'expected an object'], + ['unknown kind', { ...validReplay, kind: 'other' }, 'unknown state kind'], + ['non-string api', { ...validReplay, api: 1 }, 'api must be a non-empty string'], + ['empty provider', { ...validReplay, provider: '' }, 'provider must be a non-empty string'], + ['missing model', { ...validReplay, model: undefined }, 'model must be a non-empty string'], + ['unknown stop reason', { ...validReplay, stopReason: 'pause' }, 'unknown stopReason'], + ['non-string response model', { ...validReplay, responseModel: 1 }, 'responseModel must be a string'], + ['non-string response id', { ...validReplay, responseId: 1 }, 'responseId must be a string'], + ['non-array blocks', { ...validReplay, blocks: 'text' }, 'blocks must be an array'], + ['number block', { ...validReplay, blocks: [1] }, 'block 0 must be an object'], + ['null block', { ...validReplay, blocks: [null] }, 'block 0 must be an object'], + ['array block', { ...validReplay, blocks: [[]] }, 'block 0 must be an object'], + ['unknown block type', { ...validReplay, blocks: [{ type: 'audio' }] }, 'block 0 has an unknown type'], + ['non-string signature', { ...validReplay, blocks: [{ type: 'text', textSignature: 1 }] }, 'textSignature must be a string'], + ['non-boolean redaction', { ...validReplay, blocks: [{ type: 'reasoning', redacted: 'yes' }] }, 'redacted must be boolean'], + ])('rejects malformed replay state: %s', (_name, replayState, message) => { + expect(() => toPiContext({ + provider: 'deepseek', + model: 'm', + messages: [{ + role: 'assistant', + content: [{ type: 'text', text: 'done' }], + provenance: { provider: 'deepseek', model: 'old', replayState }, + }], + })).toThrow(message) + }) }) describe('toStreamChunks', () => { @@ -205,7 +380,19 @@ describe('toStreamChunks', () => { { type: 'text-delta', index: 0, text: 'hi' }, { type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } }, { type: 'usage', usage: { inputTokens: 3, outputTokens: 2 } }, - { type: 'finish', reason: { kind: 'stop' } }, + { + type: 'finish', + reason: { kind: 'stop' }, + replayState: { + kind: 'pi-ai', + version: 1, + api: 'openai-completions', + provider: 'deepseek', + model: 'deepseek-v4-flash', + stopReason: 'stop', + blocks: [{ type: 'text' }], + }, + }, ]) }) @@ -234,7 +421,7 @@ describe('toStreamChunks', () => { toolCall: { type: 'toolCall', id: 'call-1', name: 'f', arguments: { a: 1 } }, partial: partialWithToolCall, }, - { type: 'done', reason: 'toolUse', message: assistant({ stopReason: 'toolUse' }) }, + { type: 'done', reason: 'toolUse', message: assistant({ content: partialWithToolCall.content, stopReason: 'toolUse' }) }, ))) expect(chunks).toEqual([ { type: 'block-start', index: 0, blockType: 'tool-call' }, @@ -242,7 +429,19 @@ describe('toStreamChunks', () => { { type: 'tool-call-delta', index: 0, id: 'call-1', name: 'f', argumentsDelta: ':1}' }, { type: 'block-end', index: 0, block: { type: 'tool-call', id: 'call-1', name: 'f', arguments: '{"a":1}' } }, { type: 'usage', usage: { inputTokens: 0, outputTokens: 0 } }, - { type: 'finish', reason: { kind: 'tool-calls' } }, + { + type: 'finish', + reason: { kind: 'tool-calls' }, + replayState: { + kind: 'pi-ai', + version: 1, + api: 'openai-completions', + provider: 'deepseek', + model: 'deepseek-v4-flash', + stopReason: 'toolUse', + blocks: [{ type: 'tool-call' }], + }, + }, ]) }) diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 42694ba5ea..4a65e423ca 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -8,8 +8,8 @@ An adapter registry plus a single streaming call surface, interceptable via a wa ### Public API -- `ctx.llm.registerAdapter(models: string[], adapter: LlmAdapter): () => void` Register an adapter for the given model names. Disposed with the calling fiber. -- `ctx.llm.models(): string[]` — model names with a registered adapter. +- `ctx.llm.registerAdapter(providers: string[], adapter: LlmAdapter): () => void` Register one adapter instance for the given provider routes. Registration is all-or-nothing, and is disposed with the calling fiber. +- `ctx.llm.providers(): string[]` — provider routes with a registered adapter. - `ctx.llm.stream(options: GenerateOptions): AsyncIterable` Stream one model call as raw chunks (token-level deltas). Consumers assemble the chunks into blocks/messages with `BlockAssembler`. ### Events @@ -20,18 +20,18 @@ An adapter registry plus a single streaming call surface, interceptable via a wa ### Extension points -- Subclass `LlmAdapter` and call `ctx.llm.registerAdapter(models, adapter)` to add a new model provider. +- Subclass `LlmAdapter` and call `ctx.llm.registerAdapter(providers, adapter)` to add one or more provider routes. `GenerateOptions.provider` selects the adapter; `GenerateOptions.model` is adapter-owned and may be resolved dynamically. - Wrap `llm/stream` via `ctx.on()` waterfall listeners for caching, retry, logging, rate-limiting, etc. ### Content-block vocabulary (`types.ts`) -Messages are arrays of typed content blocks: `text`, `reasoning`, `tool-call`, `tool-result`. The union is derived from the merge-extensible `ContentBlockMap`, so plugins can add block types via declaration merging. The core set is limited to blocks every shipping path honors — multimodal content (images, audio, …) has no core block type; a feature that needs one adds it via the map together with the adapter/UI/compaction support that honors it. +Messages are arrays of typed content blocks: `text`, `reasoning`, `tool-call`, `tool-result`. The union is derived from the merge-extensible `ContentBlockMap`, so plugins can add block types via declaration merging. Assistant messages produced by the loop also carry provider/model provenance and optional adapter-private replay state. Before dispatch, `LlmService` retains that state only when the historical provider route and target provider route are currently owned by the exact same adapter instance; the adapter then decides whether it can restore or convert the state across models/providers. The core block set is limited to blocks every shipping path honors — multimodal content (images, audio, …) has no core block type; a feature that needs one adds it via the map together with the adapter/UI/compaction support that honors it. Streaming is a raw chunk protocol (`block-start`, `text-delta`, `reasoning-delta`, `tool-call-delta`, `block-end`, `usage`, `finish`). `BlockAssembler` is the single shared implementation that assembles chunks into blocks/messages. ### Call configuration (`call-config.ts`) -`LlmCallConfig` is the model + sampling scalars of one conversation's requests (`model`, `temperature`, `maxTokens`, `stop` — each mapping 1:1 onto the same-named `GenerateOptions` field). It is per-conversation state recorded in the session log as part of the request header (see the dsh-session `request/header` events), never a silently-adjustable per-call knob: the `agent/request` waterfall proposes a replacement and the loop logs a real change. `callConfigEquals(a, b)` is the field-wise real-change detector; `deepFreeze(value)` is the ownership helper the loop applies to every built request before dispatch (`llm/stream` listeners and adapters read, never rewrite). +`LlmCallConfig` is the provider + model + sampling scalars of one conversation's requests (`provider`, `model`, `temperature`, `maxTokens`, `stop` — each mapping 1:1 onto the same-named `GenerateOptions` field). It is per-conversation state recorded in the session log as part of the request header (see the dsh-session `request/header` events), never a silently-adjustable per-call knob: the `agent/request` waterfall proposes a replacement and the loop logs a real change. `callConfigEquals(a, b)` is the field-wise real-change detector; `deepFreeze(value)` is the ownership helper the loop applies to every built request before dispatch (`llm/stream` listeners and adapters read, never rewrite). ### App attribution (`attribution.ts`) @@ -46,4 +46,4 @@ Every product adapter must identify the application on every provider HTTP reque ### Real adapters -Two adapters implement `LlmAdapter` against this vocabulary, deliberately built on different internals to keep the contract honest (see [the twin LLM adapters](../../../docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md)): [`@deepseek-ai/dsh-llm-deepseek`](../llm-deepseek) (hand-rolled fetch/SSE) and [`@deepseek-ai/dsh-llm-pi-ai`](../llm-pi-ai) (via `@earendil-works/pi-ai`). The pair pinned down the `StreamChunk` conventions now documented in `types.ts` (usage before finish, raw-string tool arguments, the two sanctioned error paths). +Two adapters implement `LlmAdapter` against this vocabulary, deliberately built on different internals to keep the contract honest (see [the twin LLM adapters](../../../docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md)): [`@deepseek-ai/dsh-llm-deepseek`](../llm-deepseek) is a hand-rolled DeepSeek fetch/SSE adapter, while [`@deepseek-ai/dsh-llm-pi-ai`](../llm-pi-ai) dynamically resolves any configured provider/model in pi-ai's installed catalog. The pair pinned down the `StreamChunk` conventions now documented in `types.ts` (usage before finish, raw-string tool arguments, the two sanctioned error paths). diff --git a/packages/llm/llm/src/assembler.ts b/packages/llm/llm/src/assembler.ts index 1b8ba6e60c..31efccae37 100644 --- a/packages/llm/llm/src/assembler.ts +++ b/packages/llm/llm/src/assembler.ts @@ -36,6 +36,7 @@ export class BlockAssembler { private order: number[] = [] private _usage: TokenUsage | undefined private _finish: FinishReason | undefined + private _replayState: unknown /** * Feed one chunk. Returns the completed block when the chunk closes one @@ -87,6 +88,7 @@ export class BlockAssembler { } case 'finish': { this._finish = chunk.reason + this._replayState = chunk.replayState return } default: return assertNever(chunk, 'BlockAssembler.push') @@ -144,6 +146,11 @@ export class BlockAssembler { return this._finish ?? { kind: 'stop' } } + /** Adapter-private replay state from the terminal finish chunk, if any. */ + get replayState(): unknown { + return this._replayState + } + /** * The assembled assistant message. * @returns an assistant-role message over `blocks()` (same open-block assembly rules). diff --git a/packages/llm/llm/src/call-config.ts b/packages/llm/llm/src/call-config.ts index 53cb157214..6a117c877f 100644 --- a/packages/llm/llm/src/call-config.ts +++ b/packages/llm/llm/src/call-config.ts @@ -2,9 +2,9 @@ * The call configuration of a conversation and its comparison/freeze * utilities. `LlmCallConfig` is the non-content third of the request header * (see `EpochHeader` in dsh-session): everything about a request besides its - * message content that can undermine provider KV-cache reuse — `model` - * selects the cache namespace outright, and the sampling scalars are treated - * the same way out of caution. It is per-conversation state recorded in the + * message content that can undermine provider KV-cache reuse — `provider` and + * `model` select the adapter and cache namespace outright, and the sampling + * scalars are treated the same way out of caution. It is per-conversation state recorded in the * session log (the reconstructability RFC), never a silently-drifting * per-call knob: the `agent/request` waterfall proposes a replacement, and * the loop logs a real change as a `request/header-delta` event. @@ -13,11 +13,12 @@ */ /** - * Model + sampling scalars of one conversation's requests. Every field maps + * Provider + model + sampling scalars of one conversation's requests. Every field maps * 1:1 onto the same-named `GenerateOptions` field; the loop builds requests * from the logged header rather than accepting these per call. */ export interface LlmCallConfig { + provider: string model: string temperature?: number maxTokens?: number @@ -33,7 +34,7 @@ export interface LlmCallConfig { * @returns whether every field (including the `stop` list, element-wise) matches. */ export function callConfigEquals(a: LlmCallConfig, b: LlmCallConfig): boolean { - if (a.model !== b.model || a.temperature !== b.temperature || a.maxTokens !== b.maxTokens) return false + if (a.provider !== b.provider || a.model !== b.model || a.temperature !== b.temperature || a.maxTokens !== b.maxTokens) return false if (a.stop === undefined || b.stop === undefined) return a.stop === b.stop return a.stop.length === b.stop.length && a.stop.every((s, i) => s === b.stop?.[i]) } diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 667e9bca78..47bdc64e69 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -7,8 +7,9 @@ */ import { Context, Service } from 'cordis' -import type { GenerateOptions, StreamChunk } from './types.ts' +import type { GenerateOptions, Message, StreamChunk } from './types.ts' import { HarnessError } from './error.ts' +import { deepFreeze } from './call-config.ts' export * from './attribution.ts' export * from './brand.ts' @@ -58,7 +59,7 @@ export class LlmError extends HarnessError { * * An adapter translates between the harness vocabulary (Message/ContentBlock/ * StreamChunk) and one provider's wire format. Adapters register themselves - * via `ctx.llm.registerAdapter(models, adapter)`. + * via `ctx.llm.registerAdapter(providers, adapter)`. * * Real implementations: `@deepseek-ai/dsh-llm-deepseek` (hand-rolled * fetch/SSE) and `@deepseek-ai/dsh-llm-pi-ai` (pi-ai-backed) — two @@ -93,23 +94,27 @@ export class LlmService extends Service { } /** - * Register an adapter for the given model names. Throws `LlmError` with code - * `DUPLICATE_ADAPTER` if any model already has an adapter (all-or-nothing). + * Register an adapter for the given provider routes. Throws `LlmError` with code + * `DUPLICATE_ADAPTER` if any provider already has an adapter (all-or-nothing). * Disposed with the fiber. - * @param models - every model name this adapter should serve. - * @param adapter - the adapter that streams calls for those models. + * @param providers - every provider route this adapter should serve. + * @param adapter - the adapter that streams calls for those providers. * @returns the disposer that unregisters all of them. */ - registerAdapter(models: string[], adapter: LlmAdapter): () => void { + registerAdapter(providers: string[], adapter: LlmAdapter): () => void { const dispose = this.ctx.effect(function* (this: LlmService) { - for (const model of models) { - if (this.adapters.has(model)) { - throw new LlmError(`an adapter for model "${model}" is already registered`, 'DUPLICATE_ADAPTER') + if (providers.length === 0) throw new LlmError('an adapter must register at least one provider', 'INVALID_ADAPTER') + const unique = new Set() + for (const provider of providers) { + if (provider.length === 0) throw new LlmError('adapter provider names must be non-empty', 'INVALID_ADAPTER') + if (unique.has(provider) || this.adapters.has(provider)) { + throw new LlmError(`an adapter for provider "${provider}" is already registered`, 'DUPLICATE_ADAPTER') } + unique.add(provider) } - for (const model of models) this.adapters.set(model, adapter) + for (const provider of providers) this.adapters.set(provider, adapter) yield () => { - for (const model of models) this.adapters.delete(model) + for (const provider of providers) this.adapters.delete(provider) } }.bind(this), 'llm.registerAdapter()') // ctx.effect's disposer returns Promise; our disposer API is @@ -118,29 +123,48 @@ export class LlmService extends Service { } /** - * Model names with a registered adapter. - * @returns the registered names, in registration order. + * Provider routes with a registered adapter. + * @returns the registered provider names, in registration order. */ - models(): string[] { + providers(): string[] { return [...this.adapters.keys()] } - private adapter(model: string): LlmAdapter { - const adapter = this.adapters.get(model) - if (!adapter) throw new LlmError(`no adapter registered for model "${model}"`, 'NO_ADAPTER') + private adapter(provider: string): LlmAdapter { + const adapter = this.adapters.get(provider) + if (!adapter) throw new LlmError(`no adapter registered for provider "${provider}"`, 'NO_ADAPTER') return adapter } + /** Remove replay state whose historical route is owned by another adapter. */ + private forAdapter(options: GenerateOptions, adapter: LlmAdapter): GenerateOptions { + const messages: Message[] = options.messages.map((message) => { + const provenance = message.provenance + if (message.role !== 'assistant' || provenance?.replayState === undefined) return message + if (this.adapters.get(provenance.provider) === adapter) return message + return { + ...message, + provenance: { provider: provenance.provider, model: provenance.model }, + } + }) + if (messages.every((message, index) => message === options.messages[index])) return options + const filtered = { ...options, messages } + return Object.isFrozen(options) ? deepFreeze(filtered) : filtered + } + /** * Stream one model call as raw chunks (token-level deltas). Throws * `LlmError` with code `NO_ADAPTER` if no adapter is registered for - * `options.model`. Dispatches through the `llm/stream` waterfall. - * @param options - the full request; `options.model` selects the adapter. + * `options.provider`. Replay state is retained only when the same adapter + * instance owns its historical provider and the target provider. Dispatches + * through the `llm/stream` waterfall. + * @param options - the full request; `options.provider` selects the adapter. * @returns the chunk stream, possibly wrapped by `llm/stream` listeners. */ stream(options: GenerateOptions): AsyncIterable { return this.ctx.waterfall(this, 'llm/stream', options, () => { - return this.adapter(options.model).stream(options) + const adapter = this.adapter(options.provider) + return adapter.stream(this.forAdapter(options, adapter)) }) } } diff --git a/packages/llm/llm/src/types.ts b/packages/llm/llm/src/types.ts index e3339869a5..b3280acb03 100644 --- a/packages/llm/llm/src/types.ts +++ b/packages/llm/llm/src/types.ts @@ -75,10 +75,29 @@ export type ContentBlockType = keyof ContentBlockMap /** Any known content block, derived from {@link ContentBlockMap}; switch on `type` and fall through unknowns (merge-extensible). */ export type ContentBlock = ContentBlockMap[ContentBlockType] -/** A single message in a conversation history. */ +/** Provider ownership and adapter-private replay data for an assistant message. */ +export interface AssistantProvenance { + /** Provider route that produced the message. */ + provider: string + /** Provider model id that produced the message. */ + model: string + /** + * Lossless-JSON adapter state needed to replay the provider response. + * `LlmService` exposes it to a target adapter only when that adapter instance + * currently owns both this historical provider and the target provider. + */ + replayState?: unknown +} + +/** + * A single message in a conversation history. Loop-derived assistant messages + * always carry provenance; callers may omit it on hand-built foreign history. + */ export interface Message { role: 'system' | 'user' | 'assistant' content: ContentBlock[] + /** Present only on assistant messages produced by a routed adapter. */ + provenance?: AssistantProvenance } /** @@ -153,7 +172,12 @@ export type StreamChunk = | { type: 'tool-call-delta'; index: number; id: CallId; name?: string; argumentsDelta: string } | { type: 'block-end'; index: number; block: ContentBlock } | { type: 'usage'; usage: TokenUsage } - | { type: 'finish'; reason: FinishReason } + | { + type: 'finish' + reason: FinishReason + /** Adapter-private lossless-JSON state for replaying a successful response. */ + replayState?: unknown + } /** * JSON-schema description of a tool, as sent to the model. @@ -171,6 +195,8 @@ export interface ToolSchema { /** A single model request, fully assembled. */ export interface GenerateOptions { + /** Registered provider route selecting the adapter instance. */ + provider: string model: string /** * Ordered conversation messages, exactly as the provider sees them (after diff --git a/packages/llm/llm/tests/call-config.spec.ts b/packages/llm/llm/tests/call-config.spec.ts index 65ff7d7d34..4bccd2520a 100644 --- a/packages/llm/llm/tests/call-config.spec.ts +++ b/packages/llm/llm/tests/call-config.spec.ts @@ -9,14 +9,16 @@ import { callConfigEquals, deepFreeze } from '../src/call-config.ts' describe('callConfigEquals', () => { it('compares every field, including the stop list element-wise', () => { - expect(callConfigEquals({ model: 'm' }, { model: 'm' })).toBe(true) - expect(callConfigEquals({ model: 'm' }, { model: 'x' })).toBe(false) - expect(callConfigEquals({ model: 'm', temperature: 0.5 }, { model: 'm' })).toBe(false) - expect(callConfigEquals({ model: 'm', maxTokens: 1 }, { model: 'm', maxTokens: 2 })).toBe(false) - expect(callConfigEquals({ model: 'm', stop: ['a'] }, { model: 'm' })).toBe(false) - expect(callConfigEquals({ model: 'm', stop: ['a'] }, { model: 'm', stop: ['a', 'b'] })).toBe(false) - expect(callConfigEquals({ model: 'm', stop: ['a'] }, { model: 'm', stop: ['b'] })).toBe(false) - expect(callConfigEquals({ model: 'm', stop: ['a', 'b'] }, { model: 'm', stop: ['a', 'b'] })).toBe(true) + const base = { provider: 'p', model: 'm' } + expect(callConfigEquals(base, base)).toBe(true) + expect(callConfigEquals(base, { provider: 'x', model: 'm' })).toBe(false) + expect(callConfigEquals(base, { provider: 'p', model: 'x' })).toBe(false) + expect(callConfigEquals({ ...base, temperature: 0.5 }, base)).toBe(false) + expect(callConfigEquals({ ...base, maxTokens: 1 }, { ...base, maxTokens: 2 })).toBe(false) + expect(callConfigEquals({ ...base, stop: ['a'] }, base)).toBe(false) + expect(callConfigEquals({ ...base, stop: ['a'] }, { ...base, stop: ['a', 'b'] })).toBe(false) + expect(callConfigEquals({ ...base, stop: ['a'] }, { ...base, stop: ['b'] })).toBe(false) + expect(callConfigEquals({ ...base, stop: ['a', 'b'] }, { ...base, stop: ['a', 'b'] })).toBe(true) }) }) diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index f669069c44..2308a7eb3b 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -12,6 +12,15 @@ class ScriptedAdapter extends LlmAdapter { } } +class RecordingAdapter extends ScriptedAdapter { + lastOptions: GenerateOptions | undefined + + override async * stream(options: GenerateOptions): AsyncIterable { + this.lastOptions = options + yield * super.stream(options) + } +} + const SCRIPT: StreamChunk[] = [ { type: 'block-start', index: 0, blockType: 'text' }, { type: 'text-delta', index: 0, text: 'hi' }, @@ -22,18 +31,18 @@ describe('LlmService', () => { it('routes stream() to the registered adapter', async () => { const ctx = new Context() await ctx.plugin(LlmService) - ctx.llm.registerAdapter(['test-model'], new ScriptedAdapter(SCRIPT)) + ctx.llm.registerAdapter(['test-provider'], new ScriptedAdapter(SCRIPT)) const chunks: StreamChunk[] = [] - for await (const chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) chunks.push(chunk) + for await (const chunk of ctx.llm.stream({ provider: 'test-provider', model: 'test-model', messages: [] })) chunks.push(chunk) expect(chunks).toEqual(SCRIPT) }) - it('throws NO_ADAPTER for unregistered models', async () => { + it('throws NO_ADAPTER for unregistered providers', async () => { const ctx = new Context() await ctx.plugin(LlmService) await expect((async () => { - for await (const _ of ctx.llm.stream({ model: 'nope', messages: [] })) { /* drain */ } + for await (const _ of ctx.llm.stream({ provider: 'nope', model: 'any-model', messages: [] })) { /* drain */ } })()).rejects.toThrow('no adapter registered') }) @@ -44,10 +53,10 @@ describe('LlmService', () => { const fiber = await ctx.plugin(Object.assign((inner: Context) => { inner.llm.registerAdapter(['scoped-model'], new ScriptedAdapter(SCRIPT)) }, { inject: ['llm'] })) - expect(ctx.llm.models()).toEqual(['scoped-model']) + expect(ctx.llm.providers()).toEqual(['scoped-model']) await fiber.dispose() - expect(ctx.llm.models()).toEqual([]) + expect(ctx.llm.providers()).toEqual([]) }) it('lets llm/stream waterfall listeners wrap the underlying stream', async () => { @@ -64,11 +73,90 @@ describe('LlmService', () => { }) const chunks: StreamChunk[] = [] - for await (const chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) chunks.push(chunk) + for await (const chunk of ctx.llm.stream({ provider: 'test-model', model: 'dynamic-model', messages: [] })) chunks.push(chunk) expect(chunks).toHaveLength(4) expect(chunks[0]).toMatchObject({ index: 99 }) }) + it('resolves the provider after llm/stream listeners have had a chance to route it', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + const adapter = new RecordingAdapter(SCRIPT) + ctx.llm.registerAdapter(['routed'], adapter) + ctx.on('llm/stream', (options, next) => { + options.provider = 'routed' + return next() + }) + + for await (const _chunk of ctx.llm.stream({ provider: 'initial', model: 'm', messages: [] })) { /* drain */ } + expect(adapter.lastOptions?.provider).toBe('routed') + }) + + it('keeps replay state when historical and target providers belong to the same adapter instance', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + const adapter = new RecordingAdapter(SCRIPT) + ctx.llm.registerAdapter(['historical', 'target'], adapter) + const replayState = { private: 'state' } + + for await (const _chunk of ctx.llm.stream({ + provider: 'target', + model: 'new-model', + messages: [{ + role: 'assistant', + content: [{ type: 'text', text: 'old response' }], + provenance: { provider: 'historical', model: 'old-model', replayState }, + }], + })) { /* drain */ } + + expect(adapter.lastOptions?.messages[0]?.provenance).toEqual({ + provider: 'historical', model: 'old-model', replayState, + }) + }) + + it('strips replay state but preserves provenance when the target uses a different adapter instance', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['historical'], new RecordingAdapter(SCRIPT)) + const target = new RecordingAdapter(SCRIPT) + ctx.llm.registerAdapter(['target'], target) + + for await (const _chunk of ctx.llm.stream({ + provider: 'target', + model: 'new-model', + messages: [{ + role: 'assistant', + content: [{ type: 'text', text: 'old response' }], + provenance: { provider: 'historical', model: 'old-model', replayState: { private: 'state' } }, + }], + })) { /* drain */ } + + expect(target.lastOptions?.messages[0]?.provenance).toEqual({ provider: 'historical', model: 'old-model' }) + }) + + it('preserves immutability while stripping replay state from frozen requests', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['historical'], new RecordingAdapter(SCRIPT)) + const target = new RecordingAdapter(SCRIPT) + ctx.llm.registerAdapter(['target'], target) + const options = Object.freeze({ + provider: 'target', + model: 'new-model', + messages: [{ + role: 'assistant' as const, + content: [{ type: 'text' as const, text: 'old response' }], + provenance: { provider: 'historical', model: 'old-model', replayState: { private: 'state' } }, + }], + }) + + for await (const _chunk of ctx.llm.stream(options)) { /* drain */ } + + expect(target.lastOptions).not.toBe(options) + expect(Object.isFrozen(target.lastOptions)).toBe(true) + expect(target.lastOptions?.messages[0]?.provenance).toEqual({ provider: 'historical', model: 'old-model' }) + }) + it('creates LlmError with a code for programmatic handling', () => { const err = new LlmError('something went wrong', 'CUSTOM_CODE') expect(err).toBeInstanceOf(Error) @@ -104,9 +192,9 @@ describe('LlmService', () => { await ctx.plugin(LlmService) const dispose = ctx.llm.registerAdapter(['m1'], new ScriptedAdapter(SCRIPT)) - expect(ctx.llm.models()).toEqual(['m1']) + expect(ctx.llm.providers()).toEqual(['m1']) dispose() - expect(ctx.llm.models()).toEqual([]) + expect(ctx.llm.providers()).toEqual([]) }) it('rejects duplicate adapter registration with DUPLICATE_ADAPTER code', async () => { @@ -123,19 +211,30 @@ describe('LlmService', () => { } }) + it('rejects empty and internally duplicated provider registrations atomically', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + const adapter = new ScriptedAdapter(SCRIPT) + + expect(() => ctx.llm.registerAdapter([], adapter)).toThrow(expect.objectContaining({ code: 'INVALID_ADAPTER' })) + expect(() => ctx.llm.registerAdapter([''], adapter)).toThrow(expect.objectContaining({ code: 'INVALID_ADAPTER' })) + expect(() => ctx.llm.registerAdapter(['first', 'first'], adapter)).toThrow(expect.objectContaining({ code: 'DUPLICATE_ADAPTER' })) + expect(ctx.llm.providers()).toEqual([]) + }) + it('re-registers a model after its prior registration is disposed', async () => { const ctx = new Context() await ctx.plugin(LlmService) const dispose = ctx.llm.registerAdapter(['m1'], new ScriptedAdapter(SCRIPT)) - expect(ctx.llm.models()).toEqual(['m1']) + expect(ctx.llm.providers()).toEqual(['m1']) dispose() - expect(ctx.llm.models()).toEqual([]) + expect(ctx.llm.providers()).toEqual([]) // The duplicate check is not wedged: the same model registers cleanly again. const disposeAgain = ctx.llm.registerAdapter(['m1'], new ScriptedAdapter(SCRIPT)) - expect(ctx.llm.models()).toEqual(['m1']) + expect(ctx.llm.providers()).toEqual(['m1']) disposeAgain() - expect(ctx.llm.models()).toEqual([]) + expect(ctx.llm.providers()).toEqual([]) }) }) diff --git a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts index 757ba03aac..d842c2d52d 100644 --- a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts +++ b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts @@ -137,7 +137,7 @@ describe('SessionPersistenceJsonl: durability and crash semantics', () => { { type: 'step/start', seq: 1, time: 2, data: { turn: 1, step: 1 } }, { type: 'assistant/chunk', seq: 2, time: 3, data: { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'he' } } }, { type: 'assistant/chunk', seq: 3, time: 4, data: { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'llo' } } }, - { type: 'assistant/message', seq: 4, time: 5, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'hello' }] }, surfaceOp: 'append', sourceEventSeqs: [2, 3] }, + { type: 'assistant/message', seq: 4, time: 5, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'hello' }], provenance: { provider: 'mock', model: 'mock' } }, surfaceOp: 'append', sourceEventSeqs: [2, 3] }, { type: 'step/end', seq: 5, time: 6, data: { turn: 1, step: 1 } }, { type: 'turn/end', seq: 6, time: 7, data: { turn: 1, reason: { kind: 'completed' } } }, ] diff --git a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts index a6eda72685..72498d71f8 100644 --- a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts +++ b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts @@ -466,7 +466,7 @@ describe('surface field round-trip', () => { const session = ctx.sessions.create(SessionId('roundtrip-surface')) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [0] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [0] }) session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) await ctx.parallel('session/flush', session) const loaded = await ctx.sessionPersistence.load(SessionId('roundtrip-surface')) diff --git a/packages/session-persistence/session-persistence/tests/contract.ts b/packages/session-persistence/session-persistence/tests/contract.ts index 789aa72c91..ac5b33e637 100644 --- a/packages/session-persistence/session-persistence/tests/contract.ts +++ b/packages/session-persistence/session-persistence/tests/contract.ts @@ -36,7 +36,7 @@ export function oneTurnLog(): SessionEvent[] { { type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } }, { type: 'user/message', seq: 1, time: 2, data: { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, surfaceOp: 'append' }, { type: 'step/start', seq: 2, time: 3, data: { turn: 1, step: 1 } }, - { type: 'assistant/message', seq: 3, time: 4, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'hello' }] }, surfaceOp: 'append' }, + { type: 'assistant/message', seq: 3, time: 4, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'hello' }], provenance: { provider: 'mock', model: 'mock' } }, surfaceOp: 'append' }, { type: 'step/end', seq: 4, time: 5, data: { turn: 1, step: 1 } }, { type: 'turn/end', seq: 5, time: 6, data: { turn: 1, reason: { kind: 'completed' } } }, ] @@ -142,7 +142,7 @@ export function runPersistenceContract(name: string, make: () => Promise startInProcessRun(request, {}), }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(AgentId('parent'), { provider: 'mock', model: 'mock' }) return { ctx, parent, adapter, disposeProvider } } diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index 0005246523..f685490acd 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -24,7 +24,7 @@ async function setup(script: Script) { await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(AgentId('parent'), { provider: 'mock', model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-spawn/tests/harness.ts b/packages/subagent/subagent-spawn/tests/harness.ts index e4ee2e6ab7..ac02b7abf9 100644 --- a/packages/subagent/subagent-spawn/tests/harness.ts +++ b/packages/subagent/subagent-spawn/tests/harness.ts @@ -31,7 +31,7 @@ export async function spawnHarness(workdir: string): Promise { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) - await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) + await ctx.plugin(LlmDeepSeek) await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 }) await ctx.plugin(ToolBash) await ctx.plugin(SubagentService) diff --git a/packages/subagent/subagent-spawn/tests/spawn.e2e.ts b/packages/subagent/subagent-spawn/tests/spawn.e2e.ts index daa032199e..1b278c9748 100644 --- a/packages/subagent/subagent-spawn/tests/spawn.e2e.ts +++ b/packages/subagent/subagent-spawn/tests/spawn.e2e.ts @@ -29,7 +29,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('spawn backend with-key smoke', ( it('a parent delegates to a child that writes a file on disk', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-subagent-spawn-e2e-')) ctx = await spawnHarness(workdir) - const parent = ctx.agentLoop.create(AgentId('e2e-parent'), { model: 'deepseek-v4-flash' }) + const parent = ctx.agentLoop.create(AgentId('e2e-parent'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) parent.send([{ type: 'text', text: 'Use the subagent tool to delegate this exact task: "Use the bash tool to write the text ' diff --git a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts index 9e4e489882..5bc9a72fb6 100644 --- a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts +++ b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts @@ -36,7 +36,7 @@ async function setup(script: Script) { await ctx.plugin(SubagentService) await ctx.plugin(spawn, { providerName: 'spawn' }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(AgentId('parent'), { provider: 'mock', model: 'mock' }) return { ctx, parent, adapter } } @@ -240,7 +240,7 @@ describe('dsh-subagent-spawn', () => { agentId: AgentId('cwd-parent'), sessionId: SessionId('cwd-parent-session'), meta: { cwd: '/tmp/parent-workspace' }, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'p' }], parent: parentHandle.agent }) await run.result @@ -262,7 +262,7 @@ describe('dsh-subagent-spawn', () => { const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'p' }], parent: parentHandle.agent, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const result = await run.result expect(result.stopReason).toBe('completed') @@ -318,7 +318,7 @@ describe('dsh-subagent-spawn', () => { await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(AgentId('parent'), { provider: 'mock', model: 'mock' }) const controller = new AbortController() const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'q' }], @@ -349,7 +349,7 @@ describe('dsh-subagent-spawn', () => { await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(AgentId('parent'), { provider: 'mock', model: 'mock' }) const parentEffects = parent.ctx.fiber.getEffects().length const published: string[] = [] ctx.on('session/created', () => void published.push('session/created')) @@ -444,7 +444,7 @@ describe('dsh-subagent-spawn', () => { const parentHandle = await ctx.agents.create({ agentId: AgentId('doomed-parent'), sessionId: SessionId('doomed-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) await parentHandle.dispose() const before = ctx.agents.list().length @@ -467,7 +467,7 @@ describe('dsh-subagent-spawn', () => { const parentHandle = await ctx.agents.create({ agentId: AgentId('setup-race-parent'), sessionId: SessionId('setup-race-parent-session'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const published: string[] = [] ctx.on('session/created', () => void published.push('session/created')) diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index d07e6726dd..8696992eba 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -102,8 +102,9 @@ export const Config: z = z.object({ // present — the request would carry `agentOptions: {}` and the presence // check in execute() could never be false through config. agentOptions: z.object({ + provider: z.string(), model: z.string(), - }).default(undefined as unknown as { model: string }), + }).default(undefined as unknown as { provider: string; model: string }), persona: z.string(), // A schemastery object materializes {} (with [] for nested arrays) when the // key is omitted — for toolFilter that would mean an EMPTY ALLOW-LIST, i.e. diff --git a/packages/support/invariants/tests/invariants.spec.ts b/packages/support/invariants/tests/invariants.spec.ts index a1e824524b..c43100e602 100644 --- a/packages/support/invariants/tests/invariants.spec.ts +++ b/packages/support/invariants/tests/invariants.spec.ts @@ -48,7 +48,7 @@ describe('session-log invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) session.append('step/start', { turn: 1, step: 1 }) session.append('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'h' } }) - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c1'), name: 'echo', arguments: '{}' }] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c1'), name: 'echo', arguments: '{}' }] }, { surfaceOp: 'append' }) session.append('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'echo', arguments: '{}' }) session.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'ok' }], isError: false }, { surfaceOp: 'append' }) session.append('step/end', { turn: 1, step: 1 }) @@ -195,7 +195,7 @@ describe('session-log invariants', () => { expect(() => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) - session.append('assistant/message', { turn: 1, step: 1, content: [ + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [ { type: 'tool-call', id: CallId('crashed'), name: 'bash', arguments: '{}' }, ] }, { surfaceOp: 'append' }) session.append('tool/result', { @@ -251,10 +251,10 @@ describe('session-log invariants', () => { expect(() => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append' }) session.append('step/end', { turn: 1, step: 1 }) session.append('step/start', { turn: 1, step: 2 }) - session.append('assistant/message', { turn: 1, step: 2, content: [] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 2, content: [] }, { surfaceOp: 'append' }) session.append('step/end', { turn: 1, step: 2 }) session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) @@ -316,7 +316,7 @@ describe('session-log invariants', () => { const session = ctx.sessions.create() session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) - expect(() => session.append('assistant/message', { turn: 1, step: 2, content: [] }, { surfaceOp: 'append' })) + expect(() => session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 2, content: [] }, { surfaceOp: 'append' })) .toThrow(/open is turn 1\/step 1/) }) }) @@ -475,7 +475,7 @@ describe('surface invariants', () => { session.append('step/start', { turn: 1, step: 1 }) expect(() => { session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1] }) }).not.toThrow() }) @@ -485,7 +485,7 @@ describe('surface invariants', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [2] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [2] }) // no throw — well-formed replace op }) @@ -494,7 +494,7 @@ describe('surface invariants', () => { const session = ctx.sessions.create() session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [] }) }).toThrow(InvariantError) }) @@ -504,7 +504,7 @@ describe('surface invariants', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1, 1] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1, 1] }) }).toThrow(/must not contain duplicates/) }) @@ -515,7 +515,7 @@ describe('surface invariants', () => { // The next event is seq 1. Referencing its own seq fails on "must reference // earlier events" (the check order is: earlier first, then unknown). expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1] }) }).toThrow(/must reference earlier/) }) @@ -527,7 +527,7 @@ describe('surface invariants', () => { session.append('step/start', { turn: 1, step: 1 }) // seqs so far: 0, 1. The next event at seq 2 references seq 1 → valid. expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1] }) }).not.toThrow() }) @@ -536,7 +536,7 @@ describe('surface invariants', () => { const session = ctx.sessions.create() session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [99] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [99] }) }).toThrow(/must reference earlier/) }) @@ -561,7 +561,7 @@ describe('surface invariants', () => { // is seq 3 (log.length). Reference seq 2: passes earlier (2 < 3) but not // in knownSeqs ({0, 1, 3} — gap at 2). expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [2] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [2] }) }).toThrow(/unknown seq 2/) }) @@ -574,7 +574,7 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 3 // Reversed range: start seq 3 is at a later surface position than end seq 2. expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 3, end: 2 }, sourceEventSeqs: [2, 3] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 3, end: 2 }, sourceEventSeqs: [2, 3] }) }).toThrow(/is after end seq 2 .* on the surface/) }) @@ -587,7 +587,7 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 3 // Replace shadows surface nodes [2, 3] but records provenance for only [2]. expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'sum' }] }, { surfaceOp: { op: 'replace', start: 2, end: 3 }, sourceEventSeqs: [2] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'sum' }] }, { surfaceOp: { op: 'replace', start: 2, end: 3 }, sourceEventSeqs: [2] }) }).toThrow(/must include every shadowed surface node; missing 3/) }) @@ -599,7 +599,7 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2 session.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 3 expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'sum' }] }, { surfaceOp: { op: 'replace', start: 2, end: 3 }, sourceEventSeqs: [2, 3] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'sum' }] }, { surfaceOp: { op: 'replace', start: 2, end: 3 }, sourceEventSeqs: [2, 3] }) }).not.toThrow() }) @@ -611,7 +611,7 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2 // seq 1 (step/start) is a real earlier event but never entered the surface. expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 1, end: 2 }, sourceEventSeqs: [1, 2] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 1, end: 2 }, sourceEventSeqs: [1, 2] }) }).toThrow(/start seq 1 is not on the surface/) }) @@ -623,7 +623,7 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2 // start (2) is on the surface but end (99) never entered it. expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 2, end: 99 }, sourceEventSeqs: [2] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 2, end: 99 }, sourceEventSeqs: [2] }) }).toThrow(/end seq 99 is not on the surface/) }) @@ -636,11 +636,11 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 3 // Replace node 2 (position 0) with seq 4 — surface is now [4, 3], so seq 4 // precedes seq 3 in linked-list order even though 4 > 3 numerically. - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [2] }) // seq 4 + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [2] }) // seq 4 // A replace with start=3, end=4 passes the seq check (3 <= 4) but is // reversed positionally (3 is at pos 1, 4 is at pos 0). expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 3, end: 4 }, sourceEventSeqs: [3, 4] }) // seq 5 + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 3, end: 4 }, sourceEventSeqs: [3, 4] }) // seq 5 }).toThrow(/is after end seq 4 .* on the surface/) }) @@ -655,9 +655,9 @@ describe('surface invariants', () => { // head seq (4) is numerically GREATER than the tail seq (3): the surface is // not seq-ordered. A replace spanning start=4 (pos 0) … end=3 (pos 1) is // valid positionally and must be accepted even though start seq > end seq. - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [2] }) // seq 4 + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [2] }) // seq 4 expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 4, end: 3 }, sourceEventSeqs: [4, 3] }) // seq 5 + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 4, end: 3 }, sourceEventSeqs: [4, 3] }) // seq 5 }).not.toThrow() }) @@ -669,7 +669,7 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2 // A replace with no sourceEventSeqs records no provenance for the node it shadows. expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 2, end: 2 } }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 2, end: 2 } }) }).toThrow(/must include every shadowed surface node; missing 2/) }) @@ -680,7 +680,7 @@ describe('surface invariants', () => { { type: 'step/start' as const, seq: 1, time: 0, data: { turn: 1, step: 1 } }, { type: 'user/message' as const, seq: 2, time: 0, data: { content: [{ type: 'text' as const, text: 'a' }], source: { kind: 'user' as const } }, surfaceOp: 'append' as const }, { type: 'user/message' as const, seq: 3, time: 0, data: { content: [{ type: 'text' as const, text: 'b' }], source: { kind: 'user' as const } }, surfaceOp: 'append' as const }, - { type: 'assistant/message' as const, seq: 4, time: 0, data: { turn: 1, step: 1, content: [{ type: 'text' as const, text: 'sum' }] }, surfaceOp: { op: 'replace' as const, start: 2, end: 3 }, sourceEventSeqs: [2] }, + { type: 'assistant/message' as const, seq: 4, time: 0, data: { turn: 1, step: 1, content: [{ type: 'text' as const, text: 'sum' }], provenance: { provider: 'mock', model: 'mock' } }, surfaceOp: { op: 'replace' as const, start: 2, end: 3 }, sourceEventSeqs: [2] }, ] expect(() => ctx.sessions.create(undefined, { seed: badSeed })).toThrow(/must include every shadowed surface node; missing 3/) }) @@ -715,7 +715,7 @@ describe('request-reconstruction cross-check (llm/stream)', () => { session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) const boundary = session.deriveMessages() session.append('step/start', { turn: 1, step: 1 }) - session.append('request/header', { header: { config: { model: 'm' } }, reason: 'initial' }) + session.append('request/header', { header: { config: { provider: 'mock', model: 'm' } }, reason: 'initial' }) return { ctx, session, boundary } } @@ -818,7 +818,7 @@ describe('request cross-check ordering (prepend)', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) session.append('step/start', { turn: 1, step: 1 }) - session.append('request/header', { header: { config: { model: 'm' } }, reason: 'initial' }) + session.append('request/header', { header: { config: { provider: 'mock', model: 'm' } }, reason: 'initial' }) const divergent = Object.freeze({ model: 'm', diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index 3b4e8c5fee..19d5824e0f 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -214,7 +214,7 @@ describe('installLlmReplay (through the real waterfall)', () => { await ctx.plugin(LlmService) // No adapter registered for 'm' — replay must not reach it. installLlmReplay(ctx, { file }) - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) it('serves the Nth call the Nth derived entry (positional)', async () => { @@ -227,8 +227,8 @@ describe('installLlmReplay (through the real waterfall)', () => { const ctx = new Context() await ctx.plugin(LlmService) installLlmReplay(ctx, { file }) - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(second) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(second) }) it('replays a sidecar throw-entry as an LlmError with code/status, after its prefix chunks', async () => { @@ -244,7 +244,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const seen: StreamChunk[] = [] await expect((async () => { - for await (const c of ctx.llm.stream({ model: 'm', messages: [] })) seen.push(c) + for await (const c of ctx.llm.stream({ provider: 'm', model: 'm', messages: [] })) seen.push(c) })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH', status: 401 }) expect(seen).toEqual(partial) }) @@ -258,7 +258,7 @@ describe('installLlmReplay (through the real waterfall)', () => { installLlmReplay(ctx, { file, overrideFile }) const controller = new AbortController() - const iterator = ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]() + const iterator = ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]() // Deterministically consume the two pre-hang chunks (no sleep), then abort // and assert the next pull rejects — event-driven, per the no-sleeps rule. expect((await iterator.next()).value).toMatchObject({ type: 'block-start' }) @@ -272,8 +272,8 @@ describe('installLlmReplay (through the real waterfall)', () => { const ctx = new Context() await ctx.plugin(LlmService) installLlmReplay(ctx, { file }) - await drain(ctx.llm.stream({ model: 'm', messages: [] })) - await expect(drain(ctx.llm.stream({ model: 'm', messages: [] }))).rejects.toThrow(/exhausted/) + await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] })) + await expect(drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).rejects.toThrow(/exhausted/) }) it('aborts mid-replay when the signal is already set', async () => { @@ -283,7 +283,7 @@ describe('installLlmReplay (through the real waterfall)', () => { installLlmReplay(ctx, { file }) const controller = new AbortController() controller.abort() - await expect(drain(ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal }))) + await expect(drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal }))) .rejects.toThrow('aborted') }) @@ -305,11 +305,11 @@ describe('installLlmReplay (through the real waterfall)', () => { }, { inject: ['llm'] })) // While installed, replay short-circuits to the derived fixture ('hi'). - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) await fiber.dispose() // After dispose the listener is gone; the call reaches the real adapter. - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))) .toEqual([{ type: 'finish', reason: { kind: 'stop' } }]) }) @@ -321,7 +321,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const ctx = new Context() await ctx.plugin(LlmService) installLlmReplay(ctx, { file, overrideFile }) - await expect(drain(ctx.llm.stream({ model: 'm', messages: [] }))) + await expect(drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))) .rejects.toThrow(/llm-replay replay entry/) }) @@ -333,7 +333,7 @@ describe('installLlmReplay (through the real waterfall)', () => { await ctx.plugin(LlmService) installLlmReplay(ctx, { file, overrideFile }) const controller = new AbortController() - const iterator = ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]() + const iterator = ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]() // Consume the two pre-hang chunks, then start the third pull so the generator // is parked inside the await (signal NOT yet aborted — exercises the // addEventListener('abort') registration), and only THEN abort. @@ -359,7 +359,7 @@ describe('installLlmReplay (through the real waterfall)', () => { controller.abort() // Already aborted: the throw-entry's prefix loop surfaces 'aborted' before // it can reach the recorded LlmError. - await expect(drain(ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal }))) + await expect(drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal }))) .rejects.toThrow('aborted') }) @@ -373,7 +373,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const controller = new AbortController() controller.abort() // The two pre-hang chunks still flow; the abort surfaces at the await. - const iterator = ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]() + const iterator = ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]() await iterator.next() await iterator.next() await expect(iterator.next()).rejects.toThrow('aborted') @@ -509,7 +509,7 @@ describe('installLlmReplay (per-session keying)', () => { ] const live = (id: string): GenerateOptions => - ({ model: 'm', messages: [], sessionId: id as NonNullable }) + ({ provider: 'm', model: 'm', messages: [], sessionId: id as NonNullable }) it('routes each live session to its own script by FIRST-CALL order', async () => { const parentFile = writeSession('session.jsonl', { id: 'rec-parent', createdAt: 100 }, [TEXT_CHUNKS]) @@ -546,7 +546,7 @@ describe('installLlmReplay (per-session keying)', () => { await ctx.plugin(LlmService) installLlmReplay(ctx, { file: parentFile }) // No sessionId at all — the legacy single-session path. - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) it('fails loud when more distinct live sessions call than were recorded', async () => { @@ -585,7 +585,7 @@ describe('apply (the plugin entry)', () => { const ctx = new Context() await ctx.plugin(LlmService) apply(ctx, { file }) - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) it('falls back to $DSH_SNAPSHOT_FILE / $DSH_SNAPSHOT_OVERRIDE when config is empty', async () => { @@ -597,7 +597,7 @@ describe('apply (the plugin entry)', () => { const ctx = new Context() await ctx.plugin(LlmService) apply(ctx) - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) it('uses only the file when no override path is configured or in the env', async () => { @@ -607,7 +607,7 @@ describe('apply (the plugin entry)', () => { const ctx = new Context() await ctx.plugin(LlmService) apply(ctx) - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) it('throws when no fixture path is given by config or env', async () => { @@ -637,7 +637,7 @@ describe('apply (the plugin entry)', () => { await ctx.plugin(LlmService) apply(ctx, { file, childFiles: [childFile] }) const live = (id: string): GenerateOptions => - ({ model: 'm', messages: [], sessionId: id as NonNullable }) + ({ provider: 'm', model: 'm', messages: [], sessionId: id as NonNullable }) expect(await drain(ctx.llm.stream(live('A')))).toEqual(TEXT_CHUNKS) expect(await drain(ctx.llm.stream(live('B')))).toEqual(childSecond) }) @@ -657,7 +657,7 @@ describe('apply (the plugin entry)', () => { await ctx.plugin(LlmService) apply(ctx) const live = (id: string): GenerateOptions => - ({ model: 'm', messages: [], sessionId: id as NonNullable }) + ({ provider: 'm', model: 'm', messages: [], sessionId: id as NonNullable }) expect(await drain(ctx.llm.stream(live('A')))).toEqual(TEXT_CHUNKS) expect(await drain(ctx.llm.stream(live('B')))).toEqual(childChunks) }) @@ -669,6 +669,6 @@ describe('apply (the plugin entry)', () => { const ctx = new Context() await ctx.plugin(LlmService) apply(ctx) - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) }) diff --git a/packages/todo/tool-todo/tests/integration.spec.ts b/packages/todo/tool-todo/tests/integration.spec.ts index 739367a699..eaea7769e6 100644 --- a/packages/todo/tool-todo/tests/integration.spec.ts +++ b/packages/todo/tool-todo/tests/integration.spec.ts @@ -64,7 +64,7 @@ describe('todo_write tool through the agent loop', () => { textResponse('Plan recorded.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-todo'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('it-todo'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'plan a two-step task' }]) await waitForIdle(ctx, agent) @@ -92,7 +92,7 @@ describe('todo_write tool through the agent loop', () => { textResponse('Done planning.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-todo-2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('it-todo-2'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'plan then update' }]) await waitForIdle(ctx, agent) diff --git a/packages/ui/acp-agent/README.md b/packages/ui/acp-agent/README.md index d81c9cc091..597b1356d8 100644 --- a/packages/ui/acp-agent/README.md +++ b/packages/ui/acp-agent/README.md @@ -24,8 +24,9 @@ Because the package wires no logger entry, an ACP leaf has **nothing to get wron | Key | Default | Routed to | |---|---|---| +| `provider` | (required) | the provider route for each per-session agent the bridge creates | | `model` | (required) | the per-session agent template the bridge creates agents from | -| `persona` | — | the deployment persona template (may reference `{{model}}`/`{{cwd}}`), routed to `dsh-system-prompt` | +| `persona` | — | the deployment persona template (may reference `{{provider}}`/`{{model}}`/`{{cwd}}`), routed to `dsh-system-prompt` | | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | diff --git a/packages/ui/acp-agent/src/index.ts b/packages/ui/acp-agent/src/index.ts index 43186dfcb0..d912f4ed86 100644 --- a/packages/ui/acp-agent/src/index.ts +++ b/packages/ui/acp-agent/src/index.ts @@ -17,8 +17,8 @@ * The leaf supplies the swappable backends: the LLM adapter (`llm-deepseek` for * the real model, `llm-replay` for keyless snapshot replay), the bash executor * (`bash-local`), and any optional product tools it wants to expose. This app's - * {@link Config} (model, system prompt, persistence root) routes each value to - * where it is wired — model/prompt onto the bridge's per-session agent + * {@link Config} (provider/model, system prompt, persistence root) routes each value to + * where it is wired — provider/model/prompt onto the bridge's per-session agent * template, the root onto the JSONL backend. * * Plugin export shape: named `name`/`Config`/`apply`, NO default export — the @@ -41,7 +41,7 @@ import UserInteractionService from '@deepseek-ai/dsh-user-interaction' export const name = 'acp-agent' /** - * App config: the swappable per-deployment values. `model` configures the + * App config: the swappable per-deployment values. `provider` and `model` configure the * agent template the ACP bridge creates each session's agent from (NOT a * pre-created agent — ACP creates agents at `session/new`); `persona` is the * deployment persona (forwarded to the system-prompt plugin); `toolOrder` is @@ -50,6 +50,8 @@ export const name = 'acp-agent' * through agent-core); `persistenceRoot` is the JSONL backend's directory. */ export interface Config { + /** Provider route for ACP-created agents. */ + provider: string /** Model name for ACP-created agents (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ @@ -68,6 +70,7 @@ export interface Config { // the common fields would make two small app contracts depend on a new facade. /* jscpd:ignore-start */ export const Config: z = z.object({ + provider: z.string().required(), model: z.string().required(), persona: z.string(), // The array default is forced to undefined: ABSENT means "lexicographic @@ -87,7 +90,7 @@ export const Config: z = z.object({ * NO agents (its `agents` list defaults to `[]`) and carries the deployment * `persona`; the JSONL backend persists under `persistenceRoot`; the ACP * bridge owns stdout for JSON-RPC and creates one agent per `session/new` - * from `model`. No logger, no `hmr` — stdout stays pure. + * from the provider/model pair. No logger, no `hmr` — stdout stays pure. */ export function apply(ctx: Context, config: Config): void { ctx.plugin(agentCore, { @@ -98,5 +101,5 @@ export function apply(ctx: Context, config: Config): void { }) ctx.plugin(UserInteractionService) ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) - ctx.plugin(acp, { model: config.model }) + ctx.plugin(acp, { provider: config.provider, model: config.model }) } diff --git a/packages/ui/acp-agent/tests/acp-agent.spec.ts b/packages/ui/acp-agent/tests/acp-agent.spec.ts index 537155429c..1cc34b3b5f 100644 --- a/packages/ui/acp-agent/tests/acp-agent.spec.ts +++ b/packages/ui/acp-agent/tests/acp-agent.spec.ts @@ -69,7 +69,7 @@ async function withIsolatedSkillHomes(run: () => Promise): Promise { describe('dsh-acp-agent composition', () => { it('brings up the spine + persistence + the ACP bridge', async () => { - const ctx = await mount({ model: 'mock', persona: 'hi', persistenceRoot: '/tmp/dsh-acp-agent-test', skills: await isolatedSkillsConfig() }) + const ctx = await mount({ provider: 'mock', model: 'mock', persona: 'hi', persistenceRoot: '/tmp/dsh-acp-agent-test', skills: await isolatedSkillsConfig() }) expect(ctx.get('agents')).toBeDefined() expect(ctx.get('sessions')).toBeDefined() expect(ctx.get('sessionPersistence')).toBeDefined() @@ -88,7 +88,7 @@ describe('dsh-acp-agent composition', () => { // persistenceRoot, so the runtime fallback is the one that fires. const ctx = new Context() // No persona: covers the omitted-persona forwarding branch too. - acpAgent.apply(ctx, { model: 'mock', skills: await isolatedSkillsConfig() }) + acpAgent.apply(ctx, { provider: 'mock', model: 'mock', skills: await isolatedSkillsConfig() }) await new Promise(resolve => setTimeout(resolve, 50)) expect(ctx.get('sessionPersistence')).toBeDefined() await ctx.fiber.dispose() @@ -97,7 +97,7 @@ describe('dsh-acp-agent composition', () => { it('uses default skill config when apply is called directly without skills', async () => { await withIsolatedSkillHomes(async () => { const ctx = new Context() - acpAgent.apply(ctx, { model: 'mock' }) + acpAgent.apply(ctx, { provider: 'mock', model: 'mock' }) await new Promise(resolve => setTimeout(resolve, 50)) expect(ctx.skills).toBeDefined() expect(await ctx.skills.list()).toEqual([]) @@ -106,7 +106,7 @@ describe('dsh-acp-agent composition', () => { }) it('forwards skill config into agent-core', async () => { - const ctx = await mount({ model: 'mock', persona: 'hi', skills: await isolatedSkillsConfig(6) }) + const ctx = await mount({ provider: 'mock', model: 'mock', persona: 'hi', skills: await isolatedSkillsConfig(6) }) ctx.skills.register({ name: 'acp-skill', description: 'ACP skill', source: 'runtime', content: 'body' }) expect(JSON.stringify(await composePrefix(ctx))).toContain('- `acp-skill`: ACP...') await ctx.fiber.dispose() @@ -119,6 +119,7 @@ describe('dsh-acp-agent composition', () => { it('forwards toolOrder through agent-core to the system-prompt assembly', async () => { const ctx = await mount({ + provider: 'mock', model: 'mock', toolOrder: ['zulu', TOOL_ORDER_REST], persistenceRoot: '/tmp/dsh-acp-agent-test-tool-order', diff --git a/packages/ui/acp-agent/tests/built-bin.e2e.ts b/packages/ui/acp-agent/tests/built-bin.e2e.ts index de4612a40a..6bf9bfcd30 100644 --- a/packages/ui/acp-agent/tests/built-bin.e2e.ts +++ b/packages/ui/acp-agent/tests/built-bin.e2e.ts @@ -92,12 +92,12 @@ async function makeConsumer(): Promise { ' name: \'@deepseek-ai/dsh-llm-deepseek\'', ' config:', ' apiKey: !!js process.env.DEEPSEEK_API_KEY', - ' models: [deepseek-v4-flash]', '- id: bash', ' name: \'@deepseek-ai/dsh-bash-local\'', '- id: acp-agent', ' name: \'@deepseek-ai/dsh-acp-agent\'', ' config:', + ' provider: deepseek', ' model: deepseek-v4-flash', ' persona: \'test agent\'', '', diff --git a/packages/ui/acp-agent/tests/load-path.e2e.ts b/packages/ui/acp-agent/tests/load-path.e2e.ts index ec251a6e6b..b97f6c0874 100644 --- a/packages/ui/acp-agent/tests/load-path.e2e.ts +++ b/packages/ui/acp-agent/tests/load-path.e2e.ts @@ -47,12 +47,12 @@ const CORDIS_YML = ` name: '@deepseek-ai/dsh-llm-deepseek' config: apiKey: !!js process.env.DEEPSEEK_API_KEY - models: [deepseek-v4-flash] - id: bash name: '@deepseek-ai/dsh-bash-local' - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persona: 'You are a test agent.' ` diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index f4947e5d25..9496d40cf3 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -14,6 +14,7 @@ It is a **client-driver / UI plugin**, the structured analogue of the readline ` | Key | Default | Meaning | |---|---|---| +| `provider` | — | Provider route for created agents (must have a registered adapter). | | `model` | — | Model name for created agents (must have a registered adapter). | (No persona key: `dsh-system-prompt`'s own `persona` config supplies the global default section, so ACP-created agents render it without the bridge carrying prompt text. An agent-scoped same-name section may still shadow that default.) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index a3fdc38f97..7c1a2c07d6 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -248,6 +248,8 @@ function stringArrayContent( /** Plugin config: the agent template ACP sessions are created from. */ export interface AcpConfig { + /** Provider route for created agents. */ + provider?: string /** Model name for created agents (must have a registered adapter). */ model?: string /** @@ -261,6 +263,7 @@ export interface AcpConfig { } export const Config: Schema = Schema.object({ + provider: Schema.string(), model: Schema.string(), }) @@ -1015,11 +1018,12 @@ export function apply(ctx: Context, config: AcpConfig): void { * Build per-agent options from the plugin config, omitting absent fields * (exactOptionalPropertyTypes: never assign `undefined` to an optional key). * Exported for unit coverage of both the present and absent branches. - * @param config - the plugin config carrying the optional model name. - * @returns the per-agent options, with `model` present only when configured. + * @param config - the plugin config carrying the optional provider/model target. + * @returns the per-agent options, with each configured target field present. */ -export function agentOptions(config: AcpConfig): { model?: string } { +export function agentOptions(config: AcpConfig): { provider?: string; model?: string } { return { + ...config.provider !== undefined ? { provider: config.provider } : {}, ...config.model !== undefined ? { model: config.model } : {}, } } diff --git a/packages/ui/acp/tests/dispose.spec.ts b/packages/ui/acp/tests/dispose.spec.ts index f02a7b0649..02d7045379 100644 --- a/packages/ui/acp/tests/dispose.spec.ts +++ b/packages/ui/acp/tests/dispose.spec.ts @@ -230,10 +230,10 @@ describe('acp bridge — disposal & HMR safety', () => { // queryable, with its session still in the store. const harness = await makeBridgeHarness({ storageDir, script: [] }) const handleA = await harness.ctx.agents.create({ - agentId: AgentId('sib-a'), sessionId: SessionId('sib-a'), agentOptions: { model: 'mock' }, + agentId: AgentId('sib-a'), sessionId: SessionId('sib-a'), agentOptions: { provider: 'mock', model: 'mock' }, }) const handleB = await harness.ctx.agents.create({ - agentId: AgentId('sib-b'), sessionId: SessionId('sib-b'), agentOptions: { model: 'mock' }, + agentId: AgentId('sib-b'), sessionId: SessionId('sib-b'), agentOptions: { provider: 'mock', model: 'mock' }, }) expect(harness.ctx.agents.get(AgentId('sib-a'))).toBe(handleA.agent) expect(harness.ctx.agents.get(AgentId('sib-b'))).toBe(handleB.agent) @@ -262,7 +262,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: [textResponse('ok')] }) harness.ctx.on('agent/disposed', () => { throw new Error('boom disposed listener') }) const handle = await harness.ctx.agents.create({ - agentId: AgentId('guard-a'), sessionId: SessionId('guard-a'), agentOptions: { model: 'mock' }, + agentId: AgentId('guard-a'), sessionId: SessionId('guard-a'), agentOptions: { provider: 'mock', model: 'mock' }, }) handle.agent.send([{ type: 'text', text: 'go' }]) await handle.agent.whenIdle() @@ -283,7 +283,7 @@ describe('acp bridge — disposal & HMR safety', () => { // observe the same quiescence boundary. const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) const handle = await harness.ctx.agents.create({ - agentId: AgentId('conc-a'), sessionId: SessionId('conc-a'), agentOptions: { model: 'mock' }, + agentId: AgentId('conc-a'), sessionId: SessionId('conc-a'), agentOptions: { provider: 'mock', model: 'mock' }, }) // Drive a turn that hangs in the model stream, so the loop is mid-turn when // disposed — its exit runs a final session/flush we can gate to hold the diff --git a/packages/ui/acp/tests/edges.spec.ts b/packages/ui/acp/tests/edges.spec.ts index e86fb9fc94..de3a7a6f03 100644 --- a/packages/ui/acp/tests/edges.spec.ts +++ b/packages/ui/acp/tests/edges.spec.ts @@ -27,7 +27,7 @@ describe('acp bridge — demux & config edges', () => { await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) const before = harness.updates.length - const { agent: foreign } = await harness.ctx.agents.create({ agentId: AgentId('foreign'), sessionId: SessionId('foreign-session'), agentOptions: { model: 'mock' } }) + const { agent: foreign } = await harness.ctx.agents.create({ agentId: AgentId('foreign'), sessionId: SessionId('foreign-session'), agentOptions: { provider: 'mock', model: 'mock' } }) foreign.send([{ type: 'text', text: 'hi' }]) await foreign.whenIdle() await new Promise(r => setTimeout(r, 10)) diff --git a/packages/ui/acp/tests/harness.ts b/packages/ui/acp/tests/harness.ts index a24c7aa145..1a9672cafb 100644 --- a/packages/ui/acp/tests/harness.ts +++ b/packages/ui/acp/tests/harness.ts @@ -155,7 +155,7 @@ export interface BridgeHarness { * The bridge's `apply` receives the agent-side `Stream` via `config.stream`; * the test holds the `ClientSideConnection`. * - * Pass `config: { model: undefined }` to override the default `model: 'mock'` + * Pass `config: { model: undefined }` to override the default mock target * (the model key is dropped entirely when explicitly undefined). */ export async function makeBridgeHarness(options: { @@ -282,10 +282,11 @@ export async function makeBridgeHarness(options: { }) // Wire the bridge (agent side) and the client (test side). The test config - // can override `model` (including to undefined): default to 'mock' unless the - // caller explicitly set the key (even to undefined), so a `{ model: undefined }` - // override means "no model at all". + // can override either route field (including to undefined). Default both to + // `mock` unless the caller explicitly set that key, so `{ model: undefined }` + // still means "no model at all". const cfg: AcpConfig = { stream: agentStream, ...options.config } + if (!(options.config && 'provider' in options.config)) cfg.provider = 'mock' if (!(options.config && 'model' in options.config)) cfg.model = 'mock' // Mount the bridge the way production does: as a cordis PLUGIN (via // `ctx.plugin` with the real `inject`), NOT `AcpPlugin.apply(ctx, cfg)` diff --git a/packages/ui/acp/tests/stream-update.spec.ts b/packages/ui/acp/tests/stream-update.spec.ts index 0a9cf3e82e..224acce239 100644 --- a/packages/ui/acp/tests/stream-update.spec.ts +++ b/packages/ui/acp/tests/stream-update.spec.ts @@ -804,5 +804,6 @@ describe('agentOptions', () => { it('includes only the fields present in config', () => { expect(agentOptions({})).toEqual({}) expect(agentOptions({ model: 'm' })).toEqual({ model: 'm' }) + expect(agentOptions({ provider: 'p', model: 'm' })).toEqual({ provider: 'p', model: 'm' }) }) }) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 007bd1a5f1..ed256c2828 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`) and demuxes `subagent/end` through the registry. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`) from the `initialize.provider`+`initialize.model` pair and demuxes `subagent/end` through the registry. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): an already registered adapter for the provider route wins; when the route is `deepseek` and unowned, the plugin mounts `dsh-llm-deepseek` (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); any other unowned provider fails initialization. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 86af6645f3..f96993c6d8 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -26,6 +26,8 @@ import type { JsonRpcTransportPeer } from './transport.ts' export interface InitializeParams { /** Working directory recorded on every SDK-created session's header. */ cwd: string + /** Provider route every SDK-created agent runs on. */ + provider: string /** Model name every SDK-created agent runs on (see {@link HarnessSdkServer.initialize} for adapter fallback). */ model: string } @@ -73,6 +75,7 @@ interface SubagentRecord { */ export class HarnessSdkServer { private cwd = process.cwd() + private provider = 'deepseek' private model = 'deepseek' private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() @@ -132,18 +135,20 @@ export class HarnessSdkServer { } /** - * Handle `initialize`: record the SDK deployment facts (cwd, model) and, when - * no registered adapter serves `params.model`, mount the DeepSeek adapter for - * it (credentials from `$DEEPSEEK_API_KEY`/`$DEEPSEEK_BASE_URL`) — a config - * that already registered an adapter for the model wins. + * Handle `initialize`: record the SDK deployment facts and, when provider + * `deepseek` has no registered owner, mount the native DeepSeek adapter + * (credentials from `$DEEPSEEK_API_KEY`/`$DEEPSEEK_BASE_URL`). Other missing + * providers fail without guessing an implementation. * @param params - the SDK handshake parameters. * @returns the server identity for the handshake. */ async initialize(params: InitializeParams): Promise { this.cwd = resolve(params.cwd) + this.provider = params.provider this.model = params.model - if (!this.llmFiber && !this.hasAdapterFor(this.model)) { - this.llmFiber = await this.ctx.plugin(LlmDeepSeek, { models: [this.model] }) + if (!this.hasAdapterFor(this.provider)) { + if (this.provider !== 'deepseek') throw new Error(`no adapter registered for provider "${this.provider}"`) + this.llmFiber = await this.ctx.plugin(LlmDeepSeek, {}) } return { serverInfo: { name: 'deepseek-harness-sdk-runtime', version: '0.0.1' } } } @@ -258,7 +263,7 @@ export class HarnessSdkServer { agentId: AgentId(sessionId), sessionId: SessionId(sessionId), meta: { cwd: this.cwd }, - agentOptions: { model: this.model }, + agentOptions: { provider: this.provider, model: this.model }, }) const rec: SessionRecord = { handle, lastTurnEnd: undefined, activePrompt: false } this.sessions.set(sessionId, rec) @@ -270,7 +275,7 @@ export class HarnessSdkServer { return reason.kind === 'completed' ? 'ok' : 'error' } - private hasAdapterFor(model: string): boolean { - return this.ctx.get('llm')?.models().includes(model) ?? false + private hasAdapterFor(provider: string): boolean { + return this.ctx.get('llm')?.providers().includes(provider) ?? false } } diff --git a/packages/ui/jsonrpc/tests/plugin-apply.spec.ts b/packages/ui/jsonrpc/tests/plugin-apply.spec.ts index 8f4a504264..1acd2f2edd 100644 --- a/packages/ui/jsonrpc/tests/plugin-apply.spec.ts +++ b/packages/ui/jsonrpc/tests/plugin-apply.spec.ts @@ -167,7 +167,7 @@ describe('dsh-jsonrpc plugin apply', () => { vi.stubEnv('DEEPSEEK_API_KEY', 'test-key') const harness = await mountPlugin(storageDir) try { - harness.send({ jsonrpc: '2.0', id: 'init-1', method: 'initialize', params: { cwd: storageDir, model: 'apply-model' } }) + harness.send({ jsonrpc: '2.0', id: 'init-1', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'apply-model' } }) const response = await harness.waitForFrame(frame => frame.id === 'init-1', 'initialize response') expect(response).toEqual({ @@ -189,7 +189,7 @@ describe('dsh-jsonrpc plugin apply', () => { vi.stubEnv('DEEPSEEK_BASE_URL', llmServer.url) const harness = await mountPlugin(storageDir) try { - harness.send({ jsonrpc: '2.0', id: 1, method: 'initialize', params: { cwd: storageDir, model: 'dsagent-model' } }) + harness.send({ jsonrpc: '2.0', id: 1, method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'dsagent-model' } }) await harness.waitForFrame(frame => frame.id === 1, 'initialize response') harness.send({ @@ -256,7 +256,7 @@ describe('dsh-jsonrpc plugin apply', () => { // The plugin fiber is disposed: the transport reads no further frames. const before = harness.frames().length - harness.send({ jsonrpc: '2.0', id: 'after-exit', method: 'initialize', params: { cwd: storageDir, model: 'x' } }) + harness.send({ jsonrpc: '2.0', id: 'after-exit', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'x' } }) await settle() expect(harness.frames().length).toBe(before) } finally { @@ -277,7 +277,7 @@ describe('dsh-jsonrpc plugin apply', () => { expect(harness.outputErrors.map(error => error.message)).toEqual(['flush callback failed']) const before = harness.frames().length - harness.send({ jsonrpc: '2.0', id: 'after-flush-failure', method: 'initialize', params: { cwd: storageDir, model: 'x' } }) + harness.send({ jsonrpc: '2.0', id: 'after-flush-failure', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'x' } }) await settle() expect(harness.frames().length).toBe(before) } finally { @@ -304,7 +304,7 @@ describe('dsh-jsonrpc plugin apply', () => { // The effect disposer shut the server and closed the transport — later // frames are never read — and the exit seam was never touched. const before = harness.frames().length - harness.send({ jsonrpc: '2.0', id: 'probe-2', method: 'initialize', params: { cwd: storageDir, model: 'x' } }) + harness.send({ jsonrpc: '2.0', id: 'probe-2', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'x' } }) await settle() expect(harness.frames().length).toBe(before) expect(harness.exits()).toEqual([]) diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 1cde550f2e..28d1eda0f8 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -107,6 +107,7 @@ describe('HarnessSdkServer', () => { const init = await server.handleRequest('initialize', { cwd: storageDir, + provider: 'deepseek', model: 'dsagent-model', }) as { serverInfo: { name: string } } expect(init.serverInfo.name).toBe('deepseek-harness-sdk-runtime') @@ -138,7 +139,7 @@ describe('HarnessSdkServer', () => { agentId: AgentId('orphan-agent'), sessionId: SessionId('orphan-session'), meta: { cwd: storageDir }, - agentOptions: { model: 'dsagent-model' }, + agentOptions: { provider: 'deepseek', model: 'dsagent-model' }, }) orphanHandle.agent.send([{ type: 'text', text: 'outside the sdk session map' }]) await orphanHandle.agent.whenIdle() @@ -241,7 +242,7 @@ describe('HarnessSdkServer', () => { try { const server = new HarnessSdkServer(ctx, new FakeTransport()) - await server.initialize({ cwd: storageDir, model: 'plain-model' }) + await server.initialize({ cwd: storageDir, provider: 'deepseek', model: 'plain-model' }) await server.prompt({ sessionId: 'plain', contentBlocks: [{ type: 'text', text: 'hello' }], @@ -266,13 +267,13 @@ describe('HarnessSdkServer', () => { agentId: AgentId('parent-agent'), sessionId: SessionId('main'), meta: { cwd: storageDir }, - agentOptions: { model: 'deepseek' }, + agentOptions: { provider: 'deepseek', model: 'deepseek' }, }) const handle = await ctx.agents.create({ agentId: AgentId('child-agent'), sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, - agentOptions: { model: 'deepseek' }, + agentOptions: { provider: 'deepseek', model: 'deepseek' }, }) await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', @@ -314,19 +315,19 @@ describe('HarnessSdkServer', () => { agentId: AgentId('fallback-parent-agent'), sessionId: SessionId('fallback-parent'), meta: { cwd: storageDir }, - agentOptions: { model: 'deepseek' }, + agentOptions: { provider: 'deepseek', model: 'deepseek' }, }) handle = await ctx.agents.create({ agentId: AgentId('fallback-child-agent'), sessionId: SessionId('fallback-child-session'), meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') }, - agentOptions: { model: 'deepseek' }, + agentOptions: { provider: 'deepseek', model: 'deepseek' }, }) failedHandle = await ctx.agents.create({ agentId: AgentId('failed-child-agent'), sessionId: SessionId('failed-child-session'), meta: { cwd: storageDir }, - agentOptions: { model: 'deepseek' }, + agentOptions: { provider: 'deepseek', model: 'deepseek' }, }) const transport = new FakeTransport() const server = new HarnessSdkServer(ctx, transport) @@ -385,20 +386,20 @@ describe('HarnessSdkServer', () => { } }) - it('does not re-register an LLM adapter that already exists', async () => { + it('does not re-register an LLM adapter whose provider already has an owner', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-existing-llm-')) const ctx = await makeHarness(storageDir) vi.stubEnv('DEEPSEEK_API_KEY', 'test-key') - await ctx.plugin(LlmDeepSeek, { models: ['preinstalled-model'] }) + await ctx.plugin(LlmDeepSeek) try { const server = new HarnessSdkServer(ctx, new FakeTransport()) - const inspect = server as unknown as { hasAdapterFor(model: string): boolean } + const inspect = server as unknown as { hasAdapterFor(provider: string): boolean } - expect(inspect.hasAdapterFor('preinstalled-model')).toBe(true) - expect(inspect.hasAdapterFor('missing-model')).toBe(false) - await server.initialize({ cwd: storageDir, model: 'preinstalled-model' }) + expect(inspect.hasAdapterFor('deepseek')).toBe(true) + expect(inspect.hasAdapterFor('missing-provider')).toBe(false) + await server.initialize({ cwd: storageDir, provider: 'deepseek', model: 'preinstalled-model' }) - expect(ctx.get('llm')?.models().filter(model => model === 'preinstalled-model')).toEqual(['preinstalled-model']) + expect(ctx.get('llm')?.providers().filter(provider => provider === 'deepseek')).toEqual(['deepseek']) await server.shutdown() } finally { await ctx.fiber.dispose() @@ -406,17 +407,18 @@ describe('HarnessSdkServer', () => { } }) - it('registers a missing model when an LLM service already exists', async () => { + it('rejects a missing non-DeepSeek provider when an LLM service already exists', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-new-llm-')) const ctx = await makeHarness(storageDir) vi.stubEnv('DEEPSEEK_API_KEY', 'test-key') - await ctx.plugin(LlmDeepSeek, { models: ['other-model'] }) + await ctx.plugin(LlmDeepSeek) try { const server = new HarnessSdkServer(ctx, new FakeTransport()) - await server.initialize({ cwd: storageDir, model: 'new-model' }) + await expect(server.initialize({ cwd: storageDir, provider: 'private', model: 'new-model' })) + .rejects.toThrow('no adapter registered for provider "private"') - expect(ctx.get('llm')?.models()).toEqual(expect.arrayContaining(['other-model', 'new-model'])) + expect(ctx.get('llm')?.providers()).toEqual(['deepseek']) await server.shutdown() } finally { await ctx.fiber.dispose() @@ -517,15 +519,15 @@ describe('HarnessSdkServer', () => { const ctx = { on: vi.fn(() => () => undefined), agents: { create, get: () => undefined }, - get: () => ({ models: () => ['model'] }), + get: () => ({ providers: () => ['mock'] }), } as unknown as Context const server = new HarnessSdkServer(ctx, new FakeTransport()) as unknown as { - initialize(params: { cwd: string; model: string }): Promise + initialize(params: { cwd: string; provider: string; model: string }): Promise getOrCreateSession(sessionId: string): Promise shutdown(): Promise> } - await server.initialize({ cwd: '.', model: 'model' }) + await server.initialize({ cwd: '.', provider: 'mock', model: 'model' }) await server.getOrCreateSession('relative') expect(create).toHaveBeenCalledWith(expect.objectContaining({ meta: { cwd: process.cwd() } })) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 27f0d20be7..d93690a096 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -11,7 +11,7 @@ A terminal chat always wants the same cluster, so the package owns it rather tha | Plugin | Why it is here | |---|---| | `@cordisjs/plugin-logger-console` | the console logger — stdout is just the terminal here, so logging to it is correct (the ACP app must NOT have this) | -| `@deepseek-ai/dsh-agent-core` | the spine, pre-creating a `main` agent from this app's `model` with `process.cwd()` as the fresh session cwd and carrying its `persona` | +| `@deepseek-ai/dsh-agent-core` | the spine, pre-creating a `main` agent from this app's provider/model pair with `process.cwd()` as the fresh session cwd and carrying its `persona` | | `@deepseek-ai/dsh-session-persistence-jsonl` | durable JSONL session log under `persistenceRoot` | | `@deepseek-ai/dsh-user-interaction` | the human question/answer seam used by confirmation tools | | `@deepseek-ai/dsh-tool-ask-user` | the model-facing `ask_user_question` tool | @@ -25,8 +25,9 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | Key | Default | Routed to | |---|---|---| +| `provider` | (required) | the pre-created `main` agent's registered provider route | | `model` | (required) | the pre-created `main` agent's model | -| `persona` | — | the deployment persona template (may reference `{{model}}`), routed to `dsh-system-prompt` | +| `persona` | — | the deployment persona template (may reference `{{provider}}`/`{{model}}`), routed to `dsh-system-prompt` | | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | | `welcome` | `ready.` | the stdin-chat banner | @@ -50,7 +51,6 @@ Fresh stdio sessions use the process launch directory as `session.header.cwd`, s name: '@deepseek-ai/dsh-llm-deepseek' config: apiKey: !!js process.env.DEEPSEEK_API_KEY - models: [deepseek-v4-flash] - id: bash name: '@deepseek-ai/dsh-bash-local' config: @@ -58,6 +58,7 @@ Fresh stdio sessions use the process launch directory as `session.header.cwd`, s - id: stdio-agent name: '@deepseek-ai/dsh-stdio-agent' config: + provider: deepseek model: deepseek-v4-flash persona: 'You are a coding assistant powered by the {{model}} model.' ``` diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 127851eaf5..05bd9f9fd2 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -9,7 +9,7 @@ * console (stdout is just the terminal) and always pre-creates the `main` agent * the readline UI sends to. The leaf supplies the swappable backends (the LLM * adapter, the bash executor), optional product tools, the optional `hmr` - * dev-reload plugin, and this app's {@link Config} (model, prompt, persistence + * dev-reload plugin, and this app's {@link Config} (provider/model, prompt, persistence * root, welcome banner). * * `hmr` is deliberately a LEAF entry, not baked in here: it is a Loader-only, @@ -54,7 +54,7 @@ export const name = 'stdio-agent' /** * App config: the swappable per-demo values, each routed to where the app wires - * it. `model`/`resumeSessionId` configure the pre-created `main` agent (through + * it. `provider`/`model`/`resumeSessionId` configure the pre-created `main` agent (through * {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list); `persona` is * the deployment persona (forwarded to the system-prompt plugin); `toolOrder` * is the explicit model-facing tool order (forwarded to the system-prompt plugin); @@ -63,6 +63,8 @@ export const name = 'stdio-agent' * `welcome` is the UI banner. */ export interface Config { + /** Provider route for the `main` agent. */ + provider: string /** Model name for the `main` agent (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ @@ -86,6 +88,7 @@ export interface Config { } export const Config: z = z.object({ + provider: z.string().required(), model: z.string().required(), persona: z.string(), // The array default is forced to undefined: ABSENT means "lexicographic @@ -116,6 +119,7 @@ export function apply(ctx: Context, config: Config): void { ...config.tools !== undefined ? { tools: config.tools } : {}, agents: [{ id: AgentId('main'), + provider: config.provider, model: config.model, cwd: process.cwd(), ...config.resumeSessionId !== undefined ? { resumeSessionId: SessionId(config.resumeSessionId) } : {}, diff --git a/packages/ui/stdio-agent/tests/built-bin.e2e.ts b/packages/ui/stdio-agent/tests/built-bin.e2e.ts index 31cdf3eb08..537aebda89 100644 --- a/packages/ui/stdio-agent/tests/built-bin.e2e.ts +++ b/packages/ui/stdio-agent/tests/built-bin.e2e.ts @@ -91,6 +91,7 @@ async function makeConsumer(welcome: string, disabledBrokenEntry = false): Promi '- id: stdio-agent', ' name: \'@deepseek-ai/dsh-stdio-agent\'', ' config:', + ' provider: mock', ' model: mock-echo', ' persona: \'demo\'', ` welcome: '${welcome}'`, diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 0668d25fb0..d7c54642b7 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -75,7 +75,7 @@ async function withIsolatedSkillHomes(run: () => Promise): Promise { describe('dsh-stdio-agent app', () => { it('composes the spine + front-door cluster and pre-creates the main agent', async () => { - const ctx = await mount({ model: 'mock', persona: 'hi', persistenceRoot: '/tmp/dsh-stdio-agent-spec', skills: await isolatedSkillsConfig() }) + const ctx = await mount({ provider: 'mock', model: 'mock', persona: 'hi', persistenceRoot: '/tmp/dsh-stdio-agent-spec', skills: await isolatedSkillsConfig() }) // The spine services (brought up by the agent-core bundle) are all present. expect(ctx.get('agents')).toBeDefined() expect(ctx.get('agentLoop')).toBeDefined() @@ -96,7 +96,7 @@ describe('dsh-stdio-agent app', () => { // schema-bypassing direct-mount caller. const ctx = new Context() // No persona: covers the omitted-persona forwarding branch too. - stdioAgent.apply(ctx, { model: 'mock', skills: await isolatedSkillsConfig() }) + stdioAgent.apply(ctx, { provider: 'mock', model: 'mock', skills: await isolatedSkillsConfig() }) await new Promise(resolve => setTimeout(resolve, 80)) expect(ctx.get('sessionPersistence')).toBeDefined() expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() @@ -106,7 +106,7 @@ describe('dsh-stdio-agent app', () => { it('uses default skill config when apply is called directly without skills', async () => { await withIsolatedSkillHomes(async () => { const ctx = new Context() - stdioAgent.apply(ctx, { model: 'mock' }) + stdioAgent.apply(ctx, { provider: 'mock', model: 'mock' }) await new Promise(resolve => setTimeout(resolve, 80)) expect(ctx.skills).toBeDefined() expect(await ctx.skills.list()).toEqual([]) @@ -119,6 +119,7 @@ describe('dsh-stdio-agent app', () => { // session the resume is contained + logged, so no `main` agent registers — // the branch that maps resumeSessionId through is what this covers. const ctx = await mount({ + provider: 'mock', model: 'mock', persona: 'hi', persistenceRoot: '/tmp/dsh-stdio-agent-spec-resume', @@ -130,7 +131,7 @@ describe('dsh-stdio-agent app', () => { }) it('forwards skill config into agent-core', async () => { - const ctx = await mount({ model: 'mock', persona: 'hi', skills: await isolatedSkillsConfig(6) }) + const ctx = await mount({ provider: 'mock', model: 'mock', persona: 'hi', skills: await isolatedSkillsConfig(6) }) ctx.skills.register({ name: 'stdio-skill', description: 'Stdio skill', source: 'runtime', content: 'body' }) expect(JSON.stringify(await composePrefix(ctx))).toContain('- `stdio-skill`: Std...') await ctx.fiber.dispose() @@ -143,6 +144,7 @@ describe('dsh-stdio-agent app', () => { it('forwards toolOrder through agent-core to the system-prompt assembly', async () => { const ctx = await mount({ + provider: 'mock', model: 'mock', toolOrder: ['zulu', TOOL_ORDER_REST], persistenceRoot: '/tmp/dsh-stdio-agent-spec-tool-order', diff --git a/packages/ui/user-approval/tests/approval.spec.ts b/packages/ui/user-approval/tests/approval.spec.ts index ff0cd5c7d8..ea02e9b182 100644 --- a/packages/ui/user-approval/tests/approval.spec.ts +++ b/packages/ui/user-approval/tests/approval.spec.ts @@ -375,7 +375,7 @@ describe('approval policy (the approval/policy fold)', () => { /** Append a `request/header` snapshot whose system text is exactly `system`. */ function appendHeader(session: Session, system: string): void { - session.append('request/header', { header: { config: { model: 'mock' }, system }, reason: 'initial' }) + session.append('request/header', { header: { config: { provider: 'mock', model: 'mock' }, system }, reason: 'initial' }) } it('folds to the last event, or undefined without one', () => { diff --git a/packages/workflow/tool-workflow/src/index.ts b/packages/workflow/tool-workflow/src/index.ts index 7cd1606b47..a952d83921 100644 --- a/packages/workflow/tool-workflow/src/index.ts +++ b/packages/workflow/tool-workflow/src/index.ts @@ -57,10 +57,10 @@ type ResolvedConfig = Required */ const DESCRIPTION = `Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. -The workflow's identity rides the \`meta\` parameter as JSON: required \`name\` (short kebab-case) and \`description\` strings, optional \`whenToUse\` string and \`phases\` array (\`{title, detail?, model?}\`). The \`script\` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO \`export const meta\` statement — meta is a parameter, not code), running with top-level await; end with \`return \` — the value must be JSON-serializable and is this tool's result. +The workflow's identity rides the \`meta\` parameter as JSON: required \`name\` (short kebab-case) and \`description\` strings, optional \`whenToUse\` string and \`phases\` array (\`{title, detail?, provider?, model?}\`). The \`script\` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO \`export const meta\` statement — meta is a parameter, not code), running with top-level await; end with \`return \` — the value must be JSON-serializable and is this tool's result. Script-body hooks: -- \`agent(prompt, opts?): Promise\` — run one subagent to completion. Without \`opts.schema\` it resolves to the child's final text; with \`opts.schema\` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves \`null\` when the child fails (filter with \`.filter(Boolean)\`). Other opts: \`label\` (display), \`phase\` (progress group), \`model\` (override). Anything else (\`effort\`/\`isolation\`/\`agentType\`) is rejected loudly. +- \`agent(prompt, opts?): Promise\` — run one subagent to completion. Without \`opts.schema\` it resolves to the child's final text; with \`opts.schema\` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves \`null\` when the child fails (filter with \`.filter(Boolean)\`). Other opts: \`label\` (display), \`phase\` (progress group), \`provider\` and \`model\` (paired LLM target overrides). Anything else (\`effort\`/\`isolation\`/\`agentType\`) is rejected loudly. - \`pipeline(items, ...stages): Promise\` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives \`(prev, item, index)\`. An ordinary stage throw drops that ITEM to \`null\` and skips its remaining stages. - \`parallel(thunks): Promise\` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to \`null\`. - \`phase(title)\` — start a progress phase; \`log(message)\` — narrate progress; \`args\` — the tool call's \`args\` input, verbatim. @@ -71,7 +71,12 @@ Constraints: concurrency and total-agent caps apply; no filesystem, network, tim type WorkflowCallArgs = { script: string - meta: { name: string; description: string; whenToUse?: string; phases?: { title: string; detail?: string; model?: string }[] } + meta: { + name: string + description: string + whenToUse?: string + phases?: { title: string; detail?: string; provider?: string; model?: string }[] + } args?: Record } @@ -153,6 +158,7 @@ export function apply(ctx: Context, config: Config): void { properties: { title: { type: 'string', required: true, description: 'The phase title phase() calls match by exact string.' }, detail: { type: 'string', description: 'Optional one-line description of the phase.' }, + provider: { type: 'string', description: 'Optional provider override this phase is expected to use.' }, model: { type: 'string', description: 'Optional model override this phase is expected to use.' }, }, }, diff --git a/packages/workflow/workflow-workerthread/src/host.ts b/packages/workflow/workflow-workerthread/src/host.ts index 9ce754c0c6..fa2f68e307 100644 --- a/packages/workflow/workflow-workerthread/src/host.ts +++ b/packages/workflow/workflow-workerthread/src/host.ts @@ -388,7 +388,14 @@ export class WorkerRun implements WorkflowRun { parent: this.parent, signal: this.controller.signal, ...request.schema !== undefined ? { outputSchema: request.schema } : {}, - ...request.model !== undefined ? { agentOptions: { model: request.model } } : {}, + ...request.provider !== undefined || request.model !== undefined + ? { + agentOptions: { + ...request.provider !== undefined ? { provider: request.provider } : {}, + ...request.model !== undefined ? { model: request.model } : {}, + }, + } + : {}, }) } catch (error: unknown) { const failure = this.childAdmissionFailure() diff --git a/packages/workflow/workflow-workerthread/src/meta.ts b/packages/workflow/workflow-workerthread/src/meta.ts index 848a4fc9b1..e8fe222689 100644 --- a/packages/workflow/workflow-workerthread/src/meta.ts +++ b/packages/workflow/workflow-workerthread/src/meta.ts @@ -40,15 +40,17 @@ function validateMetaShape(meta: unknown): { meta?: WorkflowMeta; violations: st } const entry = phase as Record for (const key of Object.keys(entry)) { - if (!['title', 'detail', 'model'].includes(key)) violations.push(`meta.phases[${index}].${key} is not a recognized field`) + if (!['title', 'detail', 'provider', 'model'].includes(key)) violations.push(`meta.phases[${index}].${key} is not a recognized field`) } if (typeof entry.title !== 'string' || entry.title.length === 0) violations.push(`meta.phases[${index}].title must be a non-empty string`) if (entry.detail !== undefined && typeof entry.detail !== 'string') violations.push(`meta.phases[${index}].detail must be a string`) + if (entry.provider !== undefined && typeof entry.provider !== 'string') violations.push(`meta.phases[${index}].provider must be a string`) if (entry.model !== undefined && typeof entry.model !== 'string') violations.push(`meta.phases[${index}].model must be a string`) if (violations.length === 0) { phases.push({ title: entry.title as string, ...entry.detail !== undefined ? { detail: entry.detail as string } : {}, + ...entry.provider !== undefined ? { provider: entry.provider as string } : {}, ...entry.model !== undefined ? { model: entry.model as string } : {}, }) } diff --git a/packages/workflow/workflow-workerthread/src/runtime.ts b/packages/workflow/workflow-workerthread/src/runtime.ts index 94282cb173..8a66ef7bfd 100644 --- a/packages/workflow/workflow-workerthread/src/runtime.ts +++ b/packages/workflow/workflow-workerthread/src/runtime.ts @@ -61,7 +61,7 @@ export interface ExecutionObserver { } /** The `agent()` options the script may pass; everything else rejects loud. */ -const SUPPORTED_AGENT_OPTIONS = new Set(['label', 'phase', 'schema', 'model']) +const SUPPORTED_AGENT_OPTIONS = new Set(['label', 'phase', 'schema', 'provider', 'model']) /** Deferred Claude Code options we name explicitly in the rejection message. */ const DEFERRED_AGENT_OPTIONS = new Set(['effort', 'isolation', 'agentType']) @@ -302,6 +302,7 @@ export class WorkflowExecution { run = await this.children.startAgent({ prompt: rawPrompt, ...opts.schema !== undefined ? { schema: opts.schema } : {}, + ...opts.provider !== undefined ? { provider: opts.provider } : {}, ...opts.model !== undefined ? { model: opts.model } : {}, }) } catch (error: unknown) { @@ -369,7 +370,13 @@ export class WorkflowExecution { } /** Materialize + validate the `agent()` options bag from the realm. */ - private readAgentOptions(rawOpts: unknown): { label?: string; phase?: string; model?: string; schema?: StructuredOutputSchema } { + private readAgentOptions(rawOpts: unknown): { + label?: string + phase?: string + provider?: string + model?: string + schema?: StructuredOutputSchema + } { if (rawOpts === undefined) return {} let opts: unknown try { @@ -388,9 +395,9 @@ export class WorkflowExecution { if (DEFERRED_AGENT_OPTIONS.has(key)) { throw new WorkflowError(`agent() option "${key}" is deferred and not supported by this engine (supported: label, phase, schema, model)`, 'UNSUPPORTED_OPTION') } - throw new WorkflowError(`agent() option "${key}" is not recognized (supported: label, phase, schema, model)`, 'UNSUPPORTED_OPTION') + throw new WorkflowError(`agent() option "${key}" is not recognized (supported: label, phase, schema, provider, model)`, 'UNSUPPORTED_OPTION') } - for (const key of ['label', 'phase', 'model'] as const) { + for (const key of ['label', 'phase', 'provider', 'model'] as const) { if (record[key] !== undefined && typeof record[key] !== 'string') { throw new WorkflowError(`agent() option "${key}" must be a string`, 'INVALID_ARGUMENT') } @@ -409,6 +416,7 @@ export class WorkflowExecution { return { ...record.label !== undefined ? { label: record.label as string } : {}, ...record.phase !== undefined ? { phase: record.phase as string } : {}, + ...record.provider !== undefined ? { provider: record.provider as string } : {}, ...record.model !== undefined ? { model: record.model as string } : {}, ...schema !== undefined ? { schema } : {}, } diff --git a/packages/workflow/workflow-workerthread/src/types.ts b/packages/workflow/workflow-workerthread/src/types.ts index 2f29dd8137..caf5d33178 100644 --- a/packages/workflow/workflow-workerthread/src/types.ts +++ b/packages/workflow/workflow-workerthread/src/types.ts @@ -46,6 +46,8 @@ export interface ChildStartRequest { prompt: string /** The structured-output schema, if the call passed one (already subset-checked). */ schema?: StructuredOutputSchema + /** The per-child provider override, if the call passed one. */ + provider?: string /** The per-child model override, if the call passed one. */ model?: string } diff --git a/packages/workflow/workflow-workerthread/tests/integration.spec.ts b/packages/workflow/workflow-workerthread/tests/integration.spec.ts index 0e1727f877..a247f4f9e9 100644 --- a/packages/workflow/workflow-workerthread/tests/integration.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/integration.spec.ts @@ -37,7 +37,7 @@ async function setup(script: Script) { await ctx.plugin(spawn, { providerName: 'spawn' }) await ctx.plugin(WorkerWorkflowEngine, {}) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(AgentId('parent'), { provider: 'mock', model: 'mock' }) return { ctx, parent, adapter } } diff --git a/packages/workflow/workflow-workerthread/tests/meta.spec.ts b/packages/workflow/workflow-workerthread/tests/meta.spec.ts index 37b86440be..00505a6435 100644 --- a/packages/workflow/workflow-workerthread/tests/meta.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/meta.spec.ts @@ -33,7 +33,7 @@ describe('validateMeta', () => { description: 'migrate call sites', whenToUse: 'large mechanical sweeps', phases: [ - { title: 'Discover' }, + { title: 'Discover', provider: 'openai' }, { title: 'Transform', detail: 'one agent per file', model: 'deepseek-v4-pro' }, ], }) @@ -42,7 +42,7 @@ describe('validateMeta', () => { description: 'migrate call sites', whenToUse: 'large mechanical sweeps', phases: [ - { title: 'Discover' }, + { title: 'Discover', provider: 'openai' }, { title: 'Transform', detail: 'one agent per file', model: 'deepseek-v4-pro' }, ], }) @@ -73,6 +73,7 @@ describe('validateMeta', () => { expectInvalid({ name: 'x', description: 'd', phases: [{ title: '' }] }, 'meta.phases[0].title must be a non-empty string') expectInvalid({ name: 'x', description: 'd', phases: [{ title: 'Scan', order: 1 }] }, 'meta.phases[0].order is not a recognized field') expectInvalid({ name: 'x', description: 'd', phases: [{ title: 'Scan', detail: 9 }] }, 'meta.phases[0].detail must be a string') + expectInvalid({ name: 'x', description: 'd', phases: [{ title: 'Scan', provider: 9 }] }, 'meta.phases[0].provider must be a string') expectInvalid({ name: 'x', description: 'd', phases: [{ title: 'Scan', model: 9 }] }, 'meta.phases[0].model must be a string') }) diff --git a/packages/workflow/workflow-workerthread/tests/session.spec.ts b/packages/workflow/workflow-workerthread/tests/session.spec.ts index 5fc85ce647..0e5d52bab1 100644 --- a/packages/workflow/workflow-workerthread/tests/session.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/session.spec.ts @@ -35,7 +35,7 @@ interface FakeHost { interface FakeHostOptions { /** Auto-respond to child-start: reply started + settled per child index. Omit a reply to leave the child pending. */ - reply?: (request: { prompt: string; schema?: unknown; model?: string }, index: number) => ChildResult | undefined + reply?: (request: { prompt: string; schema?: unknown; provider?: string; model?: string }, index: number) => ChildResult | undefined /** Reject the start instead (child-start-error) when returning a string. */ refuse?: (index: number) => string | undefined /** Auto-send `go` on `ready` (default true). */ @@ -143,6 +143,17 @@ describe('runWorkerSession over an in-process MessageChannel', () => { host.close() }) + it('agent({provider}) forwards a provider without inventing a model', async () => { + const host = fakeHost({ reply: () => text('ok') }) + void runWorkerSession(host.port, init("return await agent('route me', { provider: 'openai' })")) + const result = await host.result() + expect(result.value).toBe('ok') + const start = host.ofType(WorkerToHostType.ChildStart)[0]! + expect(start.request.provider).toBe('openai') + expect(start.request.model).toBeUndefined() + host.close() + }) + it('a schema child completing WITHOUT a structured value resolves null with a failed outcome', async () => { const host = fakeHost({ reply: () => text('prose, no structure') }) void runWorkerSession(host.port, init("return await agent('p', { schema: { type: 'object' } })")) diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts index 1d6f61432a..d49633636d 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts @@ -35,7 +35,7 @@ async function harness(): Promise { await built.plugin(ToolRegistry) await built.plugin(AgentRegistry) await built.plugin(AgentLoop, { agents: [] }) - await built.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) + await built.plugin(LlmDeepSeek) await built.plugin(SubagentService) await built.plugin(Spawn, { providerName: 'spawn' }) await built.plugin(WorkerWorkflowEngine, { provider: 'spawn' }) @@ -64,7 +64,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('worker workflow engine with-key const parentHandle = await ctx.agents.create({ agentId: AgentId('wf-worker-e2e-parent'), sessionId: 'wf-worker-e2e-session' as never, - agentOptions: { model: 'deepseek-v4-flash' }, + agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' }, }) const events: string[] = [] diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts index 4ad00ee02f..61b00f47e5 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts @@ -236,6 +236,14 @@ describe('dsh-workflow-workerthread', () => { expect(provider.runs[0]!.request.parent).toBeDefined() }) + it('agent({provider}) forwards provider-only agentOptions across the thread', async () => { + const { ctx, parent, provider } = await setup() + const result = await run(ctx, parent, scripted("return await agent('route me', { provider: 'openai' })")) + + expect(result.value).toBe('stub reply') + expect(provider.runs[0]!.request.agentOptions).toEqual({ provider: 'openai' }) + }) + it('a fatal hook error inside the worker kills the script and reports the error', async () => { const { ctx, parent } = await setup() const result = await run(ctx, parent, scripted("return await parallel([() => agent('x', { isolation: 'worktree' })])")) diff --git a/packages/workflow/workflow/src/types.ts b/packages/workflow/workflow/src/types.ts index 981a2da172..108613c559 100644 --- a/packages/workflow/workflow/src/types.ts +++ b/packages/workflow/workflow/src/types.ts @@ -30,6 +30,8 @@ export interface WorkflowPhase { title: string /** Optional one-line description of what the phase does. */ detail?: string + /** Optional provider override this phase is expected to use (informational). */ + provider?: string /** Optional model override this phase is expected to use (informational). */ model?: string } diff --git a/python/sdk-runtime/src/deepseek_harness_runtime/runtime/cordis.yml b/python/sdk-runtime/src/deepseek_harness_runtime/runtime/cordis.yml index 76ae18b20e..f609678fc7 100644 --- a/python/sdk-runtime/src/deepseek_harness_runtime/runtime/cordis.yml +++ b/python/sdk-runtime/src/deepseek_harness_runtime/runtime/cordis.yml @@ -30,9 +30,6 @@ config: apiKey: !!js process.env.DEEPSEEK_API_KEY baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: - - deepseek-v4-flash - - deepseek-v4-pro # JSONL session persistence. $DSH_SESSION_ROOT (set by the SDK whenever # `session_root` is configured) wins; otherwise ./.sessions relative to the diff --git a/python/sdk/README.i18n.yaml b/python/sdk/README.i18n.yaml index a294dc1194..e06c748c59 100644 --- a/python/sdk/README.i18n.yaml +++ b/python/sdk/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -README.md: 60540376c5fd85b0852e204bc8bad3f01c849de5 -README.zh.md: 241c06057889f1aa4add6fc54024fba92bd19429 +README.md: b1189a789963a5e4180cc4ee402c885b0ec82dca +README.zh.md: 721221418eb65f323f521a4fa16cbc355d283f0d diff --git a/python/sdk/README.md b/python/sdk/README.md index 60540376c5..b1189a7899 100644 --- a/python/sdk/README.md +++ b/python/sdk/README.md @@ -25,12 +25,15 @@ By default, the SDK launches the bundled single-file `dsh-jsonrpc-agent` executa from deepseek_harness import DeepSeekHarness with DeepSeekHarness( + provider="deepseek", model="deepseek-v4-flash", cordis="examples/dsbench-coding-agent/cordis.yml", ) as harness: result = harness.run("Make the requested code change.") ``` +`provider` selects a provider route registered by the chosen Cordis composition; `model` is the model id resolved by that adapter. The bundled default composition registers `deepseek`. A custom composition can mount `llm-pi-ai`, configure provider-specific credentials/endpoints there, and select any provider/model present in pi-ai's installed catalog. + `TurnResult.final_response` is the text content from the last `assistant/message` event in the turn. Use `TurnResult.events` for the complete event stream, including intermediate assistant messages and tool activity. diff --git a/python/sdk/README.zh.md b/python/sdk/README.zh.md index 241c060578..721221418e 100644 --- a/python/sdk/README.zh.md +++ b/python/sdk/README.zh.md @@ -21,12 +21,15 @@ with DeepSeekHarness() as harness: from deepseek_harness import DeepSeekHarness with DeepSeekHarness( + provider="deepseek", model="deepseek-v4-flash", cordis="examples/dsbench-coding-agent/cordis.yml", ) as harness: result = harness.run("Make the requested code change.") ``` +`provider` 用于选择当前 Cordis 组合已注册的 provider 路由；`model` 是该适配器解析的模型 ID。内置默认组合注册 `deepseek`。自定义组合可以挂载 `llm-pi-ai`，在其中配置各 provider 的凭据与端点，再选择 pi-ai 已安装目录中的任意 provider/model。 + `TurnResult.final_response` 是本轮次最后一个 `assistant/message` 事件的文本内容。完整的事件流（包括中间的助手消息与工具活动）用 `TurnResult.events` 获取。 同样的行为也可以通过 `DSH_CORDIS_CONFIG` 为运行时子进程选定。注入逻辑位于 `HarnessClient.start()`，因此底层客户端的默认启动也具有此行为：当启动解析到内置运行时，且 `cordis` 与非空的 `DSH_CORDIS_CONFIG` 均未设置时（运行时把空值视为缺省，注入检查与之一致），使用内置的默认配置；显式给出 `runtime_bin` 或 `launch_args_override` 则完全禁用注入。运行时载体（生产用 exe 与仅限开发的 `node` 闭包）及其获取方式见 [sdk-runtime README](../sdk-runtime/README.md)。 diff --git a/python/sdk/src/deepseek_harness/api.py b/python/sdk/src/deepseek_harness/api.py index 3743371cea..2b44a50c64 100644 --- a/python/sdk/src/deepseek_harness/api.py +++ b/python/sdk/src/deepseek_harness/api.py @@ -18,6 +18,7 @@ class DeepSeekHarnessConfig: intentionally override or inject variables for a subprocess. """ + provider: str = "deepseek" model: str = "deepseek-v4-flash" cwd: str | None = None runtime_cwd: str | None = None @@ -97,6 +98,7 @@ class DeepSeekHarness: self._client.start() self._client.initialize( cwd=self._cwd, + provider=self.config.provider, model=self.config.model, ) self._initialized = True diff --git a/python/sdk/src/deepseek_harness/client.py b/python/sdk/src/deepseek_harness/client.py index be457c538a..a7c8c8c7a7 100644 --- a/python/sdk/src/deepseek_harness/client.py +++ b/python/sdk/src/deepseek_harness/client.py @@ -115,10 +115,12 @@ class HarnessClient: self, *, cwd: str, + provider: str, model: str, ) -> InitializeResponse: payload: JsonObject = { "cwd": str(Path(cwd).resolve()), + "provider": provider, "model": model, } try: diff --git a/python/sdk/tests/test_bundled_runtime.py b/python/sdk/tests/test_bundled_runtime.py index a55c6c2c6a..2a04f7b7b1 100644 --- a/python/sdk/tests/test_bundled_runtime.py +++ b/python/sdk/tests/test_bundled_runtime.py @@ -74,7 +74,7 @@ def test_bundled_runtime_boots_a_cordis_config(tmp_path: Path, mode: str) -> Non (tmp_path / "cordis.yml").write_text(_CORDIS_YML) with _client(tmp_path, launch_args) as client: - init = client.initialize(cwd=str(tmp_path), model="deepseek-v4-pro") + init = client.initialize(provider="deepseek", cwd=str(tmp_path), model="deepseek-v4-pro") assert init.serverInfo is not None assert init.serverInfo.name == "deepseek-harness-sdk-runtime" @@ -91,7 +91,7 @@ def test_bundled_runtime_surfaces_unbundled_plugin_failure(tmp_path: Path, mode: client.start() try: with pytest.raises((TransportClosedError, TimeoutError)) as excinfo: - client.initialize(cwd=str(tmp_path), model="deepseek-v4-pro") + client.initialize(provider="deepseek", cwd=str(tmp_path), model="deepseek-v4-pro") finally: client.close() diff --git a/python/sdk/tests/test_client.py b/python/sdk/tests/test_client.py index 327e5f5c39..c09fc594a3 100644 --- a/python/sdk/tests/test_client.py +++ b/python/sdk/tests/test_client.py @@ -330,7 +330,7 @@ for line in sys.stdin: with HarnessClient( HarnessConfig(launch_args_override=(sys.executable, str(script))) ) as client: - init = client.initialize(cwd="/workspace", model="dsagent") + init = client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") assert init.serverInfo.name == "fake-dsh" client.session_prompt("main", [{"type": "text", "text": "fix it"}]) @@ -382,7 +382,7 @@ for line in sys.stdin: raise RuntimeError("bad notification filter") with HarnessClient(HarnessConfig(launch_args_override=(sys.executable, str(script)))) as client: - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") with ( client.subscribe_notifications(broken_filter) as broken, client.subscribe_notifications(lambda notification: notification.method == "tick") as healthy, @@ -419,7 +419,7 @@ for line in sys.stdin: ) with HarnessClient(HarnessConfig(launch_args_override=(sys.executable, str(script)))) as client: - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") with pytest.raises(ValueError): client.session_prompt("main", [{"type": "text", "text": "fix it"}]) @@ -448,7 +448,7 @@ for line in sys.stdin: with HarnessClient( HarnessConfig(launch_args_override=(sys.executable, str(script))) ) as client: - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") request = client.next_request() assert request.id == "bridge-req-1" @@ -482,7 +482,7 @@ for line in sys.stdin: with HarnessClient( HarnessConfig(launch_args_override=(sys.executable, str(script))) ) as client: - init = client.initialize(cwd="/workspace", model="dsagent") + init = client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") assert init.serverInfo.name == "fake-dsh" @@ -504,7 +504,7 @@ time.sleep(60) ) as client: start = time.monotonic() try: - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") except TimeoutError: assert time.monotonic() - start < 2 else: @@ -540,7 +540,7 @@ for line in sys.stdin: client.start() proc = client._proc assert proc is not None - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") start = time.monotonic() client.close() assert time.monotonic() - start < 2 @@ -571,7 +571,7 @@ for line in sys.stdin: assert proc is not None with pytest.raises(Exception, match="bad initialize"): - client.initialize(cwd=".", model="dsagent") + client.initialize(provider="deepseek", cwd=".", model="dsagent") assert proc.wait(timeout=1) is not None assert client._proc is None @@ -611,7 +611,7 @@ for line in sys.stdin: client = HarnessClient(HarnessConfig(launch_args_override=(sys.executable, str(script)))) client.start() - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") client.close() client.close() @@ -634,7 +634,7 @@ sys.exit(42) ) ) as client: with pytest.raises(Exception, match="fatal bridge exploded"): - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") def test_client_serializes_concurrent_writes(tmp_path: Path) -> None: @@ -665,7 +665,7 @@ with open(os.environ["SEEN"], "w") as seen: env={"SEEN": str(output)}, ) ) as client: - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") threads = [ threading.Thread(target=client.notify, args=(f"notice-{index}", {"index": index})) for index in range(50) @@ -738,7 +738,7 @@ def test_client_default_launch_uses_bundled_runtime_and_injects_default_config( monkeypatch.setenv("DSH_CORDIS_CONFIG", ambient_config) with HarnessClient(HarnessConfig(env={"ENV_DUMP": str(env_dump)})) as client: - init = client.initialize(cwd="/workspace", model="deepseek-v4-pro") + init = client.initialize(provider="deepseek", cwd="/workspace", model="deepseek-v4-pro") assert init.serverInfo.name == "bundled-runtime" assert json.loads(env_dump.read_text())["DSH_CORDIS_CONFIG"] == str(default_config) @@ -754,7 +754,7 @@ def test_client_respects_explicit_config_over_bundled_default( with HarnessClient( HarnessConfig(env={"ENV_DUMP": str(env_dump), "DSH_CORDIS_CONFIG": "./explicit.yml"}) ) as client: - client.initialize(cwd="/workspace", model="deepseek-v4-pro") + client.initialize(provider="deepseek", cwd="/workspace", model="deepseek-v4-pro") assert json.loads(env_dump.read_text())["DSH_CORDIS_CONFIG"] == "./explicit.yml" diff --git a/scripts/smoke-python-runtime.py b/scripts/smoke-python-runtime.py index 2c61d07c19..461b828a19 100644 --- a/scripts/smoke-python-runtime.py +++ b/scripts/smoke-python-runtime.py @@ -379,6 +379,7 @@ def smoke_sdk_default(base_url: str) -> None: root = Path(temporary).resolve() sessions = root / "sessions" with DeepSeekHarness( + provider="deepseek", model="smoke-model", cwd=str(root), session_root=str(sessions), @@ -401,6 +402,7 @@ def smoke_sdk_custom(base_url: str, executable: Path) -> None: cordis = root / "cordis.yml" cordis.write_text(CUSTOM_CORDIS) with DeepSeekHarness( + provider="deepseek", model="smoke-model", cwd=str(root), session_root=str(sessions), @@ -432,6 +434,7 @@ def smoke_sdk_snapshot(base_url: str, executable: Path, update_snapshots: bool) cordis = root / "cordis.yml" cordis.write_text(CUSTOM_CORDIS) with DeepSeekHarness( + provider="deepseek", model="smoke-model", cwd=str(root), session_root=str(sessions), @@ -481,7 +484,7 @@ def smoke_direct(base_url: str, executable: Path) -> None: } peer = RuntimePeer([str(executable)], root, environment) try: - peer.send({"jsonrpc": "2.0", "id": "initialize", "method": "initialize", "params": {"cwd": str(root), "model": "smoke-model"}}) + peer.send({"jsonrpc": "2.0", "id": "initialize", "method": "initialize", "params": {"cwd": str(root), "provider": "deepseek", "model": "smoke-model"}}) peer.read_until(lambda message: message.get("id") == "initialize") peer.send({ "jsonrpc": "2.0", diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index a219ea1b1d..c352d2f90c 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -3,6 +3,7 @@ "entries": [ { "doc": "docs/core-data-structures/core.md", "symbol": "Branded", "source": "packages/util/brand/src/index.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "ContentBlockMap", "source": "packages/llm/llm/src/types.ts" }, + { "doc": "docs/core-data-structures/core.md", "symbol": "AssistantProvenance", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "Message", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "MessageSourceMap", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "FinishReasonMap", "source": "packages/llm/llm/src/types.ts" }, From 0107a7a03d659f1c38444f576c8643b752fa9dcd Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Tue, 14 Jul 2026 22:25:59 +0800 Subject: [PATCH 118/359] test(context): adapt time context to provider routing --- packages/context/time-context/tests/fixtures/cordis.yml | 1 + packages/context/time-context/tests/time-context.spec.ts | 7 +++++-- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/packages/context/time-context/tests/fixtures/cordis.yml b/packages/context/time-context/tests/fixtures/cordis.yml index e9558abec6..afd9bc24d4 100644 --- a/packages/context/time-context/tests/fixtures/cordis.yml +++ b/packages/context/time-context/tests/fixtures/cordis.yml @@ -11,6 +11,7 @@ - id: stdio-agent name: '@deepseek-ai/dsh-stdio-agent' config: + provider: mock model: mock-echo persona: 'Test the time-context plugin.' welcome: 'time-context e2e ready.' diff --git a/packages/context/time-context/tests/time-context.spec.ts b/packages/context/time-context/tests/time-context.spec.ts index 562b002b68..b371501e67 100644 --- a/packages/context/time-context/tests/time-context.spec.ts +++ b/packages/context/time-context/tests/time-context.spec.ts @@ -117,6 +117,7 @@ describe('temporal section rendering', () => { const session = new Session(SessionId('offset')) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('assistant/message', { + provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'previous' }], @@ -136,6 +137,7 @@ describe('temporal section rendering', () => { const session = new Session(SessionId('backward-duration')) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('assistant/message', { + provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'future by adjusted clock' }], @@ -152,7 +154,7 @@ describe('temporal section rendering', () => { session.append('user/message', { content: [{ type: 'text', text: 'u' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) }], ['assistant/message', (session: Session): void => { - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, { surfaceOp: 'append' }) }], ['tool/result', (session: Session): void => { session.append('tool/result', { @@ -239,6 +241,7 @@ describe('refresh policy', () => { const first = await sectionText(ctx, agent) vi.setSystemTime(BASE + 1_000) session.append('assistant/message', { + provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'done' }], @@ -330,7 +333,7 @@ describe('real agent-loop request logging', () => { return [{ type: 'text' as const, text: 'advanced' }] }, })) - const agent = ctx.agentLoop.create(AgentId('loop'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('loop'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'start' }]) await agent.whenIdle() From 0998db87d869c423fceba3d3f89d18504babf773 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:18:46 +0800 Subject: [PATCH 119/359] test: align time context with full headers --- packages/context/time-context/tests/time-context.spec.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/context/time-context/tests/time-context.spec.ts b/packages/context/time-context/tests/time-context.spec.ts index 562b002b68..1bb40fa304 100644 --- a/packages/context/time-context/tests/time-context.spec.ts +++ b/packages/context/time-context/tests/time-context.spec.ts @@ -318,7 +318,7 @@ describe('configuration and lifecycle', () => { }) describe('real agent-loop request logging', () => { - it('refreshes a long turn in the system prompt and records the header delta without context history', async () => { + it('refreshes a long turn in the system prompt and records full headers without context history', async () => { const adapter = new ScriptedAdapter([toolCallResponse(), textResponse('done'), textResponse('next turn')]) const ctx = await loopHarness(adapter, { refreshIntervalMs: 60_000 }) ctx.tools.register(defineTool({ @@ -338,7 +338,7 @@ describe('real agent-loop request logging', () => { expect(adapter.requests[0]!.system).toContain('2026-07-14T00:00:00+00:00[UTC]') expect(adapter.requests[1]!.system).toContain('2026-07-14T00:01:01+00:00[UTC]') expect(agent.session.events.some(event => event.type === 'context/message')).toBe(false) - expect(agent.session.events.filter(event => event.type === 'request/header-delta')).toHaveLength(1) + expect(agent.session.events.filter(event => event.type === 'request/header')).toHaveLength(2) expect(foldRequestHeader(agent.session.events)?.system).toBe(adapter.requests[1]!.system) vi.setSystemTime(BASE + 361_000) From 10fd0b4504b47285b67aed611e4cc0a2e86c5db4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:22:37 +0800 Subject: [PATCH 120/359] docs: align unified identity translation --- docs/cookbook/extension-cookbook.i18n.yaml | 4 ++-- docs/cookbook/extension-cookbook.zh.md | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index ef1d8d606f..2761b419e9 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -extension-cookbook.md: 40ee22b352c884d7f295c87726c54ab8e166c844 -extension-cookbook.zh.md: 4e5bc68c973649574bcb2404bea00096eb9ca41f +extension-cookbook.md: 0b95866515efa1b28a95ed48de0fe20d76a62b82 +extension-cookbook.zh.md: 038bf093ce2d289fb59be165a154cbe4df831d9e diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index 4e5bc68c97..038bf093ce 100644 --- a/docs/cookbook/extension-cookbook.zh.md +++ b/docs/cookbook/extension-cookbook.zh.md @@ -40,7 +40,7 @@ UI 插件从 `session/event` 事件流渲染（助手 token 流以 `assistant/ch ```ts import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' declare function render(text: string): void declare function onUserInput(handler: (text: string) => void): void @@ -54,7 +54,7 @@ export function apply(ctx: Context) { render(event.data.chunk.text) } }) - onUserInput(text => ctx.agents.get(AgentId('main'))?.send([{ type: 'text', text }])) + onUserInput(text => ctx.agents.get(SessionId('client-session'))?.send([{ type: 'text', text }])) } ``` From 9745a0d43a979d34c44c2a42d8a485d03a25de71 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:36:04 +0800 Subject: [PATCH 121/359] fix: reject empty configured session ids --- packages/core/agent-loop/src/index.ts | 2 +- packages/core/agent-loop/tests/config-session-id.spec.ts | 9 +++++++++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 8d9a184cc7..325ba7b92d 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -377,7 +377,7 @@ export class AgentLoop extends Service implements AgentFactory { static Config = z.object({ agents: z.array(z.object({ id: z.string().required(), - sessionId: z.string(), + sessionId: z.string().min(1), model: z.string(), cwd: z.string(), resumeSessionId: z.string(), diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 096a6eff9e..bd2a5522df 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -35,6 +35,15 @@ async function makeCoreContext(): Promise { } describe('config-driven session id', () => { + it('rejects an empty exact id before publishing an agent', async () => { + const ctx = await makeCoreContext() + await expect(ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId(''), model: 'mock' }], + })).rejects.toThrow('expected string length >= 1') + expect(ctx.agents.get(SessionId(''))).toBeUndefined() + await ctx.fiber.dispose() + }) + it('accepts one exact fresh id and rejects it alongside a resume id', async () => { const exact = await makeCoreContext() await exact.plugin(AgentLoop, { From ed3654da00fd14597b79e8e97bf61f09c5981ced Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:38:53 +0800 Subject: [PATCH 122/359] docs: reconcile hidden internals with prose standard --- ...t-variables-and-tool-guidance-ownership.md | 16 ++--- .../subagent/subagent-subprocess/src/index.ts | 61 +++++-------------- packages/subagent/tool-subagent/src/index.ts | 49 +++------------ 3 files changed, 31 insertions(+), 95 deletions(-) diff --git a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md index aae4564513..854807c109 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md +++ b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md @@ -24,21 +24,21 @@ The assembled system prompt had four defects, all of one family: facts the harne ### Prompt variables -Plugins contribute named values via `ctx.systemPrompt.variable(name, provider)`; prompt text references them as `{{name}}`. Providers are functions of the `AssembleContext` and may return `undefined` — "no value for THIS assembly". `assemble()` resolves every registered variable into `PromptAssembly.variables` (waterfall listeners can see, add, or override); `renderPrompt` interpolates. Rendering is STRICT — fail loud beats shipping a malformed prompt: a reference to an unregistered name throws (listing what exists; lookup is `Object.hasOwn`, so a prototype property like `{{constructor}}` is unknown, not a function spliced into the prompt), a registered-but-valueless reference throws, a complete `{{…}}` group that is not a well-formed name (`[a-z][a-z0-9_]*`, e.g. `{{ model }}`) throws, and a `{{` that opens no complete group while a `}}` still follows (`{{{model}}}`, `{{a{b}}`) throws. A lone `{{` with no `}}` anywhere after it is ordinary prose and passes through verbatim; substituted values are never re-scanned. Registration rejects duplicate and unreferenceable names, mirroring the tool registry — and `section()` now rejects duplicate section names, making the documented dedup real. +Plugins register `{{name}}` values through `ctx.systemPrompt.variable(name, provider)`. Assembly resolves them into the waterfall-visible variable map. Rendering rejects unknown own-property references, registered providers that return `undefined`, malformed complete references, and unbalanced references that still contain a closing `}}`; a lone unmatched `{{` remains prose, and substituted values are not rescanned. Registration rejects invalid or duplicate variable names, and section names are unique. `dsh-agent-loop` registers the two built-ins, both pure projections of the context agent: `model` (= `options.model`) and `cwd` (= `session.header.cwd`). The example personas write `powered by the {{model}} model` — the model name is stated once, in the `model:` config key. `{{cwd}}` is demonstrated in the ACP example only: every ACP session carries the client's cwd, while config-pre-created stdio agents have none (a persona claiming `{{cwd}}` there fails the turn — by design). The variables stay on the loop plugin (unlike the sections below): they are runtime facts of the agents THIS loop drives, and a replacement loop supplies its own. ### Persona as the order-0 section -`dsh-system-prompt` itself registers the two harness-owned sections (they must survive a swapped loop plugin, so they do NOT live on `dsh-agent-loop`): the static `harness:identity` at order `-100` — every prompt opens by stating the agent is powered by the DeepSeek Harness SDK — and the global default `deployment:persona` at order 0, whose text is the plugin's own `persona` config. `AgentOptions.systemPrompt` and the loop's special-case join are gone: `fullSystemPrompt ≡ renderPrompt(assembly)`, one ordered pipeline for everything the model sees, and `agent/pre-step` (compaction's token-pressure input) measures exactly the real prompt. An agent-scoped section with the same `deployment:persona` name shadows the default for that agent; programmatic setup may register one directly, and the subagent persona feature installs one before publishing an in-process child when the selected provider supports it. Order bands are convention: harness identity `-100`, persona `0`, tool guidance `100–199`; other negative orders also render before the persona. +`dsh-system-prompt` owns `harness:identity` at order `-100` and the configured `deployment:persona` at order 0, so both survive a replacement loop. Prompt rendering has one path, `renderPrompt(assembly)`, and `agent/pre-step` therefore measures the exact prompt used for compaction. An agent-scoped `deployment:persona` shadows the global default and lets subagent providers install a persona before publication. The conventional order bands are identity `-100`, persona `0`, and tool guidance `100–199`. ### Tool guidance ownership -Per-tool semantics and when-to-use live in tool DESCRIPTIONS, which already ship in every request — the YAML prose was ~fully redundant with them. Sections carry only the cross-call habits a single call's description cannot: `dsh-tool-bash` contributes `tool:bash` (order 105) — check the `[exit code: N]` marker on every result; `dsh-tool-fs`'s read section gains the "not shell commands like cat" contrast. `todo_write` and the subagent tools need NO section — their descriptions already carry the whole contract. The leaf personas shrink to identity + behavior (verify your work; keep answers brief), and the welcome banner stops enumerating tools. +Per-tool semantics and selection guidance live in tool descriptions. Prompt sections carry only cross-call habits, such as checking bash exit markers or preferring filesystem tools over shell commands. `todo_write` and subagent tools need no section because their descriptions contain the full contract. Deployment personas contain only role and behavior. ### The subagent conversation-history descriptor -`SubagentProvider` gains `readonly inheritsParentContext: boolean` — a DESCRIPTIVE conversation-history fact beside `capabilities`, not in it (capabilities are start-time validation; nothing validates against this flag). Spawn and ACP declare `false`, fork declares `true`. The name refers only to conversation seeding, not Cordis scope, services, tools, or authority. `dsh-tool-subagent` derives both the tool description and the `prompt` parameter description from the flag: the fork instance now tells the model the child is seeded with the conversation's completed turns (not the in-flight turn) and that its prompt should state only what is new. Deriving the description from a provider that arrives on its own fiber is what forced the provider-lifecycle events and the tool's reactive registration — that mechanism, its Loader-concurrency rationale, and its rejected alternatives are recorded in [the provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md). +`SubagentProvider.inheritsParentContext` describes conversation seeding, not scope, services, tools, or authority. Spawn and ACP set it to `false`; fork sets it to `true`. `dsh-tool-subagent` derives its tool and prompt-parameter descriptions from the flag, including that fork inherits completed turns but not the in-flight turn. Provider lifecycle events keep that wording synchronized with reactive provider registration; their rationale lives in the [provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md). ## Alternatives considered @@ -56,10 +56,10 @@ Per-tool semantics and when-to-use live in tool DESCRIPTIONS, which already ship ## Shipped invariants -- `renderPrompt(await assemble(assembleContextFor(agent)))` for the coding-agent example renders the harness identity, then the persona (with the agent's model name interpolated), then the fs/bash/web guidance sections; the loop has no other prompt-composition path. -- The `subagent_fork` schema description says the child inherits the conversation; the `subagent` one says it does not. The tool follows its provider: absent before the backend activates, present after, gone when the backend unloads, re-worded from the fresh provider on reload. -- Unknown/valueless/malformed/unbalanced `{{…}}` references throw with the section name in the message; duplicate section, variable, and tool-name registrations all throw. -- Snapshot goldens are prompt-independent by construction: llm-replay keys replay on (turn, step) chunk streams and never re-verifies the outgoing request. +- The coding-agent prompt renders identity, persona with the interpolated model, then fs/bash/web guidance through one assembly path. +- Fork and fresh subagent descriptions reflect whether the provider inherits completed conversation turns; the tool appears, disappears, and is reworded with provider lifecycle changes. +- Unknown, valueless, malformed, or unbalanced variable references name the section and throw; duplicate section, variable, and tool registrations also throw. +- Snapshot replay is prompt-independent: it keys recorded chunk streams by turn and step without comparing the outgoing request. ## Consequences diff --git a/packages/subagent/subagent-subprocess/src/index.ts b/packages/subagent/subagent-subprocess/src/index.ts index bd792e7f23..3831d2bb6a 100644 --- a/packages/subagent/subagent-subprocess/src/index.ts +++ b/packages/subagent/subagent-subprocess/src/index.ts @@ -1,19 +1,8 @@ /** - * Shared machinery for OUT-OF-PROCESS subagent backends — providers that spawn - * an external agent as a child process and must keep the parent deployment's - * credentials out of it, tear it down to quiescence, and isolate it from the - * host user's on-disk CLI state. The pieces: credential-shaped env scrubbing - * ({@link buildChildEnv}), spawn-failure capture ({@link spawnFailure}), - * bounded child-exit waits inside the stdin-EOF → SIGTERM → SIGKILL dispose - * ladder ({@link disposeChildProcess}), and the per-run isolated config dir - * ({@link createIsolatedConfigDir}). - * - * This package owns no provider and registers nothing; it is a pure library - * the out-of-process backend packages depend on (the `subagent-inprocess` - * shape, for the process boundary). Every tunable — the ladder's grace - * periods, a pinned config dir — is a PARAMETER here: defaults belong in each - * consuming plugin's Config, per the no-hardcoded-tunables rule. - * + * Shared machinery for OUT-OF-PROCESS subagent backends — providers that spawn an external + * agent as a child process and must keep the parent deployment's credentials out of it, tear + * it down to quiescence, and isolate it from the host user's on-disk CLI state. This package + * registers no provider; consuming plugins own and validate every timing or path default. * @module @deepseek-ai/dsh-subagent-subprocess */ @@ -50,11 +39,8 @@ export function buildChildEnv(extra: Record): NodeJS.ProcessEnv } /** - * Capture the child's spawn-level failure as a promise the run's result path - * can race. A spawn failure (e.g. `ENOENT` for a bad command) is emitted as an - * `error` EVENT, not a thrown exception — and without a listener Node treats - * it as an unhandled error and crashes the parent process. Call this in the - * SAME TICK as `spawn()`, so no window exists for the event to fire unheard. + * Capture the child's spawn-level `error` event as a promise. Call in the same tick as + * `spawn()`; otherwise an early event can be unhandled and crash the parent. * @param child - the just-spawned child process. * @returns a promise that RESOLVES (never rejects) with the child's first * `error` event; for a child that spawns cleanly it never settles. @@ -123,15 +109,8 @@ export interface DisposeLadderGraces { } /** - * Tear a child process down to QUIESCENCE: resolves only once the child has - * actually exited (or was already gone), never merely after requesting it. - * Three-tier escalation — - * - * 1. stdin EOF (when stdin is piped), then wait `disposeEofGraceMs`: a - * cooperative child quiesces on its own, its teardown and flushes intact; - * 2. `SIGTERM`, then wait `disposeGraceMs`; - * 3. `SIGKILL`, then await the (now-certain) exit — a child that ignores EOF - * and traps `SIGTERM` must not wedge dispose forever. + * Tear a child process down to quiescence, resolving only after exit: close stdin and allow + * cooperative flush, then send `SIGTERM`, then `SIGKILL` and await the forced exit. * * @param child - the child process to tear down. * @param graces - the two grace periods, from the consuming plugin's Config. @@ -139,10 +118,7 @@ export interface DisposeLadderGraces { export async function disposeChildProcess(child: ChildProcess, graces: DisposeLadderGraces): Promise { // Already gone: nothing to reap. if (child.exitCode !== null || child.signalCode !== null) return - // 1. Graceful: end the request stream (stdin EOF) and let the child quiesce - // on its own. Sending SIGTERM in the same tick (or too soon) would - // default-terminate a cooperative child mid-flush, orphaning its nested - // work. A child spawned without a stdin pipe skips straight to the wait. + // 1. Close stdin and allow cooperative teardown and durable-state flush. child.stdin?.end() if (await exitsWithin(child, graces.disposeEofGraceMs)) return // 2. SIGTERM, escalating if the child still does not exit within the grace. @@ -171,16 +147,9 @@ export interface IsolatedConfigDir { } /** - * An isolated config dir for one child run, so the child's behavior is a - * function of deployment config alone — never of whatever `~/.claude` / - * `~/.codex`-style state happens to exist on the host machine. Two modes: - * - * - no `pinnedPath` (the default): creates a FRESH private (0700) `mkdtemp` - * dir under the OS temp root; {@link IsolatedConfigDir.remove} deletes it - * best-effort; - * - `pinnedPath` set (a deployment deliberately sharing state across runs): - * the pinned path is returned as-is — never created, never removed — the - * deployment owns that directory's lifecycle. + * An isolated config dir for one child run, independent of host CLI state. Without + * `pinnedPath`, creates a private temp directory and removes it best-effort; a pinned directory + * is returned unchanged and remains deployment-owned. * * @param prefix - the `mkdtemp` name prefix for a fresh dir (e.g. * `dsh-subagent-codex-`); ignored when `pinnedPath` is set. @@ -207,10 +176,8 @@ export async function createIsolatedConfigDir(prefix: string, pinnedPath?: strin try { await rm(path, { recursive: true, force: true }) } catch { - // Best-effort by contract: swallows rm failures (EACCES/EBUSY-style — - // e.g. the dead child left an unreadable entry behind). The dir lives - // under the OS temp root, which reclaims it; failing dispose over - // cleanup would be worse than a leftover temp dir. + // Best-effort by contract: swallows rm failures (EACCES/EBUSY-style — e.g. the dead + // child left an unreadable entry behind). } }, } diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index ff54bc109a..59821147af 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -1,34 +1,11 @@ /** - * The model-facing `subagent` tool: delegate a task to a child agent and return - * its final output. Pure schema + lifecycle shaping — every transport concern - * lives behind the `ctx.subagents` provider registry - * (`@deepseek-ai/dsh-subagent`), so an in-process, ACP, or future A2A backend - * swaps in without touching what the model sees. - * - * Provider selection is config, not model-facing: this plugin is bound to - * EXACTLY ONE provider name (`Config.provider`). To expose more than one - * transport, load the plugin more than once, each bound to a different provider - * — there is no provider/type parameter in the model-facing schema. The model - * sees only `{ description, prompt }`. - * - * The tool DESCRIPTION is derived from the bound provider's conversation-history - * descriptor ({@link SubagentProvider.inheritsParentContext}): a - * fresh-conversation provider (spawn, ACP) gets the standalone-prompt wording, - * while a seeded-conversation provider (fork) tells the model the child already - * sees the conversation's completed turns. This descriptor says nothing about - * Cordis scope, services, tools, or authority. The tool MIRRORS the - * provider's lifecycle via `subagent/provider-added`/`-removed` — it registers - * when the provider is (or becomes) available and unregisters when the - * provider goes away — so no load-order requirement exists and an HMR reload - * of the backend re-derives the wording from the fresh provider. - * - * Collection is SYNCHRONOUS this cut: `execute` starts a run and awaits - * `run.result` inside a `try/finally` that always disposes the run, so the - * owned child agent/session is torn down on every path (success, error, abort) - * and never leaks as a live idle child. A non-`completed` stop reason maps to an - * `isError` tool result (by throwing) rather than returning partial output as - * success. + * Model-facing delegation tool bound by configuration to one provider; transport selection is not + * exposed in its `{ description, prompt }` schema. Provider lifecycle controls registration and + * re-derives conversation-history wording after reload, so load order is irrelevant. * + * Execution synchronously awaits the child result and always disposes the run. Non-completed stop + * reasons become error results, while transport details remain behind `ctx.subagents`. Load this + * plugin more than once to expose multiple configured providers. * @module @deepseek-ai/dsh-tool-subagent */ @@ -105,16 +82,8 @@ export const Config: z = z.object({ model: z.string(), }).default(undefined as unknown as { model: string }), persona: z.string(), - // A schemastery object materializes {} (with [] for nested arrays) when the - // key is omitted — for toolFilter that would mean an EMPTY ALLOW-LIST, i.e. - // deny-everything, silently. Force the omitted key to stay absent (the same - // shape discipline as SystemPrompt's toolOrder); the cast is needed because - // .default() expects the object type. - // The NESTED arrays get the same treatment as the object itself: a partial - // filter ({deny: […]}) must not materialize allow: [] beside it — an empty - // allow-list means deny-EVERYTHING, so the materialized default would turn - // a deny-one config into deny-all. An EXPLICIT allow: [] (grant-only - // children) survives, since only the omitted key defaults to undefined. + // Schemastery otherwise materializes omitted objects and nested arrays as `{ allow: [] }`, which + // silently means deny all. Preserve omission while retaining an explicit empty allow-list. toolFilter: z.object({ allow: z.array(z.string()).default(undefined as unknown as string[]), deny: z.array(z.string()).default(undefined as unknown as string[]), @@ -290,7 +259,7 @@ export function apply(ctx: Context, config: Config): void { if (present !== undefined) { mount(present) } else { - // Not an error: the backend's fiber may simply activate after this one. + // Not an error: the backend's fiber may activate after this one. // The tool appears the moment the provider registers; a typo'd provider // name shows up as this note plus a tool that never materializes. ctx.logger.info(`subagent provider "${config.provider}" not registered yet; the "${config.toolName ?? 'subagent'}" tool will register when it appears`) From d0df50aa8eee0c98b7eacadcdbc797f7780de565 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:43:53 +0800 Subject: [PATCH 123/359] fix: retain LLM HTTP status metadata --- packages/llm/llm-deepseek/src/adapter.ts | 2 +- packages/llm/llm-deepseek/tests/adapter.spec.ts | 7 ++++++- packages/llm/llm/README.md | 2 +- packages/llm/llm/src/index.ts | 6 ++++-- packages/llm/llm/tests/service.spec.ts | 5 ++--- packages/support/llm-replay/src/index.ts | 4 ++-- packages/support/llm-replay/tests/llm-replay.spec.ts | 10 +++++----- 7 files changed, 21 insertions(+), 15 deletions(-) diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index f6051d1ccd..30760a8fbc 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -76,7 +76,7 @@ export class DeepSeekAdapter extends LlmAdapter { // Only swallow error-body parsing: status and code are already captured, // so malformed gateway JSON must not mask the actionable HTTP failure. } - throw new LlmError(message, code) + throw new LlmError(message, code, response.status) } if (!response.body) { throw new LlmError('DeepSeek API returned no response body', 'EMPTY_RESPONSE') diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 1f1aef3f05..46f123a1c7 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -158,7 +158,7 @@ describe('DeepSeekAdapter against a mock server', () => { status, body: JSON.stringify({ error: { message: `failed with ${status}`, type: 't', code: 'c' } }), } - const server = await mockServer([behavior, behavior]) + const server = await mockServer([behavior, behavior, behavior]) const ctx = await harness(server.url) await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })) .rejects.toThrow(`failed with ${status}`) @@ -166,6 +166,11 @@ describe('DeepSeekAdapter against a mock server', () => { assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) .catch((error: unknown) => (error as LlmError).code), ).resolves.toBe(code) + // The numeric HTTP status is carried on the error for explicit handling. + await expect( + assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) + .catch((error: unknown) => (error as LlmError).status), + ).resolves.toBe(status) }) it('keeps the status-line message for JSON error bodies without a message', async () => { diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index c8f2002f9f..296fd0c3d3 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -42,7 +42,7 @@ Every product adapter sends application identity on provider HTTP requests. `att - `LlmAdapter` — abstract base class for provider adapters. The only required method is `stream()`. - `BlockAssembler` — incrementally assembles raw chunks into complete content blocks and an assistant message. The agent loop feeds it raw chunks (logging them for replay) while reading the assembled blocks/message for history. - `HarnessError` — base class for the harness error taxonomy: a stable `code` string (distinct from the human `message`) plus `cause` chaining. Lives here, in the leaf package every other imports, so a single base is shared without a new dependency edge. Per-package errors (`LlmError`, `ToolArgsError`, `InvariantError`, …) extend it. `isHarnessError(value)` narrows at seams. -- `LlmError` — extends `HarnessError`; its stable `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) is the programmatic failure contract. +- `LlmError` — extends `HarnessError`; `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) plus an optional numeric `status` when the failure came from a non-2xx provider response. ### Real adapters diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 8f2c9b4f39..08f3f54c51 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -42,10 +42,12 @@ declare module 'cordis' { /** * Typed error for LLM-related failures. Extends {@link HarnessError}, so the - * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy. + * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy; + * `status` carries the HTTP status when the error originated from a non-2xx + * provider response (absent for protocol/usage errors that have no HTTP status). */ export class LlmError extends HarnessError { - constructor(message: string, code: string, options?: ErrorOptions) { + constructor(message: string, code: string, public status?: number, options?: ErrorOptions) { super(message, code, options) this.name = 'LlmError' } diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index 125a810261..f669069c44 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -79,12 +79,11 @@ describe('LlmService', () => { it('LlmError extends the shared HarnessError base', async () => { const { HarnessError, isHarnessError } = await import('@deepseek-ai/dsh-llm') - const cause = new Error('root cause') - const err = new LlmError('boom', 'AUTH', { cause }) + const err = new LlmError('boom', 'AUTH', 401) expect(err).toBeInstanceOf(HarnessError) expect(isHarnessError(err)).toBe(true) expect(err.code).toBe('AUTH') - expect(err.cause).toBe(cause) + expect(err.status).toBe(401) }) it('HarnessError carries a code, names itself by subclass, and chains cause', async () => { diff --git a/packages/support/llm-replay/src/index.ts b/packages/support/llm-replay/src/index.ts index b7e4e30a46..2e509973e5 100644 --- a/packages/support/llm-replay/src/index.ts +++ b/packages/support/llm-replay/src/index.ts @@ -20,7 +20,7 @@ import { LlmError, assertNever } from '@deepseek-ai/dsh-llm' */ export type ReplayEntry = | { kind: 'chunks'; chunks: StreamChunk[] } - | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string } + | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string; status?: number } | { kind: 'hang' } /** Resolved plugin configuration. */ @@ -221,7 +221,7 @@ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined) if (signal?.aborted) throw new Error('aborted') yield chunk } - throw new LlmError(entry.message, entry.code) + throw new LlmError(entry.message, entry.code, entry.status) case 'hang': // Replay a stream that stalls until cancelled (mirrors MockAdapter): one // chunk, then wait for abort and surface it as the consumer expects. diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index aa3fea20d5..ac52ec11c9 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -175,7 +175,7 @@ describe('loadReplayScript', () => { it('uses the sidecar override when present, ignoring the JSONL', () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') - const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH' }] + const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH', status: 401 }] writeFileSync(overrideFile, JSON.stringify(override), 'utf8') expect(loadReplayScript({ file, overrideFile })).toEqual(override) }) @@ -231,12 +231,12 @@ describe('installLlmReplay (through the real waterfall)', () => { expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(second) }) - it('replays a sidecar throw-entry as an LlmError with its stable code, after its prefix chunks', async () => { + it('replays a sidecar throw-entry as an LlmError with code/status, after its prefix chunks', async () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) @@ -245,7 +245,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const seen: StreamChunk[] = [] await expect((async () => { for await (const c of ctx.llm.stream({ model: 'm', messages: [] })) seen.push(c) - })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH' }) + })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH', status: 401 }) expect(seen).toEqual(partial) }) @@ -350,7 +350,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) From cb177090f9573b30947af31daa876d586bea844a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:53:23 +0800 Subject: [PATCH 124/359] docs: refresh subagent config catalog --- docs/config-catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 093e534d23..d9e42366ba 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -915,7 +915,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) -Source: [`packages/subagent/tool-subagent/src/index.ts:47`](../packages/subagent/tool-subagent/src/index.ts) +Source: [`packages/subagent/tool-subagent/src/index.ts:24`](../packages/subagent/tool-subagent/src/index.ts) ## `@deepseek-ai/dsh-tool-web` From 0892831177c895b4139cb61b9c20a32b465fc923 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 00:01:00 +0800 Subject: [PATCH 125/359] docs: refresh LLM service catalog --- docs/cordis-catalog/services.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index de6bf20fd1..ca83b3c489 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -127,7 +127,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:73`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:75`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` From ff064917a25fe72af8ba109847fa822220cc4330 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 00:18:04 +0800 Subject: [PATCH 126/359] docs: refresh LLM service catalog --- docs/cordis-catalog/services.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index de6bf20fd1..ca83b3c489 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -127,7 +127,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:73`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:75`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` From 310aa9992f365e67561032d9741a4e27f78ace6e Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Wed, 15 Jul 2026 10:07:21 +0800 Subject: [PATCH 127/359] fix: address provider routing review feedback --- docs/tool-catalog.md | 2 +- .../tests/snapshots/advanced-toolchain/session.1.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.2.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.jsonl | 2 +- .../snapshots/advanced-toolchain/system-prompt.golden.md | 2 +- .../acp-agent/tests/snapshots/both-mode-turn/session.jsonl | 2 +- .../tests/snapshots/both-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/code-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/escalation-approved/session.jsonl | 4 ++-- .../tests/snapshots/escalation-rejected/session.jsonl | 4 ++-- .../tests/snapshots/hook-cc-pretool-ask/session.jsonl | 4 ++-- .../tests/snapshots/permission-switching/session.jsonl | 2 +- examples/acp-agent/tests/snapshots/skill-load/session.jsonl | 2 +- examples/acp-agent/tests/snapshots/text-turn/session.jsonl | 2 +- packages/llm/llm/src/assembler.ts | 2 +- packages/workflow/tool-workflow/src/index.ts | 2 +- packages/workflow/workflow-workerthread/src/runtime.ts | 2 +- packages/workflow/workflow-workerthread/tests/session.spec.ts | 2 +- 18 files changed, 21 insertions(+), 21 deletions(-) diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 292b592d93..b3b84ef1fe 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -480,7 +480,7 @@ Run a JavaScript workflow script that orchestrates subagents at scale. Use this The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: -- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. +- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index 0047fe075c..de08513c68 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index e9ac30a033..eae3106743 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl index 7fc796ada5..52e08e5b10 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index 20ba0b3849..3b0e7c08b4 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -96,7 +96,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ + /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ script: string; diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index c98f4a21b1..25ade25a81 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index de153cde4a..a2cdb8f70e 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -81,7 +81,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ + /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ script: string; diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index de153cde4a..a2cdb8f70e 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -81,7 +81,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ + /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ script: string; diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl index 4087857323..da999eb947 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl @@ -131,8 +131,8 @@ {"type":"assistant/chunk","seq":129,"time":1783962245385,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":130,"time":1783962245385,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a command with sandbox_permissions set to danger-full-access, no prior run needed, justified as instructed."},{"type":"tool-call","id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1501,"outputTokens":174,"cacheReadTokens":0,"reasoningTokens":28}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} {"type":"tool/call","seq":131,"time":1783962245385,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} -{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"ed807292-6499-4c75-adc4-a344e6fda38b","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} -{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"ed807292-6499-4c75-adc4-a344e6fda38b","outcome":"allowed-once"}} +{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"5d298f92-ced6-4fa0-ae01-cd0660b29f58","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"5d298f92-ced6-4fa0-ae01-cd0660b29f58","outcome":"allowed-once"}} {"type":"tool/result","seq":134,"time":1783962245399,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[131],"surfaceOp":"append"} {"type":"step/end","seq":135,"time":1783962245400,"data":{"turn":1,"step":1}} {"type":"step/start","seq":136,"time":1783962245400,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl index e2efeee9e9..657127b8f1 100644 --- a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl @@ -155,8 +155,8 @@ {"type":"assistant/chunk","seq":153,"time":1783962246274,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":154,"time":1783962246274,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command with `sandbox_permissions` set to `danger-full-access` and a specific justification. They explicitly said NOT to run it without sandbox_permissions first. Let me do exactly that."},{"type":"tool-call","id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1509,"outputTokens":198,"cacheReadTokens":0,"reasoningTokens":48}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153],"surfaceOp":"append"} {"type":"tool/call","seq":155,"time":1783962246274,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} -{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"0014f39a-22b4-4089-b90b-f42b1619e9b8","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} -{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"0014f39a-22b4-4089-b90b-f42b1619e9b8","outcome":"rejected"}} +{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"12cac992-89a6-4bbe-9d33-3254f4f13c7a","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"12cac992-89a6-4bbe-9d33-3254f4f13c7a","outcome":"rejected"}} {"type":"tool/result","seq":158,"time":1783962246275,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"danger-full-access\""}],"isError":true},"sourceEventSeqs":[155],"surfaceOp":"append"} {"type":"step/end","seq":159,"time":1783962246276,"data":{"turn":1,"step":1}} {"type":"step/start","seq":160,"time":1783962246276,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl index 654965f86a..6264b68db9 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl @@ -55,8 +55,8 @@ {"type":"tool/call","seq":53,"time":1783352172557,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}} {"type":"hook/invoked","seq":54,"time":1783352172558,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":55,"time":1783352172573,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"ask","exitCode":0,"durationMs":14.113374999999905}} -{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"efe463b8-0601-4607-a431-8eecfeb1b5f0","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} -{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"efe463b8-0601-4607-a431-8eecfeb1b5f0","outcome":"rejected"}} +{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"5ab08815-cec4-4615-88d4-2d5b519762e8","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} +{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"5ab08815-cec4-4615-88d4-2d5b519762e8","outcome":"rejected"}} {"type":"tool/result","seq":58,"time":1783962235814,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","content":[{"type":"text","text":"Error: the user rejected tool \"bash\""}],"isError":true},"sourceEventSeqs":[53],"surfaceOp":"append"} {"type":"step/end","seq":59,"time":1783962235814,"data":{"turn":1,"step":1}} {"type":"step/start","seq":60,"time":1783962235814,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl index c1cdc1d5d9..c77300fe90 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl @@ -5,7 +5,7 @@ {"type":"approval/policy","seq":3,"time":1783962244578,"data":{"policy":"ask"}} {"type":"user/message","seq":4,"time":1783962244578,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly this one command in a single call: printf 'before\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783962244579,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":7,"time":1783860667444,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":8,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":9,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 979124a654..0cbc14dedd 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index 3981137f14..69b9fccfc7 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/packages/llm/llm/src/assembler.ts b/packages/llm/llm/src/assembler.ts index 68fc2c67b4..8780718c7a 100644 --- a/packages/llm/llm/src/assembler.ts +++ b/packages/llm/llm/src/assembler.ts @@ -36,7 +36,7 @@ export class BlockAssembler { private order: number[] = [] private _usage: TokenUsage | undefined private _finish: FinishReason | undefined - private _replayState: unknown + private _replayState: unknown = undefined /** * Feed one chunk. Returns the completed block when the chunk closes one diff --git a/packages/workflow/tool-workflow/src/index.ts b/packages/workflow/tool-workflow/src/index.ts index 011e45f025..2a8ef96682 100644 --- a/packages/workflow/tool-workflow/src/index.ts +++ b/packages/workflow/tool-workflow/src/index.ts @@ -47,7 +47,7 @@ const DESCRIPTION = `Run a JavaScript workflow script that orchestrates subagent The workflow's identity rides the \`meta\` parameter as JSON: required \`name\` (short kebab-case) and \`description\` strings, optional \`whenToUse\` string and \`phases\` array (\`{title, detail?, provider?, model?}\`). The \`script\` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO \`export const meta\` statement — meta is a parameter, not code), running with top-level await; end with \`return \` — the value must be JSON-serializable and is this tool's result. Script-body hooks: -- \`agent(prompt, opts?): Promise\` — run one subagent to completion. Without \`opts.schema\` it resolves to the child's final text; with \`opts.schema\` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves \`null\` when the child fails (filter with \`.filter(Boolean)\`). Other opts: \`label\` (display), \`phase\` (progress group), \`provider\` and \`model\` (paired LLM target overrides). Anything else (\`effort\`/\`isolation\`/\`agentType\`) is rejected loudly. +- \`agent(prompt, opts?): Promise\` — run one subagent to completion. Without \`opts.schema\` it resolves to the child's final text; with \`opts.schema\` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves \`null\` when the child fails (filter with \`.filter(Boolean)\`). Other opts: \`label\` (display), \`phase\` (progress group), and independent \`provider\`/\`model\` LLM target overrides (either may be provided alone). Anything else (\`effort\`/\`isolation\`/\`agentType\`) is rejected loudly. - \`pipeline(items, ...stages): Promise\` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives \`(prev, item, index)\`. An ordinary stage throw drops that ITEM to \`null\` and skips its remaining stages. - \`parallel(thunks): Promise\` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to \`null\`. - \`phase(title)\` — start a progress phase; \`log(message)\` — narrate progress; \`args\` — the tool call's \`args\` input, verbatim. diff --git a/packages/workflow/workflow-workerthread/src/runtime.ts b/packages/workflow/workflow-workerthread/src/runtime.ts index 15caf4203a..b5dbed1744 100644 --- a/packages/workflow/workflow-workerthread/src/runtime.ts +++ b/packages/workflow/workflow-workerthread/src/runtime.ts @@ -368,7 +368,7 @@ export class WorkflowExecution { for (const key of Object.keys(record)) { if (SUPPORTED_AGENT_OPTIONS.has(key)) continue if (DEFERRED_AGENT_OPTIONS.has(key)) { - throw new WorkflowError(`agent() option "${key}" is deferred and not supported by this engine (supported: label, phase, schema, model)`, 'UNSUPPORTED_OPTION') + throw new WorkflowError(`agent() option "${key}" is deferred and not supported by this engine (supported: label, phase, schema, provider, model)`, 'UNSUPPORTED_OPTION') } throw new WorkflowError(`agent() option "${key}" is not recognized (supported: label, phase, schema, provider, model)`, 'UNSUPPORTED_OPTION') } diff --git a/packages/workflow/workflow-workerthread/tests/session.spec.ts b/packages/workflow/workflow-workerthread/tests/session.spec.ts index 9bca53f26a..102bcbd9a0 100644 --- a/packages/workflow/workflow-workerthread/tests/session.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/session.spec.ts @@ -341,7 +341,7 @@ describe('runWorkerSession over an in-process MessageChannel', () => { ["return await agent('p', { label: 3 })", '"label" must be a string'], ["return await agent('p', { get label() { throw new Error('read failed') } })", 'options must be plain JSON data'], ["return await agent('p', { bogus: true })", '"bogus" is not recognized'], - ["return await agent('p', { effort: 'high' })", '"effort" is deferred'], + ["return await agent('p', { effort: 'high' })", '"effort" is deferred and not supported by this engine (supported: label, phase, schema, provider, model)'], ["return await agent('p', { schema: { type: 'object', oneOf: [] } })", 'outside the supported subset'], ['return await parallel([() => 1, () => 2, () => 3])', 'over the per-call cap (2)'], ['return await pipeline([1, 2, 3], (x) => x)', 'maxItemsPerCall'], From 4ce32807e1b4faba5947e903b4be041dfbccc648 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 11:12:05 +0800 Subject: [PATCH 128/359] Fix async injection tool-result ordering --- docs/architecture.md | 2 +- docs/cordis-catalog/events.md | 26 +++++------ docs/event-producer-consumer.md | 26 +++++------ .../2026-06-15-turn-enclosure-invariant.md | 2 +- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/agent.ts | 43 +++++++++++++------ packages/core/agent-loop/src/loop.ts | 6 +++ packages/core/agent-loop/tests/loop.spec.ts | 41 ++++++++++++++---- packages/core/agent/README.md | 2 +- packages/core/agent/src/types.ts | 9 ++-- 10 files changed, 104 insertions(+), 55 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index b17c3302d8..79f9819ab4 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -96,7 +96,7 @@ forever: The loop renders one prompt assembly per step. Plugins contribute ordered sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn instead of shipping a hole. `dsh-system-prompt` owns the harness identity and default deployment persona; an agent-scoped persona may shadow the default. The loop supplies `model` and `cwd`. See the [prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md). -Post-tool context lands after all tool results so tool-call/result adjacency stays stable. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved. +Context that arrives while tool results are pending—including asynchronous `agent.inject()` notices and post-tool `additionalContext`—lands after the complete result batch so tool-call/result adjacency stays stable. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved. ### Failure Boundaries diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 4af431f8c0..6a18fbd359 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -23,7 +23,7 @@ A fully configured agent and live session were published. Setup is composition-o Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:139`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:140`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -35,7 +35,7 @@ An agent left the registry; AgentLoop emits this after driver quiescence but bef Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:148`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:149`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:283`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:284`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -59,7 +59,7 @@ Awaited serial checkpoint for session-surface mutation after prompt assembly and Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:202`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:203`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -71,7 +71,7 @@ Allow, rewrite, or block one drained prompt before it becomes a user message. Ca Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:212`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:213`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -83,7 +83,7 @@ Detached, frozen content entered the agent's inbox. Source defaults have already Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:167`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:168`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -95,7 +95,7 @@ Replace the frozen call configuration. Model-visible content must use logged cha Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:224`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:225`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -107,7 +107,7 @@ Compose request-only messages placed before derived history. The frozen result i Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:239`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:240`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -119,7 +119,7 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:180`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:181`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -131,7 +131,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does no Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:157`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:158`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -143,7 +143,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:250`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:251`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -155,7 +155,7 @@ Override whether the turn continues. The default continues after tool calls or s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:260`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:261`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -167,7 +167,7 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:270`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:271`](../../packages/core/agent/src/types.ts) ## `approval/*` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index bdf1c6e320..e08ab61b81 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,19 +7,19 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:139`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:148`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:283`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:202`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:212`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:167`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:224`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:239`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:180`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:157`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:250`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:260`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:270`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:140`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:149`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:284`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:203`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:213`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:168`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:225`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:240`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:181`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:158`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:251`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:261`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:271`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:59`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:68`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | diff --git a/docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md b/docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md index e55cd0853e..5ffdedba18 100644 --- a/docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md +++ b/docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md @@ -18,7 +18,7 @@ In case 2, if the injected `context/message` is the last event before a flush/di **Every session event lives inside a turn** — between a `turn/start` and its matching `turn/end`. Concretely: - The loop appends queued `user/message` events **after** `turn/start` (inside the turn), not before it. `turn/end` is therefore owed the moment those messages are recorded, and the existing finalizer guarantees it. -- An `agent.inject()` made while the agent is **running** appends its `context/message` into the already-open turn (unchanged). +- An `agent.inject()` made while the agent is **running** joins the already-open turn. If assistant tool calls are awaiting results, the accepted context waits in arrival order and appends after the complete result batch so its user-role message cannot split provider tool pairing. - An `agent.inject()` made while **idle** wraps its `context/message` in a one-shot turn: `turn/start{trigger:{kind:'injection'}}` → `context/message` → `turn/end{completed}`. A new `injection` variant joins the merge-extensible `TurnTriggerMap`. - The loop derives the next turn number from the log each iteration (`lastTurnNumber(session) + 1`) instead of keeping a private counter, so an idle injection's one-shot turn cannot collide with the next real turn's number. - The `dsh-invariants` plugin **enforces** the invariant in dev: a `user/message` / `context/message` / `steering/message` appended while no turn is open throws an `InvariantError`. diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 91ed9d5049..3eb1d0b8f6 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -44,7 +44,7 @@ Configured agents start automatically. `cwd` applies only to fresh sessions; `re - `ReactLoopAgent` — the concrete `Agent` implementation. Its inbox is a JavaScript native-private field, and one prepared session can be claimed by only one concrete driver. Everything observable happens through session events and the `agent/*` event taxonomy. -`Inbox`, `runLoop`, and the instance-bound publication/start controls are package-internal. The package root does not export them, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than constructing or starting the driver internals. `ReactLoopAgent.send()` and running `steer()` materialize content plus resolved source once as detached, deeply frozen lossless JSON, then share that accepted record between `agent/queued` and the inbox; malformed data throws before either boundary. +`Inbox`, `runLoop`, and the instance-bound publication/start controls are package-internal. The package root does not export them, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than constructing or starting the driver internals. `ReactLoopAgent.send()`, running `steer()`, and open-turn `inject()` materialize content plus resolved source once as detached, deeply frozen lossless JSON; malformed data throws before enqueue or append. An injection that arrives while assistant tool calls await results stays in a FIFO until the complete result batch is logged, keeping provider tool messages contiguous. ### Loop lifecycle (`loop.ts`) diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index a2288c65b7..c45cddda84 100644 --- a/packages/core/agent-loop/src/agent.ts +++ b/packages/core/agent-loop/src/agent.ts @@ -12,7 +12,7 @@ import type { AgentId, AgentOptions, AgentStatus, SendOptions } from '@deepseek- import type { Agent } from '@deepseek-ai/dsh-agent' import { deepFreeze } from '@deepseek-ai/dsh-llm' import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm' -import { snapshotJsonValue, type Session } from '@deepseek-ai/dsh-session' +import { isToolPairingBalanced, snapshotJsonValue, type Session } from '@deepseek-ai/dsh-session' import { Inbox, type InboxMessage } from './inbox.ts' import { isTurnOpen, lastTurnNumber, runLoop } from './loop.ts' @@ -149,6 +149,8 @@ export class ReactLoopAgent implements Agent { * this set before the lifecycle unregisters the agent or detaches its session. */ private pendingIdleFlushes = new Set>() + /** Open-turn injections waiting for the active assistant tool-call batch to close. */ + private deferredInjections: InboxMessage[] = [] constructor( private loopCtx: Context, @@ -189,12 +191,11 @@ export class ReactLoopAgent implements Agent { } /** - * Accept one public send/steer payload as the exact detached record shared by - * the live notification and inbox. Lossless-JSON materialization reads every - * nested field once; deep freeze prevents an observer from rewriting queued - * work before the loop drains it. + * Accept one public message payload as a detached record. Lossless-JSON + * materialization reads every nested field once; deep freeze prevents later + * caller mutation before an inbox or deferred-injection queue drains it. */ - private acceptInboxMessage(content: ContentBlock[], options?: SendOptions): InboxMessage { + private acceptMessage(content: ContentBlock[], options?: SendOptions): InboxMessage { const source = this.resolveSource(options) const accepted = snapshotJsonValue({ content, source }) if (accepted === undefined) { @@ -210,7 +211,7 @@ export class ReactLoopAgent implements Agent { send(content: ContentBlock[], options?: SendOptions): void { this.assertNotDisposed() - const accepted = this.acceptInboxMessage(content, options) + const accepted = this.acceptMessage(content, options) this.#inbox.enqueue(accepted) const info = { source: accepted.source, steering: false } as const agentEvents(this.loopCtx, this).emit('agent/queued', accepted.content, info) @@ -219,7 +220,7 @@ export class ReactLoopAgent implements Agent { steer(content: ContentBlock[], options?: SendOptions): void { this.assertNotDisposed() if (this._status !== 'running') { this.send(content, options); return } - const accepted = this.acceptInboxMessage(content, options) + const accepted = this.acceptMessage(content, options) this.#inbox.steer(accepted) const info = { source: accepted.source, steering: true } as const agentEvents(this.loopCtx, this).emit('agent/queued', accepted.content, info) @@ -227,14 +228,21 @@ export class ReactLoopAgent implements Agent { inject(content: ContentBlock[], options?: SendOptions): void { this.assertNotDisposed() - const source = this.resolveSource(options) if (isTurnOpen(this.session)) { - // A turn is open in the LOG (decided from the log, not agent status — - // status can be `running` with no turn open): the context/message is - // turn-enclosed by that turn, so append it directly. - this.session.append('context/message', { content, source }, { surfaceOp: 'append' }) + const accepted = this.acceptMessage(content, options) + // Provider protocols require every assistant tool-call batch to be + // followed only by its tool results. Queue arbitrary asynchronous context + // until the tail cut is balanced; an existing queue preserves FIFO in the + // narrow window after the last result and before the loop drains it. + if (this.deferredInjections.length > 0 + || !isToolPairingBalanced(this.session.surface.nodes, this.session.events, null)) { + this.deferredInjections.push(accepted) + return + } + this.session.append('context/message', accepted, { surfaceOp: 'append' }) return } + const source = this.resolveSource(options) // No turn open: wrap the injection in a one-shot turn so every event stays // turn-enclosed (the durability/replay boundary is the turn). const turn = lastTurnNumber(this.session) + 1 @@ -272,6 +280,14 @@ export class ReactLoopAgent implements Agent { } } + /** Append deferred open-turn injections after the loop closes a tool-result batch. */ + private drainDeferredInjections(): void { + const pending = this.deferredInjections.splice(0) + for (const accepted of pending) { + this.session.append('context/message', accepted, { surfaceOp: 'append' }) + } + } + cancel(reason?: string): void { // Arm only for current work; an idle marker would cancel the next prompt. if (this._status === 'running' || this.currentAbort !== undefined || this.#inbox.hasQueued || this.#inbox.hasSteering) { @@ -336,6 +352,7 @@ export class ReactLoopAgent implements Agent { isCancelled: () => this.cancelRequested, cancelReason: () => this.cancelReason, clearCancel: () => { this.cancelRequested = false }, + drainDeferredInjections: () => { this.drainDeferredInjections() }, // Pre-step cancellation re-parks without emitting a status transition. settleIdle: () => { this.settleIdleWaiters() }, }) diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 18eca40cc1..965b2353c2 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -85,6 +85,8 @@ export interface LoopHandle { clearCancel(): void /** Settle idle waiters when pre-running cancellation skips a turn, without emitting `agent/status`. */ settleIdle(): void + /** Append context that arrived while an assistant tool-call batch was awaiting its results. */ + readonly drainDeferredInjections: () => void } /** @@ -349,6 +351,10 @@ async function runTurn( break } + // A successful tool step has committed its complete result batch. Context + // accepted while that batch was pending can now join the open turn. + if (stepOutcome.hadToolCalls) handle.drainDeferredInjections() + // Preserve max-token completion unless a later disposal, abort, or error wins. const stepReason = stepFinishReason(stepOutcome.finish) if (stepReason) reason = stepReason diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index fb686928b1..851a4e63b9 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -383,22 +383,25 @@ describe('agent loop', () => { expect(flat).toContain('') }) - it('inject() while running appends into the open turn (no extra synthetic turn)', async () => { + it('defers inject() during tool execution until after the tool result', async () => { const adapter = new MockAdapter([ toolCallResponse('c1', 'noticer', {}, 'calling'), textResponse('done'), ]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - // A tool that injects mid-execution: at this point the agent is running, so - // inject must append the context/message into the ALREADY-open turn rather - // than wrap it in its own one-shot turn. + let visibleDuringTool = false ctx.tools.register(defineTool({ name: 'noticer', description: 'injects a notice', parameters: {}, async execute() { - agent.inject([{ type: 'text', text: 'mid-turn notice' }], { source: { kind: 'plugin', plugin: 'x' } }) + await Promise.resolve() + const first = { type: 'text' as const, text: 'mid-turn notice' } + agent.inject([first], { source: { kind: 'plugin', plugin: 'x' } }) + first.text = 'mutated after inject' + agent.inject([{ type: 'text', text: 'second notice' }], { source: { kind: 'plugin', plugin: 'x' } }) + visibleDuringTool = agent.session.events.some(e => e.type === 'context/message') return [{ type: 'text', text: 'ok' }] }, })) @@ -406,13 +409,35 @@ describe('agent loop', () => { send(agent, 'go') await waitForIdle(ctx, agent) - // Exactly ONE turn ran (no synthetic injection turn), and the mid-turn - // context/message sits inside it. + expect(visibleDuringTool).toBe(false) + + // The injection stays in the open turn, but its user-role context cannot + // split the assistant tool call from the provider's tool-result message. const turnStarts = agent.session.events.filter(e => e.type === 'turn/start') expect(turnStarts).toHaveLength(1) const ts0 = turnStarts[0]! expect(ts0.type === 'turn/start' && ts0.data.trigger.kind).toBe('message') - expect(agent.session.events.some(e => e.type === 'context/message')).toBe(true) + const result = agent.session.events.find(e => e.type === 'tool/result')! + const contexts = agent.session.events.filter(e => e.type === 'context/message') + expect(contexts).toHaveLength(2) + expect(result.seq).toBeLessThan(contexts[0]!.seq) + expect(contexts.flatMap(event => event.type === 'context/message' ? event.data.content : [])) + .toEqual([ + { type: 'text', text: 'mid-turn notice' }, + { type: 'text', text: 'second notice' }, + ]) + + const secondRequest = adapter.requests[1]!.messages + const resultIndex = secondRequest.findIndex(message => + message.content.some(block => block.type === 'tool-result')) + const contextIndexes = secondRequest.flatMap((message, index) => + message.content.some(block => block.type === 'text' + && (block.text.includes('mid-turn notice') || block.text.includes('second notice'))) + ? [index] + : []) + expect(resultIndex).toBeGreaterThanOrEqual(0) + expect(contextIndexes).toHaveLength(2) + expect(contextIndexes.every(index => index > resultIndex)).toBe(true) }) it('agent/turn-continuation can force-continue (/loop pattern) and force-stop', async () => { diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 5639f30daf..ed42741cc1 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -41,7 +41,7 @@ The handle every plugin programs against: - `agent.send(content, options?)` — queue a message; starts a turn when idle. Content and resolved source become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input (`agent/prompt-submit` still rewrites by returning replacement content). - `agent.steer(content, options?)` — steer a running turn (inject between steps); uses the same owned acceptance boundary and behaves like `send` when idle -- `agent.inject(content, options?)` — inject in-session context (context/message event); the next request sees it. Does not run the model. While a turn is open it joins that turn; while idle it is wrapped in a one-shot `injection` turn so every event stays turn-enclosed ([the turn-enclosure invariant](../../../docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)) +- `agent.inject(content, options?)` — accept detached in-session context without running the model; the next request sees its `context/message`. While a turn is open it joins that turn, deferring FIFO behind any pending tool-result batch so provider pairing remains contiguous; while idle it is wrapped in a one-shot `injection` turn and durability checkpoint ([the turn-enclosure invariant](../../../docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)). - `agent.cancel(reason?)` — cancel ALL pending work: clears the queued + steering FIFOs, aborts the in-flight step, and drops a turn about to start (the pre-step window) so a queued-but-not-started prompt never runs. A UI/ACP `session/cancel` maps to this. The single public stop primitive. Idle with nothing pending → a safe no-op. - `agent.whenIdle()` — resolve once the agent reaches quiescence after settling out of `running` (idle → immediately; disposed → awaits the loop exit). A non-owner's quiescence-observation hook: it observes the work settling WITHOUT tearing the agent down. Teardown is separate — a lifecycle owner stops and unregisters via `AgentHandle.dispose()`, which awaits the loop exit directly. - `agent.session`, `agent.status`, `agent.options`, `agent.id` diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index 3aad65a70e..efe66693bf 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -103,10 +103,11 @@ export interface Agent { steer(content: ContentBlock[], options?: SendOptions): void /** - * Append model-facing context without running the model. Idle injection uses - * a one-shot turn and durability checkpoint, while injection during an open - * turn joins it at the current log position. Disposal awaits idle checkpoints; - * flush failures are reported through `agent/error`, not thrown to the caller. + * Append detached model-facing context without running the model. An open-turn + * injection joins at the current log position unless tool results are pending, + * in which case it waits FIFO until the complete result batch is logged. Idle + * injection uses a one-shot turn and durability checkpoint. Disposal awaits + * idle checkpoints; flush failures report through `agent/error`. */ inject(content: ContentBlock[], options?: SendOptions): void From 1222d07da965b40be77861c8455c0efc09129eeb Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 11:43:58 +0800 Subject: [PATCH 129/359] Document host sandbox retry behavior --- AGENTS.md | 4 ++++ scripts/doc-budgets.manifest.json | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/AGENTS.md b/AGENTS.md index 22c1f47aa8..d4bfca2dab 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -58,6 +58,10 @@ pnpm run demo:cordis # self-referential demo: the agent modifies its own runt pnpm run demo:acp # ACP server agent (needs DEEPSEEK_API_KEY) ``` +### Host sandbox failures + +When required `gh`, `pnpm`, build, test, or generator commands fail because the agent sandbox blocks credentials, network, IPC, file watching, or nested `sandbox-exec`, retry unchanged with the narrowest host escalation before diagnosing authentication or project failure. Require sandbox evidence; never bypass genuine test failures or the product sandbox under test. + ### Run the CI gates locally before marking a PR ready Run narrow checks during implementation and this CI-equivalent sequence before marking a PR ready. Fresh worktrees need `pnpm run build` before publint and NodeNext inspect `lib/`: diff --git a/scripts/doc-budgets.manifest.json b/scripts/doc-budgets.manifest.json index 80957af255..87993729ba 100644 --- a/scripts/doc-budgets.manifest.json +++ b/scripts/doc-budgets.manifest.json @@ -1,5 +1,5 @@ { - "AGENTS.md": 1370, + "AGENTS.md": 1500, "docs/AGENTS.md": 1100, "docs/architecture.md": 1790, "docs/cordis-primer.md": 600, From 28144077f3da1a43cbb31639ef4a488ec5cca68e Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 12:22:39 +0800 Subject: [PATCH 130/359] Fix deferred injection lifecycle --- docs/architecture.md | 2 +- .../2026-06-15-turn-enclosure-invariant.md | 2 +- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/agent.ts | 25 ++-- packages/core/agent-loop/src/loop.ts | 98 ++++++++-------- .../tests/contract-regressions.spec.ts | 109 ++++++++++++++++++ packages/core/agent/README.md | 2 +- packages/core/agent/src/types.ts | 8 +- 8 files changed, 184 insertions(+), 64 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index 79f9819ab4..1b850da799 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -96,7 +96,7 @@ forever: The loop renders one prompt assembly per step. Plugins contribute ordered sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn instead of shipping a hole. `dsh-system-prompt` owns the harness identity and default deployment persona; an agent-scoped persona may shadow the default. The loop supplies `model` and `cwd`. See the [prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md). -Context that arrives while tool results are pending—including asynchronous `agent.inject()` notices and post-tool `additionalContext`—lands after the complete result batch so tool-call/result adjacency stays stable. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved. +Context that arrives while the current tool-call batch executes—including asynchronous `agent.inject()` notices and post-tool `additionalContext`—waits until execution settles and lands after every recorded result; successful batches keep call/result adjacency stable, while interrupted batches drain accepted context before the turn closes. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved. ### Failure Boundaries diff --git a/docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md b/docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md index 5ffdedba18..a54f735219 100644 --- a/docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md +++ b/docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md @@ -18,7 +18,7 @@ In case 2, if the injected `context/message` is the last event before a flush/di **Every session event lives inside a turn** — between a `turn/start` and its matching `turn/end`. Concretely: - The loop appends queued `user/message` events **after** `turn/start` (inside the turn), not before it. `turn/end` is therefore owed the moment those messages are recorded, and the existing finalizer guarantees it. -- An `agent.inject()` made while the agent is **running** joins the already-open turn. If assistant tool calls are awaiting results, the accepted context waits in arrival order and appends after the complete result batch so its user-role message cannot split provider tool pairing. +- An `agent.inject()` made while the agent is **running** joins the already-open turn. While the current step executes assistant tool calls, accepted context waits in arrival order until that batch settles, then appends after every recorded result and before the turn closes even when execution is interrupted. - An `agent.inject()` made while **idle** wraps its `context/message` in a one-shot turn: `turn/start{trigger:{kind:'injection'}}` → `context/message` → `turn/end{completed}`. A new `injection` variant joins the merge-extensible `TurnTriggerMap`. - The loop derives the next turn number from the log each iteration (`lastTurnNumber(session) + 1`) instead of keeping a private counter, so an idle injection's one-shot turn cannot collide with the next real turn's number. - The `dsh-invariants` plugin **enforces** the invariant in dev: a `user/message` / `context/message` / `steering/message` appended while no turn is open throws an `InvariantError`. diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 3eb1d0b8f6..1ee596c285 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -44,7 +44,7 @@ Configured agents start automatically. `cwd` applies only to fresh sessions; `re - `ReactLoopAgent` — the concrete `Agent` implementation. Its inbox is a JavaScript native-private field, and one prepared session can be claimed by only one concrete driver. Everything observable happens through session events and the `agent/*` event taxonomy. -`Inbox`, `runLoop`, and the instance-bound publication/start controls are package-internal. The package root does not export them, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than constructing or starting the driver internals. `ReactLoopAgent.send()`, running `steer()`, and open-turn `inject()` materialize content plus resolved source once as detached, deeply frozen lossless JSON; malformed data throws before enqueue or append. An injection that arrives while assistant tool calls await results stays in a FIFO until the complete result batch is logged, keeping provider tool messages contiguous. +`Inbox`, `runLoop`, and the instance-bound publication/start controls are package-internal. The package root does not export them, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than constructing or starting the driver internals. `ReactLoopAgent.send()`, running `steer()`, and open-turn `inject()` materialize content plus resolved source once as detached, deeply frozen lossless JSON; malformed data throws before enqueue or append. An injection that arrives while the current step executes assistant tool calls stays in a FIFO until the batch settles; successful batches place it after the complete result batch, and interrupted batches drain it before the turn closes. ### Loop lifecycle (`loop.ts`) diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index c45cddda84..24852aa9b7 100644 --- a/packages/core/agent-loop/src/agent.ts +++ b/packages/core/agent-loop/src/agent.ts @@ -12,7 +12,7 @@ import type { AgentId, AgentOptions, AgentStatus, SendOptions } from '@deepseek- import type { Agent } from '@deepseek-ai/dsh-agent' import { deepFreeze } from '@deepseek-ai/dsh-llm' import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm' -import { isToolPairingBalanced, snapshotJsonValue, type Session } from '@deepseek-ai/dsh-session' +import { snapshotJsonValue, type Session } from '@deepseek-ai/dsh-session' import { Inbox, type InboxMessage } from './inbox.ts' import { isTurnOpen, lastTurnNumber, runLoop } from './loop.ts' @@ -149,6 +149,8 @@ export class ReactLoopAgent implements Agent { * this set before the lifecycle unregisters the agent or detaches its session. */ private pendingIdleFlushes = new Set>() + /** Whether the current step is executing an assistant tool-call batch. */ + private toolBatchActive = false /** Open-turn injections waiting for the active assistant tool-call batch to close. */ private deferredInjections: InboxMessage[] = [] @@ -231,11 +233,9 @@ export class ReactLoopAgent implements Agent { if (isTurnOpen(this.session)) { const accepted = this.acceptMessage(content, options) // Provider protocols require every assistant tool-call batch to be - // followed only by its tool results. Queue arbitrary asynchronous context - // until the tail cut is balanced; an existing queue preserves FIFO in the - // narrow window after the last result and before the loop drains it. - if (this.deferredInjections.length > 0 - || !isToolPairingBalanced(this.session.surface.nodes, this.session.events, null)) { + // followed only by its tool results. Historical interrupted batches do + // not own new context; only the currently executing batch may defer it. + if (this.toolBatchActive) { this.deferredInjections.push(accepted) return } @@ -288,6 +288,17 @@ export class ReactLoopAgent implements Agent { } } + /** Run one tool-call batch and drain its deferred context before resolving or rejecting. */ + private async withToolBatch(run: () => Promise): Promise { + this.toolBatchActive = true + try { + return await run() + } finally { + this.toolBatchActive = false + this.drainDeferredInjections() + } + } + cancel(reason?: string): void { // Arm only for current work; an idle marker would cancel the next prompt. if (this._status === 'running' || this.currentAbort !== undefined || this.#inbox.hasQueued || this.#inbox.hasSteering) { @@ -352,7 +363,7 @@ export class ReactLoopAgent implements Agent { isCancelled: () => this.cancelRequested, cancelReason: () => this.cancelReason, clearCancel: () => { this.cancelRequested = false }, - drainDeferredInjections: () => { this.drainDeferredInjections() }, + withToolBatch: run => this.withToolBatch(run), // Pre-step cancellation re-parks without emitting a status transition. settleIdle: () => { this.settleIdleWaiters() }, }) diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 965b2353c2..4a6eea8a99 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -85,8 +85,8 @@ export interface LoopHandle { clearCancel(): void /** Settle idle waiters when pre-running cancellation skips a turn, without emitting `agent/status`. */ settleIdle(): void - /** Append context that arrived while an assistant tool-call batch was awaiting its results. */ - readonly drainDeferredInjections: () => void + /** Run an active tool-call batch and drain deferred context before resolving or rejecting. */ + readonly withToolBatch: (run: () => Promise) => Promise } /** @@ -327,7 +327,7 @@ async function runTurn( let stepOutcome: { hadToolCalls: boolean; finish: FinishReason } | { error: Error } try { stepOutcome = await runStep( - ctx, events, agent, turn, step, assembly, fullSystemPrompt, boundaryMessages, transmission, abort.signal) + ctx, events, agent, handle, turn, step, assembly, fullSystemPrompt, boundaryMessages, transmission, abort.signal) } catch (error: unknown) { stepOutcome = { error: toError(error) } } finally { @@ -351,10 +351,6 @@ async function runTurn( break } - // A successful tool step has committed its complete result batch. Context - // accepted while that batch was pending can now join the open turn. - if (stepOutcome.hadToolCalls) handle.drainDeferredInjections() - // Preserve max-token completion unless a later disposal, abort, or error wins. const stepReason = stepFinishReason(stepOutcome.finish) if (stepReason) reason = stepReason @@ -468,6 +464,7 @@ async function runStep( ctx: Context, events: AgentEventDispatch, agent: ReactLoopAgent, + handle: LoopHandle, turn: number, step: number, assembly: PromptAssembly, @@ -561,51 +558,54 @@ async function runStep( // Tool execution stays sequential; recheck abort around each normalized result. const toolCalls = message.content.filter(block => block.type === 'tool-call') - // Buffer context until all results are appended to preserve call/result adjacency. - const pendingContext: HookContext[] = [] - for (const call of toolCalls) { - /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ - if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) - const callEvent = session.append('tool/call', { turn, step, callId: call.id, name: call.name, arguments: call.arguments }) - let parsedArguments: unknown - try { - parsedArguments = call.arguments ? JSON.parse(call.arguments) : {} - } catch { - parsedArguments = call.arguments + if (toolCalls.length === 0) return { hadToolCalls: false, finish: assembler.finish } + return handle.withToolBatch(async () => { + // Buffer context until all results are appended to preserve call/result adjacency. + const pendingContext: HookContext[] = [] + for (const call of toolCalls) { + /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ + if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) + const callEvent = session.append('tool/call', { turn, step, callId: call.id, name: call.name, arguments: call.arguments }) + let parsedArguments: unknown + try { + parsedArguments = call.arguments ? JSON.parse(call.arguments) : {} + } catch { + parsedArguments = call.arguments + } + // TODO(pre-tool-input-rewrite): Keep logged history and live presentation aligned; + // see docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md. + const result = await ctx.tools.execute({ + callId: call.id, + name: call.name, + arguments: parsedArguments, + agent, + signal, + }) + session.append('tool/result', { + turn, step, + // Preserve transcript pairing even if a post-execute listener returns another id. + callId: call.id, + content: result.content, + isError: result.isError, + ...result.error ? { error: result.error } : {}, + // Persist tool-owned presentation data for replay. + ...result.meta !== undefined ? { meta: result.meta } : {}, + }, { surfaceOp: 'append', sourceEventSeqs: [callEvent.seq] }) + if (result.additionalContext) pendingContext.push(result.additionalContext) + // The signal may flip while the tool is awaited. + /* v8 ignore start -- signal.reason default unreachable: cancel()/disposal always set it */ + // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition + if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) + /* v8 ignore stop */ } - // TODO(pre-tool-input-rewrite): Keep logged history and live presentation aligned; - // see docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md. - const result = await ctx.tools.execute({ - callId: call.id, - name: call.name, - arguments: parsedArguments, - agent, - signal, - }) - session.append('tool/result', { - turn, step, - // Preserve transcript pairing even if a post-execute listener returns another id. - callId: call.id, - content: result.content, - isError: result.isError, - ...result.error ? { error: result.error } : {}, - // Persist tool-owned presentation data for replay. - ...result.meta !== undefined ? { meta: result.meta } : {}, - }, { surfaceOp: 'append', sourceEventSeqs: [callEvent.seq] }) - if (result.additionalContext) pendingContext.push(result.additionalContext) - // The signal may flip while the tool is awaited. - /* v8 ignore start -- signal.reason default unreachable: cancel()/disposal always set it */ - // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition - if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) - /* v8 ignore stop */ - } - // Append buffered context after the complete result batch. - for (const context of pendingContext) { - agent.inject(context.content, { source: context.source }) - } + // Append buffered context after the complete result batch. + for (const context of pendingContext) { + agent.inject(context.content, { source: context.source }) + } - return { hadToolCalls: toolCalls.length > 0, finish: assembler.finish } + return { hadToolCalls: true, finish: assembler.finish } + }) } function withoutToolCalls(message: Message): Message { diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 8130d4b893..1d951c16c2 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -139,6 +139,115 @@ describe('abort during tool execution ends the turn', () => { expect(adapter.requests).toHaveLength(1) // no follow-up model call expect(reasons).toEqual([{ kind: 'aborted', reason: 'user interrupt' }]) }) + + it('records context accepted before a tool-step abort in the same turn', async () => { + const adapter = new MockAdapter([toolCallResponse('c1', 'aborter', {})]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('a-abort-injection'), { model: 'mock' }) + ctx.tools.register(defineTool({ + name: 'aborter', + description: '', + parameters: {}, + async execute() { + agent.inject([{ type: 'text', text: 'accepted before abort' }], { source: { kind: 'plugin', plugin: 'test' } }) + ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('user interrupt') + return [{ type: 'text', text: 'done' }] + }, + })) + + send(agent, 'go') + await waitForIdle(ctx, agent) + + const events = [...agent.session.events] + expect(events + .filter(event => event.type === 'tool/result' || event.type === 'context/message' + || event.type === 'step/end' || event.type === 'turn/end') + .map(event => event.type)) + .toEqual(['tool/result', 'context/message', 'step/end', 'turn/end']) + expect(events.find(event => event.type === 'context/message')?.data.content) + .toEqual([{ type: 'text', text: 'accepted before abort' }]) + }) + + it('drains deferred context before disposal reaches quiescence', async () => { + const adapter = new MockAdapter([toolCallResponse('c1', 'waiter', {})]) + const ctx = await harness(adapter) + const started = Promise.withResolvers() + let agent!: ReactLoopAgent + const fiber = await ctx.plugin(Object.assign((inner: Context) => { + agent = inner.agentLoop.create(AgentId('a-dispose-injection'), { model: 'mock' }) + }, { inject: ['agentLoop'] })) + ctx.tools.register(defineTool({ + name: 'waiter', + description: '', + parameters: {}, + async execute(_args, exec) { + agent.inject([{ type: 'text', text: 'accepted before disposal' }], { source: { kind: 'plugin', plugin: 'test' } }) + started.resolve(undefined) + const signal = exec.signal + if (!signal) throw new Error('tool execution signal is missing') + await new Promise((resolve) => { + if (signal.aborted) resolve() + else signal.addEventListener('abort', () => { resolve() }, { once: true }) + }) + return [{ type: 'text', text: 'done' }] + }, + })) + + send(agent, 'go') + await started.promise + await fiber.dispose() + + expect(agent.session.events.find(event => event.type === 'context/message')?.data.content) + .toEqual([{ type: 'text', text: 'accepted before disposal' }]) + expect(agent.session.events.find(event => event.type === 'turn/end')?.data.reason) + .toEqual({ kind: 'disposed' }) + }) + + it('limits injection deferral to the current tool batch', async () => { + const adapter = new MockAdapter([ + [ + { type: 'block-start', index: 0, blockType: 'tool-call' }, + { type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('c1'), name: 'aborter', arguments: '{}' } }, + { type: 'block-start', index: 1, blockType: 'tool-call' }, + { type: 'block-end', index: 1, block: { type: 'tool-call', id: CallId('c2'), name: 'second', arguments: '{}' } }, + { type: 'finish', reason: { kind: 'tool-calls' } }, + ] satisfies StreamChunk[], + textResponse('later turn'), + ]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('a-historical-tool-pair'), { model: 'mock' }) + ctx.tools.register(defineTool({ + name: 'aborter', + description: '', + parameters: {}, + async execute() { + ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('user interrupt') + return [{ type: 'text', text: 'done' }] + }, + })) + ctx.tools.register(defineTool({ + name: 'second', + description: '', + parameters: {}, + async execute() { + return [{ type: 'text', text: 'must not run' }] + }, + })) + + send(agent, 'leave an unmatched historical call') + await waitForIdle(ctx, agent) + ctx.on('agent/pre-step', (subject, turn) => { + if (subject === agent && turn === 2) { + agent.inject([{ type: 'text', text: 'new turn context' }], { source: { kind: 'plugin', plugin: 'test' } }) + } + }) + send(agent, 'start a text-only turn') + await waitForIdle(ctx, agent) + + expect(agent.session.events.find(event => event.type === 'context/message')?.data.content) + .toEqual([{ type: 'text', text: 'new turn context' }]) + expect(JSON.stringify(adapter.requests[1]?.messages)).toContain('new turn context') + }) }) describe('steering from late extension points is never stranded', () => { diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index ed42741cc1..03b0957fbf 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -41,7 +41,7 @@ The handle every plugin programs against: - `agent.send(content, options?)` — queue a message; starts a turn when idle. Content and resolved source become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input (`agent/prompt-submit` still rewrites by returning replacement content). - `agent.steer(content, options?)` — steer a running turn (inject between steps); uses the same owned acceptance boundary and behaves like `send` when idle -- `agent.inject(content, options?)` — accept detached in-session context without running the model; the next request sees its `context/message`. While a turn is open it joins that turn, deferring FIFO behind any pending tool-result batch so provider pairing remains contiguous; while idle it is wrapped in a one-shot `injection` turn and durability checkpoint ([the turn-enclosure invariant](../../../docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)). +- `agent.inject(content, options?)` — accept detached in-session context without running the model; the next request sees its `context/message`. While a turn is open it joins that turn, deferring FIFO while the current tool batch executes and draining before turn close if execution is interrupted; while idle it is wrapped in a one-shot `injection` turn and durability checkpoint ([the turn-enclosure invariant](../../../docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)). - `agent.cancel(reason?)` — cancel ALL pending work: clears the queued + steering FIFOs, aborts the in-flight step, and drops a turn about to start (the pre-step window) so a queued-but-not-started prompt never runs. A UI/ACP `session/cancel` maps to this. The single public stop primitive. Idle with nothing pending → a safe no-op. - `agent.whenIdle()` — resolve once the agent reaches quiescence after settling out of `running` (idle → immediately; disposed → awaits the loop exit). A non-owner's quiescence-observation hook: it observes the work settling WITHOUT tearing the agent down. Teardown is separate — a lifecycle owner stops and unregisters via `AgentHandle.dispose()`, which awaits the loop exit directly. - `agent.session`, `agent.status`, `agent.options`, `agent.id` diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index efe66693bf..f1a704125a 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -104,10 +104,10 @@ export interface Agent { /** * Append detached model-facing context without running the model. An open-turn - * injection joins at the current log position unless tool results are pending, - * in which case it waits FIFO until the complete result batch is logged. Idle - * injection uses a one-shot turn and durability checkpoint. Disposal awaits - * idle checkpoints; flush failures report through `agent/error`. + * injection joins at the current log position unless the current tool batch is + * executing; then it waits FIFO until that batch settles and drains before turn + * close even when interrupted. Idle injection uses a one-shot turn and durability + * checkpoint. Disposal awaits idle checkpoints; flush failures report through `agent/error`. */ inject(content: ContentBlock[], options?: SendOptions): void From c3d5568efd6a626ae3a3a585495d3113f35aac99 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 12:31:25 +0800 Subject: [PATCH 131/359] Document deferred injection ordering --- docs/core-data-structures/core.md | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 9a9a1706fc..7adda313a4 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -281,9 +281,14 @@ interface Agent { /** * Inject in-session context (file-change notices, skill content, cron - * notifications, …): appends a `context/message` session event the next model - * request sees at its chronological position, rendered as tagged synthetic - * context rather than a user prompt. Does not run the model. + * notifications, …): accepts context for a `context/message` session event + * the next model request sees, rendered as tagged synthetic context rather + * than a user prompt. Does not run the model. + * + * In an open turn, inject appends at the current log position except while + * the current tool-call batch executes: accepted context waits FIFO until the + * batch settles, then appends after every recorded result and before turn + * close even when execution is interrupted. * * Turn-enclosure (the turn-enclosure RFC): an inject while a turn is open joins that turn; * an inject while idle wraps its `context/message` in a one-shot `injection` From baf64e8b2117ff40db66f3c8d9c8677bcd8f07e7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 00:04:00 +0800 Subject: [PATCH 132/359] fix(bash): close managed environment review gaps The managed DSH_* runtime path was correct, but its public extension and documentation contracts were incomplete. A contributor following the README could access ctx.bashEnv without declaring an injection, the new environment types had no drift-checked catalog entries, and the capability graph omitted three packages that now query sessionPersistence. Declare the README injection, catalog DshEnvironmentKey and DshEnvironment, and add tool-bash plus both hook bridges to the generated persistence consumer graph. Keep BashEnvRegistry.list() contributor-only for now because no production caller treats it as exhaustive, but record the built-in enumeration gap before diagnostics, prompt, or UI code depends on it. Validated on the exact resulting tree with typecheck, lint, coverage, snapshot, documentation, module-graph, build, hygiene, demo-smoke, and built-artifact checks. --- docs/capability-seams.md | 11 +++++++---- docs/core-data-structures/bash.md | 12 ++++++++++++ packages/bash/tool-bash/README.md | 2 ++ packages/bash/tool-bash/src/index.ts | 2 ++ scripts/gen-doc-graphs.ts | 2 +- scripts/type-equiv.manifest.json | 2 ++ 6 files changed, 26 insertions(+), 5 deletions(-) diff --git a/docs/capability-seams.md b/docs/capability-seams.md index 29cf15944e..392bde5eda 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -24,6 +24,9 @@ flowchart LR svc_sessionPersistence["ctx.sessionPersistence
Durable session persistence seam"] pkg_session_persistence_jsonl["session-persistence-jsonl"] pkg_session_persistence_sqlite["session-persistence-sqlite"] + pkg_tool_bash["tool-bash"] + pkg_hooks_claude["hooks-claude"] + pkg_hooks_codex["hooks-codex"] pkg_acp["acp"] svc_sessionQuery["ctx.sessionQuery
Exact session-history reads"] pkg_system_prompt["system-prompt"] @@ -33,7 +36,6 @@ flowchart LR pkg_tool_web["tool-web"] svc_tools["ctx.tools
Tool registry and guarded execution pipeline"] pkg_tool_ask_user["tool-ask-user"] - pkg_tool_bash["tool-bash"] pkg_tool_cordis["tool-cordis"] pkg_tool_skill["tool-skill"] pkg_tool_subagent["tool-subagent"] @@ -51,8 +53,6 @@ flowchart LR svc_bash["ctx.bash
Bash executor seam"] pkg_bash_local["bash-local"] pkg_bash_sandbox["bash-sandbox"] - pkg_hooks_claude["hooks-claude"] - pkg_hooks_codex["hooks-codex"] svc_bashEnv["ctx.bashEnv
Managed bash environment registry"] pkg_sandbox["sandbox"] svc_sandbox["ctx.sandbox
Process-sandbox seam"] @@ -151,7 +151,10 @@ flowchart LR svc_sandbox --> pkg_bash_sandbox svc_sessionPersistence --> pkg_acp svc_sessionPersistence --> pkg_agent_loop + svc_sessionPersistence --> pkg_hooks_claude + svc_sessionPersistence --> pkg_hooks_codex svc_sessionPersistence --> pkg_session_query + svc_sessionPersistence --> pkg_tool_bash svc_sessions --> pkg_agent svc_sessions --> pkg_agent_loop svc_sessions --> pkg_invariants @@ -186,7 +189,7 @@ flowchart LR | --- | --- | --- | --- | --- | --- | --- | | `ctx.llm` | `seam` | [`llm`](../packages/llm/llm) | [`llm-deepseek`](../packages/llm/llm-deepseek), [`llm-pi-ai`](../packages/llm/llm-pi-ai), [`llm-replay`](../packages/support/llm-replay) | [`agent-loop`](../packages/core/agent-loop), [`compact-basic`](../packages/compact/compact-basic) | - | Adapters register provider implementations; the loop and compaction call the provider-neutral stream service. | | `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. | -| `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`session-query`](../packages/session-query/session-query) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. | +| `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`acp`](../packages/ui/acp), [`session-query`](../packages/session-query/session-query) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. | | `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | - | - | - | Resolves live and optional persisted logs into one logical corpus for exact reads. | | `ctx.systemPrompt` | `core` | [`system-prompt`](../packages/core/system-prompt) | - | [`agent-loop`](../packages/core/agent-loop), [`tools`](../packages/core/tools), [`tool-fs`](../packages/fs/tool-fs), [`tool-web`](../packages/web/tool-web) | - | Collects prompt sections and model-facing tool schemas for each step. | | `ctx.tools` | `core` | [`tools`](../packages/core/tools) | - | [`agent-loop`](../packages/core/agent-loop), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tool-bash`](../packages/bash/tool-bash), [`tool-cordis`](../packages/cordis/tool-cordis), [`tool-fs`](../packages/fs/tool-fs), [`tool-skill`](../packages/skill/tool-skill), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-todo`](../packages/todo/tool-todo), [`tool-web`](../packages/web/tool-web), [`acp`](../packages/ui/acp) | - | Registers capabilities, owns Code Mode transport, and routes calls through pre-policy, monotonic guards, around dispatch, post-policy, and final-result observation. | diff --git a/docs/core-data-structures/bash.md b/docs/core-data-structures/bash.md index 72ca27e8cb..80697356f9 100644 --- a/docs/core-data-structures/bash.md +++ b/docs/core-data-structures/bash.md @@ -4,6 +4,18 @@ The bash execution seam — the canonical [capability seam](../rfc/implemented/a Source: [`packages/bash/bash/src/types.ts`](../../packages/bash/bash/src/types.ts) +## Managed environment vocabulary + +The exported `DSH_ENV_PREFIX` constant is `'DSH_'`, the namespace reserved for harness-owned child-process facts. `DshEnvironmentKey` restricts managed keys to that namespace, and `DshEnvironment` is the immutable per-execution snapshot carried separately from ordinary environment overrides. + +```ts type-equiv +type DshEnvironmentKey = `${typeof DSH_ENV_PREFIX}${string}` +``` + +```ts type-equiv +type DshEnvironment = Readonly> +``` + ## Request vs. spec: the `resolve()` split The seam separates the **model-/plugin-facing request** (optional `workdir`/`timeoutMs`, filled from config) from the **fully-resolved spec** the executor acts on (those fields required). The tool layer calls `ctx.bash.resolve(request)` between them — this is the repo's "explicit > implicit at package seams" rule made concrete: the reader of a `BashExecSpec` never wonders where the working directory came from. diff --git a/packages/bash/tool-bash/README.md b/packages/bash/tool-bash/README.md index 73d0abafc9..fa6a5285ed 100644 --- a/packages/bash/tool-bash/README.md +++ b/packages/bash/tool-bash/README.md @@ -32,6 +32,8 @@ Every foreground and background model bash call receives a newly collected trust import type { Context } from 'cordis' import type {} from '@deepseek-ai/dsh-tool-bash' +export const inject = ['bashEnv'] + export function apply(ctx: Context): void { ctx.bashEnv.register({ name: 'deployment-region', diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index e171033c9d..33712c1d1b 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -185,6 +185,8 @@ export class BashEnvRegistry extends Service { return Object.freeze(Object.fromEntries(Object.entries(values).sort(([left], [right]) => left.localeCompare(right)))) } + // TODO(bash-env-list-builtins): Include registry-owned built-ins before diagnostics, + // prompt, or UI code treats list() as an exhaustive environment catalog. /** * Enumerate plugin-contributed variables without executing their resolvers. * @returns declarations sorted by environment variable name. diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 446e726255..5c635d01ae 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -98,7 +98,7 @@ const SERVICE_ROLES: ServiceRole[] = [ title: 'Durable session persistence seam', mode: 'seam', implementations: ['session-persistence-jsonl', 'session-persistence-sqlite'], - consumers: ['agent-loop', 'acp', 'session-query'], + consumers: ['agent-loop', 'tool-bash', 'hooks-claude', 'hooks-codex', 'acp', 'session-query'], note: 'Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time.', }, { diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index a8eba66fc5..a4ebf4ce9e 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -84,6 +84,8 @@ { "doc": "docs/core-data-structures/approval.md", "symbol": "ApprovalPolicy", "source": "packages/ui/user-approval/src/index.ts" }, { "doc": "docs/core-data-structures/approval.md", "symbol": "ApprovalRequest", "source": "packages/ui/user-approval/src/index.ts" }, + { "doc": "docs/core-data-structures/bash.md", "symbol": "DshEnvironmentKey", "source": "packages/bash/bash/src/types.ts" }, + { "doc": "docs/core-data-structures/bash.md", "symbol": "DshEnvironment", "source": "packages/bash/bash/src/types.ts" }, { "doc": "docs/core-data-structures/bash.md", "symbol": "BashExecRequest", "source": "packages/bash/bash/src/types.ts" }, { "doc": "docs/core-data-structures/bash.md", "symbol": "BashExecSpec", "source": "packages/bash/bash/src/types.ts" }, { "doc": "docs/core-data-structures/bash.md", "symbol": "BashRunResult", "source": "packages/bash/bash/src/types.ts" }, From edfc4dc4ac8c9a5ae8c45cd2b87ef3e629685920 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 12:49:50 +0800 Subject: [PATCH 133/359] Preserve interrupted post-tool context --- docs/core-data-structures/tools.md | 9 +- .../feature/2026-06-30-interception-seams.md | 2 +- docs/tool-execution-pipeline.md | 4 +- packages/core/agent-loop/src/agent.ts | 18 +++- packages/core/agent-loop/src/loop.ts | 17 ++-- .../tests/contract-regressions.spec.ts | 85 +++++++++++++++++-- packages/core/tools/src/index.ts | 6 +- scripts/gen-doc-graphs.ts | 4 +- 8 files changed, 113 insertions(+), 32 deletions(-) diff --git a/docs/core-data-structures/tools.md b/docs/core-data-structures/tools.md index 08c289e5e5..1aa20d5383 100644 --- a/docs/core-data-structures/tools.md +++ b/docs/core-data-structures/tools.md @@ -151,10 +151,11 @@ interface ToolExecutionResult { * NEXT request (Claude Code's PostToolUse `additionalContext`). It is NOT part * of this call's `content` — `content`/`feedback` shape the tool RESULT, but * `additionalContext` is a SEPARATE `context/message`. A step can carry - * multiple tool calls, so the loop BUFFERS every call's `additionalContext` - * and appends them only AFTER all `tool/result`s for the step, keeping - * tool-call/result adjacency intact. Carried on the result purely to ferry it - * from `execute()` up to the loop's per-step buffer. + * multiple tool calls, so the loop accepts every call's `additionalContext` + * into the active-batch FIFO and appends it only when that batch settles. A + * successful batch places context AFTER all its `tool/result`s; an interrupted + * batch places it after every recorded result and before turn close. Carried + * on the result purely to ferry it from `execute()` up to that FIFO. */ additionalContext?: HookContext /** diff --git a/docs/rfc/implemented/feature/2026-06-30-interception-seams.md b/docs/rfc/implemented/feature/2026-06-30-interception-seams.md index ea371ad55a..303c78055d 100644 --- a/docs/rfc/implemented/feature/2026-06-30-interception-seams.md +++ b/docs/rfc/implemented/feature/2026-06-30-interception-seams.md @@ -36,7 +36,7 @@ Core dispatch and the tool body sit inside normalization boundaries, so tool, li 1. **Open the turn before prompt policy.** A fully blocked batch becomes a zero-step `rejected` turn, preserving enclosure and giving ACP a durable terminal event. Every veto also records `prompt/blocked` with the original prompt and reason, so mixed batches retain blocked inputs. Allowed `additionalContext` is injected into the open turn. -2. **Post-tool `additionalContext` is buffered and appended AFTER all `tool/result`s.** `content`/`feedback` shape the result `execute()` returns, but `additionalContext` is a SEPARATE `context/message`, and a single step can carry multiple tool calls. Appending context right after each result would interleave `result(c1) → context → result(c2)` and break tool-call/result adjacency. So `execute()` surfaces `additionalContext` on its `ToolExecutionResult`, and the loop buffers every per-call context for the step and appends them as `context/message`(s) only after every `tool/result` is appended. +2. **Post-tool `additionalContext` enters the active-batch FIFO and appends when that batch settles.** `content`/`feedback` shape the result `execute()` returns, but `additionalContext` is a SEPARATE `context/message`, and a single step can carry multiple tool calls. Appending context right after each result would interleave `result(c1) → context → result(c2)` and break tool-call/result adjacency. So `execute()` surfaces `additionalContext` on its `ToolExecutionResult`; the loop accepts each context into the same FIFO as asynchronous injections, then appends the FIFO after the complete result batch on success or after every recorded result before an interrupted turn closes. 3. **A forced `continue` `reason` is enqueued through the steering channel**, so the next step's top-of-loop drain records it as steering for the continued turn — next-*step* steering within the SAME turn, not a next-*turn* prompt (matching the existing `hasSteering` force-continue override). diff --git a/docs/tool-execution-pipeline.md b/docs/tool-execution-pipeline.md index 51641d4655..0caf979efd 100644 --- a/docs/tool-execution-pipeline.md +++ b/docs/tool-execution-pipeline.md @@ -20,9 +20,9 @@ flowchart TD owned["Tool-owned session events
todo/write, fs/observed, hook/invoked, hook/result, tool/code-dispatch"] post["tools/post-execute waterfall
accept, block, replace, add context"] final["tools/result synchronous notification
frozen authoritative outcome"] - context["Buffered additionalContext
context/message after all tool results"] + context["Batch-deferred additionalContext
context/message after recorded tool results"] toolResult["Session event: tool/result
single model-facing outcome"] - allResults["All calls in the step settled
and tool/result events recorded"] + allResults["Tool batch settled
recorded tool/result events complete"] presentResult["UI completed card
presentResult(args, result)"] model --> toolCall toolCall --> presentCall diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index 24852aa9b7..82d381bcae 100644 --- a/packages/core/agent-loop/src/agent.ts +++ b/packages/core/agent-loop/src/agent.ts @@ -8,7 +8,7 @@ import type { Context } from 'cordis' import { agentEvents } from '@deepseek-ai/dsh-agent' -import type { AgentId, AgentOptions, AgentStatus, SendOptions } from '@deepseek-ai/dsh-agent' +import type { AgentId, AgentOptions, AgentStatus, HookContext, SendOptions } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { deepFreeze } from '@deepseek-ai/dsh-llm' import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm' @@ -288,11 +288,21 @@ export class ReactLoopAgent implements Agent { } } - /** Run one tool-call batch and drain its deferred context before resolving or rejecting. */ - private async withToolBatch(run: () => Promise): Promise { + /** + * Run one tool-call batch and drain its deferred context before settlement. + * The loop-owned acceptor remains valid after public disposal begins because + * the interrupted turn stays open until this batch settles. + */ + private async withToolBatch( + run: (acceptContext: (context: HookContext) => void) => Promise, + ): Promise { this.toolBatchActive = true + const acceptContext = (context: HookContext): void => { + const accepted = this.acceptMessage(context.content, { source: context.source }) + this.deferredInjections.push(accepted) + } try { - return await run() + return await run(acceptContext) } finally { this.toolBatchActive = false this.drainDeferredInjections() diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 4a6eea8a99..0c6ba7a4fa 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -85,8 +85,8 @@ export interface LoopHandle { clearCancel(): void /** Settle idle waiters when pre-running cancellation skips a turn, without emitting `agent/status`. */ settleIdle(): void - /** Run an active tool-call batch and drain deferred context before resolving or rejecting. */ - readonly withToolBatch: (run: () => Promise) => Promise + /** Run an active tool-call batch, accepting post-tool context into the FIFO drained before settlement. */ + readonly withToolBatch: (run: (acceptContext: (context: HookContext) => void) => Promise) => Promise } /** @@ -559,9 +559,7 @@ async function runStep( // Tool execution stays sequential; recheck abort around each normalized result. const toolCalls = message.content.filter(block => block.type === 'tool-call') if (toolCalls.length === 0) return { hadToolCalls: false, finish: assembler.finish } - return handle.withToolBatch(async () => { - // Buffer context until all results are appended to preserve call/result adjacency. - const pendingContext: HookContext[] = [] + return handle.withToolBatch(async (acceptContext) => { for (const call of toolCalls) { /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) @@ -591,7 +589,9 @@ async function runStep( // Persist tool-owned presentation data for replay. ...result.meta !== undefined ? { meta: result.meta } : {}, }, { surfaceOp: 'append', sourceEventSeqs: [callEvent.seq] }) - if (result.additionalContext) pendingContext.push(result.additionalContext) + // Accept into the batch FIFO immediately; it remains deferred until every + // result settles and survives abort, cancellation, or disposal afterward. + if (result.additionalContext) acceptContext(result.additionalContext) // The signal may flip while the tool is awaited. /* v8 ignore start -- signal.reason default unreachable: cancel()/disposal always set it */ // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition @@ -599,11 +599,6 @@ async function runStep( /* v8 ignore stop */ } - // Append buffered context after the complete result batch. - for (const context of pendingContext) { - agent.inject(context.content, { source: context.source }) - } - return { hadToolCalls: true, finish: assembler.finish } }) } diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 1d951c16c2..cc75943c4d 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -3,7 +3,7 @@ import { Context } from 'cordis' import LlmService, { CallId, ContentBlock, MessageSource, StreamChunk } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' +import ToolRegistry, { defineTool, type PostToolDecision } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId, type ContinuationDecision } from '@deepseek-ai/dsh-agent' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { prepareReactLoopAgent } from '../src/agent.ts' @@ -154,6 +154,13 @@ describe('abort during tool execution ends the turn', () => { return [{ type: 'text', text: 'done' }] }, })) + ctx.on('tools/post-execute', async (): Promise => ({ + kind: 'accept', + additionalContext: { + content: [{ type: 'text', text: 'accepted result context after abort' }], + source: { kind: 'plugin', plugin: 'test' }, + }, + })) send(agent, 'go') await waitForIdle(ctx, agent) @@ -163,9 +170,65 @@ describe('abort during tool execution ends the turn', () => { .filter(event => event.type === 'tool/result' || event.type === 'context/message' || event.type === 'step/end' || event.type === 'turn/end') .map(event => event.type)) - .toEqual(['tool/result', 'context/message', 'step/end', 'turn/end']) + .toEqual(['tool/result', 'context/message', 'context/message', 'step/end', 'turn/end']) + expect(events + .filter(event => event.type === 'context/message') + .map(event => event.data.content)) + .toEqual([ + [{ type: 'text', text: 'accepted before abort' }], + [{ type: 'text', text: 'accepted result context after abort' }], + ]) + }) + + it('records post-tool context when a later call aborts the batch', async () => { + const adapter = new MockAdapter([[ + { type: 'block-start', index: 0, blockType: 'tool-call' }, + { type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('c1'), name: 'first', arguments: '{}' } }, + { type: 'block-start', index: 1, blockType: 'tool-call' }, + { type: 'block-end', index: 1, block: { type: 'tool-call', id: CallId('c2'), name: 'aborter', arguments: '{}' } }, + { type: 'finish', reason: { kind: 'tool-calls' } }, + ] satisfies StreamChunk[]]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('a-later-abort-context'), { model: 'mock' }) + ctx.tools.register(defineTool({ + name: 'first', + description: '', + parameters: {}, + async execute() { + return [{ type: 'text', text: 'first done' }] + }, + })) + ctx.tools.register(defineTool({ + name: 'aborter', + description: '', + parameters: {}, + async execute() { + ;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('user interrupt') + return [{ type: 'text', text: 'aborted' }] + }, + })) + ctx.on('tools/post-execute', async (exec, _result, next): Promise => { + if (exec.callId !== CallId('c1')) return next() + return { + kind: 'accept', + additionalContext: { + content: [{ type: 'text', text: 'accepted after first result' }], + source: { kind: 'plugin', plugin: 'test' }, + }, + } + }) + + send(agent, 'go') + await waitForIdle(ctx, agent) + + const events = [...agent.session.events] + expect(events + .filter(event => event.type === 'tool/result' || event.type === 'context/message' + || event.type === 'step/end' || event.type === 'turn/end') + .map(event => event.type)) + .toEqual(['tool/result', 'tool/result', 'context/message', 'step/end', 'turn/end']) expect(events.find(event => event.type === 'context/message')?.data.content) - .toEqual([{ type: 'text', text: 'accepted before abort' }]) + .toEqual([{ type: 'text', text: 'accepted after first result' }]) }) it('drains deferred context before disposal reaches quiescence', async () => { @@ -192,13 +255,25 @@ describe('abort during tool execution ends the turn', () => { return [{ type: 'text', text: 'done' }] }, })) + ctx.on('tools/post-execute', async (): Promise => ({ + kind: 'accept', + additionalContext: { + content: [{ type: 'text', text: 'accepted result context during disposal' }], + source: { kind: 'plugin', plugin: 'test' }, + }, + })) send(agent, 'go') await started.promise await fiber.dispose() - expect(agent.session.events.find(event => event.type === 'context/message')?.data.content) - .toEqual([{ type: 'text', text: 'accepted before disposal' }]) + expect(agent.session.events + .filter(event => event.type === 'context/message') + .map(event => event.data.content)) + .toEqual([ + [{ type: 'text', text: 'accepted before disposal' }], + [{ type: 'text', text: 'accepted result context during disposal' }], + ]) expect(agent.session.events.find(event => event.type === 'turn/end')?.data.reason) .toEqual({ kind: 'disposed' }) }) diff --git a/packages/core/tools/src/index.ts b/packages/core/tools/src/index.ts index 988c6a0268..695a1e2ff1 100644 --- a/packages/core/tools/src/index.ts +++ b/packages/core/tools/src/index.ts @@ -238,8 +238,8 @@ export interface ToolExecutionResult { */ error?: ToolErrorInfo /** - * Model-facing context for the next request, separate from this tool result. - * The loop buffers it until all step results are logged, preserving pairing. + * Model-facing context for the next request, separate from this tool result. The loop + * accepts it into the active-batch FIFO, then appends after recorded results even if interrupted. */ additionalContext?: HookContext /** @@ -843,7 +843,7 @@ export class ToolRegistry extends Service { * its {@link PostToolDecision}: `accept` keeps the call successful (replacing * `content` when given), `block` turns it into an `isError` whose content is * the corrective `feedback`. Either decision may attach `additionalContext`, - * which is ferried on the returned result for the loop's per-step buffer. + * which is ferried on the returned result for the loop's active-batch FIFO. * Runs inside `execute`'s outer try/catch (a throwing listener → isError). */ private async postExecute(exec: ToolExecution, result: ToolExecutionResult): Promise { diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index a6660f7cd3..a836b399e6 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -850,9 +850,9 @@ function renderToolPipeline(): string { ` owned["Tool-owned session events
${mermaidCode('todo/write')}, ${mermaidCode('fs/observed')}, ${mermaidCode('hook/invoked')}, ${mermaidCode('hook/result')}, ${mermaidCode('tool/code-dispatch')}"]`, ` post["${mermaidCode('tools/post-execute')} waterfall
accept, block, replace, add context"]`, ` final["${mermaidCode('tools/result')} synchronous notification
frozen authoritative outcome"]`, - ' context["Buffered additionalContext
context/message after all tool results"]', + ' context["Batch-deferred additionalContext
context/message after recorded tool results"]', ` toolResult["Session event: ${mermaidCode('tool/result')}
single model-facing outcome"]`, - ' allResults["All calls in the step settled
and tool/result events recorded"]', + ' allResults["Tool batch settled
recorded tool/result events complete"]', ' presentResult["UI completed card
presentResult(args, result)"]', ' model --> toolCall', ' toolCall --> presentCall', From cc546c4580721a78c0276ffa8723523a74679e6a Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 13:22:44 +0800 Subject: [PATCH 134/359] feat(compact): move pairing helpers (PR1 round 1) --- docs/cordis-catalog/events.md | 8 +- docs/cordis-catalog/services.md | 4 +- docs/core-data-structures/compaction.md | 2 + docs/core-data-structures/session.md | 2 + docs/event-producer-consumer.md | 8 +- .../2026-06-18-compaction-capability-seam.md | 4 +- packages/compact/compact-basic/README.md | 2 +- packages/compact/compact-basic/src/index.ts | 16 +- .../tests/compact-loop-repro.spec.ts | 6 +- packages/compact/compact/README.md | 8 +- packages/compact/compact/src/index.ts | 3 + packages/compact/compact/src/tool-pairing.ts | 160 +++++++++ .../compact/tests/tool-pairing.spec.ts | 327 ++++++++++++++++++ packages/core/session/README.md | 2 +- packages/core/session/src/index.ts | 1 - packages/core/session/src/tool-pairing.ts | 56 --- .../core/session/tests/tool-pairing.spec.ts | 292 ---------------- 17 files changed, 525 insertions(+), 376 deletions(-) create mode 100644 packages/compact/compact/src/tool-pairing.ts create mode 100644 packages/compact/compact/tests/tool-pairing.spec.ts delete mode 100644 packages/core/session/src/tool-pairing.ts delete mode 100644 packages/core/session/tests/tool-pairing.spec.ts diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 4af431f8c0..d2102e5e3f 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -245,7 +245,7 @@ Creation announcement during session publication. A synchronous throw vetoes and 'session/created'(this: Scoped, session: Session): void ``` -Source: [`packages/core/session/src/index.ts:47`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:46`](../../packages/core/session/src/index.ts) ### `session/disposed` — emit @@ -255,7 +255,7 @@ Emitted once when an announced session leaves the store, including publication r 'session/disposed'(this: Scoped, session: Session): void ``` -Source: [`packages/core/session/src/index.ts:57`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:56`](../../packages/core/session/src/index.ts) ### `session/event` — emit @@ -267,7 +267,7 @@ Post-commit, fire-and-forget append feed. The listener snapshot resolves before Types: [SessionEvent](../core-data-structures/core.md) -Source: [`packages/core/session/src/index.ts:69`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:68`](../../packages/core/session/src/index.ts) ### `session/flush` — parallel @@ -277,7 +277,7 @@ Awaited parallel durability checkpoint: every listener runs and the caller await 'session/flush'(this: Scoped, session: Session): Promise | void ``` -Source: [`packages/core/session/src/index.ts:79`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:78`](../../packages/core/session/src/index.ts) ## `skill/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 1509afc76a..1197570d23 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -95,7 +95,7 @@ abstract compactRegion( session: Session, start: number, end: number, agent: Com Types: [Message](../core-data-structures/core.md) -Source: [`packages/compact/compact/src/index.ts:36`](../../packages/compact/compact/src/index.ts) +Source: [`packages/compact/compact/src/index.ts:37`](../../packages/compact/compact/src/index.ts) ## `ctx.fs` — `FileSystem` (abstract seam) @@ -200,7 +200,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:564`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:563`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 82bf512eeb..05022f9937 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -53,3 +53,5 @@ interface CompactionResult { `CompactService` exposes `compactIfNeeded(...)` for pressure-triggered compaction, returning `null` when no compaction is needed, and `compactRegion(...)` for an explicit inclusive surface range. The pre-step caller supplies the agent, full prompt, session prefix, and abort signal; implementations must forward that signal to summarization. Estimation, retention, event sequencing, and summarization remain backend policy. Auto-compaction runs at serial `agent/pre-step`, before the step and request derivation, so it can replace surface nodes while keeping trace events outside the step. Region boundaries preserve tool-call/result pairing but do not preserve whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns the retention and failure details. + +The seam exports `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)` for those edge checks. Both validate current surface membership, reject stale or missing seqs and orphan results, and ignore a caller-retained `node.next`; the [package contract](../../packages/compact/compact/README.md#tool-pairing-boundaries) owns their cache semantics. diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index d8292c49b3..174f06602e 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -196,6 +196,8 @@ export interface SurfaceNode { } ``` +`SurfaceNode` is positional state, not durable identity. A replacement can remove a caller-retained node or make a copied `next` stale; consumers that cross a surface mutation validate membership and resolve successors from `Session.surface.nodes`. `SurfaceManager.replaceGeneration` increments for each replacement so incremental consumers can distinguish pure tail growth from a rewrite. + ### `SurfaceFoldReplacement` and `SurfaceFoldResult` — a complete surface replay `foldSurface(events)` returns detached current nodes together with the actual node seqs shadowed by each declared replacement range. `SurfaceManager` uses the same transition functions for its incremental cache. diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index bdf1c6e320..445078cb37 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -25,10 +25,10 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:68`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:51`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | -| `session/created` | `emit` | [`packages/core/session/src/index.ts:47`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | -| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:57`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | -| `session/event` | `emit` | [`packages/core/session/src/index.ts:69`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) | -| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:79`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | +| `session/created` | `emit` | [`packages/core/session/src/index.ts:46`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | +| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:56`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | +| `session/event` | `emit` | [`packages/core/session/src/index.ts:68`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) | +| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:78`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | | `skill/provider-added` | `emit` | [`packages/skill/skill/src/index.ts:131`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - | | `skill/provider-removed` | `emit` | [`packages/skill/skill/src/index.ts:137`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - | | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:92`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index 4a6586b159..29e3347759 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -52,7 +52,7 @@ The loop derives messages once after `agent/pre-step`. Running before `step/star Auto-compaction fires before **every** step, not once per turn. This is **load-bearing for runaway-turn survival**: a tool-heavy ReAct turn appends an `assistant/message` + a `tool/result` per step, so the surface grows *within* a turn. A single turn can grow past the window on its own (a "runaway turn") — and the only moment to rescue it before the next model call overflows is the next step's `pre-step` checkpoint. Gating compaction to a turn's first step (or, worse, retaining the whole in-flight turn verbatim) re-opens exactly the hole compaction exists to close: the harness would die when compaction is most needed. -`compactIfNeeded` retains the smallest tail of whole surface units whose estimated size reaches `retainTokens` and compacts older nodes. A unit is a complete closed step or one no-step message. If the token cutoff lands inside a step, retention expands until the cut is tool-pairing balanced. Balance is checked on surface order, not log sequence, because replacement summaries have new sequence numbers at old surface positions. `compactRegion` rejects boundaries that split a tool call from its result. The in-flight turn receives no special retention. +`compactIfNeeded` retains the smallest tail of whole surface units whose estimated size reaches `retainTokens` and compacts older nodes. A unit is a complete closed step or one no-step message. If the token cutoff lands inside a step, retention expands until the cut is tool-pairing balanced. Balance is checked on surface order, not log sequence, because replacement summaries have new sequence numbers at old surface positions. `dsh-compact` exports the before/after edge helpers; their per-session cache folds only appended surface-tail nodes while `replaceGeneration` is unchanged, does no event reads for log-only growth, and rebuilds current membership, positional successors, and balances after replacement. `compactRegion` rejects boundaries that split a tool call from its result. The in-flight turn receives no special retention. A runaway turn thus compacts exactly like any other history: its early *closed* steps get summarized while its recent steps stay verbatim. When the only compactable content left is an un-splittable open tail step (its tool-calls have no results yet), compaction declines (`null`) and retries once that step closes. @@ -113,7 +113,7 @@ Two failure paths, both documented: - **New packages**: `packages/compact/compact` (interface) and a sibling `compact-basic` (backend) under `packages/compact/`, wired into the root tsconfigs. The consumer tier is deferred. - **New loop seam**: `agent/pre-step` (`@mode serial`) declared in `dsh-agent` and emitted by `dsh-agent-loop` after system assembly and before `step/start`. This is a documented change to the loop — `docs/architecture.md` records it and the generated cordis catalog carries its signature. - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry. -- **`dsh-session`** gains the tool-pairing balance predicate (`isToolPairingBalanced`, in `tool-pairing.ts`, exported from the package index) that `compactRegion`/`compactIfNeeded` use to keep a collapsed region from splitting a step's tool-call/result pair. The surface `replace` op and the surface-metadata runtime guard already existed and are reused. +- **`dsh-compact`** owns `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)`, the cached surface-edge checks that `compactRegion` and `compactIfNeeded` use to avoid splitting a tool-call/result pair. The cache validates current membership by seq and resolves after-edges from its positional successor map instead of trusting a caller-retained `node.next`; stale or missing seqs and orphan results reject. `dsh-session` continues to own the surface `replace` operation, positional nodes, and rewrite generation. - **`dsh-invariants`** drops its `surface replace: start must be <= end` assertion: a head-anchored compaction lands a high-seq replacement node at an older range's *position*, so `start > end` numerically is normal and valid (the range is positional, validated by the surface's `indexOf` checks that remain). The turn-enclosure invariant is reused unchanged. - **Wiring**: `dsh-compact-basic` is loaded in `examples/coding-agent`'s `cordis.yml`, so the seam ships in the real demo (it was previously loaded nowhere). diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index d9c0f472a8..d05ce47356 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -9,7 +9,7 @@ This is the implementation tier of the compaction capability — see the [interf This backend owns the compaction policy: - **Estimation** — a configurable characters-per-token heuristic counts the current session prefix supplied to pre-step, derived history, and system prompt, matching the next request rather than stale logged prefix state. -- **Retention** — compact the oldest whole surface units while preserving a recent tail and balanced tool-call/result cuts. Turn boundaries do not protect old steps inside a runaway turn. An open indivisible tail declines until it closes; a single unit larger than the budget remains out of scope. +- **Retention** — compact the oldest whole surface units while preserving a recent tail and balanced tool-call/result cuts through the [`dsh-compact` boundary helpers](../compact/README.md#tool-pairing-boundaries). Turn boundaries do not protect old steps inside a runaway turn. An open indivisible tail declines until it closes; a single unit larger than the budget remains out of scope. - **Convergence** — retry head-checkpoint compaction up to `compactionRetries`; reject a summary that does not shrink its source, and throw if retries cannot return below threshold. - **Summarization** — a direct `llm/stream` call uses the configured model and cap without running the loop-only `agent/request` seam. The input transcript preserves non-text blocks as tagged placeholders; only returned text enters the checkpoint, excluding reasoning and tool calls that would leak private reasoning or create an orphaned call. - **Framing** — the replacement user message marks established checkpoint context with `` tags. The raw summary remains on the provenance event, and later automatic cycles merge the prior checkpoint. diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index bf349f7f73..fffc8e9a63 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -7,12 +7,11 @@ */ import { Context } from 'cordis' -import { CompactService, renderTranscript } from '@deepseek-ai/dsh-compact' +import { CompactService, renderTranscript, toolPairingBalancedAfter, toolPairingBalancedBefore } from '@deepseek-ai/dsh-compact' import type { CompactionResult } from '@deepseek-ai/dsh-compact' import { BlockAssembler } from '@deepseek-ai/dsh-llm' import type { ContentBlock, FinishReason, GenerateOptions, Message } from '@deepseek-ai/dsh-llm' import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' -import { isToolPairingBalanced } from '@deepseek-ai/dsh-session' import type { Agent } from '@deepseek-ai/dsh-agent' import type { BasicCompactConfig, ResolvedConfig } from './types.ts' import { resolveConfig } from './types.ts' @@ -348,15 +347,14 @@ export class BasicCompactService extends CompactService { } // Both range edges must preserve assistant tool-call/result pairing. - const events = session.events - if (!isToolPairingBalanced(nodes, events, start)) { + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + const startNode = nodes[startIdx]! + if (!toolPairingBalancedBefore(session, startNode)) { throw new Error(`compactRegion: start seq ${start} is not a balanced boundary (would split a step's tool-call/result pair)`) } - // The cut after `end` is named by `end`'s surface successor, or `null` when - // `end` is the tail. // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const afterEnd: number | null = nodes[endIdx]!.next - if (!isToolPairingBalanced(nodes, events, afterEnd)) { + const endNode = nodes[endIdx]! + if (!toolPairingBalancedAfter(session, endNode)) { throw new Error(`compactRegion: end seq ${end} is not a balanced boundary (would split a step, or the step is still open)`) } @@ -511,7 +509,7 @@ export class BasicCompactService extends CompactService { // splitting an assistant↔result pair. while (keepFromIdx > 0) { // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - if (isToolPairingBalanced(nodes, events, nodes[keepFromIdx]!.seq)) break + if (toolPairingBalancedBefore(session, nodes[keepFromIdx]!)) break keepFromIdx -= 1 } if (keepFromIdx === 0) return null diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index dbf8a3b737..49fb99acec 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -1,10 +1,10 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' +import { toolPairingBalancedAfter, toolPairingBalancedBefore } from '@deepseek-ai/dsh-compact' import LlmService from '@deepseek-ai/dsh-llm' import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' import SessionStore from '@deepseek-ai/dsh-session' -import { isToolPairingBalanced } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' @@ -124,9 +124,9 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () for (const cp of checkpoints) { const node = nodes.find(n => n.seq === cp.seq) if (!node) continue // shadowed by a later checkpoint — no longer an edge. - expect(isToolPairingBalanced(nodes, events, node.seq), + expect(toolPairingBalancedBefore(agent.session, node), `checkpoint seq ${node.seq} must be a balanced region START`).toBe(true) - expect(isToolPairingBalanced(nodes, events, node.next), + expect(toolPairingBalancedAfter(agent.session, node), `checkpoint seq ${node.seq} must be a balanced region END`).toBe(true) } } finally { diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index 9141012281..5b59893561 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -6,7 +6,7 @@ This package is the interface tier of the compaction capability, split so each c | Package | Role | |---|---| -| `@deepseek-ai/dsh-compact` (this) | the interface: abstract service + `compact/*` events + `CompactionResult` + the shared transcript renderer (`renderTranscript`/`renderContentBlocks`) | +| `@deepseek-ai/dsh-compact` (this) | the interface: abstract service + `compact/*` events + `CompactionResult` + tool-pairing boundary helpers + the shared transcript renderer (`renderTranscript`/`renderContentBlocks`) | | `@deepseek-ai/dsh-compact-basic` | a backend: chars-per-token estimation (`charsPerToken`, default 4) + token-budget retention + `llm.stream()` summarization | | `@deepseek-ai/dsh-tool-compact` (deferred) | the model-facing `/compact` tool over `ctx.compact` | @@ -23,6 +23,12 @@ Both methods are **abstract** — the backend owns the entire strategy (token es `compactIfNeeded` takes a required `signal`; `compactRegion`'s is optional. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The session being compacted comes from the agent context; the turn that the `compact/*` events belong to is recoverable from the log (the currently-open turn), so the backend stamps it from the log rather than trusting a caller-supplied value. +## Tool-pairing boundaries + +The interface exports `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)` for snapping and validating compaction edges. A safe edge has no unanswered assistant tool call crossing it. Each helper validates the node's seq against current surface membership and resolves the trailing edge from its cached positional successor, so a stale caller-held `node.next` cannot choose the cut. + +The private per-session cache is keyed by `session.surface.replaceGeneration` and the processed surface-node count. An unchanged generation extends the fold with unseen tail nodes only; a log-only append with no new surface node does no event reads, while a replacement generation rebuilds current membership, successors, and balances. Missing event seqs and a `tool/result` without a preceding open call reject as corrupt surface state. + ## Surface contract `SurfaceEventType` is a closed union — only `user/message`, `assistant/message`, `tool/result`, `context/message`, and `steering/message` may carry `surfaceOp`. A `compact/*` event therefore **cannot** appear on the surface. A successful compaction instead: diff --git a/packages/compact/compact/src/index.ts b/packages/compact/compact/src/index.ts index f59e0dc328..12eb77b362 100644 --- a/packages/compact/compact/src/index.ts +++ b/packages/compact/compact/src/index.ts @@ -14,6 +14,7 @@ import type { CompactionResult } from './types.ts' export type { CompactionResult } from './types.ts' export { renderContentBlocks, renderTranscript } from './render.ts' +export { toolPairingBalancedAfter, toolPairingBalancedBefore } from './tool-pairing.ts' /** Minimal agent context compaction needs without depending on the agent package. */ export interface CompactAgentContext { @@ -67,6 +68,8 @@ export abstract class CompactService extends Service { * balanced so assistant tool calls remain paired with their results. A model- * backed implementation forwards cancellation and rejects active, missing, * reversed, or unbalanced ranges. + * Use {@link toolPairingBalancedBefore} and {@link toolPairingBalancedAfter} + * for the edge checks. * * @param session - session to mutate. * @param start - first surface seq, inclusive. diff --git a/packages/compact/compact/src/tool-pairing.ts b/packages/compact/compact/src/tool-pairing.ts new file mode 100644 index 0000000000..a9fca01bf6 --- /dev/null +++ b/packages/compact/compact/src/tool-pairing.ts @@ -0,0 +1,160 @@ +/** + * Tool-pairing balance over a session surface. Compaction changes surface + * positions, so safe cuts are derived from tool-call/result content in current + * surface order rather than step markers or linked-list fields supplied by a + * caller. + * @module @deepseek-ai/dsh-compact/tool-pairing + */ + +import type { Session, SessionEvent, SurfaceNode } from '@deepseek-ai/dsh-session' + +/** Incremental balance state for one session surface generation. */ +interface BalanceCache { + /** Surface rewrite generation this state describes. */ + generation: number + /** Number of surface nodes already folded into the state. */ + processedNodes: number + /** Balance of the cut immediately before each current surface node. */ + beforeSeq: Map + /** Current positional successor of each surface node. */ + successorBySeq: Map + /** Unanswered tool-call count after the processed surface tail. */ + depth: number +} + +const balanceCacheBySession = new WeakMap() + +/** Return how one surface event changes the unanswered tool-call count. */ +function nodeDelta(event: SessionEvent): number { + switch (event.type) { + case 'assistant/message': + return event.data.content.filter(block => block.type === 'tool-call').length + case 'tool/result': + return -1 + default: + return 0 + } +} + +/** Read and validate the event named by a surface node. */ +function eventForNode(events: readonly SessionEvent[], node: SurfaceNode): SessionEvent { + const event = events[node.seq] + if (event === undefined || event.seq !== node.seq) { + throw new Error(`tool-pairing balance: surface seq ${node.seq} has no matching session event (corrupt surface)`) + } + return event +} + +/** Build balance state for a complete current surface. */ +function rebuildCache( + session: Session, + nodes: readonly SurfaceNode[], + generation: number, +): BalanceCache { + const beforeSeq = new Map() + const successorBySeq = new Map() + const events = session.events + let depth = 0 + let previousSeq: number | undefined + + for (const node of nodes) { + beforeSeq.set(node.seq, depth === 0) + successorBySeq.set(node.seq, null) + if (previousSeq !== undefined) successorBySeq.set(previousSeq, node.seq) + depth += nodeDelta(eventForNode(events, node)) + if (depth < 0) { + throw new Error(`tool-pairing balance: tool/result at surface seq ${node.seq} has no matching tool-call (corrupt surface)`) + } + previousSeq = node.seq + } + + return { generation, processedNodes: nodes.length, beforeSeq, successorBySeq, depth } +} + +/** Fold a pure surface tail append into existing balance state. */ +function extendCache( + session: Session, + cache: BalanceCache, + nodes: readonly SurfaceNode[], +): BalanceCache { + const tail = nodes.slice(cache.processedNodes) + // Validate the unseen tail before mutating the live cache, so a corrupt + // append cannot leave a partially advanced state behind. + const events = session.events + const pending: Array<{ seq: number; before: boolean }> = [] + let depth = cache.depth + for (const node of tail) { + pending.push({ seq: node.seq, before: depth === 0 }) + depth += nodeDelta(eventForNode(events, node)) + if (depth < 0) { + throw new Error(`tool-pairing balance: tool/result at surface seq ${node.seq} has no matching tool-call (corrupt surface)`) + } + } + + let previousSeq = nodes[cache.processedNodes - 1]?.seq + for (const entry of pending) { + if (previousSeq !== undefined) cache.successorBySeq.set(previousSeq, entry.seq) + cache.beforeSeq.set(entry.seq, entry.before) + cache.successorBySeq.set(entry.seq, null) + previousSeq = entry.seq + } + cache.processedNodes = nodes.length + cache.depth = depth + return cache +} + +/** Return balance state synchronized with the current session surface. */ +function balanceCache(session: Session): BalanceCache { + const surface = session.surface + const nodes = surface.nodes + const generation = surface.replaceGeneration + const cached = balanceCacheBySession.get(session) + + if (cached === undefined || cached.generation !== generation || cached.processedNodes > nodes.length) { + const rebuilt = rebuildCache(session, nodes, generation) + balanceCacheBySession.set(session, rebuilt) + return rebuilt + } + if (cached.processedNodes < nodes.length) return extendCache(session, cached, nodes) + return cached +} + +/** + * Whether the cut immediately before a current surface node is tool-pairing balanced. + * @param session - session whose surface is checked. + * @param node - surface node whose leading cut is checked; only its seq identifies it. + * @returns true when no unanswered tool call crosses the cut. + * @throws when the seq is absent from the current surface, a surface node has no + * matching log event, or a tool result has no preceding open call. + */ +export function toolPairingBalancedBefore(session: Session, node: SurfaceNode): boolean { + const cache = balanceCache(session) + const balanced = cache.beforeSeq.get(node.seq) + if (balanced === undefined) { + throw new Error(`tool-pairing balance: surface seq ${node.seq} not found`) + } + return balanced +} + +/** + * Whether the cut immediately after a current surface node is tool-pairing balanced. + * @param session - session whose surface is checked. + * @param node - surface node whose trailing cut is checked; only its seq identifies it. + * @returns true when no unanswered tool call crosses the cut. + * @throws when the seq is absent from the current surface, a surface node has no + * matching log event, or a tool result has no preceding open call. + */ +export function toolPairingBalancedAfter(session: Session, node: SurfaceNode): boolean { + const cache = balanceCache(session) + const successor = cache.successorBySeq.get(node.seq) + if (successor === undefined) { + throw new Error(`tool-pairing balance: surface seq ${node.seq} not found`) + } + if (successor === null) return cache.depth === 0 + // Current membership and positional successors are cache-owned. A caller may + // retain a node across surface changes, so its mutable-looking `next` field is + // never authoritative for this query. + // The successor map and balance map are committed together. + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + return cache.beforeSeq.get(successor)! +} diff --git a/packages/compact/compact/tests/tool-pairing.spec.ts b/packages/compact/compact/tests/tool-pairing.spec.ts new file mode 100644 index 0000000000..dfde2bd2ba --- /dev/null +++ b/packages/compact/compact/tests/tool-pairing.spec.ts @@ -0,0 +1,327 @@ +import { describe, expect, it } from 'vitest' +import { CallId } from '@deepseek-ai/dsh-llm' +import { toolPairingBalancedAfter, toolPairingBalancedBefore } from '@deepseek-ai/dsh-compact' +import { Session, SessionId } from '@deepseek-ai/dsh-session' +import type { SessionEvent, SurfaceNode } from '@deepseek-ai/dsh-session' + +const SURFACE = { surfaceOp: 'append' as const } + +function seqOf(session: Session, type: SessionEvent['type'], nth = 0): number { + return session.events.filter(event => event.type === type)[nth]!.seq +} + +function nodeAt(session: Session, seq: number): SurfaceNode { + const node = session.surface.nodes.find(candidate => candidate.seq === seq) + if (node === undefined) throw new Error(`seq ${seq} is not a surface node`) + return node +} + +function before(session: Session, type: SessionEvent['type'], nth = 0): boolean { + return toolPairingBalancedBefore(session, nodeAt(session, seqOf(session, type, nth))) +} + +function after(session: Session, type: SessionEvent['type'], nth = 0): boolean { + return toolPairingBalancedAfter(session, nodeAt(session, seqOf(session, type, nth))) +} + +function closedToolStep(): Session { + const session = new Session(SessionId('closed-tool-step')) + session.append('user/message', { + content: [{ type: 'text', text: 'go' }], + source: { kind: 'user' }, + }, SURFACE) + session.append('assistant/message', { + turn: 1, + step: 1, + content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], + }, SURFACE) + session.append('tool/result', { + turn: 1, + step: 1, + callId: CallId('c1'), + content: [{ type: 'text', text: 'done' }], + isError: false, + }, SURFACE) + return session +} + +describe('tool-pairing boundaries', () => { + it('classifies closed and open single-call steps', () => { + const closed = closedToolStep() + expect(before(closed, 'user/message')).toBe(true) + expect(after(closed, 'user/message')).toBe(true) + expect(before(closed, 'assistant/message')).toBe(true) + expect(after(closed, 'assistant/message')).toBe(false) + expect(before(closed, 'tool/result')).toBe(false) + expect(after(closed, 'tool/result')).toBe(true) + + const open = new Session(SessionId('open-tool-step')) + open.append('assistant/message', { + turn: 1, + step: 1, + content: [{ type: 'tool-call', id: CallId('open'), name: 'bash', arguments: '{}' }], + }, SURFACE) + expect(toolPairingBalancedAfter(open, open.surface.nodes[0]!)).toBe(false) + }) + + it('requires every result from a multiple-call assistant message', () => { + const session = new Session(SessionId('multiple-calls')) + session.append('assistant/message', { + turn: 1, + step: 1, + content: [ + { type: 'tool-call', id: CallId('c1'), name: 'one', arguments: '{}' }, + { type: 'tool-call', id: CallId('c2'), name: 'two', arguments: '{}' }, + ], + }, SURFACE) + session.append('tool/result', { + turn: 1, step: 1, callId: CallId('c1'), content: [], isError: false, + }, SURFACE) + session.append('tool/result', { + turn: 1, step: 1, callId: CallId('c2'), content: [], isError: false, + }, SURFACE) + + expect(after(session, 'tool/result', 0)).toBe(false) + expect(after(session, 'tool/result', 1)).toBe(true) + }) + + it('keeps neutral nodes inside an open pair unbalanced and free nodes balanced', () => { + const midStep = new Session(SessionId('neutral-mid-step')) + midStep.append('assistant/message', { + turn: 1, + step: 1, + content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], + }, SURFACE) + midStep.append('context/message', { + content: [{ type: 'text', text: 'background update' }], + source: { kind: 'plugin', plugin: 'test' }, + }, SURFACE) + midStep.append('tool/result', { + turn: 1, step: 1, callId: CallId('c1'), content: [], isError: false, + }, SURFACE) + expect(before(midStep, 'context/message')).toBe(false) + expect(after(midStep, 'context/message')).toBe(false) + + const free = new Session(SessionId('neutral-free')) + free.append('context/message', { + content: [{ type: 'text', text: 'idle injection' }], + source: { kind: 'user' }, + }, SURFACE) + expect(before(free, 'context/message')).toBe(true) + expect(after(free, 'context/message')).toBe(true) + }) +}) + +describe('tool-pairing surface identity', () => { + it('rebuilds after replace and rejects nodes removed from current membership', () => { + const session = closedToolStep() + const staleTail = nodeAt(session, seqOf(session, 'tool/result')) + expect(toolPairingBalancedAfter(session, staleTail)).toBe(true) + + const nodes = session.surface.nodes + session.append('user/message', { + content: [{ type: 'text', text: 'checkpoint' }], + source: { kind: 'plugin', plugin: 'compact' }, + }, { surfaceOp: { op: 'replace', start: nodes[0]!.seq, end: nodes.at(-1)!.seq } }) + + const checkpoint = session.surface.nodes[0]! + expect(toolPairingBalancedBefore(session, checkpoint)).toBe(true) + expect(toolPairingBalancedAfter(session, checkpoint)).toBe(true) + expect(() => toolPairingBalancedBefore(session, staleTail)).toThrow(/surface seq .* not found/) + expect(() => toolPairingBalancedAfter(session, staleTail)).toThrow(/surface seq .* not found/) + }) + + it('uses the cached positional successor instead of a caller node next field', () => { + const session = closedToolStep() + const assistant = nodeAt(session, seqOf(session, 'assistant/message')) + expect(toolPairingBalancedAfter(session, { ...assistant, next: null })).toBe(false) + expect(toolPairingBalancedAfter(session, { ...assistant, next: 999 })).toBe(false) + }) + + it('rejects missing seqs before and after, including an empty surface', () => { + const session = new Session(SessionId('missing-membership')) + const missing: SurfaceNode = { seq: 999, prev: null, next: null } + expect(() => toolPairingBalancedBefore(session, missing)).toThrow(/surface seq 999 not found/) + expect(() => toolPairingBalancedAfter(session, missing)).toThrow(/surface seq 999 not found/) + + session.append('user/message', { + content: [{ type: 'text', text: 'first node after empty cache' }], + source: { kind: 'user' }, + }, SURFACE) + expect(toolPairingBalancedAfter(session, session.surface.nodes[0]!)).toBe(true) + }) +}) + +describe('tool-pairing cache refresh', () => { + it('does no event reads for unchanged or log-only growth, folds only appended nodes, and rebuilds on replace', () => { + const events: SessionEvent[] = [ + { + type: 'user/message', seq: 0, time: 0, + data: { content: [{ type: 'text', text: 'user' }], source: { kind: 'user' } }, + surfaceOp: 'append', + }, + { + type: 'assistant/message', seq: 1, time: 1, + data: { turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c1'), name: 'one', arguments: '{}' }] }, + surfaceOp: 'append', + }, + { + type: 'tool/result', seq: 2, time: 2, + data: { turn: 1, step: 1, callId: CallId('c1'), content: [], isError: false }, + surfaceOp: 'append', + }, + ] + const nodes: SurfaceNode[] = [ + { seq: 0, prev: null, next: 1 }, + { seq: 1, prev: 0, next: 2 }, + { seq: 2, prev: 1, next: null }, + ] + let generation = 0 + let eventCollectionReads = 0 + let eventIndexReads = 0 + const trackedEvents = new Proxy(events, { + get(target, property, receiver) { + if (typeof property === 'string' && /^\d+$/.test(property)) eventIndexReads += 1 + return Reflect.get(target, property, receiver) as unknown + }, + }) + const surface = { + get nodes() { return nodes }, + get replaceGeneration() { return generation }, + } + const session = { + surface, + get events() { + eventCollectionReads += 1 + return trackedEvents + }, + } as unknown as Session + + expect(toolPairingBalancedAfter(session, nodes[2]!)).toBe(true) + expect(eventCollectionReads).toBe(1) + expect(eventIndexReads).toBe(3) + + expect(toolPairingBalancedBefore(session, nodes[0]!)).toBe(true) + expect(toolPairingBalancedAfter(session, nodes[1]!)).toBe(false) + expect(eventCollectionReads).toBe(1) + expect(eventIndexReads).toBe(3) + + events.push({ + type: 'turn/end', seq: 3, time: 3, + data: { turn: 1, reason: { kind: 'completed' } }, + }) + expect(toolPairingBalancedAfter(session, nodes[2]!)).toBe(true) + expect(eventCollectionReads).toBe(1) + expect(eventIndexReads).toBe(3) + + events.push({ + type: 'user/message', seq: 4, time: 4, + data: { content: [{ type: 'text', text: 'tail' }], source: { kind: 'user' } }, + surfaceOp: 'append', + }) + nodes.push({ seq: 4, prev: 2, next: null }) + expect(toolPairingBalancedAfter(session, nodes[3]!)).toBe(true) + expect(eventCollectionReads).toBe(2) + expect(eventIndexReads).toBe(4) + + events.push( + { + type: 'assistant/message', seq: 5, time: 5, + data: { turn: 2, step: 1, content: [{ type: 'tool-call', id: CallId('c2'), name: 'two', arguments: '{}' }] }, + surfaceOp: 'append', + }, + { + type: 'tool/result', seq: 6, time: 6, + data: { turn: 2, step: 1, callId: CallId('c2'), content: [], isError: false }, + surfaceOp: 'append', + }, + ) + nodes.push( + { seq: 5, prev: 4, next: 6 }, + { seq: 6, prev: 5, next: null }, + ) + expect(toolPairingBalancedAfter(session, nodes[5]!)).toBe(true) + expect(eventCollectionReads).toBe(3) + expect(eventIndexReads).toBe(6) + + events.push({ + type: 'user/message', seq: 7, time: 7, + data: { content: [{ type: 'text', text: 'replacement' }], source: { kind: 'user' } }, + surfaceOp: { op: 'replace', start: 0, end: 6 }, + }) + nodes.splice(0, nodes.length, { seq: 7, prev: null, next: null }) + generation += 1 + expect(toolPairingBalancedAfter(session, nodes[0]!)).toBe(true) + expect(eventCollectionReads).toBe(4) + expect(eventIndexReads).toBe(7) + }) + + it('rebuilds defensively when a same-generation surface node count regresses', () => { + const events: SessionEvent[] = [ + { + type: 'user/message', seq: 0, time: 0, + data: { content: [], source: { kind: 'user' } }, surfaceOp: 'append', + }, + { + type: 'user/message', seq: 1, time: 1, + data: { content: [], source: { kind: 'user' } }, surfaceOp: 'append', + }, + ] + const nodes: SurfaceNode[] = [ + { seq: 0, prev: null, next: 1 }, + { seq: 1, prev: 0, next: null }, + ] + const session = { + events, + surface: { nodes, replaceGeneration: 0 }, + } as unknown as Session + expect(toolPairingBalancedAfter(session, nodes[1]!)).toBe(true) + nodes.pop() + expect(toolPairingBalancedAfter(session, nodes[0]!)).toBe(true) + }) +}) + +describe('tool-pairing corrupt surfaces', () => { + it('throws for an orphan result during a rebuild', () => { + const session = new Session(SessionId('orphan-rebuild')) + session.append('tool/result', { + turn: 1, step: 1, callId: CallId('orphan'), content: [], isError: false, + }, SURFACE) + expect(() => toolPairingBalancedAfter(session, session.surface.nodes[0]!)).toThrow(/no matching tool-call/) + }) + + it('retries an orphan result in an appended tail without committing partial cache state', () => { + const session = new Session(SessionId('orphan-tail')) + session.append('user/message', { + content: [{ type: 'text', text: 'safe head' }], source: { kind: 'user' }, + }, SURFACE) + expect(toolPairingBalancedAfter(session, session.surface.nodes[0]!)).toBe(true) + session.append('tool/result', { + turn: 1, step: 1, callId: CallId('orphan'), content: [], isError: false, + }, SURFACE) + expect(() => toolPairingBalancedAfter(session, session.surface.nodes[1]!)).toThrow(/no matching tool-call/) + expect(() => toolPairingBalancedAfter(session, session.surface.nodes[1]!)).toThrow(/no matching tool-call/) + }) + + it('throws when a current surface seq has no matching event or indexes the wrong event', () => { + const missingNode: SurfaceNode = { seq: 1, prev: null, next: null } + const missing = { + events: [{ + type: 'user/message', seq: 0, time: 0, + data: { content: [], source: { kind: 'user' } }, surfaceOp: 'append', + } satisfies SessionEvent], + surface: { nodes: [missingNode], replaceGeneration: 0 }, + } as unknown as Session + expect(() => toolPairingBalancedBefore(missing, missingNode)).toThrow(/no matching session event/) + + const mismatchedNode: SurfaceNode = { seq: 0, prev: null, next: null } + const mismatched = { + events: [{ + type: 'user/message', seq: 99, time: 0, + data: { content: [], source: { kind: 'user' } }, surfaceOp: 'append', + } satisfies SessionEvent], + surface: { nodes: [mismatchedNode], replaceGeneration: 0 }, + } as unknown as Session + expect(() => toolPairingBalancedBefore(mismatched, mismatchedNode)).toThrow(/no matching session event/) + }) +}) diff --git a/packages/core/session/README.md b/packages/core/session/README.md index 7e201ab647..2540f988c7 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -77,7 +77,7 @@ Every `SessionEvent` carries two optional top-level fields (structural metadata) - Persistence plugins: subscribe to `session/event` (write-behind) and drain on `session/flush` (awaited) and fiber dispose. A durable backend reads the log and reloads it into a live session; the metadata seam (`SessionHeader`, `session.header`) is what such a backend stores beside the log. - Replay/fork: `create(id, { seed })` validates and freezes a contiguous log and rebuilds its surface. `fork(source, boundary?, childSessionId?)` selects a completed-turn prefix and records lineage. -- Compaction: the `dsh-compact-basic` plugin appends a `user/message` with `surfaceOp: { op: 'replace', start, end }` to shadow old surface nodes behind a summary checkpoint. +- Compaction: the `dsh-compact-basic` plugin appends a `user/message` with `surfaceOp: { op: 'replace', start, end }` to shadow old surface nodes behind a summary checkpoint. Tool-pairing boundary policy and its cache belong to the [`dsh-compact` seam](../../compact/compact/README.md), while this package owns surface membership, positional links, and `replaceGeneration`. ## Model Experience diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index 89f1627445..c3c99ae885 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -24,7 +24,6 @@ export type { JsonValue } from './json.ts' export { interruptedTurnClosers } from './repair.ts' export type { SurfaceFoldReplacement, SurfaceFoldResult, SurfaceNode } from './surface.ts' export { foldSurface, isSurfaceEvent, isSurfaceEligibleType } from './surface.ts' -export { isToolPairingBalanced } from './tool-pairing.ts' export { applyHeaderDelta, canonicalHeader, diffHeader, foldRequestHeader, headerEquals } from './request-header.ts' declare module 'cordis' { diff --git a/packages/core/session/src/tool-pairing.ts b/packages/core/session/src/tool-pairing.ts deleted file mode 100644 index ce9dc639c7..0000000000 --- a/packages/core/session/src/tool-pairing.ts +++ /dev/null @@ -1,56 +0,0 @@ -/** - * Tool-pairing balance over a session surface. Compaction changes surface - * positions, so safe cuts are derived from tool-call/result content on the - * surface rather than step markers in the append-only log. - * @module @deepseek-ai/dsh-session/tool-pairing - */ - -import type { SessionEvent } from './types.ts' -import type { SurfaceNode } from './surface.ts' - -/** - * The tool-pairing delta of a surface node: how it shifts the count of - * unanswered tool calls. An `assistant/message` opens one bracket per - * `tool-call` block; a `tool/result` closes one; every other surface node - * (`user/message`, `context/message`, `steering/message`, a usage-only - * `assistant/message` with no tool-call blocks) is pairing-neutral. - */ -function nodeDelta(event: SessionEvent): number { - switch (event.type) { - case 'assistant/message': - return event.data.content.filter(block => block.type === 'tool-call').length - case 'tool/result': - return -1 - // Non-pairing surface nodes and every non-surface event contribute nothing. - default: - return 0 - } -} - -/** - * Check that a surface cut does not split a tool call from its result. A region - * is safe to collapse only when the cuts before its first node and after its - * last node both return `true`. - * @param nodes - the surface linked list in head→tail order. - * @param events - the session log each node's `seq` indexes into. - * @param beforeSeq - node immediately after the cut; `null` or a seq absent from the surface means after-tail. - * @returns whether every call before the cut has its result before the cut. - * @throws if a result appears without a preceding open call. - */ -export function isToolPairingBalanced( - nodes: readonly SurfaceNode[], - events: readonly SessionEvent[], - beforeSeq: number | null, -): boolean { - let depth = 0 - for (const node of nodes) { - if (node.seq === beforeSeq) return depth === 0 - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - depth += nodeDelta(events[node.seq]!) - if (depth < 0) { - throw new Error(`tool-pairing balance: tool/result at surface seq ${node.seq} has no matching tool-call (corrupt surface)`) - } - } - // A missing cut node means the after-tail boundary. - return depth === 0 -} diff --git a/packages/core/session/tests/tool-pairing.spec.ts b/packages/core/session/tests/tool-pairing.spec.ts deleted file mode 100644 index eb7b1a6203..0000000000 --- a/packages/core/session/tests/tool-pairing.spec.ts +++ /dev/null @@ -1,292 +0,0 @@ -import { describe, expect, it } from 'vitest' -import { CallId } from '@deepseek-ai/dsh-llm' -import { Session, SessionId, isToolPairingBalanced } from '../src/index.ts' -import type { SessionEvent, SurfaceNode } from '../src/index.ts' - -/** - * Unit coverage for compaction-cut safety: a cut is balanced only when it - * separates no assistant tool call from its result. Non-step nodes are neutral, - * and replace operations prove surface order—not raw log order—is authoritative. - */ - -const SURFACE = { surfaceOp: 'append' as const } - -/** Surface nodes + log for a session, the two args the balance check takes. */ -function surfaceOf(session: Session): { nodes: readonly SurfaceNode[]; events: readonly SessionEvent[] } { - return { nodes: session.surface.nodes, events: session.events } -} - -/** The cut BEFORE the surface node at `seq` is balanced (safe region start). */ -function startBalanced(session: Session, seq: number): boolean { - const { nodes, events } = surfaceOf(session) - return isToolPairingBalanced(nodes, events, seq) -} - -/** The cut AFTER the surface node at `seq` is balanced (safe region end). */ -function endBalanced(session: Session, seq: number): boolean { - const { nodes, events } = surfaceOf(session) - const node = nodes.find(n => n.seq === seq) - if (!node) throw new Error(`seq ${seq} is not a surface node`) - return isToolPairingBalanced(nodes, events, node.next) -} - -/** Surface seq of the nth (0-based) event of a given type. */ -function seqOf(s: Session, type: SessionEvent['type'], nth = 0): number { - return s.events.filter(e => e.type === type)[nth]!.seq -} - -/** A closed turn with one closed step holding an assistant + its tool result. */ -function toolStepSession(): Session { - const s = new Session(SessionId('tool-step')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('user/message', { content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }, SURFACE) - s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { - turn: 1, step: 1, - content: [ - { type: 'text', text: 'calling' }, - { type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }, - ], - }, SURFACE) - s.append('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'bash', arguments: '{}' }) - s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'out' }], isError: false }, SURFACE) - s.append('step/end', { turn: 1, step: 1 }) - s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - return s -} - -describe('isToolPairingBalanced — region START (cut before a node)', () => { - it('is true for a pre-step user/message (belongs to no step)', () => { - const s = toolStepSession() - expect(startBalanced(s, seqOf(s, 'user/message'))).toBe(true) - }) - - it('is true for the first surface node of a step (the assistant/message)', () => { - // The cut before the assistant is balanced — nothing unanswered precedes it. - const s = toolStepSession() - expect(startBalanced(s, seqOf(s, 'assistant/message'))).toBe(true) - }) - - it('is false for a tool/result whose assistant/message precedes it in the same step', () => { - // The cut before the tool/result has one unanswered tool-call (the - // assistant's) → starting the region here would orphan that call. - const s = toolStepSession() - expect(startBalanced(s, seqOf(s, 'tool/result'))).toBe(false) - }) - - it('is true at the surface head (nothing precedes)', () => { - const s = new Session(SessionId('lone')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, SURFACE) - expect(startBalanced(s, seqOf(s, 'user/message'))).toBe(true) - }) -}) - -describe('isToolPairingBalanced — region END (cut after a node)', () => { - it('is true for the last surface node of a closed step (the tool/result)', () => { - // After the tool/result the assistant's single call is answered → balanced. - const s = toolStepSession() - expect(endBalanced(s, seqOf(s, 'tool/result'))).toBe(true) - }) - - it('is false for an assistant/message with a later tool/result in the same step', () => { - // After the assistant its tool-call is still unanswered → ending here strands - // the result. - const s = toolStepSession() - expect(endBalanced(s, seqOf(s, 'assistant/message'))).toBe(false) - }) - - it('is true for a pre-step user/message', () => { - const s = toolStepSession() - expect(endBalanced(s, seqOf(s, 'user/message'))).toBe(true) - }) - - it('is false at the tail when the node is inside an open (unclosed) step', () => { - // step/start then an assistant tool-call, but no tool/result yet (mid-flight). - // The after-tail cut still has one unanswered call → not balanced. - const s = new Session(SessionId('open-step')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { - turn: 1, step: 1, - content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], - }, SURFACE) - expect(endBalanced(s, seqOf(s, 'assistant/message'))).toBe(false) - }) - - it('is true at the tail when the node is a trailing inter-step node (step already closed)', () => { - // A steering message appended after step/end, at the tail. The prior step's - // pair is balanced and steering is neutral → the after-tail cut is balanced. - const s = new Session(SessionId('trailing-steer')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, SURFACE) - s.append('step/end', { turn: 1, step: 1 }) - s.append('steering/message', { turn: 1, content: [{ type: 'text', text: 's' }], source: { kind: 'user' } }, SURFACE) - expect(endBalanced(s, seqOf(s, 'steering/message'))).toBe(true) - }) - - it('is true at the tail when no step ever opened', () => { - const s = new Session(SessionId('no-step')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, SURFACE) - expect(endBalanced(s, seqOf(s, 'user/message'))).toBe(true) - }) -}) - -describe('isToolPairingBalanced — multiple tool calls in one assistant message', () => { - // An assistant message with two tool-calls needs BOTH results before the cut - // after it is balanced — depth +2, then -1, -1. - function twoCallStep(): Session { - const s = new Session(SessionId('two-call')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { - turn: 1, step: 1, - content: [ - { type: 'tool-call', id: CallId('c1'), name: 'a', arguments: '{}' }, - { type: 'tool-call', id: CallId('c2'), name: 'b', arguments: '{}' }, - ], - }, SURFACE) - s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: '1' }], isError: false }, SURFACE) - s.append('tool/result', { turn: 1, step: 1, callId: CallId('c2'), content: [{ type: 'text', text: '2' }], isError: false }, SURFACE) - s.append('step/end', { turn: 1, step: 1 }) - s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - return s - } - - it('is unbalanced after the first of two results (one call still open)', () => { - const s = twoCallStep() - expect(endBalanced(s, seqOf(s, 'tool/result', 0))).toBe(false) - }) - - it('is balanced after the second result (both calls answered)', () => { - const s = twoCallStep() - expect(endBalanced(s, seqOf(s, 'tool/result', 1))).toBe(true) - }) -}) - -describe('isToolPairingBalanced — a mid-step injection context/message', () => { - // The injected context is pairing-neutral, but both adjacent cuts remain - // unbalanced because the tool call is still open across them. - function midStepInjection(): Session { - const s = new Session(SessionId('mid-inject')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { - turn: 1, step: 1, - content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], - }, SURFACE) - s.append('context/message', { content: [{ type: 'text', text: 'bg task done' }], source: { kind: 'plugin', plugin: 'tool-bash' } }, SURFACE) - s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'out' }], isError: false }, SURFACE) - s.append('step/end', { turn: 1, step: 1 }) - s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - return s - } - - it('start cut before the mid-step context/message is unbalanced (call still open)', () => { - const s = midStepInjection() - expect(startBalanced(s, seqOf(s, 'context/message'))).toBe(false) - }) - - it('end cut after the mid-step context/message is unbalanced (call still open)', () => { - const s = midStepInjection() - expect(endBalanced(s, seqOf(s, 'context/message'))).toBe(false) - }) -}) - -describe('isToolPairingBalanced on an injection turn (no step)', () => { - // An idle inject() wraps a context/message in a bare turn/start → - // context/message → turn/end with NO step. The context node is a free boundary - // both ways (pairing-neutral, nothing open around it). - function injectionSession(): Session { - const s = new Session(SessionId('injection')) - s.append('turn/start', { turn: 1, trigger: { kind: 'injection', source: { kind: 'user' } } }) - s.append('context/message', { content: [{ type: 'text', text: 'ctx' }], source: { kind: 'user' } }, SURFACE) - s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - return s - } - - it('start: balanced', () => { - const s = injectionSession() - expect(startBalanced(s, seqOf(s, 'context/message'))).toBe(true) - }) - - it('end: balanced', () => { - const s = injectionSession() - expect(endBalanced(s, seqOf(s, 'context/message'))).toBe(true) - }) -}) - -describe('isToolPairingBalanced — CBR-001: a head checkpoint left by a replace op', () => { - // A replacement checkpoint has a high log seq but sits at the surface head; - // its cuts are balanced regardless of later raw-log neighbors. - function checkpointHeadedSession(): Session { - const s = new Session(SessionId('checkpoint')) - // A closed turn with a tool step → surface [u1, asst(call), result]. - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - s.append('user/message', { content: [{ type: 'text', text: 'u1' }], source: { kind: 'user' } }, SURFACE) - s.append('assistant/message', { - turn: 1, step: 1, - content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], - }, SURFACE) - s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'out' }], isError: false }, SURFACE) - s.append('step/end', { turn: 1, step: 1 }) - s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - // An OPEN turn whose step is in progress (loop fires compaction here). - s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 2, step: 1 }) - // Compaction replaces the whole turn-1 surface ([u1, asst, result]) with one - // summary user/message — appended now, so it carries a high log seq. - const u1 = seqOf(s, 'user/message') - const result = s.events.find(e => e.type === 'tool/result')!.seq - s.append('user/message', { - content: [{ type: 'text', text: 'CHECKPOINT' }], - source: { kind: 'plugin', plugin: 'compact' }, - }, { surfaceOp: { op: 'replace', start: u1, end: result } }) - // The step's own assistant/message lands AFTER the checkpoint in the log, - // still inside the open step. - s.append('assistant/message', { turn: 2, step: 1, content: [{ type: 'text', text: 'a2' }] }, SURFACE) - return s - } - - it('the head checkpoint sits at the surface head while a later surface node follows it in the log', () => { - const s = checkpointHeadedSession() - const nodes = s.surface.nodes - const checkpointSeq = nodes[0]!.seq - // The checkpoint heads the surface, yet a surface node (the open step's - // assistant) follows it in LOG order — the exact split between surface - // position and log position that the log-position scan tripped on. - const laterSurfaceInLog = s.events.find( - e => e.seq > checkpointSeq && nodes.some(n => n.seq === e.seq), - ) - expect(laterSurfaceInLog).toBeDefined() - expect(nodes[0]!.seq).toBe(checkpointSeq) - }) - - it('start cut before the head checkpoint is balanced (it is the head)', () => { - const s = checkpointHeadedSession() - expect(startBalanced(s, s.surface.nodes[0]!.seq)).toBe(true) - }) - - it('end cut after the head checkpoint is balanced (it carries no tool pair)', () => { - // This is the exact assertion the log-position scan failed: the forward log scan from the - // checkpoint reached the open step's assistant/message and wrongly reported mid-step. - const s = checkpointHeadedSession() - expect(endBalanced(s, s.surface.nodes[0]!.seq)).toBe(true) - }) -}) - -describe('isToolPairingBalanced — corrupt surface guard', () => { - it('throws when a tool/result has no preceding tool-call (depth goes negative)', () => { - // A surface that opens with a tool/result (no assistant call before it) is - // structurally corrupt — surfaced loudly rather than mis-classified. - const s = new Session(SessionId('corrupt')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'x' }], isError: false }, SURFACE) - const { nodes, events } = surfaceOf(s) - expect(() => isToolPairingBalanced(nodes, events, null)).toThrow(/no matching tool-call/) - }) -}) From f1d39921c9e3434f166ee106c01d7eeae362f389 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Wed, 15 Jul 2026 13:33:42 +0800 Subject: [PATCH 135/359] feat(acp): advertise and switch llm models --- docs/architecture.md | 2 +- docs/config-catalog.md | 42 ++- docs/cordis-catalog/services.md | 5 +- docs/core-data-structures/core.md | 24 ++ docs/core-data-structures/llm-streaming.md | 2 +- docs/event-producer-consumer.md | 28 +- docs/module-graph.md | 3 +- docs/rfc/INDEX.md | 1 + ...-14-provider-routed-llm-adapters.i18n.yaml | 4 +- ...2026-07-14-provider-routed-llm-adapters.md | 2 +- ...6-07-14-provider-routed-llm-adapters.zh.md | 2 +- ...-model-catalog-and-acp-selection.i18n.yaml | 6 + ...-15-llm-model-catalog-and-acp-selection.md | 66 +++++ ...-llm-model-catalog-and-acp-selection.zh.md | 66 +++++ .../2026-06-14-acp-agent-client-protocol.md | 2 +- .../acp-agent/advanced.cordis.snapshot.yml | 7 + .../acp-agent/both-mode.cordis.snapshot.yml | 7 + .../acp-agent/code-mode.cordis.snapshot.yml | 7 + examples/acp-agent/cordis.snapshot.yml | 7 + examples/acp-agent/fs.cordis.snapshot.yml | 7 + examples/acp-agent/tests/acp.snapshot.ts | 17 +- .../advanced-toolchain/stdout.golden.jsonl | 2 +- .../both-mode-turn/stdout.golden.jsonl | 2 +- .../snapshots/cancel/stdout.golden.jsonl | 2 +- .../code-mode-turn/stdout.golden.jsonl | 2 +- .../config-options/stdout.golden.jsonl | 6 +- .../error-finish/stdout.golden.jsonl | 2 +- .../escalation-approved/stdout.golden.jsonl | 4 +- .../escalation-rejected/stdout.golden.jsonl | 4 +- .../snapshots/fs-edit/stdout.golden.jsonl | 2 +- .../fs-policy-reject/stdout.golden.jsonl | 2 +- .../fs-read-window/stdout.golden.jsonl | 2 +- .../snapshots/fs-read/stdout.golden.jsonl | 2 +- .../fs-terminal-card/stdout.golden.jsonl | 2 +- .../fs-write-overwrite/stdout.golden.jsonl | 2 +- .../snapshots/fs-write/stdout.golden.jsonl | 2 +- .../snapshots/handshake/stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../hook-cc-pretool-ask/stdout.golden.jsonl | 2 +- .../hook-cc-pretool-deny/stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../hook-cc-stop-continue/stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../snapshots/model-switching/input.json | 23 ++ .../snapshots/model-switching/session.jsonl | 69 +++++ .../model-switching/stdout.golden.jsonl | 47 ++++ .../model-switching/system-prompt.golden.md | 17 ++ .../model-switching/tool-schemas.golden.json | 249 ++++++++++++++++++ .../snapshots/multi-turn/stdout.golden.jsonl | 2 +- .../permission-switching/stdout.golden.jsonl | 6 +- .../repeat-tool-guard/stdout.golden.jsonl | 2 +- .../snapshots/skill-load/stdout.golden.jsonl | 2 +- .../subagent-fork/stdout.golden.jsonl | 2 +- .../subagent-mixed/stdout.golden.jsonl | 2 +- .../subagent-multi/stdout.golden.jsonl | 2 +- .../subagent-spawn/stdout.golden.jsonl | 2 +- .../snapshots/text-turn/stdout.golden.jsonl | 2 +- .../snapshots/todo-plan/stdout.golden.jsonl | 2 +- .../tool-call-turn/stdout.golden.jsonl | 2 +- .../workflow-run/stdout.golden.jsonl | 2 +- .../workspace-edit/stdout.golden.jsonl | 2 +- .../cordis/tool-cordis/src/api-catalog.ts | 11 +- .../tests/contract-regressions.spec.ts | 2 +- packages/llm/llm-deepseek/README.md | 7 +- packages/llm/llm-deepseek/src/adapter.ts | 27 +- packages/llm/llm-deepseek/src/index.ts | 36 ++- .../llm/llm-deepseek/tests/adapter.spec.ts | 74 +++++- packages/llm/llm-pi-ai/README.md | 2 + packages/llm/llm-pi-ai/src/adapter.ts | 14 +- packages/llm/llm-pi-ai/tests/adapter.spec.ts | 19 +- packages/llm/llm/README.md | 7 +- packages/llm/llm/src/index.ts | 85 +++++- packages/llm/llm/src/types.ts | 20 ++ packages/llm/llm/tests/service.spec.ts | 106 +++++++- packages/support/llm-replay/README.md | 14 +- packages/support/llm-replay/src/index.ts | 88 ++++++- .../llm-replay/tests/llm-replay.spec.ts | 41 ++- packages/ui/acp-agent/README.md | 4 +- packages/ui/acp/README.md | 19 +- packages/ui/acp/acp-feature-support.md | 21 +- packages/ui/acp/package.json | 1 + packages/ui/acp/src/index.ts | 189 +++++++++++-- packages/ui/acp/tests/config-options.spec.ts | 208 ++++++++++++++- packages/ui/acp/tests/harness.ts | 35 ++- packages/ui/jsonrpc/src/server.ts | 2 +- packages/ui/jsonrpc/tests/server.spec.ts | 6 +- scripts/type-equiv.manifest.json | 2 + 94 files changed, 1657 insertions(+), 191 deletions(-) create mode 100644 docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml create mode 100644 docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md create mode 100644 docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md create mode 100644 examples/acp-agent/tests/snapshots/model-switching/input.json create mode 100644 examples/acp-agent/tests/snapshots/model-switching/session.jsonl create mode 100644 examples/acp-agent/tests/snapshots/model-switching/stdout.golden.jsonl create mode 100644 examples/acp-agent/tests/snapshots/model-switching/system-prompt.golden.md create mode 100644 examples/acp-agent/tests/snapshots/model-switching/tool-schemas.golden.json diff --git a/docs/architecture.md b/docs/architecture.md index 64a64d26f4..5bef5b52b2 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -126,7 +126,7 @@ Durability is a plugin concern. Persistence backends buffer synchronous `session Messages are arrays of typed content blocks (`text`, `reasoning`, `tool-call`, `tool-result`). The union derives from the merge-extensible `ContentBlockMap`; the same pattern types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New block types are coordinated across adapters, UI bridges, compaction pricing, and persistence, so block types remain a repo-wide contract. -Streaming uses raw chunks (`block-start` through `finish`) and `BlockAssembler`. The loop logs and assembles chunks, storing assistant provider/model provenance plus replay state. An `LlmAdapter` implements `stream()` and registers routes with `ctx.llm.registerAdapter(providers, adapter)`; requests route by `provider`, while the adapter resolves `model`. Replay state reaches a target only when both routes map to the same adapter instance, which owns validation and conversion. The contract lives in [llm-streaming.md](core-data-structures/llm-streaming.md). +Streaming uses raw chunks (`block-start` through `finish`) and `BlockAssembler`. The loop logs and assembles chunks, storing assistant provider/model provenance plus replay state. An `LlmAdapter` implements `stream()`, registers provider routes, and may expose advisory selector metadata; the adapter still resolves and validates model ids. Replay state reaches a target only when both routes map to the same adapter instance, which owns validation and conversion. The contract lives in [llm-streaming.md](core-data-structures/llm-streaming.md). ## Extension And Composition diff --git a/docs/config-catalog.md b/docs/config-catalog.md index b090f5b8a9..f26cd085f6 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -11,7 +11,7 @@ A `Requires:` line lists the service keys the plugin `inject`s: its `cordis.yml` ## `@deepseek-ai/dsh-acp` -Requires: `agents` · `sessions` · `sessionPersistence` · `tools` · `userInteraction` +Requires: `agents` · `sessions` · `sessionPersistence` · `tools` · `userInteraction` · `llm` · `systemPrompt` ```ts config-catalog /** Plugin config: the agent template ACP sessions are created from. */ @@ -27,7 +27,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:203`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:208`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-agent` @@ -365,10 +365,22 @@ export interface Config { thinking?: 'enabled' | 'disabled' /** Thinking effort (only meaningful with thinking enabled). */ reasoningEffort?: 'high' | 'max' + /** Advisory models shown by discovery consumers; defaults to V4 Flash and V4 Pro. */ + models?: DeepSeekCatalogModel[] +} + +/** One optional model entry advertised by the hand-written adapter. */ +export interface DeepSeekCatalogModel { + /** Wire model id accepted by the configured endpoint. */ + id: string + /** Selector label; defaults to {@link id}. */ + name?: string + /** Optional selector detail for deployments with similar model variants. */ + description?: string } ``` -Source: [`packages/llm/llm-deepseek/src/index.ts:30`](../packages/llm/llm-deepseek/src/index.ts) +Source: [`packages/llm/llm-deepseek/src/index.ts:36`](../packages/llm/llm-deepseek/src/index.ts) ## `@deepseek-ai/dsh-llm-pi-ai` @@ -431,10 +443,32 @@ export interface Config { * a nested-agent scenario; absent/empty for a single-session scenario. */ childFiles?: string[] + /** Optional replay-only provider catalog; absent or empty selects catch-all waterfall replay. */ + providers?: ReplayProviderConfig[] +} + +/** One provider route exposed by the replay adapter. */ +export interface ReplayProviderConfig { + /** Provider route used for replay requests. */ + id: string + /** Selector label; defaults to {@link id}. */ + name?: string + /** Advisory models exposed to clients such as ACP editors. */ + models?: ReplayModelConfig[] +} + +/** One model exposed by a replay-only provider catalog. */ +export interface ReplayModelConfig { + /** Model id used for replay requests. */ + id: string + /** Selector label; defaults to {@link id}. */ + name?: string + /** Optional selector description. */ + description?: string } ``` -Source: [`packages/support/llm-replay/src/index.ts:306`](../packages/support/llm-replay/src/index.ts) +Source: [`packages/support/llm-replay/src/index.ts:375`](../packages/support/llm-replay/src/index.ts) ## `@deepseek-ai/dsh-permission` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 567cbcefb2..a02bf9b0fc 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -121,13 +121,14 @@ The abstract `llm` service: an adapter registry plus a streaming model-call surf ```ts cordis-catalog registerAdapter(providers: string[], adapter: LlmAdapter): () => void -providers(): string[] +listProviders(): LlmProviderInfo[] +async listModels(provider: string): Promise stream(options: GenerateOptions): AsyncIterable ``` Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:76`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:96`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 89cd9b3cb7..0004007239 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -150,6 +150,30 @@ One model call is a fully-assembled `GenerateOptions`. The adapter answers with Source: [`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts) +Provider and model discovery uses small provider-neutral descriptors. A model catalog is advisory: routing still keys on a registered provider, and an adapter may accept unlisted model ids. + +```ts type-equiv +interface LlmProviderInfo { + /** Provider route key used by {@link GenerateOptions.provider}. */ + id: string + /** Human-readable provider name for selectors and diagnostics. */ + name: string +} +``` + +```ts type-equiv +interface LlmModelInfo { + /** Provider route that owns this model entry. */ + provider: string + /** Model id passed to {@link GenerateOptions.model}. */ + id: string + /** Human-readable model name for selectors. */ + name: string + /** Optional user-facing distinction from otherwise similar models. */ + description?: string +} +``` + ```ts type-equiv interface GenerateOptions { /** Registered provider route selecting the adapter instance. */ diff --git a/docs/core-data-structures/llm-streaming.md b/docs/core-data-structures/llm-streaming.md index b4b9d0f840..f9489a6d7f 100644 --- a/docs/core-data-structures/llm-streaming.md +++ b/docs/core-data-structures/llm-streaming.md @@ -68,7 +68,7 @@ interface TokenUsage { ## The seam -`LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm). +`LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Optional `providerInfo()` and asynchronous `listModels()` methods feed `LlmService.listProviders()` / `listModels()` with detached selector metadata. That catalog is advisory rather than a request whitelist: the adapter remains authoritative and may accept unlisted model ids. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm). `ContentBlockType` (the key set the `index`-correlated blocks carry) derives from `ContentBlockMap`: diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 4231f0fe8d..342407cde1 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,19 +7,19 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:139`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:148`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:283`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:202`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:212`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:167`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:224`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:239`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:180`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:157`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:250`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:260`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:270`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:141`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:150`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:285`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:204`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:214`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:169`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:226`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp) | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:241`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:182`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:159`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:252`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:262`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:272`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:59`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:68`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | @@ -33,7 +33,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:66`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | | `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:72`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | | `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | -| `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:27`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - | +| `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:27`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | [`acp`](../packages/ui/acp) | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:33`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:116`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | | `tools/execute` | `waterfall` | [`packages/core/tools/src/index.ts:89`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`timeout-policy`](../packages/timeout/timeout-policy) | diff --git a/docs/module-graph.md b/docs/module-graph.md index 7ceab41537..4793021e99 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -262,6 +262,7 @@ flowchart TD pkg_acp --> pkg_sandbox pkg_acp --> pkg_session pkg_acp --> pkg_session_persistence + pkg_acp --> pkg_system_prompt pkg_acp --> pkg_tools pkg_acp --> pkg_user_approval pkg_acp --> pkg_user_interaction @@ -404,7 +405,7 @@ flowchart TD | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-cordis`](../packages/cordis/tool-cordis) | `cordis` | [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | | [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | -| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`permission`](../packages/ui/permission), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`user-interaction`](../packages/ui/user-interaction) | +| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`permission`](../packages/ui/permission), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`user-interaction`](../packages/ui/user-interaction) | | [`tool-ask-user`](../packages/ui/tool-ask-user) | `ui` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) | | [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index c2d46bfa38..3573abfd5b 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -145,6 +145,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Single-file executable SDK runtime distribution (single-exe)](implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) | 2026-07-10 | | [Agent-scope runtime design and correctness](implemented/architecture/2026-07-12-agent-scope-runtime-design.md) | 2026-07-12 | | [Provider-routed LLM adapters and a generic pi-ai backend](implemented/architecture/2026-07-14-provider-routed-llm-adapters.md) | 2026-07-14 | +| [Advisory LLM catalogs and per-session ACP model selection](implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md) | 2026-07-15 | ### Process diff --git a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml index bf3c184ef9..48055ef6b7 100644 --- a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-14-provider-routed-llm-adapters.md: 4dc9a69cc37b4c6708b85f52ad62641102f20cdd -2026-07-14-provider-routed-llm-adapters.zh.md: dbf04eab6f163f9917837f0b93130efd3abff24e +2026-07-14-provider-routed-llm-adapters.md: 75ef047a7f95621d9a9c018b6dc57439e6f2bb22 +2026-07-14-provider-routed-llm-adapters.zh.md: 75ac9adbe5f8e96930a72a977c1969ff3a119ee8 diff --git a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md index 4dc9a69cc3..75ef047a7f 100644 --- a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md +++ b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md @@ -20,7 +20,7 @@ The adapter configuration also assumes one DeepSeek API key and endpoint. A gene `GenerateOptions` and `LlmCallConfig` carry `provider: string` beside `model: string`; `AgentOptions` carries the corresponding optional creation field. A loop request is valid only after both values are non-empty, and both values are part of the logged request header. `agent/request` may return a replacement pair on any step, so a session can switch providers and models without changing the Cordis plugin lifecycle. -`LlmService` registers and resolves adapters by provider. `registerAdapter(providers, adapter)` checks the entire provider list before mutating the registry, rejects a duplicate with `DUPLICATE_ADAPTER`, and disposes the whole registration as one effect. `providers()` reports the registered keys. Model ids are not registered or enumerated by the service; the selected adapter validates or forwards them. +`LlmService` registers and resolves adapters by provider. `registerAdapter(providers, adapter)` checks the entire provider list before mutating the registry, rejects a duplicate with `DUPLICATE_ADAPTER`, and disposes the whole registration as one effect. Model ids are not registration keys; the selected adapter still validates or forwards them. The later [LLM catalog and ACP selection RFC](2026-07-15-llm-model-catalog-and-acp-selection.md) added advisory `listProviders()` / `listModels()` discovery without turning model membership into request validation. A provider has exactly one adapter owner in a Cordis context. `dsh-llm-deepseek` registers `deepseek`; `dsh-llm-pi-ai` may also register `deepseek`, but loading both owners is a configuration error rather than an ordering rule or fallback. A deployment that wants the hand-rolled DeepSeek implementation excludes `deepseek` from the pi-ai profiles. A deployment that wants pi-ai's DeepSeek implementation does not mount `dsh-llm-deepseek`. diff --git a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md index dbf04eab6f..75ac9adbe5 100644 --- a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md @@ -20,7 +20,7 @@ Status: implemented `GenerateOptions` 与 `LlmCallConfig` 在 `model: string` 之外携带 `provider: string`，`AgentOptions` 则携带对应的可选创建字段。只有两个值都非空时，agent loop（智能体循环）请求才有效；两个值也都会写入请求头日志。`agent/request` 可以在任意步骤返回替换后的字段组合，因此会话可以切换提供方与模型，无需改变 Cordis 插件生命周期。 -`LlmService` 按提供方注册和解析适配器。`registerAdapter(providers, adapter)` 在修改注册表前检查整个提供方列表，遇到重复项时返回 `DUPLICATE_ADAPTER`，并将整组注册作为一个 effect 释放。`providers()` 返回已注册的键。服务不注册或枚举模型 ID；由选中的适配器负责验证或转发模型 ID。 +`LlmService` 按提供方注册和解析适配器。`registerAdapter(providers, adapter)` 在修改注册表前检查整个提供方列表，遇到重复项时返回 `DUPLICATE_ADAPTER`，并将整组注册作为一个 effect 释放。模型 ID 不作为注册键；仍由选中的适配器负责验证或转发。后续的 [LLM 目录与 ACP 模型选择 RFC](2026-07-15-llm-model-catalog-and-acp-selection.md) 增加了建议性的 `listProviders()` / `listModels()` 发现接口，但不会把目录成员关系变成请求校验规则。 在一个 Cordis 上下文中，一个提供方只能有一个适配器所有者。`dsh-llm-deepseek` 注册 `deepseek`；`dsh-llm-pi-ai` 也可以注册 `deepseek`，但同时加载两个所有者属于配置错误，不采用顺序规则或回退行为。若部署选择手写的 DeepSeek 实现，需从 pi-ai 配置中排除 `deepseek`；若部署选择 pi-ai 的 DeepSeek 实现，则不挂载 `dsh-llm-deepseek`。 diff --git a/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml new file mode 100644 index 0000000000..c2fb5daa62 --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-15-llm-model-catalog-and-acp-selection.md: bacfe180faf4d600d027a7aab6073130012b6022 +2026-07-15-llm-model-catalog-and-acp-selection.zh.md: 7e4bbf835a50c31c28bc40e3030425455390b598 diff --git a/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md b/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md new file mode 100644 index 0000000000..bacfe180fa --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md @@ -0,0 +1,66 @@ +# RFC: Advisory LLM catalogs and per-session ACP model selection + +Status: implemented + +English | [中文](2026-07-15-llm-model-catalog-and-acp-selection.zh.md) + +## Problem + +Provider-routed adapters let every request choose `provider + model`, but `LlmService` exposed only routing and streaming. A UI could not discover which providers were registered or which models an adapter was prepared to recommend. ACP clients therefore received no `model` session config option, so Zed, JetBrains, and VS Code integrations had no model list even though the request seam already supported runtime switching. + +Model discovery cannot become request validation. The hand-written DeepSeek adapter deliberately forwards arbitrary model ids to a public or private endpoint, while pi-ai has a finite installed catalog that is authoritative for its own request resolution. Treating one shared catalog as a whitelist would remove the private-endpoint behavior that provider routing was designed to preserve. + +ACP selection must also preserve the provider dimension. The same model id may appear under multiple routes, and switching a global adapter or agent template would leak one editor session's choice into every other session. Prompt variables and request routing must change together; a selection that lands during asynchronous prompt assembly cannot make `{{model}}` name one model while the request reaches another. + +## Decision + +### Provider-neutral advisory discovery + +`LlmAdapter` gains `providerInfo(provider)` and asynchronous `listModels(provider)` methods. Their provider-neutral results are `LlmProviderInfo { id, name }` and `LlmModelInfo { provider, id, name, description? }`. The defaults preserve existing adapter behavior by naming a provider after its route and advertising no models. + +`LlmService.listProviders()` returns detached metadata in registration order. `LlmService.listModels(provider)` delegates to the route owner, validates non-empty ids and names, rejects a mismatched provider or duplicate model id with `INVALID_CATALOG`, and returns detached values. Unknown providers still fail with `NO_ADAPTER`. Provider metadata is validated atomically during `registerAdapter()` so a malformed display record cannot leave a partial registration. + +Catalog membership is advisory. It drives selectors and diagnostics but never changes `stream()` routing and never rejects an otherwise valid request. Provider ownership remains exclusive and lifecycle-bound; model ids remain request-time adapter input. + +`dsh-llm-pi-ai` maps the configured provider's installed `getModels(provider)` entries into the neutral catalog. Its existing request-time catalog lookup remains authoritative and still rejects unknown models with `UNKNOWN_MODEL`. `dsh-llm-deepseek` accepts an optional `models` config containing display entries, defaulting to `deepseek-v4-flash` and `deepseek-v4-pro`. An explicit list replaces those defaults and an empty list disables discovery. The entries improve selector UX for known public or private models, while every unlisted model id continues to pass through unchanged. + +### ACP session config option + +The ACP bridge advertises one select with `id: model` and `category: model` in `session/new` and `session/load` when the session has a complete target whose provider is registered. Each opaque option value encodes the full provider/model pair. Models are grouped by provider when multiple non-empty provider groups exist; a single group is flattened for clients that render simple selects better. + +The session's current target is added to the displayed options when its adapter omits it. This preserves custom DeepSeek and private-endpoint models while keeping the adapter catalog advisory. A target with an unregistered provider is not advertised, and a model-less agent remains available to another `agent/request` supplier. + +`session/set_config_option` accepts only values from the current catalog snapshot and updates a target reference owned by that ACP session. No global `LlmService` or `AgentOptions` state changes, so concurrent sessions may select different providers and models. The existing permission select remains independent, and every response returns the complete refreshed option state. + +### Prompt/request consistency and durability + +Agent setup installs scoped `system-prompt/assemble` and `agent/request` listeners. Prompt assembly snapshots the selected pair once per step, overwrites the assembled `provider` and `model` variables after downstream prompt listeners, and the request listener applies that same snapshot after downstream request listeners. A selection during asynchronous assembly therefore starts on the next step rather than splitting prompt text from routing. Other call-config fields remain untouched. + +The request header remains the durable source of truth. When a selected target is actually used, the existing `request/header` or `request/header-delta` event records it. `session/load` initializes the ACP selection from the folded last request header before falling back to bridge config. A selection that is never used by a request is intentionally in-memory only because it never became model-visible state. + +ACP's experimental `providers/*` capability is not used. That draft surface configures provider base URLs, protocols, and headers, including secrets; it does not enumerate models and would give the UI authority to rewrite deployment-owned adapter configuration. + +## Alternatives considered + +**Return model strings only.** A model-only value loses the provider route and becomes ambiguous as soon as two providers expose the same id. + +**Make catalogs mandatory whitelists.** This conflicts with the hand-written adapter's arbitrary model pass-through and private deployments. The selected adapter already owns authoritative request validation. + +**Store selection in `AgentOptions` or `LlmService`.** Those are creation-wide or deployment-wide objects. Mutating them would couple concurrent ACP sessions and bypass the logged `agent/request` replacement path. + +**Persist a new model-selection session event immediately.** An unused UI selection has not affected a model request. Recording the existing request header when the target is consumed preserves the model-visible-if-and-only-if-logged rule without adding a second source of truth. + +**Use ACP `providers/*`.** That unstable API changes endpoint and authentication configuration rather than selecting a model for one session, and its lifecycle and secret-handling semantics do not match this feature. + +## Consequences + +- Any adapter can expose a dynamic model list without leaking provider-library types into the core seam. +- Catalog consumers must treat absence as “not advertised,” never “invalid request.” +- pi-ai-backed ACP deployments automatically inherit the installed pi-ai provider catalogs; hand-written DeepSeek deployments list known choices explicitly and retain arbitrary model support. +- ACP clients receive a standard stable model config option, with provider-aware values and per-session isolation. +- Request headers remain compatible with the provider-routed session shape; no new JSONL event or format version is required. +- A catalog read can be asynchronous. ACP reads a detached snapshot before creating or resuming an agent, so discovery failure cannot leave a partially published session. + +## Testing + +Unit coverage validates catalog detachment and malformed metadata, pi-ai and DeepSeek catalog projection, ACP provider grouping, custom-current insertion, invalid values, provider/model request routing, prompt-variable alignment, concurrent-session isolation, model-less fallback, and load restoration from the request header. The existing ACP transport suites verify that the additional config option does not change prompt, cancellation, replay, approval, or tool-rendering behavior. diff --git a/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md b/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md new file mode 100644 index 0000000000..7e4bbf835a --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md @@ -0,0 +1,66 @@ +# RFC: 建议性 LLM 目录与 ACP 会话级模型选择 + +Status: implemented + +[English](2026-07-15-llm-model-catalog-and-acp-selection.md) | 中文 + +## 问题 + +基于提供方路由的适配器允许每次请求选择 `provider + model`，但 `LlmService` 只暴露路由和流式调用。UI 无法发现已注册的提供方，也无法知道适配器愿意推荐哪些模型。因此，ACP 客户端收不到 `model` 会话配置项；即使请求接缝已经支持运行时切换，Zed、JetBrains 和 VS Code 集成仍没有模型列表。 + +模型发现不能变成请求校验。手写 DeepSeek 适配器会把任意模型 ID 原样转发给公开或私有端点，而 pi-ai 的有限安装目录则是其自身请求解析的权威依据。将共享目录视为白名单，会破坏提供方路由需要保留的私有端点能力。 + +ACP 选择还必须保留提供方维度。同一个模型 ID 可能存在于多个路由下；切换全局适配器或 agent 模板会让一个编辑器会话的选择泄漏到其他会话。Prompt 变量与请求路由必须同时变化；如果选择发生在异步 prompt 组装期间，不能让 `{{model}}` 表示一个模型、实际请求却到达另一个模型。 + +## 决策 + +### 提供方中立的建议性发现 + +`LlmAdapter` 增加 `providerInfo(provider)` 与异步 `listModels(provider)` 方法。其提供方中立结果分别为 `LlmProviderInfo { id, name }` 和 `LlmModelInfo { provider, id, name, description? }`。默认实现以路由名称作为提供方名称，并且不展示模型，从而保持现有适配器行为。 + +`LlmService.listProviders()` 按注册顺序返回分离后的元数据。`LlmService.listModels(provider)` 委托给路由所有者，校验非空 ID 和名称，并在提供方不匹配或模型 ID 重复时以 `INVALID_CATALOG` 失败，最后返回分离后的值。未知提供方仍以 `NO_ADAPTER` 失败。提供方元数据在 `registerAdapter()` 期间进行原子校验，错误展示记录不会留下部分注册。 + +目录成员关系仅提供建议。它驱动选择器与诊断，但不会改变 `stream()` 路由，也不会拒绝原本有效的请求。提供方所有权仍然具有排他性并绑定生命周期；模型 ID 仍是请求时传给适配器的输入。 + +`dsh-llm-pi-ai` 将已配置提供方的安装目录 `getModels(provider)` 映射为中立目录。其现有请求时目录查询仍是权威依据，未知模型仍以 `UNKNOWN_MODEL` 失败。`dsh-llm-deepseek` 接受可选的 `models` 配置作为展示条目，默认包含 `deepseek-v4-flash` 和 `deepseek-v4-pro`。显式列表会替换这些默认值，空列表则关闭发现。这些条目改善已知公开或私有模型的选择体验，而所有未列出的模型 ID 仍会原样透传。 + +### ACP 会话配置项 + +当会话具有完整目标且目标提供方已注册时，ACP bridge 会在 `session/new` 与 `session/load` 中展示一个 `id: model`、`category: model` 的选择项。每个不透明选项值都编码完整的提供方/模型字段组合。存在多个非空提供方分组时按提供方分组；只有一个分组时将其展开，以便对简单选择器支持更好的客户端展示。 + +如果适配器目录未包含会话当前目标，该目标仍会加入展示选项。这能保留自定义 DeepSeek 与私有端点模型，同时维持目录的建议性。提供方未注册的目标不会展示；缺少模型的 agent 仍可由其他 `agent/request` 提供者补齐。 + +`session/set_config_option` 只接受当前目录快照中的值，并更新该 ACP 会话独占的目标引用。它不会修改全局 `LlmService` 或 `AgentOptions` 状态，因此并发会话可以选择不同的提供方和模型。现有权限选择项保持独立，每次响应都返回完整的刷新后配置项状态。 + +### Prompt/请求一致性与持久化 + +Agent setup 会安装作用域内的 `system-prompt/assemble` 与 `agent/request` 监听器。Prompt 组装为每个 step 只快照一次选中的字段组合，在下游 prompt 监听器完成后覆盖组装结果中的 `provider` 与 `model` 变量；请求监听器则在下游请求监听器完成后应用同一个快照。因此，异步组装期间发生的选择会从下一个 step 生效，不会导致 prompt 文本与路由分裂。其他调用配置字段保持不变。 + +请求头仍是持久化事实来源。当选中目标被实际使用时，现有 `request/header` 或 `request/header-delta` 事件会记录它。`session/load` 先从折叠后的最后请求头初始化 ACP 选择，再回退到 bridge 配置。一个从未被请求使用的选择只保留在内存中，因为它从未成为模型可见状态。 + +本功能不使用 ACP 的实验性 `providers/*` 能力。该草案接口配置提供方 base URL、协议和 headers，其中可能包含密钥；它不枚举模型，并且会赋予 UI 改写部署所有的适配器配置的权力。 + +## 考虑过的替代方案 + +**只返回模型字符串。** 仅模型值会丢失提供方路由；两个提供方暴露相同 ID 时立刻产生歧义。 + +**将目录设为强制白名单。** 这与手写适配器的任意模型透传和私有部署冲突。请求的权威校验本就属于被选中的适配器。 + +**将选择存入 `AgentOptions` 或 `LlmService`。** 这些对象分别面向创建过程或整个部署。修改它们会耦合并发 ACP 会话，并绕开带日志归因的 `agent/request` 替换路径。 + +**立即写入新的模型选择会话事件。** 尚未使用的 UI 选择没有影响模型请求。目标被消费时记录现有请求头，既满足“模型可见当且仅当已记录”的规则，也不会引入第二个事实来源。 + +**使用 ACP `providers/*`。** 该不稳定 API 用于修改端点与认证配置，而不是为单个会话选择模型；其生命周期和密钥处理语义都不适合本功能。 + +## 结果 + +- 任意适配器都能暴露动态模型列表，无需把提供方库类型泄漏到核心接缝。 +- 目录消费者必须把缺失理解为“未展示”，而不是“请求无效”。 +- 基于 pi-ai 的 ACP 部署会自动继承已安装的 pi-ai 提供方目录；手写 DeepSeek 部署显式列出已知选项，同时保留任意模型能力。 +- ACP 客户端会收到稳定标准的模型配置项，其中的值保留提供方信息，并按会话隔离。 +- 请求头继续使用基于提供方路由的会话结构；不需要增加 JSONL 事件或格式版本。 +- 目录读取可以是异步的。ACP 在创建或恢复 agent 前读取分离后的快照，因此发现失败不会留下部分发布的会话。 + +## 测试 + +单元测试覆盖目录分离与错误元数据、pi-ai 和 DeepSeek 目录投影、ACP 提供方分组、自定义当前模型补入、无效值、提供方/模型请求路由、prompt 变量一致性、并发会话隔离、无模型回退，以及从请求头恢复选择。现有 ACP 传输测试验证新增配置项不会改变 prompt、取消、回放、审批或工具展示行为。 diff --git a/docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md b/docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md index bfd0e6a10e..ea4b98c31d 100644 --- a/docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md +++ b/docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md @@ -48,7 +48,7 @@ The precise supported and deferred protocol rows live in [`packages/ui/acp/acp-f Editors can create, load, prompt, cancel, render, ask, and reconfigure multiple harness sessions over one ACP connection without a loop-specific dependency. The session event log remains the durable source for replay, prompt settlement, cwd, and per-session configuration. Tool presentation and human-answer channels remain extensible plugin contracts instead of ACP-specific behavior. -The bridge deliberately does not implement session list/delete/resume/close capabilities, MCP passthrough, additional directories, image/audio/embedded-resource prompts, runtime model selection, plans, slash commands, usage updates, editor filesystem delegation, or the ACP terminal execution sub-protocol. The feature checklist records these as unsupported rather than silently accepting them. +The bridge deliberately does not implement session list/delete/resume/close capabilities, MCP passthrough, additional directories, image/audio/embedded-resource prompts, plans, slash commands, usage updates, editor filesystem delegation, or the ACP terminal execution sub-protocol. Runtime model selection was added later through standard session config options by the [LLM catalog and ACP selection RFC](../architecture/2026-07-15-llm-model-catalog-and-acp-selection.md). An idle config selection is truthful in the live response but not durable until the next `agent/prompt-submit` anchors it inside the open turn. Crashing before that boundary loses the pending selection; this is the cost of keeping session events turn-enclosed and replay-safe. diff --git a/examples/acp-agent/advanced.cordis.snapshot.yml b/examples/acp-agent/advanced.cordis.snapshot.yml index a70da9fb49..bff2f73bd5 100644 --- a/examples/acp-agent/advanced.cordis.snapshot.yml +++ b/examples/acp-agent/advanced.cordis.snapshot.yml @@ -26,3 +26,10 @@ name: '@deepseek-ai/dsh-tool-cordis' - id: llm-replay name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek + name: DeepSeek + models: + - id: deepseek-v4-flash + - id: deepseek-v4-pro diff --git a/examples/acp-agent/both-mode.cordis.snapshot.yml b/examples/acp-agent/both-mode.cordis.snapshot.yml index 2b9391bcbd..51c96cf2fa 100644 --- a/examples/acp-agent/both-mode.cordis.snapshot.yml +++ b/examples/acp-agent/both-mode.cordis.snapshot.yml @@ -26,3 +26,10 @@ name: '@deepseek-ai/dsh-code-runtime-worker' - id: llm-replay name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek + name: DeepSeek + models: + - id: deepseek-v4-flash + - id: deepseek-v4-pro diff --git a/examples/acp-agent/code-mode.cordis.snapshot.yml b/examples/acp-agent/code-mode.cordis.snapshot.yml index a4f2878def..ccd5d62751 100644 --- a/examples/acp-agent/code-mode.cordis.snapshot.yml +++ b/examples/acp-agent/code-mode.cordis.snapshot.yml @@ -26,3 +26,10 @@ name: '@deepseek-ai/dsh-code-runtime-worker' - id: llm-replay name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek + name: DeepSeek + models: + - id: deepseek-v4-flash + - id: deepseek-v4-pro diff --git a/examples/acp-agent/cordis.snapshot.yml b/examples/acp-agent/cordis.snapshot.yml index 90a2fa6a2a..e4d717a399 100644 --- a/examples/acp-agent/cordis.snapshot.yml +++ b/examples/acp-agent/cordis.snapshot.yml @@ -28,3 +28,10 @@ - insert: - id: llm-replay name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek + name: DeepSeek + models: + - id: deepseek-v4-flash + - id: deepseek-v4-pro diff --git a/examples/acp-agent/fs.cordis.snapshot.yml b/examples/acp-agent/fs.cordis.snapshot.yml index 53f2d677e2..d66bfa61cd 100644 --- a/examples/acp-agent/fs.cordis.snapshot.yml +++ b/examples/acp-agent/fs.cordis.snapshot.yml @@ -19,3 +19,10 @@ name: '@deepseek-ai/dsh-tool-fs' - id: llm-replay name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek + name: DeepSeek + models: + - id: deepseek-v4-flash + - id: deepseek-v4-pro diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 0d29f7b5ce..09af1f12a5 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -62,6 +62,17 @@ const SCENARIOS: Scenario[] = [ { name: 'fs-read-window', hasModelTurn: true, recorded: true, headerClass: 'fs', configPath: FS_CONFIG }, { name: 'fs-policy-reject', hasModelTurn: true, recorded: true, headerClass: 'fs', configPath: FS_CONFIG }, { name: 'multi-turn', hasModelTurn: true, recorded: true }, + // ACP exposes the adapter catalog as a session-scoped model select. This + // scenario pins the default flash request, the switch response, and the + // resulting request-header delta to pro. + { + name: 'model-switching', + hasModelTurn: true, + recorded: true, + pinsHeader: true, + expectedHeaderDeltas: 1, + headerClass: 'model-switching', + }, { name: 'error-finish', hasModelTurn: true, recorded: false, overridden: true }, // Keyless, authored (like error-finish/cancel): deterministically forcing a // LIVE model to repeat one call three times is not a stable recording, so @@ -117,9 +128,9 @@ const SCENARIOS: Scenario[] = [ // tool/code-dispatch events. Each overlay composes and pins its own header class. { name: 'code-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'code', configPath: CODE_MODE_CONFIG }, { name: 'both-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'both', configPath: BOTH_MODE_CONFIG }, - // The default tree owns the single Permissions select. Snapshot mode starts - // in danger-full-access so established fixtures stay runner-independent; - // these policy scenarios switch to workspace-write in their input scripts. + // The default tree also owns the Permissions select. Snapshot mode starts in + // danger-full-access so established fixtures stay runner-independent; these + // policy scenarios switch to workspace-write in their input scripts. // Real-kernel confinement remains in escalation.e2e.ts and the sandbox // packages' e2e suites. { name: 'config-options', hasModelTurn: false, recorded: false, headerClass: 'sandbox' }, diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl index bc4da17bb0..45d5628762 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-mount","title":"Mount plugin into live cordis runtime","kind":"execute","status":"in_progress","rawInput":{"code":"return { name: 'snapshot-marker', apply() {} }"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"advanced-mount","status":"completed","content":[{"type":"content","content":{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-code","title":"return await tools.cordis_inspect({ what: 'dynamic' })","kind":"execute","status":"in_progress","rawInput":"return await tools.cordis_inspect({ what: 'dynamic' })"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl index 577f10445b..7b2dbd604c 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl index 60235cac75..d31c8fdcfb 100644 --- a/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl @@ -1,4 +1,4 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"partial"}}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl index bfa379815e..31ec5df39a 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl index aa033fb673..1aca0c6586 100644 --- a/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":5,"error":{"code":-32602,"message":"Invalid params: unknown permission value \"plan\""}} {"jsonrpc":"2.0","id":6,"error":{"code":-32602,"message":"Invalid params: unknown config option \"reasoning-effort\""}} diff --git a/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl index d5d4f1c400..484b241427 100644 --- a/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"error":{"code":-32603,"message":"Internal error: turn failed: simulated provider error (HTTP 401)"}} diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl index f438444dc4..9180f2426a 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl index b926355bd7..871f3e3281 100644 --- a/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl index 800d7d608a..df664a96b4 100644 --- a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl index fd5c9f1aea..dda4f70968 100644 --- a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl index ab3eb2da31..fde77464d8 100644 --- a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl index fc0edbbe8b..d6b2e00b1e 100644 --- a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl index 0e7dcca6f8..b35af2c650 100644 --- a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl index f0ca9674cb..c5dcf0a7b0 100644 --- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl index 3c01ab158c..7969eeba3b 100644 --- a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl index e4c4984fc5..011175a871 100644 --- a/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl @@ -1,2 +1,2 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl index 8c97f359b7..90ab26d54e 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl index e9243d8a05..e60a33bcd5 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl index 3905e82ca7..a748546e51 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl index 92906adb59..60ae1f14e4 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl index 6304582220..765dd87f7f 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl index c4ad3ba541..e609fc0d70 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"'s"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl index 5c4a564d26..c7e8beeab3 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl index bd1e04bc59..6257014596 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl index 4bf92f3197..55310f6b3a 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl index 5459da1a17..8eba2d862e 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl index 6304582220..765dd87f7f 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl index 8cae81a5c9..76140724de 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl index 66d8c816be..af9959379d 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/model-switching/input.json b/examples/acp-agent/tests/snapshots/model-switching/input.json new file mode 100644 index 0000000000..3612f367f6 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/model-switching/input.json @@ -0,0 +1,23 @@ +{ + "steps": [ + { + "op": "initialize" + }, + { + "op": "newSession" + }, + { + "op": "prompt", + "text": "Without using tools, reply with exactly FLASH and stop." + }, + { + "op": "setConfigOption", + "configId": "model", + "value": "[\"deepseek\",\"deepseek-v4-pro\"]" + }, + { + "op": "prompt", + "text": "Without using tools, reply with exactly PRO and stop." + } + ] +} diff --git a/examples/acp-agent/tests/snapshots/model-switching/session.jsonl b/examples/acp-agent/tests/snapshots/model-switching/session.jsonl new file mode 100644 index 0000000000..4402c9582b --- /dev/null +++ b/examples/acp-agent/tests/snapshots/model-switching/session.jsonl @@ -0,0 +1,69 @@ +{"type":"session","version":0,"id":"622d16ce-0a94-476b-97a4-26dad50b1fbf","createdAt":1784086275585,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-Cwf7Bh"} +{"type":"turn/start","seq":0,"time":1784086275588,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784086275588,"data":{"content":[{"type":"text","text":"Without using tools, reply with exactly FLASH and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784086275590,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784086275590,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784086276525,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1784086276526,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1784086276605,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1784086276639,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1784086276640,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1784086276640,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1784086276640,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":11,"time":1784086276640,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":12,"time":1784086276661,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":13,"time":1784086276661,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":14,"time":1784086276661,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"FL"}}} +{"type":"assistant/chunk","seq":15,"time":1784086276661,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ASH"}}} +{"type":"assistant/chunk","seq":16,"time":1784086276661,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":17,"time":1784086276661,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":18,"time":1784086276710,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} +{"type":"assistant/chunk","seq":19,"time":1784086276710,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":20,"time":1784086276771,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" without"}}} +{"type":"assistant/chunk","seq":21,"time":1784086276771,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" using"}}} +{"type":"assistant/chunk","seq":22,"time":1784086276772,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" any"}}} +{"type":"assistant/chunk","seq":23,"time":1784086276772,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tools"}}} +{"type":"assistant/chunk","seq":24,"time":1784086276772,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":25,"time":1784086276777,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":26,"time":1784086276777,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"FL"}}} +{"type":"assistant/chunk","seq":27,"time":1784086276778,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ASH"}}} +{"type":"assistant/chunk","seq":28,"time":1784086276778,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly \"FLASH\" and stop, without using any tools."}}}} +{"type":"assistant/chunk","seq":29,"time":1784086276778,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"FLASH"}}}} +{"type":"assistant/chunk","seq":30,"time":1784086276778,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3133,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":20}}}} +{"type":"assistant/chunk","seq":31,"time":1784086276778,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":32,"time":1784086276782,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly \"FLASH\" and stop, without using any tools."},{"type":"text","text":"FLASH"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3133,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":20}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} +{"type":"step/end","seq":33,"time":1784086276782,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":34,"time":1784086276783,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"turn/start","seq":35,"time":1784086276811,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":36,"time":1784086276812,"data":{"content":[{"type":"text","text":"Without using tools, reply with exactly PRO and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":37,"time":1784086276812,"data":{"turn":2,"step":1}} +{"type":"request/header-delta","seq":38,"time":1784086276813,"data":{"system":{"keepStart":2,"keepEnd":10,"insert":["{{system}}"]},"config":{"provider":"deepseek","model":"deepseek-v4-pro"}}} +{"type":"assistant/chunk","seq":39,"time":1784086278053,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":40,"time":1784086278053,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":41,"time":1784086278242,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":42,"time":1784086278312,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":43,"time":1784086278312,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":44,"time":1784086278313,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":45,"time":1784086278313,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":46,"time":1784086278355,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":47,"time":1784086278356,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":48,"time":1784086278356,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":49,"time":1784086278356,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"PRO"}}} +{"type":"assistant/chunk","seq":50,"time":1784086278400,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":51,"time":1784086278400,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":52,"time":1784086278400,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} +{"type":"assistant/chunk","seq":53,"time":1784086278400,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":54,"time":1784086278441,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" without"}}} +{"type":"assistant/chunk","seq":55,"time":1784086278442,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" using"}}} +{"type":"assistant/chunk","seq":56,"time":1784086278442,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" any"}}} +{"type":"assistant/chunk","seq":57,"time":1784086278442,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tools"}}} +{"type":"assistant/chunk","seq":58,"time":1784086278442,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":59,"time":1784086278494,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":60,"time":1784086278495,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"PRO"}}} +{"type":"assistant/chunk","seq":61,"time":1784086278495,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly \"PRO\" and stop, without using any tools."}}}} +{"type":"assistant/chunk","seq":62,"time":1784086278495,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PRO"}}}} +{"type":"assistant/chunk","seq":63,"time":1784086278495,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3149,"outputTokens":21,"cacheReadTokens":0,"reasoningTokens":19}}}} +{"type":"assistant/chunk","seq":64,"time":1784086278495,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":65,"time":1784086278495,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly \"PRO\" and stop, without using any tools."},{"type":"text","text":"PRO"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-pro"},"usage":{"inputTokens":3149,"outputTokens":21,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64],"surfaceOp":"append"} +{"type":"step/end","seq":66,"time":1784086278495,"data":{"turn":2,"step":1}} +{"type":"turn/end","seq":67,"time":1784086278495,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/model-switching/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/model-switching/stdout.golden.jsonl new file mode 100644 index 0000000000..011d06f5d2 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/model-switching/stdout.golden.jsonl @@ -0,0 +1,47 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"FL"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ASH"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" stop"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" without"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" using"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" any"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tools"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"FL"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ASH"}}}} +{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} +{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-pro\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"PRO"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" stop"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" without"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" using"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" any"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tools"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"PRO"}}}} +{"jsonrpc":"2.0","id":5,"result":{"stopReason":"end_turn"}} diff --git a/examples/acp-agent/tests/snapshots/model-switching/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/model-switching/system-prompt.golden.md new file mode 100644 index 0000000000..90c8cb4b17 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/model-switching/system-prompt.golden.md @@ -0,0 +1,17 @@ +You are an AI agent powered by the DeepSeek Harness SDK. + +You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. + +Verify your work by running the code or tests. Keep answers brief and factual. + + +Check the [exit code: N] marker on every bash result; investigate failures before moving on. + +Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). + + +Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. + + + +You are a coding assistant powered by the deepseek-v4-pro model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. diff --git a/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.golden.json new file mode 100644 index 0000000000..d71283647e --- /dev/null +++ b/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.golden.json @@ -0,0 +1,249 @@ +{ + "initial": [ + { + "name": "bash", + "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.", + "parameters": { + "type": "object", + "properties": { + "command": { + "type": "string", + "description": "The bash command to execute." + }, + "description": { + "type": "string", + "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"." + }, + "timeoutMs": { + "type": "number", + "description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry." + }, + "workdir": { + "type": "string", + "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it." + }, + "run_in_background": { + "type": "boolean", + "description": "Run in the background and return a task id immediately. No timeout applies." + }, + "sandbox_permissions": { + "type": "string", + "description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.", + "enum": [ + "workspace-write", + "danger-full-access" + ] + }, + "justification": { + "type": "string", + "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access." + } + }, + "required": [ + "command", + "description" + ] + } + }, + { + "name": "bash_kill", + "description": "Ask the executor to kill a running background bash task by task id.", + "parameters": { + "type": "object", + "properties": { + "task_id": { + "type": "string", + "description": "Task id returned by the bash tool." + } + }, + "required": [ + "task_id" + ] + } + }, + { + "name": "bash_output", + "description": "Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.", + "parameters": { + "type": "object", + "properties": { + "task_id": { + "type": "string", + "description": "Task id returned by the bash tool." + } + }, + "required": [ + "task_id" + ] + } + }, + { + "name": "skill", + "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.", + "parameters": { + "type": "object", + "properties": { + "name": { + "type": "string", + "description": "The exact skill name from the available skills list." + } + }, + "required": [ + "name" + ] + } + }, + { + "name": "subagent", + "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.", + "parameters": { + "type": "object", + "properties": { + "description": { + "type": "string", + "description": "A short (3-5 word) description of the delegated task, for display." + }, + "prompt": { + "type": "string", + "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs." + } + }, + "required": [ + "description", + "prompt" + ] + } + }, + { + "name": "subagent_fork", + "description": "Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.", + "parameters": { + "type": "object", + "properties": { + "description": { + "type": "string", + "description": "A short (3-5 word) description of the delegated task, for display." + }, + "prompt": { + "type": "string", + "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new." + } + }, + "required": [ + "description", + "prompt" + ] + } + }, + { + "name": "todo_write", + "description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).", + "parameters": { + "type": "object", + "properties": { + "todos": { + "type": "array", + "description": "The COMPLETE task list, replacing any previous list.", + "items": { + "type": "object", + "properties": { + "content": { + "type": "string", + "description": "What the task is — a short imperative line." + }, + "status": { + "type": "string", + "description": "pending (not started) | in_progress (now) | completed (done).", + "enum": [ + "pending", + "in_progress", + "completed" + ] + } + }, + "required": [ + "content", + "status" + ] + } + } + }, + "required": [ + "todos" + ] + } + }, + { + "name": "workflow", + "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", + "parameters": { + "type": "object", + "properties": { + "script": { + "type": "string", + "description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)." + }, + "meta": { + "type": "object", + "description": "The workflow identity block (plain JSON — never code).", + "properties": { + "name": { + "type": "string", + "description": "Short kebab-case workflow name." + }, + "description": { + "type": "string", + "description": "One-line description of what the workflow does." + }, + "whenToUse": { + "type": "string", + "description": "Optional guidance on when this workflow applies." + }, + "phases": { + "type": "array", + "description": "Optional phase declarations matched by phase() calls.", + "items": { + "type": "object", + "properties": { + "title": { + "type": "string", + "description": "The phase title phase() calls match by exact string." + }, + "detail": { + "type": "string", + "description": "Optional one-line description of the phase." + }, + "provider": { + "type": "string", + "description": "Optional provider override this phase is expected to use." + }, + "model": { + "type": "string", + "description": "Optional model override this phase is expected to use." + } + }, + "required": [ + "title" + ] + } + } + }, + "required": [ + "name", + "description" + ] + }, + "args": { + "type": "object", + "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})." + } + }, + "required": [ + "script", + "meta" + ] + } + } + ], + "deltas": [] +} diff --git a/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl index 1d9d45954a..5c38cacf55 100644 --- a/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl index 651897e850..be9ca10cf5 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} @@ -44,7 +44,7 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","id":4,"result":{"stopReason":"end_turn"}} -{"jsonrpc":"2.0","id":5,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":5,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl index a0901b6297..3a900cfe34 100644 --- a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_1","title":"Update todo list","kind":"other","status":"in_progress","rawInput":[{"content":"watch the kettle boil","status":"in_progress"}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"plan","entries":[{"content":"watch the kettle boil","priority":"medium","status":"in_progress"}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_1","status":"completed","content":[{"type":"content","content":{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}}]}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl index 10198918d6..6a3dfcc4c4 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Load the requested skill."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skill_load","title":"Load skill snapshot-skill","kind":"read","status":"in_progress","rawInput":"snapshot-skill"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skill_load","status":"completed","content":[{"type":"content","content":{"type":"text","text":"\n\nBase directory for this skill: {{cwd}}/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n\n\n\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n\n"}}]}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl index 44fc4402fc..0574f2e6c4 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl index 08ad14dc9c..bfc195aa36 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl index 93b38e33cb..7f9d2c51fa 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl index 26d45699cc..4a07c313e0 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl index 1059a9cc6c..29528d9984 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl index f060b6b92f..fb2cd46879 100644 --- a/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl index 041ea02703..6abf7023b5 100644 --- a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl index 9c0bbd37be..4566071090 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl index 5f6c7f4c52..1c76f1ac61 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 2db00fe7cc..eb441da8f8 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -130,7 +130,8 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ summary: 'The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall.', methods: [ 'registerAdapter(providers: string[], adapter: LlmAdapter): () => void', - 'providers(): string[]', + 'listProviders(): LlmProviderInfo[]', + 'async listModels(provider: string): Promise', 'stream(options: GenerateOptions): AsyncIterable', ], }, @@ -741,6 +742,14 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'HookContext', declaration: 'export interface HookContext {\n content: ContentBlock[];\n source: MessageSource;\n}', }, + { + name: 'LlmModelInfo', + declaration: 'export interface LlmModelInfo {\n provider: string;\n id: string;\n name: string;\n description?: string;\n}', + }, + { + name: 'LlmProviderInfo', + declaration: 'export interface LlmProviderInfo {\n id: string;\n name: string;\n}', + }, { name: 'Message', declaration: 'export interface Message {\n role: \'system\' | \'user\' | \'assistant\';\n content: ContentBlock[];\n provenance?: AssistantProvenance;\n}', diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index f899b6b26c..746113a0e5 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -381,7 +381,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => { expect(() => ctx.llm.registerAdapter(['m1'], new MockAdapter([]))) .toThrow('already registered') // the original registration survives the failed attempt - expect(ctx.llm.providers()).toEqual(['m1']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'm1', name: 'm1' }]) }) it('an agent without a model fails the step with a clear error (not NO_ADAPTER for "default")', async () => { diff --git a/packages/llm/llm-deepseek/README.md b/packages/llm/llm-deepseek/README.md index ded2bf2379..7da98cdebf 100644 --- a/packages/llm/llm-deepseek/README.md +++ b/packages/llm/llm-deepseek/README.md @@ -14,9 +14,14 @@ A second, library-backed implementation of the same seam exists in `@deepseek-ai baseURL: !!js process.env.DEEPSEEK_BASE_URL # default: https://api.deepseek.com thinking: enabled # optional; provider default is enabled reasoningEffort: high # optional; high | max — omitted ⇒ not sent + models: # optional; defaults to V4 Flash and V4 Pro + - id: deepseek-v4-flash + name: DeepSeek V4 Flash + - id: private-reasoner + description: Company-hosted reasoning model ``` -The plugin registers the single provider route `deepseek`. A request selects it with `provider: deepseek`; its `model` is passed through as the wire `model` string, so changing DeepSeek models does not require lifecycle-time registration. Registering another adapter for `deepseek` throws `LlmError('DUPLICATE_ADAPTER')`. +The plugin registers the single provider route `deepseek`. A request selects it with `provider: deepseek`; its `model` is passed through as the wire `model` string, so changing DeepSeek models does not require lifecycle-time registration. Omitting `models` advertises `deepseek-v4-flash` and `deepseek-v4-pro`; an explicit list replaces those defaults, while `models: []` advertises none. Catalog entries are exposed through `ctx.llm.listModels('deepseek')` for clients such as ACP editors, but remain advisory: unlisted model ids still pass through unchanged. An omitted entry name defaults to its id. Registering another adapter for `deepseek` throws `LlmError('DUPLICATE_ADAPTER')`. `reasoningEffort` is **omitted by default** — when unset, the `reasoning_effort` wire field is not sent and the server applies its own default for the model. The only accepted values are `high` and `max` (DeepSeek's official effort levels). It is meaningful only with thinking enabled (the provider default). diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index 30760a8fbc..ece053c6b3 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -6,13 +6,23 @@ */ import { attributionHeaders, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm' -import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' +import type { GenerateOptions, LlmModelInfo, LlmProviderInfo, StreamChunk } from '@deepseek-ai/dsh-llm' import { serializeRequest } from './serialize.ts' import type { RequestDefaults } from './serialize.ts' import { parseSse } from './sse.ts' import { translate } from './translate.ts' import type { WireError } from './types.ts' +/** One optional model entry advertised by the hand-written adapter. */ +export interface DeepSeekCatalogModel { + /** Wire model id accepted by the configured endpoint. */ + id: string + /** Selector label; defaults to {@link id}. */ + name?: string + /** Optional selector detail for deployments with similar model variants. */ + description?: string +} + /** Constructor options for {@link DeepSeekAdapter}; the plugin's `apply` resolves them from Config + environment. */ export interface DeepSeekAdapterOptions { /** Bearer token sent in the `authorization` header on every request. */ @@ -21,6 +31,8 @@ export interface DeepSeekAdapterOptions { baseURL: string /** Request defaults applied to every call (thinking mode, effort). */ defaults?: RequestDefaults + /** Advisory models exposed to discovery consumers; requests remain unrestricted. */ + models?: readonly DeepSeekCatalogModel[] } /** @@ -49,6 +61,19 @@ export class DeepSeekAdapter extends LlmAdapter { super() } + override providerInfo(provider: string): LlmProviderInfo { + return { id: provider, name: 'DeepSeek' } + } + + override listModels(provider: string): Promise { + return Promise.resolve((this.options.models ?? []).map(model => ({ + provider, + id: model.id, + name: model.name ?? model.id, + ...model.description === undefined ? {} : { description: model.description }, + }))) + } + async * stream(options: GenerateOptions): AsyncIterable { const body = serializeRequest(options, this.options.defaults ?? {}) diff --git a/packages/llm/llm-deepseek/src/index.ts b/packages/llm/llm-deepseek/src/index.ts index fc68f011f1..695831b1bd 100644 --- a/packages/llm/llm-deepseek/src/index.ts +++ b/packages/llm/llm-deepseek/src/index.ts @@ -9,9 +9,10 @@ import type { Context } from 'cordis' import z from 'schemastery' import type {} from '@deepseek-ai/dsh-llm' import { DeepSeekAdapter } from './adapter.ts' +import type { DeepSeekCatalogModel } from './adapter.ts' export { DeepSeekAdapter, httpErrorCode } from './adapter.ts' -export type { DeepSeekAdapterOptions } from './adapter.ts' +export type { DeepSeekAdapterOptions, DeepSeekCatalogModel } from './adapter.ts' export { serializeMessages, serializeRequest } from './serialize.ts' export type { RequestDefaults } from './serialize.ts' export { DONE, parseSse } from './sse.ts' @@ -21,6 +22,11 @@ export type * from './types.ts' export const name = 'llm-deepseek' export const inject = ['llm'] +const DEFAULT_MODELS: DeepSeekCatalogModel[] = [ + { id: 'deepseek-v4-flash' }, + { id: 'deepseek-v4-pro' }, +] + /** * Plugin config, validated by the same-named schemastery schema. Every field * is optional in yml: credentials/endpoint fall back to the environment (a @@ -36,18 +42,45 @@ export interface Config { thinking?: 'enabled' | 'disabled' /** Thinking effort (only meaningful with thinking enabled). */ reasoningEffort?: 'high' | 'max' + /** Advisory models shown by discovery consumers; defaults to V4 Flash and V4 Pro. */ + models?: DeepSeekCatalogModel[] } +const catalogModel: z = z.object({ + id: z.string().required(), + name: z.string(), + description: z.string(), +}) + export const Config: z = z.object({ apiKey: z.string(), baseURL: z.string(), thinking: z.union(['enabled', 'disabled']), reasoningEffort: z.union(['high', 'max']), + models: z.array(catalogModel).default(DEFAULT_MODELS), }) /** Public API default; the internal endpoint comes from $DEEPSEEK_BASE_URL. */ export const PUBLIC_BASE_URL = 'https://api.deepseek.com' +/** Resolve, validate, and detach the advisory model catalog. */ +function resolveModels(models: readonly DeepSeekCatalogModel[] | undefined): DeepSeekCatalogModel[] { + const seen = new Set() + return (models ?? DEFAULT_MODELS).map((model) => { + if (model.id.length === 0) throw new Error('llm-deepseek: catalog model ids must be non-empty') + if (model.name !== undefined && model.name.length === 0) { + throw new Error(`llm-deepseek: catalog model "${model.id}" has an empty name`) + } + if (seen.has(model.id)) throw new Error(`llm-deepseek: duplicate catalog model "${model.id}"`) + seen.add(model.id) + return { + id: model.id, + ...model.name === undefined ? {} : { name: model.name }, + ...model.description === undefined ? {} : { description: model.description }, + } + }) +} + export function apply(ctx: Context, config: Config): void { const apiKey = config.apiKey ?? process.env.DEEPSEEK_API_KEY if (apiKey === undefined || apiKey.length === 0) { @@ -61,5 +94,6 @@ export function apply(ctx: Context, config: Config): void { thinking: config.thinking, reasoningEffort: config.reasoningEffort, }, + models: resolveModels(config.models), })) } diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index e31b1c2e41..c0a2f8f482 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -249,16 +249,73 @@ describe('plugin registration and config', () => { apiKey: 'k', baseURL: server.url, }) - expect(ctx.llm.providers()).toEqual(['deepseek']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }]) await fiber.dispose() - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) }) - it('always owns the deepseek provider', async () => { + it('owns the deepseek provider and advertises the default models', async () => { const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(LlmDeepSeek, { apiKey: 'k', baseURL: 'http://127.0.0.1:1' }) - expect(ctx.llm.providers()).toEqual(['deepseek']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }]) + await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([ + { provider: 'deepseek', id: 'deepseek-v4-flash', name: 'deepseek-v4-flash' }, + { provider: 'deepseek', id: 'deepseek-v4-pro', name: 'deepseek-v4-pro' }, + ]) + }) + + it('uses the default model catalog when apply is called directly', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + LlmDeepSeek.apply(ctx, { apiKey: 'k', baseURL: 'http://127.0.0.1:1' }) + await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([ + { provider: 'deepseek', id: 'deepseek-v4-flash', name: 'deepseek-v4-flash' }, + { provider: 'deepseek', id: 'deepseek-v4-pro', name: 'deepseek-v4-pro' }, + ]) + }) + + it('advertises configured models without restricting arbitrary request ids', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(LlmDeepSeek, { + apiKey: 'k', + baseURL: 'http://127.0.0.1:1', + models: [ + { id: 'private-fast' }, + { id: 'private-reasoner', name: 'Private Reasoner', description: 'Higher reasoning budget' }, + ], + }) + await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([ + { provider: 'deepseek', id: 'private-fast', name: 'private-fast' }, + { provider: 'deepseek', id: 'private-reasoner', name: 'Private Reasoner', description: 'Higher reasoning budget' }, + ]) + }) + + it('allows an explicit empty model catalog', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(LlmDeepSeek, { + apiKey: 'k', + baseURL: 'http://127.0.0.1:1', + models: [], + }) + await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([]) + }) + + it.each([ + [[{ id: '' }], /ids must be non-empty/], + [[{ id: 'm', name: '' }], /empty name/], + [[{ id: 'm' }, { id: 'm' }], /duplicate catalog model/], + ] as const)('rejects invalid advisory model config', async (models, message) => { + const ctx = new Context() + await ctx.plugin(LlmService) + await expect(ctx.plugin(LlmDeepSeek, { + apiKey: 'k', + baseURL: 'http://127.0.0.1:1', + models: [...models], + })).rejects.toThrow(message) + expect(ctx.llm.listProviders()).toEqual([]) }) it('falls back to DEEPSEEK_API_KEY and DEEPSEEK_BASE_URL env vars', async () => { @@ -267,7 +324,7 @@ describe('plugin registration and config', () => { const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(LlmDeepSeek, {}) - expect(ctx.llm.providers()).toEqual(['deepseek']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }]) }) it('throws a clear error when no API key is available', async () => { @@ -276,7 +333,7 @@ describe('plugin registration and config', () => { await ctx.plugin(LlmService) await expect(ctx.plugin(LlmDeepSeek, {})) .rejects.toThrow(/an API key is required/) - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) }) it('prefers explicit config over env for key and base URL', async () => { @@ -305,11 +362,12 @@ describe('plugin registration and config', () => { await ctx.plugin(LlmService) // Registration succeeds; no call is made (would hit api.deepseek.com). await ctx.plugin(LlmDeepSeek, {}) - expect(ctx.llm.providers()).toEqual(['deepseek']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }]) }) - it('adapter is constructible directly for embedding', () => { + it('adapter is constructible directly for embedding', async () => { const adapter = new DeepSeekAdapter({ apiKey: 'k', baseURL: 'http://127.0.0.1:1' }) expect(adapter).toBeInstanceOf(DeepSeekAdapter) + await expect(adapter.listModels('deepseek')).resolves.toEqual([]) }) }) diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index 0fa563f763..e5e9439713 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -26,6 +26,8 @@ Configure credentials and deployment-specific transport settings per provider. O Each provider name must exist in pi-ai's installed catalog and may appear only once in this plugin instance. Registration with `ctx.llm` is atomic: a collision with any provider route already owned by another adapter fails plugin loading without registering the remaining routes. Model ids are not lifecycle config; an unknown model fails before any provider request with `LlmError('UNKNOWN_MODEL')`. +The adapter exposes each configured provider's installed pi-ai models through `ctx.llm.listModels(provider)`. This is provider-neutral selector metadata derived from `getModels(provider)`; request-time resolution still performs the authoritative catalog lookup, so discovery does not create a second model registry. + Supported profile fields are `provider`, `apiKey`, `baseURL`, `headers`, `reasoning`, `thinkingBudgets`, `cacheRetention`, `transport`, `timeoutMs`, `websocketConnectTimeoutMs`, `maxRetries`, and `maxRetryDelayMs`. They map to pi-ai's common stream options. Harness app attribution wins a conflicting configured header name. ## Provider/model routing and replay diff --git a/packages/llm/llm-pi-ai/src/adapter.ts b/packages/llm/llm-pi-ai/src/adapter.ts index 185e6395b3..8eb37cfb4f 100644 --- a/packages/llm/llm-pi-ai/src/adapter.ts +++ b/packages/llm/llm-pi-ai/src/adapter.ts @@ -15,7 +15,7 @@ import type { SimpleStreamOptions, } from '@earendil-works/pi-ai' import { attributionHeaders, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm' -import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' +import type { GenerateOptions, LlmModelInfo, StreamChunk } from '@deepseek-ai/dsh-llm' import type { PiAiProviderProfile } from './config.ts' import { toPiContext } from './context.ts' import { toStreamChunks } from './stream.ts' @@ -65,6 +65,18 @@ export class PiAiAdapter extends LlmAdapter { this.profiles = new Map(options.profiles.map(profile => [profile.provider, profile])) } + override listModels(provider: string): Promise { + const profile = this.profiles.get(provider) + if (profile === undefined) { + return Promise.reject(new LlmError(`pi-ai adapter does not own provider "${provider}"`, 'NO_ADAPTER')) + } + return Promise.resolve(getModels(profile.provider as KnownProvider).map(model => ({ + provider, + id: model.id, + name: model.name, + }))) + } + async * stream(options: GenerateOptions): AsyncIterable { if (options.stop !== undefined) { throw new LlmError('llm-pi-ai does not support GenerateOptions.stop', 'UNSUPPORTED_OPTION') diff --git a/packages/llm/llm-pi-ai/tests/adapter.spec.ts b/packages/llm/llm-pi-ai/tests/adapter.spec.ts index 6e6368611d..5cb065cb48 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.spec.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.spec.ts @@ -186,9 +186,23 @@ describe('provider profile lifecycle', () => { const fiber = await ctx.plugin(LlmPiAi, { providers: [{ provider: 'openai' }, { provider: 'anthropic' }], }) - expect(ctx.llm.providers()).toEqual(['openai', 'anthropic']) + expect(ctx.llm.listProviders()).toEqual([ + { id: 'openai', name: 'openai' }, + { id: 'anthropic', name: 'anthropic' }, + ]) await fiber.dispose() - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) + }) + + it('exposes the installed pi-ai model catalog through provider-neutral metadata', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(LlmPiAi, { providers: [{ provider: 'openai' }] }) + const models = await ctx.llm.listModels('openai') + expect(models.find(model => model.id === 'gpt-4.1')).toEqual({ + provider: 'openai', id: 'gpt-4.1', name: 'GPT-4.1', + }) + expect(models.every(model => model.provider === 'openai')).toBe(true) }) it('accepts absent credentials for pi-ai ambient authentication', async () => { @@ -210,6 +224,7 @@ describe('provider profile lifecycle', () => { it('constructs the adapter directly and rejects routes it does not own', async () => { const adapter = new PiAiAdapter({ profiles: [{ provider: 'openai' }] }) + await expect(adapter.listModels('anthropic')).rejects.toMatchObject({ code: 'NO_ADAPTER' }) await expect((async () => { for await (const _chunk of adapter.stream({ provider: 'anthropic', model: 'claude-sonnet-4', messages: [] })) { /* drain */ } })()).rejects.toMatchObject({ code: 'NO_ADAPTER' }) diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 1f64577c60..a67859ed19 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -9,9 +9,12 @@ An adapter registry plus a single streaming call surface, interceptable via a wa ### Public API - `ctx.llm.registerAdapter(providers: string[], adapter: LlmAdapter): () => void` Register one adapter instance for the given provider routes. Registration is all-or-nothing, and is disposed with the calling fiber. -- `ctx.llm.providers(): string[]` — provider routes with a registered adapter. +- `ctx.llm.listProviders(): LlmProviderInfo[]` Describe registered provider routes in registration order. +- `ctx.llm.listModels(provider: string): Promise` Discover the models one registered provider currently advertises. - `ctx.llm.stream(options: GenerateOptions): AsyncIterable` Stream one model call as raw chunks (token-level deltas). Consumers assemble the chunks into blocks/messages with `BlockAssembler`. +Provider and model metadata is a discovery surface, not a routing whitelist. `registerAdapter()` still owns provider exclusivity, while an adapter may accept model ids absent from `listModels()`; consumers must not reject a request because its model is unlisted. Returned metadata is detached and invalid or duplicate adapter entries fail with `INVALID_ADAPTER` or `INVALID_CATALOG`. + ### Events | Event | Mode | Purpose | @@ -20,7 +23,7 @@ An adapter registry plus a single streaming call surface, interceptable via a wa ### Extension points -- Subclass `LlmAdapter` and call `ctx.llm.registerAdapter(providers, adapter)` to add one or more provider routes. `GenerateOptions.provider` selects the adapter; `GenerateOptions.model` is adapter-owned and may be resolved dynamically. +- Subclass `LlmAdapter` and call `ctx.llm.registerAdapter(providers, adapter)` to add one or more provider routes. `GenerateOptions.provider` selects the adapter; `GenerateOptions.model` is adapter-owned and may be resolved dynamically. Override `providerInfo()` and asynchronous `listModels()` to expose selector metadata; their defaults use the route id as its name and advertise no models. - Wrap `llm/stream` via `ctx.on()` waterfall listeners for caching, retry, logging, rate-limiting, etc. ### Content-block vocabulary (`types.ts`) diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 9b826a79fd..26e9e3b289 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -7,7 +7,7 @@ */ import { Context, Service } from 'cordis' -import type { GenerateOptions, Message, StreamChunk } from './types.ts' +import type { GenerateOptions, LlmModelInfo, LlmProviderInfo, Message, StreamChunk } from './types.ts' import { HarnessError } from './error.ts' import { deepFreeze } from './call-config.ts' @@ -61,6 +61,26 @@ export class LlmError extends HarnessError { * DeepSeek and pi-ai adapters intentionally exercise this contract through different internals. */ export abstract class LlmAdapter { + /** + * Describe one provider route owned by this adapter. + * @param provider - a route passed to `registerAdapter()` for this instance. + * @returns detached display metadata whose id must equal `provider`. + */ + providerInfo(provider: string): LlmProviderInfo { + return { id: provider, name: provider } + } + + /** + * List models this adapter can currently advertise for one owned provider. + * The result is advisory: an adapter may accept unlisted model ids, and + * consumers must not turn absence into request rejection. + * @param _provider - one provider route owned by this adapter. + * @returns discoverable models in adapter-preferred order. + */ + listModels(_provider: string): Promise { + return Promise.resolve([]) + } + /** * Stream one model call as raw chunks. The only required method. * @param options - the fully-assembled request; implementations must honor `options.signal`. @@ -74,7 +94,7 @@ export abstract class LlmAdapter { * surface, interceptable via the `llm/stream` waterfall. */ export class LlmService extends Service { - private adapters = new Map() + private adapters = new Map() constructor(ctx: Context) { super(ctx, 'llm') @@ -92,14 +112,20 @@ export class LlmService extends Service { const dispose = this.ctx.effect(function* (this: LlmService) { if (providers.length === 0) throw new LlmError('an adapter must register at least one provider', 'INVALID_ADAPTER') const unique = new Set() + const registrations: { adapter: LlmAdapter; provider: LlmProviderInfo }[] = [] for (const provider of providers) { if (provider.length === 0) throw new LlmError('adapter provider names must be non-empty', 'INVALID_ADAPTER') if (unique.has(provider) || this.adapters.has(provider)) { throw new LlmError(`an adapter for provider "${provider}" is already registered`, 'DUPLICATE_ADAPTER') } + const info = adapter.providerInfo(provider) + if (typeof info.id !== 'string' || info.id !== provider || typeof info.name !== 'string' || info.name.length === 0) { + throw new LlmError(`adapter metadata for provider "${provider}" must preserve its id and have a non-empty name`, 'INVALID_ADAPTER') + } unique.add(provider) + registrations.push({ adapter, provider: { id: info.id, name: info.name } }) } - for (const provider of providers) this.adapters.set(provider, adapter) + for (const registration of registrations) this.adapters.set(registration.provider.id, registration) yield () => { for (const provider of providers) this.adapters.delete(provider) } @@ -110,17 +136,50 @@ export class LlmService extends Service { } /** - * Provider routes with a registered adapter. - * @returns the registered provider names, in registration order. + * Describe provider routes with a registered adapter. + * @returns detached provider metadata in registration order. */ - providers(): string[] { - return [...this.adapters.keys()] + listProviders(): LlmProviderInfo[] { + return [...this.adapters.values()].map(({ provider }) => ({ ...provider })) } - private adapter(provider: string): LlmAdapter { - const adapter = this.adapters.get(provider) - if (!adapter) throw new LlmError(`no adapter registered for provider "${provider}"`, 'NO_ADAPTER') - return adapter + /** + * Discover models advertised by one registered provider. Catalog membership + * is advisory and never changes routing or request validation. + * @param provider - registered provider route to inspect. + * @returns detached model metadata in adapter-preferred order. + */ + async listModels(provider: string): Promise { + const adapter = this.registration(provider).adapter + const models = await adapter.listModels(provider) + const seen = new Set() + return models.map((model) => { + if ( + typeof model.provider !== 'string' + || model.provider !== provider + || typeof model.id !== 'string' + || model.id.length === 0 + || typeof model.name !== 'string' + || model.name.length === 0 + || (model.description !== undefined && typeof model.description !== 'string') + || seen.has(model.id) + ) { + throw new LlmError(`adapter returned invalid or duplicate model metadata for provider "${provider}"`, 'INVALID_CATALOG') + } + seen.add(model.id) + return { + provider: model.provider, + id: model.id, + name: model.name, + ...model.description === undefined ? {} : { description: model.description }, + } + }) + } + + private registration(provider: string): { adapter: LlmAdapter; provider: LlmProviderInfo } { + const registration = this.adapters.get(provider) + if (!registration) throw new LlmError(`no adapter registered for provider "${provider}"`, 'NO_ADAPTER') + return registration } /** Remove replay state whose historical route is owned by another adapter. */ @@ -128,7 +187,7 @@ export class LlmService extends Service { const messages: Message[] = options.messages.map((message) => { const provenance = message.provenance if (message.role !== 'assistant' || provenance?.replayState === undefined) return message - if (this.adapters.get(provenance.provider) === adapter) return message + if (this.adapters.get(provenance.provider)?.adapter === adapter) return message return { ...message, provenance: { provider: provenance.provider, model: provenance.model }, @@ -150,7 +209,7 @@ export class LlmService extends Service { */ stream(options: GenerateOptions): AsyncIterable { return this.ctx.waterfall(this, 'llm/stream', options, () => { - const adapter = this.adapter(options.provider) + const adapter = this.registration(options.provider).adapter return adapter.stream(this.forAdapter(options, adapter)) }) } diff --git a/packages/llm/llm/src/types.ts b/packages/llm/llm/src/types.ts index c1bc33bf08..b8054c2046 100644 --- a/packages/llm/llm/src/types.ts +++ b/packages/llm/llm/src/types.ts @@ -121,6 +121,26 @@ export interface TokenUsage { reasoningTokens?: number } +/** Display metadata for one registered provider route. */ +export interface LlmProviderInfo { + /** Provider route key used by {@link GenerateOptions.provider}. */ + id: string + /** Human-readable provider name for selectors and diagnostics. */ + name: string +} + +/** One adapter-discovered model; catalog membership is advisory, not request validation. */ +export interface LlmModelInfo { + /** Provider route that owns this model entry. */ + provider: string + /** Model id passed to {@link GenerateOptions.model}. */ + id: string + /** Human-readable model name for selectors. */ + name: string + /** Optional user-facing distinction from otherwise similar models. */ + description?: string +} + /** * Raw streaming protocol emitted by adapters. * Block indexes correlate interleaved deltas, and `block-end` carries the diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index 2308a7eb3b..83429ba0cd 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -1,6 +1,7 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { GenerateOptions, LlmAdapter, LlmError, StreamChunk } from '@deepseek-ai/dsh-llm' +import type { LlmModelInfo, LlmProviderInfo } from '@deepseek-ai/dsh-llm' class ScriptedAdapter extends LlmAdapter { constructor(private script: StreamChunk[]) { @@ -21,6 +22,23 @@ class RecordingAdapter extends ScriptedAdapter { } } +class CatalogAdapter extends ScriptedAdapter { + constructor( + private readonly provider: LlmProviderInfo, + private readonly models: readonly LlmModelInfo[], + ) { + super(SCRIPT) + } + + override providerInfo(_provider: string): LlmProviderInfo { + return this.provider + } + + override listModels(_provider: string): Promise { + return Promise.resolve(this.models) + } +} + const SCRIPT: StreamChunk[] = [ { type: 'block-start', index: 0, blockType: 'text' }, { type: 'text-delta', index: 0, text: 'hi' }, @@ -53,10 +71,80 @@ describe('LlmService', () => { const fiber = await ctx.plugin(Object.assign((inner: Context) => { inner.llm.registerAdapter(['scoped-model'], new ScriptedAdapter(SCRIPT)) }, { inject: ['llm'] })) - expect(ctx.llm.providers()).toEqual(['scoped-model']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'scoped-model', name: 'scoped-model' }]) await fiber.dispose() - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) + }) + + it('discovers detached provider and advisory model metadata', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + const provider = { id: 'catalog', name: 'Catalog Provider' } + const model = { provider: 'catalog', id: 'fast', name: 'Fast', description: 'Low latency' } + ctx.llm.registerAdapter(['catalog'], new CatalogAdapter(provider, [model])) + + const providers = ctx.llm.listProviders() + const models = await ctx.llm.listModels('catalog') + expect(providers).toEqual([provider]) + expect(models).toEqual([model]) + + providers[0]!.name = 'mutated' + models[0]!.name = 'mutated' + provider.name = 'source mutated' + model.name = 'source mutated' + expect(ctx.llm.listProviders()).toEqual([{ id: 'catalog', name: 'Catalog Provider' }]) + await expect(ctx.llm.listModels('catalog')).resolves.toEqual([{ + provider: 'catalog', id: 'fast', name: 'source mutated', description: 'Low latency', + }]) + }) + + it('defaults adapters to their route name and an empty advisory model list', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['plain'], new ScriptedAdapter(SCRIPT)) + expect(ctx.llm.listProviders()).toEqual([{ id: 'plain', name: 'plain' }]) + await expect(ctx.llm.listModels('plain')).resolves.toEqual([]) + await expect(ctx.llm.listModels('missing')).rejects.toMatchObject({ code: 'NO_ADAPTER' }) + }) + + it.each([ + [{ id: 1, name: 'Name' }, 'non-string id'], + [{ id: 'other', name: 'Name' }, 'mismatched id'], + [{ id: 'route', name: 1 }, 'non-string name'], + [{ id: 'route', name: '' }, 'empty name'], + ] as const)('rejects invalid provider metadata atomically (%s: %s)', async (metadata, _label) => { + const ctx = new Context() + await ctx.plugin(LlmService) + const adapter = new CatalogAdapter(metadata as unknown as LlmProviderInfo, []) + expect(() => ctx.llm.registerAdapter(['route'], adapter)).toThrow(expect.objectContaining({ code: 'INVALID_ADAPTER' })) + expect(ctx.llm.listProviders()).toEqual([]) + }) + + it.each([ + [{ provider: 1, id: 'm', name: 'M' }, 'non-string provider'], + [{ provider: 'other', id: 'm', name: 'M' }, 'mismatched provider'], + [{ provider: 'route', id: 1, name: 'M' }, 'non-string id'], + [{ provider: 'route', id: '', name: 'M' }, 'empty id'], + [{ provider: 'route', id: 'm', name: 1 }, 'non-string name'], + [{ provider: 'route', id: 'm', name: '' }, 'empty name'], + [{ provider: 'route', id: 'm', name: 'M', description: 1 }, 'non-string description'], + ] as const)('rejects invalid model metadata (%s: %s)', async (metadata, _label) => { + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['route'], new CatalogAdapter( + { id: 'route', name: 'Route' }, + [metadata as unknown as LlmModelInfo], + )) + await expect(ctx.llm.listModels('route')).rejects.toMatchObject({ code: 'INVALID_CATALOG' }) + }) + + it('rejects duplicate model ids in one provider catalog', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + const model = { provider: 'route', id: 'same', name: 'Same' } + ctx.llm.registerAdapter(['route'], new CatalogAdapter({ id: 'route', name: 'Route' }, [model, model])) + await expect(ctx.llm.listModels('route')).rejects.toMatchObject({ code: 'INVALID_CATALOG' }) }) it('lets llm/stream waterfall listeners wrap the underlying stream', async () => { @@ -192,9 +280,9 @@ describe('LlmService', () => { await ctx.plugin(LlmService) const dispose = ctx.llm.registerAdapter(['m1'], new ScriptedAdapter(SCRIPT)) - expect(ctx.llm.providers()).toEqual(['m1']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'm1', name: 'm1' }]) dispose() - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) }) it('rejects duplicate adapter registration with DUPLICATE_ADAPTER code', async () => { @@ -219,7 +307,7 @@ describe('LlmService', () => { expect(() => ctx.llm.registerAdapter([], adapter)).toThrow(expect.objectContaining({ code: 'INVALID_ADAPTER' })) expect(() => ctx.llm.registerAdapter([''], adapter)).toThrow(expect.objectContaining({ code: 'INVALID_ADAPTER' })) expect(() => ctx.llm.registerAdapter(['first', 'first'], adapter)).toThrow(expect.objectContaining({ code: 'DUPLICATE_ADAPTER' })) - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) }) it('re-registers a model after its prior registration is disposed', async () => { @@ -227,14 +315,14 @@ describe('LlmService', () => { await ctx.plugin(LlmService) const dispose = ctx.llm.registerAdapter(['m1'], new ScriptedAdapter(SCRIPT)) - expect(ctx.llm.providers()).toEqual(['m1']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'm1', name: 'm1' }]) dispose() - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) // The duplicate check is not wedged: the same model registers cleanly again. const disposeAgain = ctx.llm.registerAdapter(['m1'], new ScriptedAdapter(SCRIPT)) - expect(ctx.llm.providers()).toEqual(['m1']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'm1', name: 'm1' }]) disposeAgain() - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) }) }) diff --git a/packages/support/llm-replay/README.md b/packages/support/llm-replay/README.md index 847064b160..3272f29b9a 100644 --- a/packages/support/llm-replay/README.md +++ b/packages/support/llm-replay/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-llm-replay -A replay LLM plugin for keyless snapshot tests. It installs a single `llm/stream` waterfall listener that short-circuits the waterfall (never calls `next()`) and yields model streams reconstructed from a recorded **session JSONL** fixture — so a test can boot the real agent against a fixed model transcript with no API key. +A replay LLM plugin for keyless snapshot tests. It yields model streams reconstructed from a recorded **session JSONL** fixture, so a test can boot the real agent against a fixed model transcript with no API key. With `providers` configured it registers a replay-only adapter whose catalog is visible to clients such as ACP editors; without `providers` it installs the catch-all `llm/stream` waterfall used by tests that do not need discovery. Its consumer is the ACP snapshot harness in `examples/acp-agent`, which loads this plugin (via `cordis.snapshot.yml`) in place of a real LLM adapter. The package exists so its derive/parse/replay logic falls under the per-file 100% coverage gate on `packages/*/src` (the same logic, while it lived under `examples/`, was outside the gate). @@ -23,10 +23,18 @@ Replay keys every call by its calling session id (`GenerateOptions.sessionId`, s | `file` | string | `$DSH_SNAPSHOT_FILE` | Path to the primary (parent) `session.jsonl` fixture. Required (config or env). | | `overrideFile` | string | `$DSH_SNAPSHOT_OVERRIDE` | Optional path to a `ReplayEntry[]` sidecar that replaces the PRIMARY session's derived script. | | `childFiles` | string[] | `$DSH_SNAPSHOT_CHILD_FILES` (path-delimited) | Recorded subagent child-session logs for a nested scenario; empty for a single-session scenario. | +| `providers` | `ReplayProviderConfig[]` | — | Optional replay-only provider and model catalog. Configured routes dispatch through the replay adapter and never perform provider I/O. | ```yaml - id: llm-replay name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek + name: DeepSeek + models: + - id: deepseek-v4-flash + - id: deepseek-v4-pro # file/overrideFile/childFiles default to $DSH_SNAPSHOT_FILE / # $DSH_SNAPSHOT_OVERRIDE / $DSH_SNAPSHOT_CHILD_FILES, set by the snapshot # harness per scenario. @@ -34,11 +42,11 @@ Replay keys every call by its calling session id (`GenerateOptions.sessionId`, s ## Exports -- `installLlmReplay(ctx, config)` — install the `llm/stream` listener; returns the disposer (HMR safety). Use this in tests to drive replay without the Loader or env vars. +- `installLlmReplay(ctx, config)` — install the configured replay adapter or catch-all `llm/stream` listener; returns the disposer (HMR safety). Use this in tests to drive replay without the Loader or env vars. - `loadSessionScripts(config)` — resolve the ordered `SessionScript[]` (primary + children) for a scenario, ready to bind to live sessions in first-call order. - `loadReplayScript(config)` — resolve the `ReplayEntry[]` for the PRIMARY session only (sidecar override if present, else derived from the JSONL; fail-loud if the fixture is missing). - `deriveReplayScript(events)` / `parseSessionLog(text)` / `parseSessionHeader(text)` — the pure helpers that turn a recorded session log into a script and read its header `id`/`createdAt`. A derived group must end in a `finish` chunk; a group without one is the fingerprint of a thrown `stream()` and must instead be expressed via an override sidecar. -- Types `ReplayEntry` / `SessionScript` / `ReplayConfig` / `Config`. +- Types `ReplayEntry` / `SessionScript` / `ReplayConfig` / `ReplayProviderConfig` / `ReplayModelConfig` / `Config`. ## Plugin export shape diff --git a/packages/support/llm-replay/src/index.ts b/packages/support/llm-replay/src/index.ts index 2e509973e5..51e799114f 100644 --- a/packages/support/llm-replay/src/index.ts +++ b/packages/support/llm-replay/src/index.ts @@ -10,8 +10,8 @@ import { existsSync, readFileSync } from 'node:fs' import { delimiter as pathDelimiter } from 'node:path' import type { Context } from 'cordis' import type { SessionEvent } from '@deepseek-ai/dsh-session' -import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' -import { LlmError, assertNever } from '@deepseek-ai/dsh-llm' +import type { GenerateOptions, LlmModelInfo, LlmProviderInfo, StreamChunk } from '@deepseek-ai/dsh-llm' +import { LlmAdapter, LlmError, assertNever } from '@deepseek-ai/dsh-llm' /** * One recorded model call. `throw` may replay prefix chunks before failing; @@ -23,6 +23,26 @@ export type ReplayEntry = | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string; status?: number } | { kind: 'hang' } +/** One model exposed by a replay-only provider catalog. */ +export interface ReplayModelConfig { + /** Model id used for replay requests. */ + id: string + /** Selector label; defaults to {@link id}. */ + name?: string + /** Optional selector description. */ + description?: string +} + +/** One provider route exposed by the replay adapter. */ +export interface ReplayProviderConfig { + /** Provider route used for replay requests. */ + id: string + /** Selector label; defaults to {@link id}. */ + name?: string + /** Advisory models exposed to clients such as ACP editors. */ + models?: ReplayModelConfig[] +} + /** Resolved plugin configuration. */ export interface ReplayConfig { /** @@ -45,6 +65,12 @@ export interface ReplayConfig { * for a single-session scenario. */ childFiles?: string[] + /** + * Optional provider catalog. When non-empty, replay registers an adapter for + * these routes; when absent or empty, it retains the catch-all waterfall used + * by tests that do not need discovery. + */ + providers?: ReplayProviderConfig[] } /** @@ -203,6 +229,42 @@ export function loadSessionScripts(config: ReplayConfig): SessionScript[] { return [primary, ...children] } +/** Replay adapter that makes a configured provider catalog discoverable without provider I/O. */ +class ReplayAdapter extends LlmAdapter { + private readonly providers: ReadonlyMap + + constructor( + providers: readonly ReplayProviderConfig[], + private readonly replay: (options: GenerateOptions) => AsyncIterable, + ) { + super() + this.providers = new Map(providers.map(provider => [provider.id, provider])) + } + + override providerInfo(provider: string): LlmProviderInfo { + const configured = this.providers.get(provider) + /* v8 ignore next -- LlmService only asks about routes registered from this same map. */ + if (configured === undefined) return super.providerInfo(provider) + return { id: provider, name: configured.name ?? provider } + } + + override listModels(provider: string): Promise { + const configured = this.providers.get(provider) + /* v8 ignore next -- LlmService only asks about routes registered from this same map. */ + if (configured === undefined) return Promise.resolve([]) + return Promise.resolve((configured.models ?? []).map(model => ({ + provider, + id: model.id, + name: model.name ?? model.id, + ...model.description === undefined ? {} : { description: model.description }, + }))) + } + + override stream(options: GenerateOptions): AsyncIterable { + return this.replay(options) + } +} + /** Yield a recorded stream back, honoring abort like a real adapter. */ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined): AsyncIterable { switch (entry.kind) { @@ -243,12 +305,14 @@ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined) /** * Install per-session positional replay. A newly seen live session takes the * next ordered recorded script, then advances its own cursor synchronously at - * invocation time; calls without `sessionId` share one anonymous session. - * Returns the effect disposer for HMR-safe removal. + * invocation time; calls without `sessionId` share one anonymous session. A + * non-empty provider catalog registers a routed replay adapter; otherwise a + * catch-all waterfall intercepts requests. Returns the effect disposer for + * HMR-safe removal. * - * @param ctx - the context whose `llm/stream` waterfall the listener short-circuits. + * @param ctx - the context whose LLM service receives the replay route or waterfall. * @param config - the resolved fixture paths (env-var defaulting is `apply`'s job). - * @returns the `ctx.on` disposer that removes the listener. + * @returns the disposer that removes the registered adapter or listener. */ export function installLlmReplay(ctx: Context, config: ReplayConfig): () => void { const scripts = loadSessionScripts(config) @@ -258,7 +322,7 @@ export function installLlmReplay(ctx: Context, config: ReplayConfig): () => void const bound = new Map() let nextScript = 0 const ANON = '\0anon\0' // the key for a call that carries no sessionId - return ctx.on('llm/stream', (options: GenerateOptions, _next) => { + const replay = (options: GenerateOptions): AsyncIterable => { const key = options.sessionId ?? ANON let state = bound.get(key) let unrecorded = false @@ -296,7 +360,12 @@ export function installLlmReplay(ctx: Context, config: ReplayConfig): () => void } yield* replayEntry(entry, options.signal) })() - }) + } + const providers = config.providers ?? [] + if (providers.length > 0) { + return ctx.llm.registerAdapter(providers.map(provider => provider.id), new ReplayAdapter(providers, replay)) + } + return ctx.on('llm/stream', (options: GenerateOptions, _next) => replay(options)) } export const name = 'llm-replay' @@ -314,6 +383,8 @@ export interface Config { * a nested-agent scenario; absent/empty for a single-session scenario. */ childFiles?: string[] + /** Optional replay-only provider catalog; absent or empty selects catch-all waterfall replay. */ + providers?: ReplayProviderConfig[] } export function apply(ctx: Context, config: Config = {}): void { @@ -329,5 +400,6 @@ export function apply(ctx: Context, config: Config = {}): void { file, ...overrideFile !== undefined && overrideFile.length > 0 ? { overrideFile } : {}, ...childFiles.length > 0 ? { childFiles } : {}, + ...config.providers !== undefined ? { providers: config.providers } : {}, }) } diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index 86e77473a5..c9bd545b36 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -198,7 +198,7 @@ describe('loadReplayScript', () => { }) }) -describe('installLlmReplay (through the real waterfall)', () => { +describe('installLlmReplay (through the real LlmService)', () => { function writeLog(...calls: StreamChunk[][]): void { let seq = 1 const events: SessionEvent[] = [] @@ -217,6 +217,40 @@ describe('installLlmReplay (through the real waterfall)', () => { expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) + it('registers a replay-only provider catalog when configured', async () => { + writeLog(TEXT_CHUNKS) + const ctx = new Context() + await ctx.plugin(LlmService) + const dispose = installLlmReplay(ctx, { + file, + providers: [ + { + id: 'deepseek', + name: 'DeepSeek', + models: [ + { id: 'flash' }, + { id: 'pro', name: 'Pro', description: 'Larger model' }, + ], + }, + { id: 'empty' }, + ], + }) + + expect(ctx.llm.listProviders()).toEqual([ + { id: 'deepseek', name: 'DeepSeek' }, + { id: 'empty', name: 'empty' }, + ]) + await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([ + { provider: 'deepseek', id: 'flash', name: 'flash' }, + { provider: 'deepseek', id: 'pro', name: 'Pro', description: 'Larger model' }, + ]) + await expect(ctx.llm.listModels('empty')).resolves.toEqual([]) + expect(await drain(ctx.llm.stream({ provider: 'deepseek', model: 'pro', messages: [] }))).toEqual(TEXT_CHUNKS) + + dispose() + expect(ctx.llm.listProviders()).toEqual([]) + }) + it('serves the Nth call the Nth derived entry (positional)', async () => { const second: StreamChunk[] = [ { type: 'block-start', index: 0, blockType: 'text' }, @@ -574,11 +608,12 @@ describe('apply (the plugin entry)', () => { expect(inject).toEqual(['llm']) }) - it('installs replay from an explicit config.file', async () => { + it('installs replay and its catalog from explicit config', async () => { writeFileSync(file, sessionJsonl(TEXT_CHUNKS.map((c, i) => chunkEvent(i + 1, 1, 1, c))), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) - apply(ctx, { file }) + apply(ctx, { file, providers: [{ id: 'm', models: [{ id: 'm' }] }] }) + expect(ctx.llm.listProviders()).toEqual([{ id: 'm', name: 'm' }]) expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) diff --git a/packages/ui/acp-agent/README.md b/packages/ui/acp-agent/README.md index 53e54545a2..97964e3b01 100644 --- a/packages/ui/acp-agent/README.md +++ b/packages/ui/acp-agent/README.md @@ -25,8 +25,8 @@ Because the package wires no logger entry, an ACP leaf has **nothing to get wron | Key | Default | Routed to | |---|---|---| -| `provider` | (required) | the provider route for each per-session agent the bridge creates | -| `model` | (required) | the per-session agent template the bridge creates agents from | +| `provider` | (required) | the initial provider route for each per-session agent the bridge creates; ACP model selection may replace it per session | +| `model` | (required) | the initial model for each per-session agent; ACP clients may switch among adapter-advertised models | | `persona` | — | the deployment persona template (may reference `{{provider}}`/`{{model}}`/`{{cwd}}`), routed to `dsh-system-prompt` | | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | | `tools` | `{ mode: 'native' }` | tool-registry presentation config (`native` / `code` / `both`), routed through `dsh-agent-core` | diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index eaf3f6c6d2..324552e7e1 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -8,14 +8,14 @@ It is a **client-driver / UI plugin**, the structured analogue of the readline ` `apply(ctx, config)` — wires an `AgentSideConnection` (from `@agentclientprotocol/sdk`) to `process.stdin`/`process.stdout` and implements the ACP `Agent` method surface. -The plugin injects `agents`, `sessions`, `sessionPersistence`, `tools`, and `userInteraction`, never the concrete loop. Persistence backs `session/load`; tool definitions own presentation; user interaction maps agent questions to ACP forms. +The plugin injects `agents`, `sessions`, `sessionPersistence`, `tools`, `userInteraction`, `llm`, and `systemPrompt`, never the concrete loop. Persistence backs `session/load`; the LLM catalog backs model selection; prompt assembly keeps model variables aligned with routing; tool definitions own presentation; user interaction maps agent questions to ACP forms. ### Config | Key | Default | Meaning | |---|---|---| -| `provider` | — | Provider route for created agents (must have a registered adapter). | -| `model` | — | Model name for created agents (must have a registered adapter). | +| `provider` | — | Initial provider route for created agents (must have a registered adapter). | +| `model` | — | Initial model id for created agents. | (No persona key: `dsh-system-prompt`'s own `persona` config supplies the global default section, so ACP-created agents render it without the bridge carrying prompt text. An agent-scoped same-name section may still shadow that default.) @@ -33,7 +33,7 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name: | `session/update` | `session/event` | streams user replay, assistant text/reasoning, and tool render intents | | `elicitation/create` | `ctx.userInteraction.ask()` | maps `ask_user_question` questions to ACP form elicitations; option descriptions are shown in enum titles, `multi_select` uses ACP array enums, optionless requests use a required `custom` field, and a non-empty custom answer overrides any selected choice | | `session/request_permission` | `approval/request` listener | answers one-shot allow/reject requests for bridge-owned calls; foreign or call-less requests delegate and fail closed if unanswered — see "Permission prompts" | -| `session/set_config_option` | `ctx.permission.set()` | per-session permission-preset switching over [session config options](https://agentclientprotocol.com/protocol/session-config-options) — see "Session config options" | +| `session/set_config_option` | agent-scoped request target / `ctx.permission.set()` | per-session provider+model and permission-preset switching over [session config options](https://agentclientprotocol.com/protocol/session-config-options) — see "Session config options" | ## Multi-session @@ -41,7 +41,9 @@ Forward and reverse indexes route every event, prompt, cancel, and approval to o ## Session config options -When `ctx.permission` is composed, the bridge advertises one `permission` select in `session/new` and `session/load`. Options come from the deployment's preset table; the current value comes from the session fold, with switch-away-only `custom` for unmatched knobs. `session/set_config_option` accepts advertised presets and writes both sandbox-mode and approval-policy events through `PermissionService.set()`. Open-turn switches append immediately; idle switches overlay responses and anchor at the next `agent/prompt-submit`, before request assembly. A crash before anchoring restores the durable fold. See the [sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md), [`dsh-permission`](../permission/README.md), and [protocol matrix](acp-feature-support.md#6-session-config-options). +The bridge advertises a `model`-category select in `session/new` and `session/load` when the session has a complete target whose provider is registered. Values encode the complete provider/model pair, are grouped by provider when more than one group is available, and come from `ctx.llm.listProviders()` / `listModels()`. The configured or last-requested model is added when absent because catalogs are advisory and private adapters may accept unlisted ids. A selection changes only that ACP session. Agent-scoped prompt assembly snapshots the selected pair for one step, supplies matching `{{provider}}` / `{{model}}` variables, and the `agent/request` waterfall applies the same pair; a concurrent selection therefore takes effect on the next step instead of splitting prompt text from routing. The resulting request header is the durable record restored by `session/load`; a selection never used by a request remains in-memory only. + +When `ctx.permission` is composed, the bridge also advertises a `permission` select. Options come from the deployment's preset table; the current value comes from the session fold, with switch-away-only `custom` for unmatched knobs. `session/set_config_option` accepts advertised presets and writes both sandbox-mode and approval-policy events through `PermissionService.set()`. Open-turn switches append immediately; idle switches overlay responses and anchor at the next `agent/prompt-submit`, before request assembly. A crash before anchoring restores the durable fold. See the [model-catalog RFC](../../../docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md), [sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md), [`dsh-permission`](../permission/README.md), and [protocol matrix](acp-feature-support.md#6-session-modes--config-options--models). Background bash tasks use the session id as an opaque owner token, so one session cannot inspect or stop another's task. That contract belongs to [`dsh-tool-bash`](../../bash/tool-bash/). @@ -108,6 +110,12 @@ The JSON-RPC frames go on stdout, so this plugin MUST run in an example that loa **Token effect**: Zero direct tokens from the ACP option or the log-only `permission/preset` event. Downstream cost is limited to the owning plugins' policy prompt, conditional retained change notice, and any changed tool outcome. +### Model switches + +**What the model sees**: The ACP selector itself emits no message. The selected provider/model pair supplies the next step's `{{provider}}` / `{{model}}` prompt variables and request routing together; all other call-config fields continue through the `agent/request` waterfall unchanged. + +**Token effect**: The selector adds no direct tokens. A changed model may tokenize the same retained prompt/history differently, and any persona text that interpolates provider or model changes accordingly. + ### Loaded sessions **What the model sees**: `session/load` resumes the persisted log, after which the loop sends its reconstructed history and request header. Replaying that log to the editor is not an extra model message. @@ -118,6 +126,5 @@ The JSON-RPC frames go on stdout, so this plugin MUST run in an example that loa - **`additionalDirectories`** — rejected. A session operates in its single `cwd` (see Per-session cwd); widening the tool/filesystem scope to extra roots is a separate sandbox concern, not yet implemented. - **Prompt content is `text` + `resource_link` only** — image, audio, and embedded-resource blocks are rejected, as is a non-empty `mcpServers` list at `session/new`. -- **One configured `model` for every created session** — per-session model selection has no config or protocol surface here yet. - **Terminal cards render completed output** — live incremental streaming and command classification are named follow-ups of [the terminal-rendering RFC](../../../docs/rfc/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md). - **Permission answers are one-shot only** — the bridge offers `allow_once` / `reject_once`; durable `allow_always` grants and their storage/revocation policy remain deferred to the approval seam. diff --git a/packages/ui/acp/acp-feature-support.md b/packages/ui/acp/acp-feature-support.md index 121af7cc2f..de390020c3 100644 --- a/packages/ui/acp/acp-feature-support.md +++ b/packages/ui/acp/acp-feature-support.md @@ -10,7 +10,7 @@ Legend: ✅ supported · ⚠️ partial / fallback · ❌ not yet · — n/a. Th ## At a glance -The bridge implements the **core prompt-turn loop** for N concurrent sessions: initialize, session new/load, prompt, cancel, streamed assistant/thought chunks, tool-call rendering (including Zed terminal cards), resumable session replay, one-shot permission prompts, and per-session permission presets. The largest **unbuilt** areas are **MCP passthrough**, runtime model selection, **slash commands**, and **agent plans**, plus the client **filesystem** and **terminal** method families (which the adapters mostly do NOT drive either — see rows 43-49). See [Gap summary](#gap-summary). +The bridge implements the **core prompt-turn loop** for N concurrent sessions: initialize, session new/load, prompt, cancel, streamed assistant/thought chunks, tool-call rendering (including Zed terminal cards), resumable session replay, one-shot permission prompts, per-session model selection, and permission presets. The largest **unbuilt** areas are **MCP passthrough**, **slash commands**, and **agent plans**, plus the client **filesystem** and **terminal** method families (which the adapters mostly do NOT drive either — see rows 43-49). See [Gap summary](#gap-summary). ## 1. Agent methods (client → agent) @@ -26,8 +26,8 @@ The bridge implements the **core prompt-turn loop** for N concurrent sessions: i | `session/prompt` | S | ✅ | ✅ | ✅ | Maps to `agent.send`; one in-flight prompt per session; settles on the owning turn's end. | | `session/cancel` | S | ✅ | ✅ | ✅ | Queue-aware `agent.cancel`; settles the in-flight prompt `cancelled`, scoped to the one session. | | `session/set_mode` | S | ❌ | ✅ | ✅ | Session modes deliberately skipped: config options are the spec's replacement and modes are slated for removal in ACP v2 (see [§6](#6-session-modes--config-options--models)). | -| `session/set_config_option` | S | ✅ | ✅ | ✅ | One `permission` select when `ctx.permission` is composed; values come from the deployment preset table, a switch writes its preset event through to both knob events, and the response carries the complete refreshed state ([sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)). | -| model selection | S | ❌ | ✅ | ✅ | No distinct stable `session/set_model` — model is the `model`-category `session/set_config_option`. The bridge fixes the model per-bridge via config; no runtime switch. Codex still uses the legacy `unstable_setSessionModel` ext method. | +| `session/set_config_option` | S | ✅ | ✅ | ✅ | A provider/model select is present for a complete registered target; one `permission` select is added when `ctx.permission` is composed. Every response carries the complete refreshed state. | +| model selection | S | ✅ | ✅ | ✅ | No distinct stable `session/set_model` — model is the `model`-category `session/set_config_option`. Values preserve the provider/model pair, catalogs come from `ctx.llm`, selection is per session, and `session/load` restores the last requested pair. Codex also supports the legacy `unstable_setSessionModel` ext method. | | `session/list` | S | ❌ | ✅ | ✅ | Gated by `sessionCapabilities.list`. The harness HAS `sessionPersistence.list()` (used internally for load-cwd validation) but does not expose it over ACP. | | `session/delete` | S | ❌ | ✅ | ✅ | Gated by `sessionCapabilities.delete`. | | `session/fork` | U | ❌ | ✅ | ❌ | Claude ships `unstable_forkSession`; Codex does not. | @@ -111,7 +111,7 @@ Tool-call presentation is **owned by each tool** (`presentCall` / `presentResult ## 6. Session modes / config options / models -Config options ✅ (the [sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)): when `ctx.permission` is composed, the bridge advertises one `permission` select whose values come from the deployment preset table and whose current value derives from the session log; `session/set_config_option` switches the preset end to end, with idle switches anchoring at the next `agent/prompt-submit` inside its open turn. Session modes stay deliberately unmodeled because config options replace them in ACP v2. Runtime model selection is still not modeled — the harness fixes the model per bridge via `AcpConfig.model` (both reference adapters ship a model selector). +Config options ✅: the bridge advertises a `model` select from the advisory LLM provider/model catalog, preserving each provider/model pair in an opaque value and grouping multiple providers. A selected pair is isolated to one session, snapshotted with the prompt for each step, applied through `agent/request`, and restored from the logged request header on load. When `ctx.permission` is composed, the bridge also advertises one `permission` select whose values come from the deployment preset table and whose current value derives from the session log; idle permission switches anchor at the next `agent/prompt-submit` inside its open turn. Session modes stay deliberately unmodeled because config options replace them in ACP v2. See the [model-catalog RFC](../../../docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md) and [sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). ## 7. Content blocks @@ -141,13 +141,12 @@ The bridge rejects unsupported prompt blocks rather than silently dropping them Ranked by how commonly the reference adapters ship them and how much UX they unlock: 1. **Session lifecycle** — `session/list` + `session/delete` (the persistence layer already lists), then `session/resume` / `session/close`. -2. **Model selection** — sandbox and approval config options are implemented; selecting the bridge's model at runtime remains open. -3. **Agent plan** (`sessionUpdate: 'plan'`) — surface the loop's plan as structured entries. -4. **Slash commands** (`available_commands_update`). -5. **MCP passthrough** (`mcpServers` on `session/new` + `mcpCapabilities`). -6. **Richer prompt content** — image / embedded `resource` blocks (needs a multimodal model path). -7. **Usage reporting** (`usage_update`) — the harness already records token usage internally (on `assistant/message`). -8. **Editor filesystem delegation** (`fs/read_text_file` / `fs/write_text_file`) — lets the agent see unsaved buffers; lower priority since the harness has direct disk access. +2. **Agent plan** (`sessionUpdate: 'plan'`) — surface the loop's plan as structured entries. +3. **Slash commands** (`available_commands_update`). +4. **MCP passthrough** (`mcpServers` on `session/new` + `mcpCapabilities`). +5. **Richer prompt content** — image / embedded `resource` blocks (needs a multimodal model path). +6. **Usage reporting** (`usage_update`) — the harness already records token usage internally (on `assistant/message`). +7. **Editor filesystem delegation** (`fs/read_text_file` / `fs/write_text_file`) — lets the agent see unsaved buffers; lower priority since the harness has direct disk access. ## Out of scope diff --git a/packages/ui/acp/package.json b/packages/ui/acp/package.json index 71efc51a07..6d0e8ed1d3 100644 --- a/packages/ui/acp/package.json +++ b/packages/ui/acp/package.json @@ -34,6 +34,7 @@ "@deepseek-ai/dsh-sandbox": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-session-persistence": "^0.0.1", + "@deepseek-ai/dsh-system-prompt": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", "@deepseek-ai/dsh-user-approval": "^0.0.1", "@deepseek-ai/dsh-user-interaction": "^0.0.1", diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 404384bda8..e8fb326d9b 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -34,13 +34,15 @@ import { type PromptRequest, type PromptResponse, type SessionConfigOption, + type SessionConfigSelectGroup, + type SessionConfigSelectOption, type SessionNotification, type SetSessionConfigOptionRequest, type SetSessionConfigOptionResponse, type Stream, type StopReason, } from '@agentclientprotocol/sdk' -import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import type { ContentBlock, LlmCallConfig, LlmModelInfo, LlmProviderInfo } from '@deepseek-ai/dsh-llm' import { assertNever, CallId } from '@deepseek-ai/dsh-llm' import type { Agent } from '@deepseek-ai/dsh-agent' import { AgentId } from '@deepseek-ai/dsh-agent' @@ -52,6 +54,9 @@ import type { ToolCallView, ToolRegistry, ToolResultView, TerminalResultView } f // Side-effect type import: declaration-merges `ctx.sessionPersistence` onto // Context (the bridge injects it and reads `list()` for load cwd validation). import type {} from '@deepseek-ai/dsh-session-persistence' +// Side-effect type import: declaration-merges prompt assembly onto Context and +// the scoped waterfall used to keep persona variables aligned with requests. +import type {} from '@deepseek-ai/dsh-system-prompt' // Side-effect type import: declaration-merges the `approval/request` waterfall // the bridge answers for its own agents (see the approval answerer below). import type {} from '@deepseek-ai/dsh-user-approval' @@ -73,7 +78,7 @@ import { export const name = 'acp' // Interface services back advertised loading, tool-owned presentation with a generic fallback, and interaction. // TODO(acp-session-inject): remove `sessions`; the bridge never reads it, and ownership is already behind `agents`. -export const inject = ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction'] +export const inject = ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction', 'llm', 'systemPrompt'] /** Build an ACP invalid-params error with visible human detail. */ function invalidParams(detail: string): RequestError { @@ -214,6 +219,31 @@ export const Config: Schema = Schema.object({ model: Schema.string(), }) +/** Provider/model pair selected for one ACP session. */ +interface LlmTarget { + provider: string + model: string +} + +/** Mutable target shared by one agent's scoped assembly and request listeners. */ +interface LlmTargetRef { + current: LlmTarget | undefined + /** Step snapshot captured by prompt assembly so target switches cannot split prompt and request. */ + assembled: LlmTarget | undefined +} + +/** One resolved ACP model selector plus its opaque value lookup. */ +interface ModelDirectory { + option: Extract | undefined + targets: ReadonlyMap +} + +/** One provider and its adapter-advertised models, detached for one RPC. */ +interface ModelCatalogEntry { + provider: LlmProviderInfo + models: LlmModelInfo[] +} + /** Per-session bridge state keyed by ACP session id. */ interface SessionRecord { sessionId: SessionId @@ -224,6 +254,8 @@ interface SessionRecord { presenter: ToolPresenter /** Session-creation snapshot of terminal-card support for call/result consistency. */ terminalEnabled: boolean + /** Session-local provider/model selection and the current step snapshot. */ + target: LlmTargetRef /** In-flight prompt and its captured turn number for exact settlement. */ inflight: { resolve: (reason: StopReason) => void @@ -246,6 +278,7 @@ interface SessionRecord { export function apply(ctx: Context, config: AcpConfig): void { // Handlers run later outside this injection scope, so capture services now. const agents = ctx.agents + const llm = ctx.llm const sessionPersistence = ctx.sessionPersistence const logger = ctx.logger const tools = ctx.tools @@ -253,6 +286,101 @@ export function apply(ctx: Context, config: AcpConfig): void { // Presenter failures are logged and contained per session or replay. const makePresenter = (agent?: Agent): ToolPresenter => new ToolPresenter(tools, (message) => { logger.warn(message) }, agent) + /** Resolve a complete target only; partial config remains available to other request listeners. */ + const configuredTarget = (): LlmTarget | undefined => config.provider !== undefined && config.model !== undefined + ? { provider: config.provider, model: config.model } + : undefined + + /** Install the ACP target as an agent-scoped prompt/request override. */ + const installTarget = (agentCtx: Context, target: LlmTargetRef): void => { + const agent = agentCtx.agent + /* v8 ignore next -- setup is invoked only with the freshly created agent's scoped context. */ + if (agent === undefined) throw new Error('acp: agent setup has no scoped agent') + const logged = agent.session.requestHeader()?.config + if (logged !== undefined) target.current = { provider: logged.provider, model: logged.model } + + // Capture once at assembly entry and apply the same pair after downstream + // prompt listeners. A selector change during async assembly therefore takes + // effect on the following step instead of splitting {{model}} from routing. + agentCtx.on('system-prompt/assemble', async (_assembly, _context, next) => { + const selected = target.current + const assembled = await next() + target.assembled = selected + if (selected === undefined) return assembled + return { + ...assembled, + variables: { + ...assembled.variables, + provider: selected.provider, + model: selected.model, + }, + } + }) + agentCtx.on('agent/request', async (_agent, _turn, _step, _callConfig, next): Promise => { + const resolved = await next() + const selected = target.assembled + return selected === undefined ? resolved : { + ...resolved, + provider: selected.provider, + model: selected.model, + } + }) + } + + /** Opaque ACP value preserving both routing dimensions. */ + const targetValue = (target: LlmTarget): string => JSON.stringify([target.provider, target.model]) + + /** Read one detached advisory catalog snapshot before mutating session state. */ + const readModelCatalog = async (): Promise => Promise.all( + llm.listProviders().map(async provider => ({ + provider, + models: await llm.listModels(provider.id), + })), + ) + + /** Resolve one catalog snapshot into the ACP model selector for a session. */ + const modelDirectory = (catalog: readonly ModelCatalogEntry[], current: LlmTarget | undefined): ModelDirectory => { + if (current === undefined) return { option: undefined, targets: new Map() } + const models = catalog.map(entry => ({ provider: entry.provider, models: [...entry.models] })) + const currentProvider = models.find(entry => entry.provider.id === current.provider) + if (currentProvider === undefined) return { option: undefined, targets: new Map() } + if (!currentProvider.models.some(model => model.id === current.model)) { + currentProvider.models = [...currentProvider.models, { + provider: current.provider, + id: current.model, + name: current.model, + }] + } + + const targets = new Map() + const groups = models.flatMap(({ provider, models: entries }) => { + if (entries.length === 0) return [] + const options = entries.map((model): SessionConfigSelectOption => { + const target = { provider: model.provider, model: model.id } + const value = targetValue(target) + targets.set(value, target) + return { + value, + name: model.name, + ...model.description === undefined ? {} : { description: model.description }, + } + }) + return [{ group: provider.id, name: provider.name, options } satisfies SessionConfigSelectGroup] + }) + return { + option: { + id: 'model', + name: 'Model', + description: 'Sets this session\'s provider and model.', + category: 'model', + type: 'select', + currentValue: targetValue(current), + options: groups.length === 1 ? groups.flatMap(group => group.options) : groups, + }, + targets, + } + } + // TODO(derive-acp-session-id): derive event ids from `agent.session`, verify ownership, then remove the reverse map. // Agent events currently carry only the Agent, so retain `SessionRecord.sessionId` and update both indexes together. // Dropping the forward record lets the weak reverse entry expire. @@ -436,16 +564,17 @@ export function apply(ctx: Context, config: AcpConfig): void { // --- The ACP Agent method surface ----------------------------------------- - /** - * Build the single Permissions option when `ctx.permission` is composed. - * Its value comes from the session log, overlaid by an unanchored idle - * switch, so `session/load` needs no catch-up state. - */ - const configOptionsFor = (agent: Agent, pending: SessionRecord['pendingSwitches'] = {}): SessionConfigOption[] => { + /** Build every ACP session option from the model directory and live services. */ + const configOptionsFor = ( + agent: Agent, + directory: ModelDirectory, + pending: SessionRecord['pendingSwitches'] = {}, + ): SessionConfigOption[] => { + const options = directory.option === undefined ? [] : [directory.option] const presets = ctx.get('permission') - if (presets === undefined) return [] + if (presets === undefined) return options const currentValue = pending.preset ?? presets.current(agent.session.events) - return [{ + return [...options, { id: 'permission', name: 'Permissions', description: 'Sets this session\'s sandbox and approval behavior.', @@ -544,11 +673,15 @@ export function apply(ctx: Context, config: AcpConfig): void { validateWorkspaceParams(params) validateMcpServers(params) const sessionId = SessionId(randomUUID()) + const target: LlmTargetRef = { current: configuredTarget(), assembled: undefined } + const directory = modelDirectory(await readModelCatalog(), target.current) + assertOpen() const handle = await agents.create({ agentId: AgentId(sessionId), sessionId, meta: { cwd: params.cwd }, agentOptions: agentOptions(config), + setup: (agentCtx) => { installTarget(agentCtx, target) }, }) // Creation awaits the unpublished setup transaction. A client disconnect // can therefore close this bridge @@ -567,10 +700,11 @@ export function apply(ctx: Context, config: AcpConfig): void { dispose: () => handle.dispose(), presenter: makePresenter(handle.agent), terminalEnabled: terminalOutputCap, + target, inflight: undefined, pendingSwitches: {}, }) - const configOptions = configOptionsFor(handle.agent) + const configOptions = configOptionsFor(handle.agent, directory) return { sessionId, ...configOptions.length > 0 ? { configOptions } : {} } }, @@ -615,10 +749,14 @@ export function apply(ctx: Context, config: AcpConfig): void { throw invalidParams(`session ${sessionId} cwd mismatch: persisted ${persistedCwd}, requested ${params.cwd}`) } } + const catalog = await readModelCatalog() + assertOpen() + const target: LlmTargetRef = { current: configuredTarget(), assembled: undefined } const handle = await agents.resume({ agentId: AgentId(sessionId), resumeSessionId: sessionId, agentOptions: agentOptions(config), + setup: (agentCtx) => { installTarget(agentCtx, target) }, }) // The bridge may have torn down (disposal / client disconnect) while // resume() was pending. Its listeners are gone, so installing a record @@ -634,6 +772,7 @@ export function apply(ctx: Context, config: AcpConfig): void { await handle.dispose() throw invalidParams('connection closed during session/load') } + const directory = modelDirectory(catalog, target.current) const agent = handle.agent bySession.set(agent, sessionId) // Snapshot the terminal capability ONCE for this session (used by both @@ -646,6 +785,7 @@ export function apply(ctx: Context, config: AcpConfig): void { dispose: () => handle.dispose(), presenter: makePresenter(agent), terminalEnabled, + target, inflight: undefined, pendingSwitches: {}, } @@ -671,7 +811,7 @@ export function apply(ctx: Context, config: AcpConfig): void { for (const event of agent.session.events) { streamSessionEventUpdate(sessionId, event, notify, replayPresenter, replayTerminal) } - const configOptions = configOptionsFor(agent) + const configOptions = configOptionsFor(agent, directory) return configOptions.length > 0 ? { configOptions } : {} } finally { loadingIds.delete(sessionId) @@ -725,18 +865,35 @@ export function apply(ctx: Context, config: AcpConfig): void { return Promise.resolve() }, - setSessionConfigOption(params: SetSessionConfigOptionRequest): Promise { + async setSessionConfigOption(params: SetSessionConfigOptionRequest): Promise { assertOpen() const rec = requireSession(SessionId(params.sessionId)) - // The advertised option is a select, so the boolean-shaped variant of - // the request is a protocol misuse regardless of configId. + // Every advertised option is a select, so the boolean-shaped variant + // is a protocol misuse regardless of configId. if (typeof params.value !== 'string') { throw invalidParams(`config option ${params.configId} is a select; boolean values are not accepted`) } + let directory = modelDirectory(await readModelCatalog(), rec.target.current) // Open-turn switches append immediately; idle switches wait for the // next prompt-submit. Only values advertised by this composition are // accepted, and the session log remains the durable store. switch (params.configId) { + case 'model': { + const target = directory.targets.get(params.value) + if (target === undefined) { + throw invalidParams(`unknown model value ${JSON.stringify(params.value)}`) + } + rec.target.current = { ...target } + const option = directory.option + /* v8 ignore next -- `targets` is populated only while constructing + this selector; a found target therefore proves it exists. */ + if (option === undefined) throw internalError('model directory target has no selector') + directory = { + ...directory, + option: { ...option, currentValue: params.value }, + } + break + } case 'permission': { const presets = ctx.get('permission') if (presets === undefined) { @@ -758,7 +915,7 @@ export function apply(ctx: Context, config: AcpConfig): void { } // The spec requires the COMPLETE refreshed config state in the response // (a change may cascade); ours are independent, but the contract holds. - return Promise.resolve({ configOptions: configOptionsFor(rec.agent, rec.pendingSwitches) }) + return { configOptions: configOptionsFor(rec.agent, directory, rec.pendingSwitches) } }, } } diff --git a/packages/ui/acp/tests/config-options.spec.ts b/packages/ui/acp/tests/config-options.spec.ts index f914004e8b..806aaa3ab6 100644 --- a/packages/ui/acp/tests/config-options.spec.ts +++ b/packages/ui/acp/tests/config-options.spec.ts @@ -40,6 +40,26 @@ function permissionOption(currentValue: string): object { } } +function modelValue(provider = 'mock', model = 'mock'): string { + return JSON.stringify([provider, model]) +} + +function modelOption(currentValue = modelValue()): object { + return { + id: 'model', + name: 'Model', + description: 'Sets this session\'s provider and model.', + category: 'model', + type: 'select', + currentValue, + options: [{ value: modelValue(), name: 'Mock' }], + } +} + +function optionsWithPermission(currentValue: string): object[] { + return [modelOption(), permissionOption(currentValue)] +} + describe('acp bridge — session config options', () => { let storageDir: string let h: BridgeHarness | undefined @@ -64,19 +84,111 @@ describe('acp bridge — session config options', () => { return harness } - it('advertises no configOptions without the permission service — even with both knobs composed', async () => { + it('advertises the model selector without requiring the permission service', async () => { h = await makeBridgeHarness({ storageDir }) await h.ctx.plugin(SandboxedLocalExecutor, { timeoutMs: 10_000 }) await h.ctx.plugin(ApprovalService) await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const res = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - expect(res.configOptions).toBeUndefined() + expect(res.configOptions).toEqual([modelOption()]) + }) + + it('groups models by provider and switches routing plus prompt variables as one session target', async () => { + h = await makeBridgeHarness({ + storageDir, + script: [textResponse('ok')], + config: { provider: 'alpha', model: 'a1' }, + persona: 'Route {{provider}} / {{model}}', + catalog: { + providers: [{ id: 'alpha', name: 'Alpha' }, { id: 'beta', name: 'Beta' }], + models: [ + { provider: 'alpha', id: 'a1', name: 'Alpha One', description: 'Fast' }, + { provider: 'beta', id: 'b1', name: 'Beta One' }, + ], + }, + }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const created = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + expect(created.configOptions).toEqual([{ + id: 'model', + name: 'Model', + description: 'Sets this session\'s provider and model.', + category: 'model', + type: 'select', + currentValue: modelValue('alpha', 'a1'), + options: [ + { group: 'alpha', name: 'Alpha', options: [{ value: modelValue('alpha', 'a1'), name: 'Alpha One', description: 'Fast' }] }, + { group: 'beta', name: 'Beta', options: [{ value: modelValue('beta', 'b1'), name: 'Beta One' }] }, + ], + }]) + + const switched = await h.client.setSessionConfigOption({ + sessionId: created.sessionId, + configId: 'model', + value: modelValue('beta', 'b1'), + }) + expect(switched.configOptions?.[0]).toMatchObject({ currentValue: modelValue('beta', 'b1') }) + await h.client.prompt({ sessionId: created.sessionId, prompt: [{ type: 'text', text: 'use beta' }] }) + expect(h.adapter.requests[0]).toMatchObject({ + provider: 'beta', + model: 'b1', + }) + expect(h.adapter.requests[0]?.system).toContain('Route beta / b1') + expect(h.ctx.agents.list()[0]?.session.requestHeader()?.config).toMatchObject({ provider: 'beta', model: 'b1' }) + }) + + it('adds the configured private model to an advisory catalog and ignores empty non-current groups', async () => { + h = await makeBridgeHarness({ + storageDir, + config: { provider: 'alpha', model: 'private-model' }, + catalog: { + providers: [{ id: 'alpha', name: 'Alpha' }, { id: 'empty', name: 'Empty' }], + models: [{ provider: 'alpha', id: 'public-model', name: 'Public Model' }], + }, + }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const res = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + expect(res.configOptions?.[0]).toMatchObject({ + currentValue: modelValue('alpha', 'private-model'), + options: [ + { value: modelValue('alpha', 'public-model'), name: 'Public Model' }, + { value: modelValue('alpha', 'private-model'), name: 'private-model' }, + ], + }) + }) + + it('omits model selection without a complete or registered current target', async () => { + h = await makeBridgeHarness({ storageDir, config: { model: undefined } }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const missing = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + expect(missing.configOptions).toBeUndefined() + await h.dispose() + + h = await makeBridgeHarness({ storageDir, config: { provider: 'unregistered', model: 'm' } }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const unknown = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + expect(unknown.configOptions).toBeUndefined() + }) + + it('leaves model-less agents available to another agent/request supplier', async () => { + h = await makeBridgeHarness({ storageDir, config: { model: undefined }, script: [textResponse('ok')] }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + const agent = h.ctx.agents.list()[0] + if (agent === undefined) throw new Error('expected an agent') + agent.ctx.on('agent/request', async (_agent, _turn, _step, callConfig, _next) => ({ + ...callConfig, + provider: 'mock', + model: 'mock', + })) + await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'supplied elsewhere' }] }) + expect(h.adapter.requests[0]).toMatchObject({ provider: 'mock', model: 'mock' }) }) it('advertises the Permissions select with the default preset current', async () => { h = await presetStack() const res = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - expect(res.configOptions).toEqual([permissionOption('workspace-write')]) + expect(res.configOptions).toEqual(optionsWithPermission('workspace-write')) }) it('an idle switch is pending (overlaid, not yet logged), then anchors inside the next prompt\'s turn', async () => { @@ -84,7 +196,7 @@ describe('acp bridge — session config options', () => { const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) const after = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) - expect(after.configOptions).toEqual([permissionOption('danger-full-access')]) + expect(after.configOptions).toEqual(optionsWithPermission('danger-full-access')) const session = h.ctx.agents.list()[0]?.session expect(session?.events.some(e => e.type === 'permission/preset' || e.type === 'bash/sandbox-mode' || e.type === 'approval/policy')).toBe(false) @@ -105,7 +217,7 @@ describe('acp bridge — session config options', () => { const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) const again = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) - expect(again.configOptions).toEqual([permissionOption('danger-full-access')]) + expect(again.configOptions).toEqual(optionsWithPermission('danger-full-access')) await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'anchor' }] }) const events = h.ctx.agents.list()[0]?.session.events ?? [] expect(events.filter(e => e.type === 'permission/preset')).toHaveLength(1) @@ -119,7 +231,7 @@ describe('acp bridge — session config options', () => { const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) const back = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'workspace-write' }) - expect(back.configOptions).toEqual([permissionOption('workspace-write')]) + expect(back.configOptions).toEqual(optionsWithPermission('workspace-write')) await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'anchor' }] }) const events = h.ctx.agents.list()[0]?.session.events ?? [] expect(events.some(e => e.type === 'permission/preset' || e.type === 'bash/sandbox-mode' || e.type === 'approval/policy')).toBe(false) @@ -129,10 +241,10 @@ describe('acp bridge — session config options', () => { h = await presetStack({ script: [textResponse('ok')] }) const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) const echo = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'workspace-write' }) - expect(echo.configOptions).toEqual([permissionOption('workspace-write')]) + expect(echo.configOptions).toEqual(optionsWithPermission('workspace-write')) await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) const repeat = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) - expect(repeat.configOptions).toEqual([permissionOption('danger-full-access')]) + expect(repeat.configOptions).toEqual(optionsWithPermission('danger-full-access')) await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'anchor' }] }) const events = h.ctx.agents.list()[0]?.session.events ?? [] expect(events.filter(e => e.type === 'permission/preset').map(e => e.data)).toEqual([{ preset: 'danger-full-access' }]) @@ -167,6 +279,8 @@ describe('acp bridge — session config options', () => { // This composition never advertised `permission`. await expect(h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' })) .rejects.toThrow(/unknown permission value/) + await expect(h.client.setSessionConfigOption({ sessionId, configId: 'model', value: modelValue('mock', 'missing') })) + .rejects.toThrow(/unknown model value/) await expect(h.client.setSessionConfigOption({ sessionId, configId: 'permission', type: 'boolean', value: true })) .rejects.toThrow(/select; boolean values are not accepted/) }) @@ -184,9 +298,31 @@ describe('acp bridge — session config options', () => { const b = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) await h.client.setSessionConfigOption({ sessionId: a.sessionId, configId: 'permission', value: 'danger-full-access' }) const bAfter = await h.client.setSessionConfigOption({ sessionId: b.sessionId, configId: 'permission', value: 'workspace-write' }) - expect(bAfter.configOptions).toEqual([permissionOption('workspace-write')]) + expect(bAfter.configOptions).toEqual(optionsWithPermission('workspace-write')) const aAfter = await h.client.setSessionConfigOption({ sessionId: a.sessionId, configId: 'permission', value: 'danger-full-access' }) - expect(aAfter.configOptions).toEqual([permissionOption('danger-full-access')]) + expect(aAfter.configOptions).toEqual(optionsWithPermission('danger-full-access')) + }) + + it('keeps model targets isolated across concurrent sessions', async () => { + h = await makeBridgeHarness({ + storageDir, + script: [textResponse('a'), textResponse('b')], + config: { provider: 'mock', model: 'one' }, + catalog: { + providers: [{ id: 'mock', name: 'Mock' }], + models: [ + { provider: 'mock', id: 'one', name: 'One' }, + { provider: 'mock', id: 'two', name: 'Two' }, + ], + }, + }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const a = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + const b = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + await h.client.setSessionConfigOption({ sessionId: a.sessionId, configId: 'model', value: modelValue('mock', 'two') }) + await h.client.prompt({ sessionId: a.sessionId, prompt: [{ type: 'text', text: 'a' }] }) + await h.client.prompt({ sessionId: b.sessionId, prompt: [{ type: 'text', text: 'b' }] }) + expect(h.adapter.requests.map(request => request.model)).toEqual(['two', 'one']) }) it('a knob drifted outside the table derives a visible-but-untargetable custom current', async () => { @@ -199,12 +335,12 @@ describe('acp bridge — session config options', () => { agent.session.append('bash/sandbox-mode', { mode: 'read-only' }) agent.session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) const echo = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'custom' }) - const option = echo.configOptions?.[0] + const option = echo.configOptions?.find(entry => entry.id === 'permission') expect(option).toMatchObject({ currentValue: 'custom' }) if (option === undefined || !('options' in option)) throw new Error('expected a select option') expect(option.options.map(o => 'value' in o ? o.value : o)).toEqual(['workspace-write', 'danger-full-access', 'custom']) const away = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) - const afterOption = away.configOptions?.[0] + const afterOption = away.configOptions?.find(entry => entry.id === 'permission') expect(afterOption).toMatchObject({ currentValue: 'danger-full-access' }) if (afterOption === undefined || !('options' in afterOption)) throw new Error('expected a select option') expect(afterOption.options.map(o => 'value' in o ? o.value : o)).toEqual(['workspace-write', 'danger-full-access']) @@ -223,6 +359,52 @@ describe('acp bridge — session config options', () => { loader = await presetStack() const res = await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] }) - expect(res.configOptions).toEqual([permissionOption('danger-full-access')]) + expect(res.configOptions).toEqual(optionsWithPermission('danger-full-access')) + }) + + it('session/load restores the last requested provider/model from the request header', async () => { + const catalog = { + providers: [{ id: 'mock', name: 'Mock' }], + models: [ + { provider: 'mock', id: 'one', name: 'One' }, + { provider: 'mock', id: 'two', name: 'Two' }, + ], + } + h = await makeBridgeHarness({ + storageDir, + script: [textResponse('ok')], + config: { provider: 'mock', model: 'one' }, + catalog, + }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + await h.client.setSessionConfigOption({ sessionId, configId: 'model', value: modelValue('mock', 'two') }) + await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'persist target' }] }) + await h.dispose() + h = undefined + + loader = await makeBridgeHarness({ storageDir, config: { provider: 'mock', model: 'one' }, catalog }) + await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const loaded = await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] }) + expect(loaded.configOptions?.find(option => option.id === 'model')).toMatchObject({ + currentValue: modelValue('mock', 'two'), + }) + }) + + it('session/load omits config options when the persisted session has no target or permission service', async () => { + h = await makeBridgeHarness({ storageDir, config: { model: undefined } }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + const agent = h.ctx.agents.list()[0] + if (agent === undefined) throw new Error('expected an agent') + agent.inject([{ type: 'text', text: 'checkpoint' }], { source: { kind: 'plugin', plugin: 'test' } }) + await agent.whenIdle() + await h.dispose() + h = undefined + + loader = await makeBridgeHarness({ storageDir, config: { model: undefined } }) + await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const loaded = await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] }) + expect(loaded.configOptions).toBeUndefined() }) }) diff --git a/packages/ui/acp/tests/harness.ts b/packages/ui/acp/tests/harness.ts index a667243a7d..38ff7d515c 100644 --- a/packages/ui/acp/tests/harness.ts +++ b/packages/ui/acp/tests/harness.ts @@ -5,7 +5,7 @@ */ import { Context } from 'cordis' -import LlmService, { CallId, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm' +import LlmService, { CallId, type GenerateOptions, type LlmModelInfo, type LlmProviderInfo, type StreamChunk } from '@deepseek-ai/dsh-llm' import { LlmAdapter } from '@deepseek-ai/dsh-llm' import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' @@ -39,10 +39,24 @@ import { type AcpConfig } from '../src/index.ts' /** A scripted mock adapter (mirrors the agent-loop test adapter). */ class MockAdapter extends LlmAdapter { requests: GenerateOptions[] = [] - constructor(private script: (StreamChunk[] | 'hang')[]) { + constructor( + private script: (StreamChunk[] | 'hang')[], + private readonly providers: readonly LlmProviderInfo[], + private readonly models: readonly LlmModelInfo[], + ) { super() } + override providerInfo(provider: string): LlmProviderInfo { + const info = this.providers.find(entry => entry.id === provider) + if (info === undefined) throw new Error(`MockAdapter: unknown provider ${provider}`) + return info + } + + override listModels(provider: string): Promise { + return Promise.resolve(this.models.filter(model => model.provider === provider)) + } + async * stream(options: GenerateOptions): AsyncIterable { this.requests.push(options) const entry = this.script.shift() @@ -142,6 +156,9 @@ export interface BridgeHarness { storageDir: string } +/** Test-only overrides preserve explicit undefined to suppress harness defaults. */ +type AcpConfigOverrides = { [K in keyof AcpConfig]?: AcpConfig[K] | undefined } + /** * Build the bridge + a connected client over an in-memory transport pair. * @@ -155,7 +172,9 @@ export interface BridgeHarness { */ export async function makeBridgeHarness(options: { script?: (StreamChunk[] | 'hang')[] - config?: Partial + config?: AcpConfigOverrides + /** Provider-neutral directory exposed to ACP model-selection tests. */ + catalog?: { providers: LlmProviderInfo[]; models: LlmModelInfo[] } /** Deployment persona for the tree (the system-prompt plugin's config). */ persona?: string storageDir: string @@ -185,7 +204,11 @@ export async function makeBridgeHarness(options: { withFs?: boolean fsCwd?: string } = { storageDir: '' }): Promise { - const adapter = new MockAdapter(options.script ?? []) + const catalog = options.catalog ?? { + providers: [{ id: 'mock', name: 'Mock' }], + models: [{ provider: 'mock', id: 'mock', name: 'Mock' }], + } + const adapter = new MockAdapter(options.script ?? [], catalog.providers, catalog.models) const ctx = new Context() await ctx.plugin(LlmService) @@ -211,7 +234,7 @@ export async function makeBridgeHarness(options: { await ctx.plugin(FsPolicy) await ctx.plugin(ToolFs) } - ctx.llm.registerAdapter(['mock'], adapter) + ctx.llm.registerAdapter(catalog.providers.map(provider => provider.id), adapter) // Two identity byte pipes cross-wired into the two ndJsonStreams: bytes the agent writes flow // to the client's reader and vice versa. (ndJsonStream takes (output, input): the agent @@ -272,7 +295,7 @@ export async function makeBridgeHarness(options: { }) // Default route fields only when the caller omitted them; explicit undefined values must survive. - const cfg: AcpConfig = { stream: agentStream, ...options.config } + const cfg = { stream: agentStream, ...options.config } as AcpConfig if (!(options.config && 'provider' in options.config)) cfg.provider = 'mock' if (!(options.config && 'model' in options.config)) cfg.model = 'mock' // Mount the bridge the way production does: as a cordis plugin (via `ctx.plugin` with the diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 6f25f53ffc..2b3646c731 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -262,6 +262,6 @@ export class HarnessSdkServer { } private hasAdapterFor(provider: string): boolean { - return this.ctx.get('llm')?.providers().includes(provider) ?? false + return this.ctx.get('llm')?.listProviders().some(entry => entry.id === provider) ?? false } } diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 28d1eda0f8..1dbeecb68a 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -399,7 +399,7 @@ describe('HarnessSdkServer', () => { expect(inspect.hasAdapterFor('missing-provider')).toBe(false) await server.initialize({ cwd: storageDir, provider: 'deepseek', model: 'preinstalled-model' }) - expect(ctx.get('llm')?.providers().filter(provider => provider === 'deepseek')).toEqual(['deepseek']) + expect(ctx.get('llm')?.listProviders().filter(provider => provider.id === 'deepseek')).toEqual([{ id: 'deepseek', name: 'DeepSeek' }]) await server.shutdown() } finally { await ctx.fiber.dispose() @@ -418,7 +418,7 @@ describe('HarnessSdkServer', () => { await expect(server.initialize({ cwd: storageDir, provider: 'private', model: 'new-model' })) .rejects.toThrow('no adapter registered for provider "private"') - expect(ctx.get('llm')?.providers()).toEqual(['deepseek']) + expect(ctx.get('llm')?.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }]) await server.shutdown() } finally { await ctx.fiber.dispose() @@ -519,7 +519,7 @@ describe('HarnessSdkServer', () => { const ctx = { on: vi.fn(() => () => undefined), agents: { create, get: () => undefined }, - get: () => ({ providers: () => ['mock'] }), + get: () => ({ listProviders: () => [{ id: 'mock', name: 'Mock' }] }), } as unknown as Context const server = new HarnessSdkServer(ctx, new FakeTransport()) as unknown as { initialize(params: { cwd: string; provider: string; model: string }): Promise diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index d7324a8712..745362f3c2 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -7,6 +7,8 @@ { "doc": "docs/core-data-structures/core.md", "symbol": "Message", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "MessageSourceMap", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "FinishReasonMap", "source": "packages/llm/llm/src/types.ts" }, + { "doc": "docs/core-data-structures/core.md", "symbol": "LlmProviderInfo", "source": "packages/llm/llm/src/types.ts" }, + { "doc": "docs/core-data-structures/core.md", "symbol": "LlmModelInfo", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "GenerateOptions", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "ToolSchema", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "LlmCallConfig", "source": "packages/llm/llm/src/call-config.ts" }, From f689fde0bfec5091fb424e3604bfd04a20284d03 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Wed, 15 Jul 2026 13:39:56 +0800 Subject: [PATCH 136/359] test(acp): cover model selector in keyless e2e --- examples/acp-agent/tests/escalation.e2e.ts | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/examples/acp-agent/tests/escalation.e2e.ts b/examples/acp-agent/tests/escalation.e2e.ts index 1a690367aa..e3e20524ff 100644 --- a/examples/acp-agent/tests/escalation.e2e.ts +++ b/examples/acp-agent/tests/escalation.e2e.ts @@ -63,7 +63,7 @@ function spawnAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once'): Spawn // A dummy key lets the deepseek adapter boot keyless (presence-checked at // apply, used only on a real model call); the with-key tests carry the // real key, so the fallback is inert there. - env: { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot', TSX_TSCONFIG_PATH: repoTsconfig }, + env: { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY || 'sk-dummy-for-boot', TSX_TSCONFIG_PATH: repoTsconfig }, stdio: ['pipe', 'pipe', 'pipe'], }, ) @@ -115,15 +115,16 @@ describe('default sandbox composition keyless smoke (real cordis.yml via the Loa expect(sessionId.length).toBeGreaterThan(0) }, 30_000) - it('advertises the Permissions select and honors a switch end to end (no key, no model)', async () => { + it('advertises model and Permissions selects and honors a permission switch without a model call', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-config-')) spawned = spawnAcpAgent(workdir, 'reject-once') const { client } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const created = await client.newSession({ cwd: workdir, mcpServers: [] }) const advertised = created.configOptions ?? [] + const modelValue = JSON.stringify(['deepseek', 'deepseek-v4-flash']) expect(advertised.map(option => [option.id, 'currentValue' in option ? option.currentValue : undefined])) - .toEqual([['permission', 'workspace-write']]) + .toEqual([['model', modelValue], ['permission', 'workspace-write']]) const afterFullAccess = await client.setSessionConfigOption({ sessionId: created.sessionId, configId: 'permission', value: 'danger-full-access', }) @@ -133,7 +134,7 @@ describe('default sandbox composition keyless smoke (real cordis.yml via the Loa sessionId: created.sessionId, configId: 'permission', value: 'danger-full-access', }) expect((again.configOptions ?? []).map(option => [option.id, 'currentValue' in option ? option.currentValue : undefined])) - .toEqual([['permission', 'danger-full-access']]) + .toEqual([['model', modelValue], ['permission', 'danger-full-access']]) await expect(client.setSessionConfigOption({ sessionId: created.sessionId, configId: 'permission', value: 'plan', })).rejects.toThrow(/unknown permission value/) From d3f8cb0f23b6cf074c214aac9fb3051977193c0d Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Wed, 15 Jul 2026 13:45:19 +0800 Subject: [PATCH 137/359] fix: harden replay and pi-ai request boundaries --- packages/core/agent-loop/src/loop.ts | 12 ++++++----- .../tests/contract-regressions.spec.ts | 20 +++++++++++++++++++ packages/llm/llm-pi-ai/src/adapter.ts | 12 ++++++++++- packages/llm/llm-pi-ai/src/config.ts | 10 +++++----- packages/llm/llm-pi-ai/tests/adapter.spec.ts | 16 ++++++++++++++- 5 files changed, 58 insertions(+), 12 deletions(-) diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 501c673577..ebae2c898e 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -6,7 +6,7 @@ */ import type { Context } from 'cordis' -import type { FinishReason, GenerateOptions, LlmCallConfig, Message } from '@deepseek-ai/dsh-llm' +import type { ContentBlock, FinishReason, GenerateOptions, LlmCallConfig, Message } from '@deepseek-ai/dsh-llm' import { isDeepStrictEqual } from 'node:util' import { BlockAssembler, HarnessError, deepFreeze } from '@deepseek-ai/dsh-llm' import { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' @@ -529,20 +529,22 @@ async function runStep( if (assembler.finish.kind === 'max-tokens') { const assembled = assembler.message() + const assembledContent = structuredClone(assembled.content) let message: Message = withoutToolCalls(assembled) message = withoutToolCalls(await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message))) // Preserve usage even when max-token truncation produced no content. - recordAssistantMessage(session, turn, step, header.config, assembled, message, assembler, chunkSeqs) + recordAssistantMessage(session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs) return { hadToolCalls: false, finish: assembler.finish } } // Record the post-waterfall message that tool dispatch uses. const assembled = assembler.message() + const assembledContent = structuredClone(assembled.content) let message: Message = assembled message = await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message)) // Empty messages exist only to carry usage; the helper also omits empty chunk provenance. - recordAssistantMessage(session, turn, step, header.config, assembled, message, assembler, chunkSeqs) + recordAssistantMessage(session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs) // Tool execution stays sequential; recheck abort around each normalized result. const toolCalls = message.content.filter(block => block.type === 'tool-call') @@ -600,7 +602,7 @@ function recordAssistantMessage( turn: number, step: number, config: LlmCallConfig, - assembled: Message, + assembledContent: ContentBlock[], message: Message, assembler: BlockAssembler, chunkSeqs: number[], @@ -615,7 +617,7 @@ function recordAssistantMessage( provenance: assistantProvenance( config, assembler.replayState, - isDeepStrictEqual(message.content, assembled.content), + isDeepStrictEqual(message.content, assembledContent), ), ...assembler.usage === undefined ? {} : { usage: assembler.usage }, }, diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 746113a0e5..5ee3f563a7 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -110,6 +110,26 @@ describe('session log records what agent/step-result actually produced', () => { provider: 'mock', model: 'next-model', replayState, }) }) + + it('drops adapter replay state when step-result mutates assembled content in place', async () => { + const response = textResponse('original') + response[response.length - 1] = { type: 'finish', reason: { kind: 'stop' }, replayState: { private: 'state' } } + const adapter = new MockAdapter([response]) + const ctx = await harness(adapter) + ctx.on('agent/step-result', async (_agent, _turn, _step, message) => { + const block = message.content[0] + if (block?.type === 'text') block.text = 'mutated' + return message + }) + const agent = ctx.agentLoop.create(AgentId('mutated-replay-state'), { provider: 'mock', model: 'next-model' }) + + send(agent, 'go') + await waitForIdle(ctx, agent) + + const recorded = agent.session.events.find(event => event.type === 'assistant/message') + expect(recorded?.type === 'assistant/message' && recorded.data.content).toEqual([{ type: 'text', text: 'mutated' }]) + expect(recorded?.type === 'assistant/message' && recorded.data.provenance.replayState).toBeUndefined() + }) }) describe('abort during tool execution ends the turn', () => { diff --git a/packages/llm/llm-pi-ai/src/adapter.ts b/packages/llm/llm-pi-ai/src/adapter.ts index 8eb37cfb4f..26e28ecd1f 100644 --- a/packages/llm/llm-pi-ai/src/adapter.ts +++ b/packages/llm/llm-pi-ai/src/adapter.ts @@ -53,6 +53,16 @@ function profileOptions(profile: PiAiProviderProfile): SimpleStreamOptions { } } +/** Merge deployment headers while removing case-insensitive attribution collisions. */ +function requestHeaders(headers: Readonly> | undefined): Record { + const attribution = attributionHeaders() + const reserved = new Set(Object.keys(attribution).map(name => name.toLowerCase())) + return { + ...Object.fromEntries(Object.entries(headers ?? {}).filter(([name]) => !reserved.has(name.toLowerCase()))), + ...attribution, + } +} + /** * pi-ai-backed multi-provider adapter. Model descriptors are resolved for each * request, so models need not be registered during the Cordis lifecycle. @@ -103,7 +113,7 @@ export class PiAiAdapter extends LlmAdapter { signal: controller.signal, // Profile headers are deployment-owned; attribution names are // Harness-owned and therefore win collisions. - headers: { ...profile.headers, ...attributionHeaders() }, + headers: requestHeaders(profile.headers), }) yield* toStreamChunks(events) } finally { diff --git a/packages/llm/llm-pi-ai/src/config.ts b/packages/llm/llm-pi-ai/src/config.ts index b41ca2dd61..f7570aff64 100644 --- a/packages/llm/llm-pi-ai/src/config.ts +++ b/packages/llm/llm-pi-ai/src/config.ts @@ -58,10 +58,10 @@ const profile = z.object({ thinkingBudgets, cacheRetention: z.union(['none', 'short', 'long']), transport: z.union(['sse', 'websocket', 'websocket-cached', 'auto']), - timeoutMs: z.number(), - websocketConnectTimeoutMs: z.number(), - maxRetries: z.number(), - maxRetryDelayMs: z.number(), + timeoutMs: z.natural(), + websocketConnectTimeoutMs: z.natural(), + maxRetries: z.natural(), + maxRetryDelayMs: z.natural(), }) /** Runtime schema for {@link Config}. */ @@ -83,7 +83,7 @@ export function resolveProfiles(profiles: readonly PiAiProviderProfile[]): PiAiP if (source.provider.length === 0) throw new Error('llm-pi-ai: provider names must be non-empty') if (!supported.has(source.provider)) throw new Error(`llm-pi-ai: unknown pi-ai provider "${source.provider}"`) if (seen.has(source.provider)) throw new Error(`llm-pi-ai: duplicate provider profile "${source.provider}"`) - if (source.apiKey !== undefined && source.apiKey.length === 0) { + if (source.apiKey !== undefined && source.apiKey.trim().length === 0) { throw new Error(`llm-pi-ai: provider "${source.provider}" has an empty apiKey; omit it to use ambient authentication`) } if (source.baseURL !== undefined && source.baseURL.length === 0) { diff --git a/packages/llm/llm-pi-ai/tests/adapter.spec.ts b/packages/llm/llm-pi-ai/tests/adapter.spec.ts index 5cb065cb48..1767447d7d 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.spec.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.spec.ts @@ -90,7 +90,7 @@ describe('PiAiAdapter provider routing', () => { it('merges profile headers with Harness attribution winning', async () => { const server = await mockServer([{ events: textEvents }]) const ctx = await harness(server.url, { - headers: { 'x-company': 'private', 'user-agent': 'wrong' }, + headers: { 'x-company': 'private', 'User-Agent': 'wrong' }, }) await assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }) expect(server.headers[0]?.['x-company']).toBe('private') @@ -219,9 +219,23 @@ describe('provider profile lifecycle', () => { expect(() => resolveProfiles([{ provider: 'not-real' }])).toThrow(/unknown/) expect(() => resolveProfiles([{ provider: 'openai' }, { provider: 'openai' }])).toThrow(/duplicate/) expect(() => resolveProfiles([{ provider: 'openai', apiKey: '' }])).toThrow(/empty apiKey/) + expect(() => resolveProfiles([{ provider: 'openai', apiKey: ' ' }])).toThrow(/empty apiKey/) expect(() => resolveProfiles([{ provider: 'openai', baseURL: '' }])).toThrow(/empty baseURL/) }) + it('rejects negative or fractional stream tunables at schema validation', () => { + const invalid = [ + { timeoutMs: -1 }, + { websocketConnectTimeoutMs: -1 }, + { maxRetries: -1 }, + { maxRetries: 0.5 }, + { maxRetryDelayMs: -1 }, + ] + for (const entry of invalid) { + expect(() => new LlmPiAi.Config({ providers: [{ provider: 'openai', ...entry }] })).toThrow() + } + }) + it('constructs the adapter directly and rejects routes it does not own', async () => { const adapter = new PiAiAdapter({ profiles: [{ provider: 'openai' }] }) await expect(adapter.listModels('anthropic')).rejects.toMatchObject({ code: 'NO_ADAPTER' }) From f038780ff65691efcce782461848c1b6fdfa67aa Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 14:47:29 +0800 Subject: [PATCH 138/359] feat(llm): add replay token metering (PR2 round 1) --- docs/agent-lifecycle.md | 2 + docs/architecture.md | 3 +- docs/capability-seams.md | 5 + docs/config-catalog.md | 71 +- docs/cordis-catalog/services.md | 14 +- docs/core-data-structures/compaction.md | 2 +- docs/core-data-structures/core.md | 1 + docs/core-data-structures/session.md | 4 + docs/core-data-structures/token-meter.md | 52 + docs/event-producer-consumer.md | 2 +- docs/module-graph.md | 7 +- docs/rfc/INDEX.md | 1 + .../2026-06-18-session-surface.md | 6 +- ...07-15-replay-token-meter-service.i18n.yaml | 6 + .../2026-07-15-replay-token-meter-service.md | 57 + ...026-07-15-replay-token-meter-service.zh.md | 57 + .../2026-06-18-compaction-capability-seam.md | 18 +- examples/coding-agent/composition.md | 3 + examples/coding-agent/cordis.yml | 15 +- examples/coding-agent/tests/compaction.e2e.ts | 11 +- examples/coding-agent/tests/harness.ts | 13 +- packages/compact/README.md | 4 +- packages/compact/compact-basic/README.md | 37 +- packages/compact/compact-basic/package.json | 9 +- .../compact/compact-basic/src/automatic.ts | 60 + packages/compact/compact-basic/src/config.ts | 117 + packages/compact/compact-basic/src/index.ts | 624 +---- packages/compact/compact-basic/src/region.ts | 196 ++ .../compact/compact-basic/src/summarizer.ts | 153 ++ packages/compact/compact-basic/src/types.ts | 114 +- .../compact-basic/tests/compact-basic.spec.ts | 2427 ++++++----------- .../tests/compact-loop-repro.spec.ts | 14 +- .../tests/loader-composition.spec.ts | 66 + packages/compact/compact-basic/tsconfig.json | 2 + packages/compact/compact/README.md | 6 +- packages/compact/compact/src/index.ts | 9 +- .../cordis/tool-cordis/src/api-catalog.ts | 35 + packages/core/agent-loop/README.md | 2 + packages/core/agent-loop/src/loop.ts | 33 +- .../tests/contract-regressions.spec.ts | 9 +- packages/core/agent-loop/tests/loop.spec.ts | 30 +- packages/core/session/README.md | 2 +- packages/core/session/src/types.ts | 10 +- packages/llm/README.md | 3 +- packages/llm/token-meter/README.md | 57 + packages/llm/token-meter/package.json | 37 + packages/llm/token-meter/src/index.ts | 193 ++ packages/llm/token-meter/src/replay.ts | 367 +++ packages/llm/token-meter/src/types.ts | 101 + .../llm/token-meter/tests/token-meter.spec.ts | 603 ++++ packages/llm/token-meter/tsconfig.json | 27 + packages/support/invariants/README.md | 1 + packages/support/invariants/src/index.ts | 4 +- .../invariants/tests/invariants.spec.ts | 8 +- pnpm-lock.yaml | 34 +- python/sdk-runtime/package.json | 1 + scripts/gen-doc-graphs.ts | 10 + scripts/type-equiv.manifest.json | 4 + .../verify-package-readme-model-experience.ts | 1 + tsconfig.build.json | 1 + tsconfig.json | 1 + 61 files changed, 3393 insertions(+), 2369 deletions(-) create mode 100644 docs/core-data-structures/token-meter.md create mode 100644 docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml create mode 100644 docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md create mode 100644 docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md create mode 100644 packages/compact/compact-basic/src/automatic.ts create mode 100644 packages/compact/compact-basic/src/config.ts create mode 100644 packages/compact/compact-basic/src/region.ts create mode 100644 packages/compact/compact-basic/src/summarizer.ts create mode 100644 packages/compact/compact-basic/tests/loader-composition.spec.ts create mode 100644 packages/llm/token-meter/README.md create mode 100644 packages/llm/token-meter/package.json create mode 100644 packages/llm/token-meter/src/index.ts create mode 100644 packages/llm/token-meter/src/replay.ts create mode 100644 packages/llm/token-meter/src/types.ts create mode 100644 packages/llm/token-meter/tests/token-meter.spec.ts create mode 100644 packages/llm/token-meter/tsconfig.json diff --git a/docs/agent-lifecycle.md b/docs/agent-lifecycle.md index fa2c4bd0fb..b9292aa80e 100644 --- a/docs/agent-lifecycle.md +++ b/docs/agent-lifecycle.md @@ -45,6 +45,8 @@ sequenceDiagram Driver-->>SDK: agent/status idle ``` +The `assistant/message` edge records every successful provider call, including content-less and `max-tokens` finishes. Empty content stays out of derived history while the durable anchor retains usage and exact chunk provenance, including an explicit empty source set. + SDK users that need replayable transcript data should consume `session/event`; `agent/*` is the live coordination surface for queue/status, prompt interception, request shaping, steering, continuation, and errors. Maintenance mode: curated Mermaid sequence; exact event signatures live in the generated Cordis catalog. diff --git a/docs/architecture.md b/docs/architecture.md index b17c3302d8..75a03c474c 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -24,6 +24,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service | ctx key | Package family | Role | |---|---|---| | `ctx.llm` | [`llm/`](../packages/llm/README.md) | adapter registry and streaming model calls | +| `ctx.tokenMeter` | [`llm/token-meter`](../packages/llm/token-meter/README.md) | replay-aware per-model request and surface pressure | | `ctx.bash` | [`bash/`](../packages/bash/README.md) | foreground/background command execution | | `ctx.sandbox` | [`sandbox/`](../packages/sandbox/README.md) | same-world process confinement (argv wrapping, per-call policy) | | `ctx.codeRuntime` | [`code-runtime/`](../packages/code-runtime/README.md) | model-written program execution | @@ -124,7 +125,7 @@ Durability is a plugin concern. Persistence backends buffer synchronous `session ### Model Content -Messages are arrays of typed content blocks (`text`, `reasoning`, `tool-call`, `tool-result`). The union derives from the merge-extensible `ContentBlockMap`; the same pattern types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New block types are coordinated across adapters, UI bridges, compaction pricing, and persistence, so block types remain a repo-wide contract. +Messages are arrays of typed content blocks (`text`, `reasoning`, `tool-call`, `tool-result`). The union derives from the merge-extensible `ContentBlockMap`; the same pattern types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New block types are coordinated across adapters, UI bridges, token metering, and persistence, so block types remain a repo-wide contract. Replay measurement types are cataloged in [token-meter.md](core-data-structures/token-meter.md). Streaming is a raw chunk protocol (`block-start` through `finish`) with `BlockAssembler` as the shared chunk-to-block assembler. The loop logs raw chunks while assembling them for dispatch. `LlmAdapter` is the provider seam: subclass, implement `stream()`, and register with `ctx.llm.registerAdapter(models, adapter)`. StreamChunk conventions live in [llm-streaming.md](core-data-structures/llm-streaming.md). diff --git a/docs/capability-seams.md b/docs/capability-seams.md index fb4746dc68..fae89bfcfb 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -14,6 +14,8 @@ flowchart LR pkg_llm_replay["llm-replay"] pkg_agent_loop["agent-loop"] pkg_compact_basic["compact-basic"] + pkg_token_meter["token-meter"] + svc_tokenMeter["ctx.tokenMeter
Replay token measurement"] pkg_session["session"] svc_sessions["ctx.sessions
In-memory session store"] pkg_agent["agent"] @@ -120,6 +122,7 @@ flowchart LR pkg_subagent_mock --> svc_subagents pkg_subagent_spawn --> svc_subagents pkg_system_prompt --> svc_systemPrompt + pkg_token_meter --> svc_tokenMeter pkg_tools --> svc_tools pkg_user_interaction --> svc_userInteraction pkg_web --> svc_web @@ -162,6 +165,7 @@ flowchart LR svc_systemPrompt --> pkg_tool_fs svc_systemPrompt --> pkg_tool_web svc_systemPrompt --> pkg_tools + svc_tokenMeter --> pkg_compact_basic svc_tools --> pkg_acp svc_tools --> pkg_agent_loop svc_tools --> pkg_tool_ask_user @@ -183,6 +187,7 @@ flowchart LR | ctx key | Role | Owner | Implementations | Direct consumers | Companion plugins | Note | | --- | --- | --- | --- | --- | --- | --- | | `ctx.llm` | `seam` | [`llm`](../packages/llm/llm) | [`llm-deepseek`](../packages/llm/llm-deepseek), [`llm-pi-ai`](../packages/llm/llm-pi-ai), [`llm-replay`](../packages/support/llm-replay) | [`agent-loop`](../packages/core/agent-loop), [`compact-basic`](../packages/compact/compact-basic) | - | Adapters register provider implementations; the loop and compaction call the provider-neutral stream service. | +| `ctx.tokenMeter` | `core` | [`token-meter`](../packages/llm/token-meter) | - | [`compact-basic`](../packages/compact/compact-basic) | - | Owns isolated per-model/session replay folds; pressure consumers share immutable revisioned measurements. | | `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. | | `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`session-query`](../packages/session-query/session-query) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. | | `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | - | - | - | Resolves live and optional persisted logs into one logical corpus for exact reads. | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 8139f4d943..4bbab27e16 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -207,44 +207,33 @@ Source: [`packages/code-runtime/code-runtime-worker/src/index.ts:24`](../package ## `@deepseek-ai/dsh-compact-basic` -Requires: `llm` +Requires: `llm` · `tokenMeter` ```ts config-catalog -/** - * Backend configuration. Every knob is REQUIRED except `auto` and - * `charsPerToken`: there is no concrete data yet to justify default - * thresholds/budgets, so a consumer must state each value explicitly rather - * than inherit a guessed default. `auto` alone defaults to `true` - * (auto-compaction is the intended posture), and `charsPerToken` defaults to - * the English-text heuristic its estimator was calibrated on. - */ +/** Basic compaction configuration; every common field has a deployment default. */ export interface BasicCompactConfig { - /** Context window size in tokens. */ - contextWindow: number - /** Compact when estimated token usage exceeds this fraction of context window. */ - thresholdRatio: number - /** Number of tokens of recent context to retain during compaction. */ - retainTokens: number - /** Model to use for summarization (`''` — uses the agent's model). */ - summarizationModel: string - /** Provider generation cap for the summarization call. */ - maxTokens: number - /** Extra compaction attempts when the first compacted surface is still over threshold. */ - compactionRetries: number - /** Enable automatic compaction on the `agent/pre-step` seam (default true). */ + /** Field-wise pressure/retention overrides keyed by configured token-meter model name. */ + models?: Record + /** Summary model; `''` resolves the latest routed model, then `AgentOptions.model`. Defaults to `''`. */ + summarizationModel?: string + /** Provider generation cap for summarization. Defaults to `8192`. */ + maxTokens?: number + /** Extra attempts after the first compaction when pressure remains above threshold. Defaults to `1`. */ + compactionRetries?: number + /** Enable the automatic `agent/pre-step` pressure listener. Defaults to `true`. */ auto?: boolean - /** - * Text density for the token estimator: estimated tokens = chars / - * `charsPerToken`. Defaults to 4 (typical English text). A CJK-heavy - * deployment should set ~1-2 — CJK runs at roughly 1-2 chars per token, so - * the default UNDERestimates several-fold and compaction fires far too late. - * May be fractional. - */ - charsPerToken?: number +} + +/** Optional pressure and retention policy for one metered model. */ +export interface ModelCompactConfig { + /** Compact at this fraction of the model's configured context window. Defaults to `0.8`. */ + thresholdRatio?: number + /** Recent surface tokens retained verbatim. Defaults to `floor(contextWindow * 0.16)`. */ + retainTokens?: number } ``` -Source: [`packages/compact/compact-basic/src/types.ts:20`](../packages/compact/compact-basic/src/types.ts) +Source: [`packages/compact/compact-basic/src/types.ts:16`](../packages/compact/compact-basic/src/types.ts) ## `@deepseek-ai/dsh-fs-local` @@ -796,6 +785,26 @@ export interface Config { Source: [`packages/context/time-context/src/index.ts:22`](../packages/context/time-context/src/index.ts) +## `@deepseek-ai/dsh-token-meter` + +```ts config-catalog +/** Token-meter plugin configuration. */ +export interface TokenMeterConfig { + /** Built-in field overrides and custom model profiles, keyed by routed model name. */ + models?: Record +} + +/** Optional pricing fields for one configured model. */ +export interface ModelTokenMeterConfig { + /** Provider context-window capacity in tokens. Required for a custom model. */ + contextWindow?: number + /** Heuristic text density in characters per token. Defaults to `4`. */ + charsPerToken?: number +} +``` + +Source: [`packages/llm/token-meter/src/types.ts:19`](../packages/llm/token-meter/src/types.ts) + ## `@deepseek-ai/dsh-tool-cordis` Requires: `tools` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 3339381e0e..ae808e7fe2 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -86,7 +86,7 @@ Source: [`packages/code-runtime/code-runtime/src/index.ts:31`](../../packages/co ## `ctx.compact` — `CompactService` (abstract seam) -Abstract compaction service. Implementations own token estimation, retention, and summarization, but a successful run must replace the selected surface span with one summary node and prevent concurrent compaction of the same session. Load one implementation per context as `ctx.compact`. +Abstract compaction service. Implementations own trigger policy, retention, and summarization, and may consume a separate measurement service. A successful run replaces the selected surface span with one summary node and prevents concurrent compaction of the same session. Load one implementation per context as `ctx.compact`. ```ts cordis-catalog abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise @@ -95,7 +95,7 @@ abstract compactRegion( session: Session, start: number, end: number, agent: Com Types: [Message](../core-data-structures/core.md) -Source: [`packages/compact/compact/src/index.ts:37`](../../packages/compact/compact/src/index.ts) +Source: [`packages/compact/compact/src/index.ts:38`](../../packages/compact/compact/src/index.ts) ## `ctx.fs` — `FileSystem` (abstract seam) @@ -241,6 +241,16 @@ async assemble(context: AssembleContext = {}): Promise Source: [`packages/core/system-prompt/src/index.ts:213`](../../packages/core/system-prompt/src/index.ts) +## `ctx.tokenMeter` — `TokenMeterService` + +Concrete registry and replay owner for all configured model meters. + +```ts cordis-catalog +resolve(model: string): ModelTokenMeter +``` + +Source: [`packages/llm/token-meter/src/index.ts:145`](../../packages/llm/token-meter/src/index.ts) + ## `ctx.tools` — `ToolRegistry` Tool registry and execution pipeline. Scoped registrations shadow globals; one visibility resolver feeds presentation, lookup, and dispatch. diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 05022f9937..50a80208a9 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -50,7 +50,7 @@ interface CompactionResult { ## The service -`CompactService` exposes `compactIfNeeded(...)` for pressure-triggered compaction, returning `null` when no compaction is needed, and `compactRegion(...)` for an explicit inclusive surface range. The pre-step caller supplies the agent, full prompt, session prefix, and abort signal; implementations must forward that signal to summarization. Estimation, retention, event sequencing, and summarization remain backend policy. +`CompactService` exposes `compactIfNeeded(...)` for pressure-triggered compaction, returning `null` when no compaction is needed, and `compactRegion(...)` for an explicit inclusive surface range. The pre-step caller supplies the agent, full prompt, session prefix, and abort signal; implementations must forward that signal to summarization. The seam owns no pricing API: `dsh-compact-basic` resolves the routed model through [`ctx.tokenMeter`](token-meter.md), whose model-bound handle owns estimation and replay, while the backend owns retention, event sequencing, and summarization. Auto-compaction runs at serial `agent/pre-step`, before the step and request derivation, so it can replace surface nodes while keeping trace events outside the step. Region boundaries preserve tool-call/result pairing but do not preserve whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns the retention and failure details. diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 9a9a1706fc..09805063ac 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -16,6 +16,7 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t | Sub-page | Owns | |---|---| | [llm-streaming.md](llm-streaming.md) | the `StreamChunk` wire protocol + adapter contract, `BlockAssembler`, the `LlmAdapter` seam | +| [token-meter.md](token-meter.md) | immutable scalar and positional replay measurements with consumed-log revisions | | [scope.md](scope.md) | scoped registration identity, dispatch carriers, and the owned `Scope` context | | [session.md](session.md) | the full `SessionEventMap` variant catalog, `TurnTrigger`/`TurnEndReason`, `deriveMessages()`, the turn-enclosure invariant | | [persistence.md](persistence.md) | the durability seam: `SessionPersistence`, JSONL + SQLite backends, `session/flush`, crash recovery, `SessionHeader` | diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index 174f06602e..d7e503677f 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -150,6 +150,8 @@ type SessionEvent = { `SessionEventType = keyof SessionEventMap`. Because `SessionEventMap` is merge-extensible, switches over `SessionEvent` must NOT use `assertNever` — a plugin-added variant is a valid unknown value; handle the known cases and fall through `default`. +For `assistant/message`, a present `sourceEventSeqs: []` is a complete known-empty provider stream, while an absent field means legacy or otherwise unrecorded provenance. The loop writes the field for every successful model call; every other surface event requires a non-empty list when the field is present. + ## Surface types The five message-producing types (`SurfaceEventType` — `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`) carry surface metadata declaring how they join the derived surface linked list. See the [session surface RFC](../rfc/implemented/architecture/2026-06-18-session-surface.md). @@ -186,6 +188,8 @@ export interface SurfaceIntent { Required for `SurfaceEventType` events — every message-producing event must declare how it joins the surface, the sole source of derived history. Non-surface types reject it at compile time. +The same provenance distinction applies here: only `assistant/message` may carry a present empty `sourceEventSeqs`; omission does not assert that its source stream was empty. + ### `SurfaceNode` — a node in the surface linked list ```ts type-equiv diff --git a/docs/core-data-structures/token-meter.md b/docs/core-data-structures/token-meter.md new file mode 100644 index 0000000000..98467f3715 --- /dev/null +++ b/docs/core-data-structures/token-meter.md @@ -0,0 +1,52 @@ +# Token Meter + +`@deepseek-ai/dsh-token-meter` exposes detached replay measurements for request pressure and positional surface pricing. Scalar and surface snapshots carry the number of durable events consumed as `logRevision`; consumers compare revisions before making a joint decision. + +Source: [`packages/llm/token-meter/src/types.ts`](../../packages/llm/token-meter/src/types.ts) + +## `TokenMeasurement` + +```ts type-equiv +interface TokenMeasurement { + /** Model profile used for every heuristic component. */ + readonly model: string + /** Number of durable events consumed; equal to the next unread event seq. */ + readonly logRevision: number + /** Provider or heuristic anchor used for this measurement. */ + readonly baseline: TokenMeasurementBaseline + /** Signed repricing of current surface content relative to the baseline anchor. */ + readonly surfaceDeltaTokens: number + /** Non-negative current request-and-response pressure. */ + readonly totalTokens: number +} +``` + +`baseline.kind === 'usage'` means a successful provider call has the same model and canonical envelope. `estimated` means the meter repriced the complete envelope and surface. Signed `surfaceDeltaTokens` preserves growth and shrinkage relative to a matching provider or estimated anchor. + +## `TokenSurfaceNode` + +```ts type-equiv +interface TokenSurfaceNode { + /** Durable sequence number of the surface event. */ + readonly seq: number + /** Heuristic tokens for the exact message projected by this node. */ + readonly tokens: number +} +``` + +## `TokenSurfaceMeasurement` + +```ts type-equiv +interface TokenSurfaceMeasurement { + /** Model profile used to price every node. */ + readonly model: string + /** Number of durable events consumed; equal to the next unread event seq. */ + readonly logRevision: number + /** Total heuristic tokens across the current surface. */ + readonly totalTokens: number + /** Current surface nodes in positional head-to-tail order. */ + readonly nodes: readonly TokenSurfaceNode[] +} +``` + +Surface order is authoritative; replacement nodes can have higher durable seqs than later positional nodes. The snapshot is immutable and does not grow when the underlying replay fold advances. diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 2de200fbba..b4f32dbbae 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -27,7 +27,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | | `session/created` | `emit` | [`packages/core/session/src/index.ts:46`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:56`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | -| `session/event` | `emit` | [`packages/core/session/src/index.ts:68`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) | +| `session/event` | `emit` | [`packages/core/session/src/index.ts:68`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent), [`token-meter`](../packages/llm/token-meter) | | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:78`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:92`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:66`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | diff --git a/docs/module-graph.md b/docs/module-graph.md index 19d471f175..64319b7813 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -15,6 +15,7 @@ flowchart TD pkg_llm["llm"] pkg_llm_deepseek["llm-deepseek"] pkg_llm_pi_ai["llm-pi-ai"] + pkg_token_meter["token-meter"] end subgraph group_core["packages/core"] pkg_agent["agent"] @@ -135,6 +136,8 @@ flowchart TD pkg_fs --> pkg_llm pkg_web --> pkg_llm pkg_sandbox --> pkg_llm + pkg_token_meter --> pkg_llm + pkg_token_meter --> pkg_session pkg_agent --> pkg_brand pkg_agent --> pkg_llm pkg_agent --> pkg_scope @@ -165,6 +168,7 @@ flowchart TD pkg_compact_basic --> pkg_compact pkg_compact_basic --> pkg_llm pkg_compact_basic --> pkg_session + pkg_compact_basic --> pkg_token_meter pkg_hook_protocol --> pkg_bash pkg_hook_protocol --> pkg_session pkg_session_persistence_jsonl --> pkg_session @@ -358,6 +362,7 @@ flowchart TD | [`fs`](../packages/fs/fs) | `fs` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) | | [`web`](../packages/web/web) | `web` | [`llm`](../packages/llm/llm) | | [`sandbox`](../packages/sandbox/sandbox) | `sandbox` | [`llm`](../packages/llm/llm) | +| [`token-meter`](../packages/llm/token-meter) | `llm` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`agent`](../packages/core/agent) | `core` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) | | [`bash`](../packages/bash/bash) | `bash` | [`brand`](../packages/util/brand), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session) | | [`fs-local`](../packages/fs/fs-local) | `fs` | [`fs`](../packages/fs/fs) | @@ -372,7 +377,7 @@ flowchart TD | [`llm-replay`](../packages/support/llm-replay) | `support` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) | | [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash), [`timeout`](../packages/util/timeout) | -| [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | +| [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`token-meter`](../packages/llm/token-meter) | | [`hook-protocol`](../packages/hooks/hook-protocol) | `hooks` | [`bash`](../packages/bash/bash), [`session`](../packages/core/session) | | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) | | [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index e37f975827..f62e5e4d14 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -144,6 +144,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [The agent is a registration scope](implemented/architecture/2026-07-08-agent-scope-contexts.md) | 2026-07-08 | | [Single-file executable SDK runtime distribution (single-exe)](implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) | 2026-07-10 | | [Agent-scope runtime design and correctness](implemented/architecture/2026-07-12-agent-scope-runtime-design.md) | 2026-07-12 | +| [Replay token meter service](implemented/architecture/2026-07-15-replay-token-meter-service.md) | 2026-07-15 | ### Process diff --git a/docs/rfc/implemented/architecture/2026-06-18-session-surface.md b/docs/rfc/implemented/architecture/2026-06-18-session-surface.md index 6ba0df41c4..3a8805ddb6 100644 --- a/docs/rfc/implemented/architecture/2026-06-18-session-surface.md +++ b/docs/rfc/implemented/architecture/2026-06-18-session-surface.md @@ -14,7 +14,7 @@ Add a **surface** — a derived, cached linked list of "surface nodes" (the subs Every `SessionEvent` gains two optional fields (structural metadata, like `seq`/`time`): -- **`sourceEventSeqs?: number[]`** — seq numbers of events that are provenance sources (e.g., the `assistant/chunk` seqs that built an `assistant/message`, or the surface nodes shadowed by a compaction marker). Provenance is a core design principle; without it, the replace-range operation cannot be validated on replay. +- **`sourceEventSeqs?: number[]`** — seq numbers of events that are provenance sources (e.g., the `assistant/chunk` seqs that built an `assistant/message`, or the surface nodes shadowed by a compaction marker). A present `[]` is valid only on `assistant/message` and records a known empty provider stream; omission there means legacy or otherwise unrecorded provenance. Other surface events require a non-empty list when the field is present. Provenance is a core design principle; without it, the replace-range operation cannot be validated on replay. - **`surfaceOp?: SurfaceOp`** — how this event entered the surface. Absent for non-surface events. ### SurfaceOp: two operations @@ -25,7 +25,7 @@ export type SurfaceOp = | { op: 'replace'; start: number; end: number } // shadow [start, end] inclusive ``` -1. **Append** — add a new node to the tail. Used by `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`. The loop passes `surfaceOp: 'append'` on all such appends, and `sourceEventSeqs` where applicable (e.g., `assistant/message` records its `assistant/chunk` sources; `tool/result` records its `tool/call` source). +1. **Append** — add a new node to the tail. Used by `user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`. The loop passes `surfaceOp: 'append'` on all such appends and records `sourceEventSeqs` where applicable: every successful `assistant/message` records its complete `assistant/chunk` source set, including `[]`, while `tool/result` records its `tool/call` source. 2. **Replace** — remove nodes from `start` through `end` (both inclusive) and insert a new node in their place. Both `start` and `end` must be valid surface node seqs in the current surface; `start === end` replaces a single node. The node's `sourceEventSeqs` must contain every shadowed surface node. The shadowed events remain in the log but are no longer on the surface. @@ -47,7 +47,7 @@ The `repair.ts` module synthesizes `tool/result` closers for orphaned tool calls ### Invariants -The dev-mode invariants plugin validates: `sourceEventSeqs` references (non-empty, no duplicates, references earlier events, references known seqs) and `surfaceOp` (replace `start ≤ end`, both endpoints are on the tracked surface, the range is non-reversed in surface position, and `sourceEventSeqs` includes every node the range shadows). +The dev-mode invariants plugin validates: `sourceEventSeqs` references (only `assistant/message` may use an empty list; otherwise no duplicates, references earlier events, and references known seqs) and `surfaceOp` (replace `start ≤ end`, both endpoints are on the tracked surface, the range is non-reversed in surface position, and `sourceEventSeqs` includes every node the range shadows). Every surface-eligible event must carry `surfaceOp` or it would disappear from derived history. Typed `append` overloads enforce this for literal event types; runtime checks in `append` and the seed constructor cover widened unions and loaded logs. Invalid seeds are rejected rather than upgraded under the pre-release format policy. diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml new file mode 100644 index 0000000000..99c6301f25 --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-15-replay-token-meter-service.md: 4452c151e122c4a4ad72e3f0bc2616cd2fa28b9d +2026-07-15-replay-token-meter-service.zh.md: 23edc11ffd19b9cfaeb794f3608e9ced4e7dbb7b diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md new file mode 100644 index 0000000000..4452c151e1 --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md @@ -0,0 +1,57 @@ +# RFC: Replay token meter service + +Status: implemented + +English | [中文](2026-07-15-replay-token-meter-service.zh.md) + +## Problem + +Context pressure is useful outside compaction. A compaction backend, an overflow guard, or a future request-policy plugin can all need the same answer: how much of one model's window does the durable request consume? Keeping that fold inside `dsh-compact-basic` duplicates replay logic, makes measurement unavailable without compaction, and encourages callers to reuse accounting from the wrong model. + +Provider usage is not a complete answer. It describes one successful call under one exact request envelope, while the current surface can grow, shrink, or be replaced afterward. Sessions also switch models, old logs can lack chunk provenance, and provider fields separate input, cache-read, cache-write, output, and reasoning counts. A useful service therefore combines exact anchors with conservative model-specific repricing and exposes the log revision consumed by each result. + +## Decision + +### One concrete LLM-family service + +`@deepseek-ai/dsh-token-meter` is one concrete package under `packages/llm/` and registers `ctx.tokenMeter`. It is not split into an interface and backend before a second implementation exists. Its public entry point resolves an exact model name to a stable `ModelTokenMeter`; unknown names throw `TokenMeterError` with `TOKEN_METER_MODEL_UNCONFIGURED` instead of inheriting a universal window. + +The built-in `deepseek-v4-flash` and `deepseek-v4-pro` profiles use a 128,000-token context window and four characters per estimated token. `models` overrides merge field-by-field. A custom name requires `contextWindow`, while `charsPerToken` defaults to four. Direct construction reports typed profile errors; Loader mounts first apply the package's Schemastery shape validation. + +### Model-bound replay folds + +Each model/session pair owns an isolated incremental fold. Active folds advance from `session/event`; every read catches up through the durable tail, so listener ordering, seeded sessions, and service reload do not change the answer. The fold tracks canonical request headers and deltas, step boundaries, surface appends and replacements, assistant usage, and assistant-chunk provenance. A malformed next event fails transactionally and remains unread rather than partially mutating state. + +`measure(session, requestHeader?)` returns scalar pressure. `measureSurface(session)` returns positional per-node prices for retention and replacement decisions. `estimateMessage(message)` applies the handle's profile without session state. Results are detached, deeply immutable snapshots carrying `logRevision`; a consumer compares scalar and surface revisions before making one decision. + +Provider usage is reused only when the handle's model and canonical request envelope equal the successful-call anchor. Any system, prefix, tool, or call-config change causes complete repricing under the requested model. Surface changes remain a signed delta from a matching anchor, including negative values after a shrinking replacement. A success by another model changes the shared surface but never overwrites this model's anchor. + +Usage sums the disjoint input, cache-read, cache-write, and output buckets. Reasoning is not added a second time. Every successful model call records an `assistant/message`, including content-less and max-token calls, with its exact earlier chunk seqs. An explicit empty provenance list means a known empty provider stream; absent legacy provenance conservatively treats the durable assistant output as provider output. + +### Compact-basic consumes, but does not own, measurement + +`dsh-compact-basic` requires `ctx.tokenMeter`; `CompactService` gains no token methods or types. The backend is factored into configuration, automatic triggering, region transaction, and summarizer modules, while `summarize()` remains its sole subclass hook. The conversation model's meter consistently prices pressure, retention, shadowed content, provenance, and non-shrinking-summary rejection. + +Every metered model receives a compact policy with defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, summarization model `''`, maximum summary output `8192`, one extra compaction attempt, and automatic triggering enabled. Per-model compact overrides merge `thresholdRatio` and `retainTokens`; retention must remain below the resulting threshold. Empty summarization model resolves the latest logged routed model, then `AgentOptions.model`. + +The pre-step trigger measures a provisional envelope: the current prompt and prefix override logged values, while the latest logged header supplies model, tools, and other call config. A model-less router-only agent skips that provisional check because `agent/request` can route later; naming an unknown model remains an error. + +## Testing + +Unit coverage pins profiles, field-wise overrides, custom and unknown models, envelope invalidation, model switching, usage and missing-usage paths, seeded append/replace replay, signed deltas, provenance modes, malformed boundaries, immutable snapshots, listener ordering, reload, compact defaults, routing fallback, retention, convergence, and transaction rollback. A real Loader/Include YAML fixture loads the exact zero-config token-meter and compact-basic package names in dependency order. + +## Alternatives considered + +- **Keep estimation inside `CompactService`** — rejected because measurement has consumers and replay semantics independent of compaction; it would also force every compactor to expose the same unrelated API. +- **Split a token-meter interface from a heuristic backend immediately** — rejected because only one implementation exists. One concrete service preserves the future seam without speculative packages or configuration. +- **Give unknown models a 128,000-token fallback** — rejected because a plausible but wrong capacity can trigger destructive policy at the wrong point. Unknown routed names fail with their exact name. +- **Copy complete history into each scalar result** — rejected because below-threshold reads are common. Immutable revisioned scalars and a separate surface snapshot preserve consistency without an O(history) copy. +- **Treat provider usage as portable between models or envelopes** — rejected because tokenization, context capacity, tools, prefixes, and call config are model/request facts. Mismatch reprices the whole current request. + +## Consequences + +- Token pressure has one replay-aware owner that compaction and future plugins can share. +- Defaults make the bundled DeepSeek composition usable with two zero-config plugin entries, while custom models must state the one fact that cannot be guessed safely: context capacity. +- Heuristic density and provider usage remain estimates of provider behavior. Maintainers must update built-in profiles and overflow wording as models evolve. +- Measurements fail loudly on malformed durable boundaries. This turns corrupted replay into a named integration failure instead of silently drifting pressure. +- The pre-step compact integration can skip a router-only first check and can miss tool or routing changes applied later in request middleware. diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md new file mode 100644 index 0000000000..23edc11ffd --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md @@ -0,0 +1,57 @@ +# RFC: 重放式 token 计量服务 + +Status: implemented + +[English](2026-07-15-replay-token-meter-service.md) | 中文 + +## 问题 + +上下文压力并不只对压缩有用。压缩后端、溢出保护或未来的请求策略插件都可能需要回答同一个问题：持久请求占用了某个模型多少上下文窗口？如果把该折叠逻辑留在 `dsh-compact-basic` 内部，就会重复实现重放逻辑，使未加载压缩的调用方无法使用计量，并诱使调用方错误复用其他模型的核算结果。 + +提供方 usage 也不是完整答案。它只描述某个精确请求信封下的一次成功调用，而当前表层之后还可能增长、缩小或被替换。会话也可能切换模型，旧日志可能缺少 chunk 来源，提供方字段还会分别报告输入、缓存读取、缓存写入、输出与推理计数。因此，可用的服务必须把精确锚点与保守的逐模型重新定价结合起来，并公开每个结果已经消费的日志修订号。 + +## 决策 + +### 一个具体的 LLM 家族服务 + +`@deepseek-ai/dsh-token-meter` 是 `packages/llm/` 下的单个具体 package，并注册 `ctx.tokenMeter`。在第二种实现出现之前，它不会被拆成接口与后端。公开入口把精确模型名解析为稳定的 `ModelTokenMeter`；未知名称抛出带 `TOKEN_METER_MODEL_UNCONFIGURED` 的 `TokenMeterError`，而不是继承通用窗口。 + +内置的 `deepseek-v4-flash` 与 `deepseek-v4-pro` profile 都采用 128,000 token 上下文窗口，以及每 token 四个字符的估算密度。`models` 覆盖按字段合并。自定义名称必须提供 `contextWindow`，而 `charsPerToken` 默认为四。直接构造会报告类型化 profile 错误；Loader 挂载则先应用 package 的 Schemastery 形状校验。 + +### 绑定模型的重放折叠 + +每个模型/会话对都有隔离的增量折叠。活跃折叠通过 `session/event` 前进；每次读取都会追到持久日志尾部，因此监听器顺序、种子会话与服务重载不会改变答案。折叠跟踪规范请求头及其增量、步骤边界、表层追加与替换、assistant usage，以及 assistant chunk 来源。下一个畸形事件会以事务方式失败并保持未读，不会让状态只修改一半。 + +`measure(session, requestHeader?)` 返回标量压力。`measureSurface(session)` 返回用于保留与替换决策的逐位置节点价格。`estimateMessage(message)` 不依赖会话状态，直接应用该 handle 的 profile。结果是分离且深度不可变的快照，并携带 `logRevision`；消费者在一次联合决策前比较标量与表层修订号。 + +只有当 handle 的模型与规范请求信封都等于成功调用锚点时，服务才复用提供方 usage。系统提示词、前缀、工具或调用配置任一变化都会在请求模型下重新定价完整当前请求。表层变化相对匹配锚点保留有符号增量，包括缩小替换后的负值。其他模型的成功调用会改变共享表层，但绝不会覆盖当前模型的锚点。 + +Usage 会对互不重叠的输入、缓存读取、缓存写入与输出 bucket 求和，不会再次加入推理计数。每次成功模型调用都会记录 `assistant/message`，包括无内容调用与达到 token 上限的调用，并带上精确的更早 chunk seq。显式空来源列表表示已知为空的提供方流；旧日志中缺失的来源则保守地把持久 assistant 输出视为提供方输出。 + +### compact-basic 消费计量，但不拥有计量 + +`dsh-compact-basic` 要求 `ctx.tokenMeter`；`CompactService` 不增加 token 方法或类型。后端拆分为配置、自动触发、区域事务与摘要器模块，而 `summarize()` 仍是唯一的子类 hook。会话模型的 meter 一致用于压力、保留、被遮蔽内容、来源以及非缩小摘要拒绝。 + +每个已计量模型都会获得默认压缩策略：阈值比例 `0.8`、保留尾部 `floor(contextWindow × 0.16)`、摘要模型 `''`、摘要最大输出 `8192`、一次额外压缩尝试，以及启用自动触发。逐模型压缩覆盖按字段合并 `thresholdRatio` 与 `retainTokens`；保留值必须小于最终阈值。空摘要模型先解析最近记录的实际路由模型，再使用 `AgentOptions.model`。 + +pre-step 触发器计量临时请求信封：当前提示词与前缀覆盖日志值，最近记录的请求头提供模型、工具及其他调用配置。没有模型的纯路由 agent 会跳过该临时检查，因为 `agent/request` 仍可稍后路由；显式命名未知模型仍然报错。 + +## 测试 + +单元覆盖固定 profile、按字段覆盖、自定义与未知模型、信封失效、模型切换、有无 usage 的路径、种子追加/替换重放、有符号增量、来源模式、畸形边界、不可变快照、监听器顺序、重载、压缩默认值、路由回退、保留、收敛与事务回滚。真实 Loader/Include YAML fixture 按依赖顺序加载精确的零配置 token-meter 与 compact-basic package 名称。 + +## 考虑过的替代方案 + +- **把估算保留在 `CompactService` 内**——不予采纳，因为计量拥有独立于压缩的消费者与重放语义；它还会强迫每个压缩器暴露同一套无关 API。 +- **立即把 token meter 拆成接口与启发式后端**——不予采纳，因为目前只有一种实现。单个具体服务保留未来接缝，同时避免推测性的 package 与配置。 +- **给未知模型提供 128,000 token 回退**——不予采纳，因为看似合理但错误的容量会在错误时点触发破坏性策略。未知路由名称会携带精确名称失败。 +- **在每个标量结果中复制完整历史**——不予采纳，因为低于阈值的读取很常见。不可变且带修订号的标量与独立表层快照，在不进行 O(history) 复制的情况下保持一致性。 +- **在模型或信封之间移用提供方 usage**——不予采纳，因为分词、上下文容量、工具、前缀与调用配置都是模型/请求事实。不匹配时会重新定价完整当前请求。 + +## 后果 + +- Token 压力拥有一个可供压缩与未来插件共享的重放感知所有者。 +- 默认值让内置 DeepSeek 组合只需两个零配置插件条目即可使用，而自定义模型必须声明唯一不能安全猜测的事实：上下文容量。 +- 启发式密度与提供方 usage 仍然只是提供方行为的估计。随着模型演进，维护者必须更新内置 profile 与溢出措辞。 +- 遇到畸形持久边界时，计量会明确失败。这会把损坏的重放转化为具名集成错误，而不是让压力静默漂移。 +- pre-step 压缩集成可能跳过纯路由的首次检查，也可能错过请求中间件稍后应用的工具或路由变化。 diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index 29e3347759..d5d254cf4a 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -8,7 +8,7 @@ A long-running agent conversation grows without bound. As the event log accumula The [session surface](../../implemented/architecture/2026-06-18-session-surface.md) was built as the foundation for exactly this — a linked list over the event log with a `surfaceOp: { op: 'replace', start, end }` operation purpose-built to shadow a range of nodes and insert a replacement, with `sourceEventSeqs` recording provenance so the decision replays deterministically. What remained was the plugin that *decides what to compact and produces the summary*. -Two forces shape the design. First, compaction is **swappable**: token counting can be a char/4 heuristic or a real tokenizer, and summarization can be a model call, a template, or a remote service — these vary independently of *when* and *which range* to compact. Second, `SurfaceEventType` is closed to five event types (`user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`); only those may carry `surfaceOp`. A bespoke `compaction/*` event therefore **cannot** itself appear on the surface — the compiler rejects `surfaceOp` on it and the invariants plugin rejects it at runtime. +Two forces shape the design. First, compaction policy and reusable token measurement vary independently: measurement belongs to the LLM-family [`ctx.tokenMeter` service](../../implemented/architecture/2026-07-15-replay-token-meter-service.md), while summarization can be a model call, a template, or a remote service. Second, `SurfaceEventType` is closed to five event types (`user/message`, `assistant/message`, `tool/result`, `context/message`, `steering/message`); only those may carry `surfaceOp`. A bespoke `compaction/*` event therefore **cannot** itself appear on the surface — the compiler rejects `surfaceOp` on it and the invariants plugin rejects it at runtime. ## Decision @@ -17,7 +17,7 @@ Two forces shape the design. First, compaction is **swappable**: token counting Per the [capability-seams RFC](../../implemented/architecture/2026-06-13-capability-seams.md), compaction ships as separate packages so the contract, the algorithm, and (later) the consumer surface evolve independently: 1. **Interface** — `@deepseek-ai/dsh-compact`: an abstract `CompactService` owning the `ctx.compact` key, the `CompactionResult` vocabulary, and the `compact/*` session events. It declares `compactIfNeeded()` and `compactRegion()` as **abstract** — the contract states *what* compaction does, not *how*. -2. **Implementation** — `@deepseek-ai/dsh-compact-basic`: a concrete `BasicCompactService` that owns the entire algorithm — token estimation (chars per token — the `charsPerToken` config, default 4 — + per-block overhead), the tail→head retention walk, summarization via `ctx.llm.stream()`, the surface replacement, the lock, and the `agent/pre-step` auto-compaction listener. A tokenizer-based or template-based backend is a sibling package (or a subclass overriding the two protected estimation/summarization hooks). +2. **Implementation** — `@deepseek-ai/dsh-compact-basic`: a concrete `BasicCompactService` that consumes `ctx.tokenMeter` and owns the tail→head retention walk, summarization via `ctx.llm.stream()`, the surface replacement, the lock, and the `agent/pre-step` auto-compaction listener. `summarize()` is its sole subclass hook; pricing and replay stay with the meter. 3. **Consumer** — deferred. A `/compact` tool and slash command will `inject: ['compact']` and call the contract; they are intentionally out of scope here so the seam settles first. ### The contract depends on `dsh-session` and `dsh-llm` — a deliberate deviation @@ -28,9 +28,9 @@ This is not a coupling smell — it is the contract's domain. The "only cordis" ### Abstract `compactIfNeeded` / `compactRegion`, algorithm in the backend -An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface, with only `estimateContentTokens()` and `summarize()` abstract. That recouples the contract to one strategy: a backend that wants a different retention policy or a different event-sequencing would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend, where it belongs, and keeps the interface a pure statement of *what*. The backend remains internally factored — `estimateContentTokens()` and `summarize()` are `protected` hooks a sub-backend can override without reimplementing the walk — but that factoring is the backend's private concern, not the contract's. +An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the standalone service lets multiple consumers share one model/session replay fold. -`compactIfNeeded(agent, turn, step, fullSystemPrompt, signal)` takes **required** parameters (not the original all-optional shape). The auto-compaction seam (below) always supplies the agent, lifecycle context, assembled system prompt (counted toward the estimate), and the turn's abort signal, so optionality would only invite a hidden default at the seam. The session being compacted comes from the agent context. `compactRegion(session, start, end, agent, turn, step, signal?)` keeps an optional signal (a manual caller may omit it). Passing lifecycle context rather than a concrete model keeps router agents honest: the backend's summarization request can run through `agent/request`, where model-routing plugins already choose the actual model. +`compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` takes required pressure inputs and cancellation. The session comes from the agent. `compactRegion(session, start, end, agent, signal?)` keeps an optional signal for manual callers. The pre-step integration resolves a provisional model from the latest logged request header, then `AgentOptions.model`; a model-less router-only first step skips pressure because `agent/request` can route later. The default summarizer resolves its model from explicit config, the latest logged routed model, then agent options. ### Auto-compaction runs on `agent/pre-step`, a dedicated surface-mutation seam @@ -40,7 +40,7 @@ The fix is a dedicated loop seam, **`agent/pre-step`** (`@mode serial`), fired b ``` assembly = ctx.systemPrompt.assemble() -await ctx.serial('agent/pre-step', agent, turn, step, system, signal) ⟵ compaction mutates the surface here +await ctx.serial('agent/pre-step', agent, turn, step, system, prefix, signal) ⟵ compaction mutates the surface here session('step/start') ⟵ the step opens AFTER the seam messages = session.deriveMessages() ⟵ single derive, reflects the compaction request = waterfall agent/request ⟵ pure request transform (hooks, model switch) @@ -64,7 +64,7 @@ Auto-compaction always starts at the surface head, merging the prior checkpoint ### Approximate convergence invariant -`resolveConfig` validates numeric knobs but does NOT reject based on a pretend summary-length invariant. Convergence is dynamic: provider output caps can be spent on hidden or surfaced reasoning tokens, and the model may emit a summary of unpredictable size. `maxTokens` is only the provider-side generation cap for the summarization call; reasoning blocks are stripped before the checkpoint is stored. If a compacted surface is still over threshold, `compactIfNeeded()` re-compacts the head checkpoint up to `compactionRetries` extra times, but each committed summary must be smaller than the content it shadows. The sole residual is the single-unit-overflow case above (a backward-rounded oversized step can push the retained tail over budget) — which is exactly the out-of-scope concern, not a thrash bug. +`resolveConfig` supplies usable common defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, empty summarization-model override, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. Optional per-model threshold/retention fields merge over those defaults and must name a configured meter profile; retained tokens must be below the resulting threshold. Convergence remains dynamic because provider output caps can be spent on hidden or surfaced reasoning tokens and summary size is unpredictable. If the compacted surface remains over threshold, `compactIfNeeded()` re-compacts the head checkpoint up to the configured retry count, but each committed summary must be smaller than what it shadows. ### Surface replacement: `compact/*` events are log-only; one `user/message` carries the summary @@ -103,19 +103,19 @@ Two failure paths, both documented: ## Alternatives considered -- **The full algorithm as concrete interface methods** (only estimation/summarization abstract) — the earlier draft; rejected because it recouples the contract to one retention strategy. Both core methods are abstract; the `protected` estimation/summarization hooks are the backend's private factoring, not the contract's. +- **The full algorithm as concrete interface methods** — rejected because it recouples the contract to one retention strategy. Both core methods are abstract; reusable measurement is a separate LLM-family service and `summarize()` is basic's sole hook. - **Compaction on the `agent/request` waterfall** — the earlier cut; rejected for the double-derive it forced and for handing the listener context it structurally cannot compact. The dedicated `agent/pre-step` seam makes the layering correct by construction. - **A separate `compact/error` event** — rejected: `compact/end` keeps an `error?` field, mirroring `tool/result`'s self-contained error — one event tells success from failure without correlating a sibling. - **Teaching core turn-repair about `compact/*`** — rejected: the log-only orphan is inert, and a core module patched for every future `xxx/start … xxx/end` plugin pair is exactly the coupling the capability-seam architecture exists to avoid. ## Consequences -- **New packages**: `packages/compact/compact` (interface) and a sibling `compact-basic` (backend) under `packages/compact/`, wired into the root tsconfigs. The consumer tier is deferred. +- **Packages**: `packages/compact/compact` supplies the interface and `compact-basic` supplies the backend. `packages/llm/token-meter` owns replay-aware measurement independently. The consumer tier is deferred. - **New loop seam**: `agent/pre-step` (`@mode serial`) declared in `dsh-agent` and emitted by `dsh-agent-loop` after system assembly and before `step/start`. This is a documented change to the loop — `docs/architecture.md` records it and the generated cordis catalog carries its signature. - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry. - **`dsh-compact`** owns `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)`, the cached surface-edge checks that `compactRegion` and `compactIfNeeded` use to avoid splitting a tool-call/result pair. The cache validates current membership by seq and resolves after-edges from its positional successor map instead of trusting a caller-retained `node.next`; stale or missing seqs and orphan results reject. `dsh-session` continues to own the surface `replace` operation, positional nodes, and rewrite generation. - **`dsh-invariants`** drops its `surface replace: start must be <= end` assertion: a head-anchored compaction lands a high-seq replacement node at an older range's *position*, so `start > end` numerically is normal and valid (the range is positional, validated by the surface's `indexOf` checks that remain). The turn-enclosure invariant is reused unchanged. -- **Wiring**: `dsh-compact-basic` is loaded in `examples/coding-agent`'s `cordis.yml`, so the seam ships in the real demo (it was previously loaded nowhere). +- **Wiring**: `examples/coding-agent/cordis.yml` loads zero-config `dsh-token-meter` before `dsh-compact-basic`; bundled DeepSeek profiles and compact defaults make the pair usable without repeated numeric policy. ## Testing diff --git a/examples/coding-agent/composition.md b/examples/coding-agent/composition.md index be9a457124..46788808a5 100644 --- a/examples/coding-agent/composition.md +++ b/examples/coding-agent/composition.md @@ -23,6 +23,8 @@ flowchart LR bundle_agent_core --> spine_sessions["ctx.sessions"] bundle_agent_core --> spine_tools["ctx.tools + tool-bash"] bundle_agent_core --> spine_loop["ctx.agents + ctx.agentLoop"] + plugin_coding_token_meter["token-meter
@deepseek-ai/dsh-token-meter"] + cfg --> plugin_coding_token_meter plugin_coding_compact_basic["compact-basic
@deepseek-ai/dsh-compact-basic"] cfg --> plugin_coding_compact_basic plugin_coding_subagent["subagent
@deepseek-ai/dsh-subagent"] @@ -55,6 +57,7 @@ flowchart LR | `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` | | `bash` | `@deepseek-ai/dsh-bash-local` | | `stdio-agent` | `@deepseek-ai/dsh-stdio-agent` | +| `token-meter` | `@deepseek-ai/dsh-token-meter` | | `compact-basic` | `@deepseek-ai/dsh-compact-basic` | | `subagent` | `@deepseek-ai/dsh-subagent` | | `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` | diff --git a/examples/coding-agent/cordis.yml b/examples/coding-agent/cordis.yml index 5581a910b1..1208480388 100644 --- a/examples/coding-agent/cordis.yml +++ b/examples/coding-agent/cordis.yml @@ -45,17 +45,14 @@ Verify your work by running the code or tests. Keep answers brief and factual. -# Summarize an older range when derived history approaches the context window. -# This leaf consumes `ctx.llm` and the app's `agent/pre-step` seam. +# Replay-aware request pressure for the bundled DeepSeek model profiles. +- id: token-meter + name: '@deepseek-ai/dsh-token-meter' + +# Summarize an older range when measured history approaches the context window. +# Built-in model policies provide the ordinary threshold and retained-tail defaults. - id: compact-basic name: '@deepseek-ai/dsh-compact-basic' - config: - contextWindow: 128000 - thresholdRatio: 0.8 - retainTokens: 20480 - summarizationModel: '' - maxTokens: 8192 - compactionRetries: 1 # Expose fresh-child `spawn` and completed-prefix `fork` through independent # in-process backends. Each tool instance needs a distinct `toolName`; the registry diff --git a/examples/coding-agent/tests/compaction.e2e.ts b/examples/coding-agent/tests/compaction.e2e.ts index 932209115f..c2aa809327 100644 --- a/examples/coding-agent/tests/compaction.e2e.ts +++ b/examples/coding-agent/tests/compaction.e2e.ts @@ -33,10 +33,15 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa // Reasoning tokens require a larger generation cap than the retained checkpoint. ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT, + tokenMeter: { + models: { + 'deepseek-v4-flash': { contextWindow: 2000 }, + }, + }, compact: { - contextWindow: 2000, - thresholdRatio: 0.5, - retainTokens: 400, + models: { + 'deepseek-v4-flash': { thresholdRatio: 0.5, retainTokens: 400 }, + }, summarizationModel: '', maxTokens: 1024, compactionRetries: 1, diff --git a/examples/coding-agent/tests/harness.ts b/examples/coding-agent/tests/harness.ts index dd0bc42a1b..923b5efe84 100644 --- a/examples/coding-agent/tests/harness.ts +++ b/examples/coding-agent/tests/harness.ts @@ -10,6 +10,8 @@ import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' +import TokenMeterService from '@deepseek-ai/dsh-token-meter' +import type { TokenMeterConfig } from '@deepseek-ai/dsh-token-meter' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic' @@ -46,6 +48,8 @@ export interface CodingHarnessOptions { * compaction plugin (the default suites run without it). */ compact?: BasicCompactConfig + /** Optional meter profiles loaded before compact-basic. */ + tokenMeter?: TokenMeterConfig } export async function codingHarness(workdir: string, options: CodingHarnessOptions = {}): Promise { @@ -60,9 +64,12 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 }) await ctx.plugin(ToolBash) await ctx.plugin(ToolTodo) - // Compaction is opt-in: only the compaction e2e loads it, with a lowered - // contextWindow/retainTokens so a short real session crosses the threshold. - if (options.compact !== undefined) await ctx.plugin(BasicCompactService, options.compact) + // Compaction is opt-in: only the compaction e2e loads the reusable meter and + // backend, with a lowered profile window so a short real session crosses the threshold. + if (options.compact !== undefined) { + await ctx.plugin(TokenMeterService, options.tokenMeter) + await ctx.plugin(BasicCompactService, options.compact) + } // Durable JSONL persistence is opt-in: only the resume e2e needs it, and the // other suites stay file-free. Loaded last so a resume's deferred // `ctx.inject(['sessionPersistence'])` resolves once this is present. diff --git a/packages/compact/README.md b/packages/compact/README.md index 08c3ddd707..b5f5987571 100644 --- a/packages/compact/README.md +++ b/packages/compact/README.md @@ -5,7 +5,7 @@ A three-package capability seam (see [capability seams](../../docs/rfc/implement | Package | Role | ctx key | |---|---|---| | `compact/` | Abstract compaction seam (interface + `compact/*` events + `CompactionResult`) | `ctx.compact` | -| `compact-basic/` | A backend: chars-per-token estimation (`charsPerToken`, default 4) + token-budget retention + `llm.stream()` summarization | (registers `ctx.compact`) | +| `compact-basic/` | A backend: `ctx.tokenMeter` pressure + token-budget retention + `llm.stream()` summarization | (registers `ctx.compact`) | | `tool-compact/` (deferred) | Model-facing `/compact` tool over `ctx.compact` | (registers on `ctx.tools`) | -The interface lives at `compact/compact/`, the backend at `compact/compact-basic/`. Unlike the bash seam, it depends on `dsh-session` and `dsh-llm` — its verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so the contract cannot be expressed without naming them. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). A tokenizer- or template-based backend would replace `compact-basic` without touching the interface or the tool. +The interface lives at `compact/compact/`, the backend at `compact/compact-basic/`. Unlike the bash seam, it depends on `dsh-session` and `dsh-llm` — its verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so the contract cannot be expressed without naming them. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). Token measurement is a reusable LLM-family service rather than a `CompactService` method; a template- or model-backed compactor can replace `compact-basic` without changing the meter or callers. diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index d05ce47356..435e14d875 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-compact-basic -The **basic compaction backend**: a `BasicCompactService` implementing the `@deepseek-ai/dsh-compact` seam with a chars-per-token heuristic (the `charsPerToken` config, default 4), token-budget retention, and summarization as a direct one-shot `ctx.llm.stream()` call (interceptable at `llm/stream`). +The **basic compaction backend**: a `BasicCompactService` implementing the `@deepseek-ai/dsh-compact` seam with reusable `ctx.tokenMeter` pressure, token-budget retention, and summarization as a direct one-shot `ctx.llm.stream()` call (interceptable at `llm/stream`). This is the implementation tier of the compaction capability — see the [interface package](../compact/README.md) for the seam and the [capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md) for the design. @@ -8,7 +8,7 @@ This is the implementation tier of the compaction capability — see the [interf This backend owns the compaction policy: -- **Estimation** — a configurable characters-per-token heuristic counts the current session prefix supplied to pre-step, derived history, and system prompt, matching the next request rather than stale logged prefix state. +- **Measurement** — the effective conversation model's `ModelTokenMeter` prices the provisional request envelope and current surface at one consumed-log revision. The current prompt and prefix override their logged values; the pre-step boundary reuses logged tools and call config. - **Retention** — compact the oldest whole surface units while preserving a recent tail and balanced tool-call/result cuts through the [`dsh-compact` boundary helpers](../compact/README.md#tool-pairing-boundaries). Turn boundaries do not protect old steps inside a runaway turn. An open indivisible tail declines until it closes; a single unit larger than the budget remains out of scope. - **Convergence** — retry head-checkpoint compaction up to `compactionRetries`; reject a summary that does not shrink its source, and throw if retries cannot return below threshold. - **Summarization** — a direct `llm/stream` call uses the configured model and cap without running the loop-only `agent/request` seam. The input transcript preserves non-text blocks as tagged placeholders; only returned text enters the checkpoint, excluding reasoning and tool calls that would leak private reasoning or create an orphaned call. @@ -16,41 +16,34 @@ This backend owns the compaction policy: - **Lifecycle** — `compactRegion()` records its start, summary, replacement, and end. The serial `agent/pre-step` listener checks pressure before every step, outside an open step, so a tool-heavy turn remains compactable and the loop derives history once after mutation. - **Failure handling** — an unmatched `compact/start` is an inert crash marker because no replacement landed. Recoverable failure records an error end and leaves the surface unchanged. -`estimateContentTokens()` and `summarize()` are overridable hooks: a tokenizer-based or template-based backend can subclass `BasicCompactService` and override just those, reusing the retention walk and surface plumbing. `summarize()` returns the summary blocks together with the call envelope it actually used (`{ summary, model, maxTokens? }`) — the caller logs that envelope on the `compact/summary` provenance event, so an overriding backend reports its own envelope honestly. +`summarize()` is the sole subclass hook. A template- or remote-summarizer subclass can override it while pressure, retention, provenance, shrink validation, and shadowed-token accounting stay on the conversation model's meter. The hook returns the summary blocks together with the call envelope it used (`{ summary, model, maxTokens? }`), which is logged on `compact/summary`. ## Config (`BasicCompactConfig`) -Every knob is **required** except `auto` — there is no concrete data yet to justify default thresholds/budgets, so a consumer states each value explicitly rather than inherit a guessed default. `auto` alone defaults to `true`. +Every common setting is optional. Every model known to `ctx.tokenMeter` receives the default compact policy lazily; named overrides merge only the fields supplied and must name a configured meter profile. | Key | Required | Meaning | |---|---|---| -| `contextWindow` | yes | Context window size in tokens. | -| `thresholdRatio` | yes | Compact when estimated usage exceeds this fraction of the window. | -| `retainTokens` | yes | Tokens of recent context to keep intact. | -| `summarizationModel` | yes | Model for summarization (`''` → use the agent's model). | -| `maxTokens` | yes | Provider generation cap for the summarization call; may include reasoning tokens. | -| `compactionRetries` | yes | Extra compaction attempts after the first if the compacted surface remains over threshold. | -| `auto` | no (default `true`) | Register the `agent/pre-step` auto-compaction listener. Set `false` for manual-only. | -| `charsPerToken` | no (default `4`) | Token-estimator text density (estimated tokens = chars / `charsPerToken`; may be fractional). The default suits English text; CJK-heavy deployments should set ~1-2 or the estimate undershoots several-fold and compaction fires too late. | +| `models..thresholdRatio` | no (default `0.8`) | Compact at `floor(contextWindow × ratio)`. | +| `models..retainTokens` | no (default `floor(contextWindow × 0.16)`) | Recent surface budget kept verbatim; must be below the threshold. | +| `summarizationModel` | no (default `''`) | Empty resolves the latest logged routed model, then `AgentOptions.model`. | +| `maxTokens` | no (default `8192`) | Provider generation cap for the summarization call; may include reasoning tokens. | +| `compactionRetries` | no (default `1`) | Extra attempts after the first when pressure remains above threshold. | +| `auto` | no (default `true`) | Register the `agent/pre-step` automatic listener. Set `false` for manual-only. | ## Usage ```ts import type { Context } from 'cordis' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' +import TokenMeterService from '@deepseek-ai/dsh-token-meter' export const name = 'compact-basic' export const inject = ['llm'] export function apply(ctx: Context): void { - ctx.plugin(BasicCompactService, { - contextWindow: 128000, - thresholdRatio: 0.8, - retainTokens: 20480, - summarizationModel: '', - maxTokens: 8192, - compactionRetries: 1, - }) + ctx.plugin(TokenMeterService) + ctx.plugin(BasicCompactService) } ``` @@ -122,8 +115,8 @@ Rules: ## Known Limitations and Deferred Work -- **Token estimation is the chars/`charsPerToken` heuristic** — a marked TODO schedules replacing it with an exact count (a real tokenizer, or provider `usage` fed back) so thresholds track the model's actual budget. -- **`estimatePressure()` does not count the request's `tools` field** — pressure is underestimated by the size of the serialized tool schemas the request also carries. +- **Pre-step sees a provisional request envelope** — the current prompt and prefix are exact, but routing and tool changes made later in `agent/request` are not logged yet. A router-only agent with no provisional model skips that check. +- **Meter accuracy follows the selected profile** — missing provider usage falls back to the token meter's configured character density and structural overhead. - **`compactRegion` requires an open turn** — a manual call on a fully-closed session throws ("no open turn") rather than compacting. - **Summarization failure fails closed with full, over-budget history** — including truncation at the summarization `maxTokens`, which hidden reasoning tokens can consume; the auto path logs a warning and proceeds. - **The summarization call has no transcript-snapshot coverage** — `dsh-llm-replay` derives calls from `assistant/chunk` events, so this chunk-less direct `ctx.llm.stream()` call cannot replay (named deferred replay infrastructure in [the seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)). diff --git a/packages/compact/compact-basic/package.json b/packages/compact/compact-basic/package.json index 32852a060f..d50fa45777 100644 --- a/packages/compact/compact-basic/package.json +++ b/packages/compact/compact-basic/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-compact-basic", - "description": "Basic compaction backend (chars-per-token estimation + token-budget retention + llm.generate() summarization) for the DeepSeek Harness", + "description": "Token-meter-driven compaction policy and LLM summarization backend for the DeepSeek Harness", "version": "0.0.1", "private": true, "type": "module", @@ -26,9 +26,15 @@ "@deepseek-ai/dsh-compact": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", + "@deepseek-ai/dsh-token-meter": "^0.0.1", "cordis": "^4.0.0-rc.7" }, + "dependencies": { + "schemastery": "^3.18.0" + }, "devDependencies": { + "@cordisjs/plugin-include": "workspace:^", + "@cordisjs/plugin-loader": "workspace:^", "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-compact": "workspace:^", @@ -36,6 +42,7 @@ "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", + "@deepseek-ai/dsh-token-meter": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.7" } diff --git a/packages/compact/compact-basic/src/automatic.ts b/packages/compact/compact-basic/src/automatic.ts new file mode 100644 index 0000000000..504b0d8a9f --- /dev/null +++ b/packages/compact/compact-basic/src/automatic.ts @@ -0,0 +1,60 @@ +/** + * Automatic pre-step pressure listener for compact-basic. + * + * @module @deepseek-ai/dsh-compact-basic/automatic + */ + +import type { Context } from 'cordis' +import type { CompactionResult } from '@deepseek-ai/dsh-compact' +import type { Message } from '@deepseek-ai/dsh-llm' +import { + TOKEN_METER_MODEL_UNCONFIGURED, + TokenMeterError, +} from '@deepseek-ai/dsh-token-meter' +import type { Agent } from '@deepseek-ai/dsh-agent' + +interface AutomaticCompactor { + compactIfNeeded( + agent: Agent, + fullSystemPrompt: string, + sessionPrefix: readonly Message[], + signal: AbortSignal, + ): Promise +} + +/** + * Register the implementation-owned automatic compaction listener. + * @param ctx - context owning the listener effect and logger. + * @param service - compactor whose public methods remain dynamically dispatched. + */ +export function registerAutomaticCompaction( + ctx: Context, + service: AutomaticCompactor, +): void { + ctx.on('agent/pre-step', async ( + agent: Agent, + _turn: number, + _step: number, + fullSystemPrompt: string, + sessionPrefix: readonly Message[], + signal: AbortSignal, + ) => { + try { + const result = await service.compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal) + if (result !== null) { + ctx.logger.info( + `compaction: shadowed ${result.shadowedSeqs.length} surface nodes ` + + `(seqs ${result.shadowedRange.start}-${result.shadowedRange.end}, ` + + `~${result.shadowedTokenCount} tokens)`, + ) + } + } catch (error: unknown) { + // A named routed model without a meter profile is configuration failure, + // not an optional operational compaction miss. + if (error instanceof TokenMeterError + && error.code === TOKEN_METER_MODEL_UNCONFIGURED) throw error + const message = error instanceof Error ? error.message : String(error) + ctx.logger.warn(`compaction failed: ${message}; proceeding with full history`) + } + }) +} diff --git a/packages/compact/compact-basic/src/config.ts b/packages/compact/compact-basic/src/config.ts new file mode 100644 index 0000000000..3169d7f5aa --- /dev/null +++ b/packages/compact/compact-basic/src/config.ts @@ -0,0 +1,117 @@ +/** + * Runtime defaulting and per-model policy validation for compact-basic. + * + * @module @deepseek-ai/dsh-compact-basic/config + */ + +import { deepFreeze } from '@deepseek-ai/dsh-llm' +import type { ModelTokenMeter, TokenMeterService } from '@deepseek-ai/dsh-token-meter' +import type { + BasicCompactConfig, + ModelCompactConfig, + ResolvedConfig, + ResolvedModelCompactConfig, +} from './types.ts' + +/** Default request-pressure fraction for every metered model. */ +const DEFAULT_THRESHOLD_RATIO = 0.8 + +/** Default verbatim-tail fraction of a model's context window. */ +const DEFAULT_RETAIN_RATIO = 0.16 + +/** + * Resolve common defaults and validate every named model override. + * @param config - raw compact-basic configuration. + * @param tokenMeter - owning meter service used to reject unknown override names. + * @returns a detached deeply immutable top-level configuration. + */ +export function resolveConfig( + config: BasicCompactConfig = {}, + tokenMeter: TokenMeterService, +): ResolvedConfig { + const configuredModels: unknown = config.models + const models = configuredModels === undefined ? {} : configuredModels + if (typeof models !== 'object' || models === null || Array.isArray(models)) { + throw new Error('BasicCompactConfig: models must be an object') + } + + const detachedModels: Record = {} + for (const [model, override] of Object.entries(models as Record)) { + if (typeof override !== 'object' || override === null || Array.isArray(override)) { + throw new Error(`BasicCompactConfig: models.${model} must be an object`) + } + const meter = tokenMeter.resolve(model) + detachedModels[model] = { ...override as ModelCompactConfig } + resolveModelConfig({ + models: detachedModels, + summarizationModel: '', + maxTokens: 8192, + compactionRetries: 1, + auto: true, + }, meter) + } + + const resolved: ResolvedConfig = { + models: detachedModels, + summarizationModel: config.summarizationModel ?? '', + maxTokens: config.maxTokens ?? 8192, + compactionRetries: config.compactionRetries ?? 1, + auto: config.auto ?? true, + } + assertPositiveInteger('maxTokens', resolved.maxTokens) + assertNonNegativeInteger('compactionRetries', resolved.compactionRetries) + if (typeof resolved.summarizationModel !== 'string') { + throw new Error('BasicCompactConfig: summarizationModel must be a string') + } + if (typeof resolved.auto !== 'boolean') { + throw new Error('BasicCompactConfig: auto must be a boolean') + } + return deepFreeze(structuredClone(resolved)) +} + +/** + * Resolve one effective model's default policy plus optional field overrides. + * @param config - validated compact-basic configuration. + * @param meter - effective model's token-meter handle and context capacity. + * @returns a detached immutable model policy. + */ +export function resolveModelConfig( + config: ResolvedConfig, + meter: ModelTokenMeter, +): ResolvedModelCompactConfig { + const override = config.models[meter.model] + const thresholdRatio = override?.thresholdRatio ?? DEFAULT_THRESHOLD_RATIO + const retainTokens = override?.retainTokens ?? Math.floor(meter.contextWindow * DEFAULT_RETAIN_RATIO) + assertRatio(`models.${meter.model}.thresholdRatio`, thresholdRatio) + assertNonNegativeInteger(`models.${meter.model}.retainTokens`, retainTokens) + const thresholdTokens = Math.floor(meter.contextWindow * thresholdRatio) + if (retainTokens >= thresholdTokens) { + throw new Error( + `BasicCompactConfig: models.${meter.model}.retainTokens (${retainTokens}) must be less than threshold tokens ${thresholdTokens}`, + ) + } + return deepFreeze({ + model: meter.model, + contextWindow: meter.contextWindow, + thresholdRatio, + retainTokens, + }) +} + +function assertPositiveInteger(name: string, value: number): void { + if (!Number.isInteger(value) || value <= 0) { + throw new Error(`BasicCompactConfig: ${name} (${value}) must be a positive integer`) + } +} + +function assertNonNegativeInteger(name: string, value: number): void { + if (!Number.isInteger(value) || value < 0) { + throw new Error(`BasicCompactConfig: ${name} (${value}) must be a non-negative integer`) + } +} + +function assertRatio(name: string, value: number): void { + if (typeof value !== 'number' || !Number.isFinite(value) || value <= 0 || value > 1) { + throw new Error(`BasicCompactConfig: ${name} (${value}) must be a number in (0, 1]`) + } +} diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index fffc8e9a63..f8a9060aa9 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -1,286 +1,120 @@ /** - * Basic compaction backend. It estimates request pressure, retains a recent - * tool-balanced surface tail, summarizes the older head through a one-shot model - * call, and replaces that head with one checkpoint. Auto-compaction runs before - * every step so a growing turn can compact its earlier closed steps. + * Basic replay-aware compaction backend. + * * @module @deepseek-ai/dsh-compact-basic */ import { Context } from 'cordis' -import { CompactService, renderTranscript, toolPairingBalancedAfter, toolPairingBalancedBefore } from '@deepseek-ai/dsh-compact' +import z from 'schemastery' +import { CompactService } from '@deepseek-ai/dsh-compact' import type { CompactionResult } from '@deepseek-ai/dsh-compact' -import { BlockAssembler } from '@deepseek-ai/dsh-llm' -import type { ContentBlock, FinishReason, GenerateOptions, Message } from '@deepseek-ai/dsh-llm' -import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' +import { canonicalHeader } from '@deepseek-ai/dsh-session' +import type { EpochHeader, Session } from '@deepseek-ai/dsh-session' +import type { ContentBlock, Message } from '@deepseek-ai/dsh-llm' +import type { ModelTokenMeter } from '@deepseek-ai/dsh-token-meter' import type { Agent } from '@deepseek-ai/dsh-agent' -import type { BasicCompactConfig, ResolvedConfig } from './types.ts' -import { resolveConfig } from './types.ts' +import { registerAutomaticCompaction } from './automatic.ts' +import { resolveConfig, resolveModelConfig } from './config.ts' +import { compactSurfaceRegion, selectCompactableRange } from './region.ts' +import { summarizeWithLlm } from './summarizer.ts' +import type { + BasicCompactConfig, + ResolvedConfig, + ResolvedModelCompactConfig, +} from './types.ts' -export type { BasicCompactConfig, ResolvedConfig } from './types.ts' -export { resolveConfig } from './types.ts' +export { resolveConfig, resolveModelConfig } from './config.ts' +export type { + BasicCompactConfig, + ModelCompactConfig, + ResolvedConfig, + ResolvedModelCompactConfig, +} from './types.ts' -/** Per-block structural overhead for JSON framing / type tag. */ -const BLOCK_OVERHEAD = 4 - -/** Role-field framing overhead added per message in {@link BasicCompactService.estimateTokens}. */ -const ROLE_OVERHEAD = 4 - -/** Tags wrapping the structured summary inside the landed checkpoint node. */ -const SUMMARY_OPEN_TAG = '' -const SUMMARY_CLOSE_TAG = '' - -/** - * Fixed summary structure for resumable checkpoints. A tagged prior checkpoint - * is merged with newer history instead of copied forward verbatim. - */ -const SUMMARIZE_SYSTEM_PROMPT = [ - 'You are a compaction engine for an AI coding assistant. Condense the conversation transcript into a structured checkpoint that lets another model resume the work with no loss of essential context.', - '', - 'Output EXACTLY the Markdown structure below: keep every section, in order. Use terse bullets, not prose paragraphs. Write "(none)" for an empty section — never drop a section.', - '', - '## Primary Request and Intent', - "- [the user's original and evolving goals; quote verbatim where the exact wording matters]", - '', - '## Key Technical Concepts', - '- [technologies, frameworks, patterns, and conventions in play]', - '', - '## Files and Code', - '- [exact path: why it matters, key changes or snippets]', - '', - '## Errors and Fixes', - '- [error: how it was resolved, plus any related user feedback]', - '', - '## Pending Tasks', - '- [explicitly requested work not yet completed]', - '', - '## Current Work', - '- [precisely what was in progress at this checkpoint]', - '', - '## Next Step', - '- [the single next action, directly in line with the most recent request, or "(none)"]', - '', - '## Critical Context', - '- [decisions and their rationale, constraints, user preferences, open questions, data needed to continue]', - '', - 'Rules:', - '- Preserve exact file paths, commands, error strings, identifiers, and function signatures.', - '- Capture user feedback and explicit instructions faithfully, especially corrections.', - '- Do NOT mention this summarization process or that the context was compacted.', - `- If the transcript already contains a ${SUMMARY_OPEN_TAG} block, it is a PRIOR checkpoint. Do not copy it forward verbatim: preserve still-true facts, drop stale ones, and merge newer information into a single consolidated summary under the same structure.`, -].join('\n') - -/** Framing that makes a landed summary established context rather than a new request. */ -const CHECKPOINT_PREAMBLE = - 'This is an automatically generated checkpoint condensing an earlier span of the conversation to free up context. Treat the captured context as established background and build on it without restating it. Continue the task directly from the messages that follow, without acknowledging this checkpoint.' - -/** - * Map a terminal summary failure to an error. A max-token finish is rejected - * because committing an incomplete checkpoint would shadow the full history. - */ -function finishError(finish: FinishReason): Error | undefined { - switch (finish.kind) { - case 'error': { - const error = new Error(finish.message) as Error & { code?: string } - if (finish.code !== undefined) error.code = finish.code - return error - } - case 'aborted': { - const error = new Error('summarization stream aborted') as Error & { code?: string } - error.code = 'ABORTED' - return error - } - case 'max-tokens': { - const error = new Error('summarization truncated at the token cap (incomplete checkpoint)') as Error & { code?: string } - error.code = 'MAX_TOKENS' - return error - } - default: - return undefined - } +/** Resolve the latest actual routed model, then the agent's configured fallback. */ +function effectiveModel(agent: Agent): string | undefined { + return agent.session.requestHeader()?.config.model ?? agent.options.model } /** - * Basic, dependency-light compaction backend: estimates the surface's token - * footprint, summarizes the stale prefix through the model, and shadows it - * behind a durable checkpoint. Every threshold/budget knob is required config - * ({@link BasicCompactConfig}); the estimator's text density is the - * `charsPerToken` knob. + * Build the provisional pre-step request envelope. Prompt and prefix are exact; + * tools and non-model call config come from the latest logged request because + * later request middleware has not run yet. + */ +function provisionalHeader( + model: string, + session: Session, + fullSystemPrompt: string, + sessionPrefix: readonly Message[], +): EpochHeader { + const latest = session.requestHeader() + return canonicalHeader({ + config: latest === undefined ? { model } : { ...latest.config, model }, + ...fullSystemPrompt.length === 0 ? {} : { system: fullSystemPrompt }, + ...latest?.tools === undefined ? {} : { tools: latest.tools }, + ...sessionPrefix.length === 0 ? {} : { messagePrefix: [...sessionPrefix] }, + }) +} + +/** + * Dependency-light compaction backend using `ctx.tokenMeter` for pressure, + * retention, provenance, and summary-convergence pricing. + * + * `summarize()` is the sole subclass customization hook; the replay and durable + * mutation strategy stays fixed so every pricing decision uses one effective + * conversation-model meter. */ export class BasicCompactService extends CompactService { - static inject = ['llm'] + static inject = ['llm', 'tokenMeter'] - /** Resolved configuration (`auto` defaulted). */ + static Config: z = z.object({ + models: z.dict(z.object({ + thresholdRatio: z.number(), + retainTokens: z.number().step(1), + })), + summarizationModel: z.string().default(''), + maxTokens: z.number().step(1).min(1).default(8192), + compactionRetries: z.number().step(1).min(0).default(1), + auto: z.boolean().default(true), + }) + + /** Resolved and validated common configuration plus named partial overrides. */ readonly config: ResolvedConfig - constructor(ctx: Context, config: BasicCompactConfig) { + private readonly modelConfigs = new Map() + + constructor(ctx: Context, config: BasicCompactConfig = {}) { super(ctx) - this.config = resolveConfig(config) - - if (this.config.auto) { - // Check before every step so a single growing turn can compact earlier closed steps. - // This serial pre-step seam mutates the surface outside the pending step. - ctx.on('agent/pre-step', async (agent: Agent, _turn: number, _step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal) => { - try { - const result = await this.compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal) - if (result) { - const after = this.estimatePressure(agent.session, fullSystemPrompt, sessionPrefix) - ctx.logger.info( - `compaction: shadowed ${result.shadowedSeqs.length} surface nodes ` + - `(seqs ${result.shadowedRange.start}-${result.shadowedRange.end}, ` + - `~${result.shadowedTokenCount} tokens) ` + - `→ ${after} estimated tokens after compaction`, - ) - } - } catch (error: unknown) { - // A failed compaction must not prevent the model call — the surface is - // untouched on failure, so the loop derives the full history and the - // call proceeds. - const msg = error instanceof Error ? error.message : String(error) - ctx.logger.warn(`compaction failed: ${msg}; proceeding with full history`) - } - }) - } - } - - // ---- Token estimation (overridable hooks) ---- - - // TODO: chars/charsPerToken is a coarse heuristic. Replace with an exact - // count — a real tokenizer, or the provider's post-response `usage` (input - // tokens) fed back as a correction — so threshold decisions match the - // model's actual budget. - /** - * Estimate the token count of content blocks — chars divided by the - * `charsPerToken` config, with per-block overhead. Override in a subclass to - * plug in a real tokenizer. - * - * @param blocks - the blocks to estimate; `tool-result` blocks recurse into - * their nested content, and unknown (merge-extended) types fall back to - * their JSON-stringified length. - * @returns the estimated token count. - */ - estimateContentTokens(blocks: readonly ContentBlock[]): number { - const { charsPerToken } = this.config - let tokens = 0 - for (const block of blocks) { - switch (block.type) { - case 'text': - case 'reasoning': - tokens += Math.ceil(block.text.length / charsPerToken) + BLOCK_OVERHEAD - break - case 'tool-call': - tokens += Math.ceil(block.name.length / charsPerToken) - + Math.ceil(block.arguments.length / charsPerToken) - + BLOCK_OVERHEAD - break - case 'tool-result': - tokens += this.estimateContentTokens(block.content) + BLOCK_OVERHEAD - break - default: - // Unknown block types (merge-extensible ContentBlockMap): - // estimate conservatively via JSON stringify. - tokens += BLOCK_OVERHEAD + Math.ceil(JSON.stringify(block).length / charsPerToken) - } - } - return tokens + this.config = resolveConfig(config, ctx.tokenMeter) + if (this.config.auto) registerAutomaticCompaction(ctx, this) } /** - * Estimate token count for a single session event. Returns 0 for non-message - * event types (boundaries, chunks, usage, errors, compact markers). - * - * @param event - any session event; only the message-bearing types carry - * content to count. - * @returns the estimated token count of the event's content, or 0 for a - * non-message event. - */ - estimateEventTokens(event: SessionEvent): number { - switch (event.type) { - case 'user/message': - case 'assistant/message': - case 'context/message': - case 'steering/message': - case 'tool/result': - return this.estimateContentTokens(event.data.content) - default: - return 0 - } - } - - /** - * Estimate total tokens across a list of messages plus optional system prompt. - * - * @param messages - the derived conversation messages; each adds a fixed - * role-framing overhead on top of its content estimate. - * @param systemPrompt - counted at chars / `charsPerToken` when provided. - * @returns the estimated token footprint of the whole request. - */ - estimateTokens(messages: readonly Message[], systemPrompt?: string): number { - let total = 0 - for (const msg of messages) { - total += this.estimateContentTokens(msg.content) - total += ROLE_OVERHEAD - } - if (systemPrompt) total += Math.ceil(systemPrompt.length / this.config.charsPerToken) - return total - } - - /** - * Summarize through a direct one-shot `ctx.llm.stream()` call, not an agent - * step or `agent/request` dispatch. Failure finishes and truncated summaries - * reject; the signal is forwarded and only text reaches the checkpoint. - * - * @param text - plain-text rendering of the conversation region to condense. - * @param agent - supplies the fallback model and the session id stamped on - * the call; throws when neither it nor the config names a model. - * @param signal - optional abort signal, forwarded into the model call. - * @returns the text-only summary blocks plus the call envelope used - * (`model`, and `maxTokens` when the summarizer has a cap). + * Summarize a rendered region through a direct one-shot `ctx.llm.stream()` + * call. Override this sole hook for a template or remote summarizer. + * @param text - plain-text conversation region to condense. + * @param agent - supplies routed-model history, fallback model, and session id. + * @param signal - optional cancellation forwarded to the adapter. + * @returns safe text summary blocks and exact auxiliary-call provenance. */ async summarize( - text: string, agent: Agent, signal?: AbortSignal, + text: string, + agent: Agent, + signal?: AbortSignal, ): Promise<{ summary: ContentBlock[]; model: string; maxTokens?: number }> { - const assembler = new BlockAssembler() - const options: GenerateOptions = { - model: this.config.summarizationModel || agent.options.model || '', - messages: [{ - role: 'user', - content: [{ type: 'text', text: `Summarize this conversation history:\n\n${text}\n\nSummary:` }], - }], - system: SUMMARIZE_SYSTEM_PROMPT, - maxTokens: this.config.maxTokens, - sessionId: agent.session.id, - } - // exactOptionalPropertyTypes: only set `signal` when present — assigning - // `undefined` to an optional `signal?: AbortSignal` is a type error. - if (signal) options.signal = signal - if (!options.model) { - throw new Error('no model available for summarization: set BasicCompactConfig.summarizationModel or AgentOptions.model') - } - for await (const chunk of this.ctx.llm.stream(options)) { - assembler.push(chunk) - } - - const error = finishError(assembler.finish) - if (error) throw error - - const summary = this._textOnly(assembler.message().content) - if (!summary.some(block => block.type === 'text' && block.text.trim().length > 0)) { - throw new Error('summarization produced no text summary content') - } - - // config.maxTokens is required and validated positive, so this backend's - // envelope always carries the cap; the return type's optionality exists - // for overriding subclasses whose summarizer has none. - return { summary, model: options.model, maxTokens: this.config.maxTokens } + return summarizeWithLlm(this.ctx, this.config, text, agent, signal) } - // ---- Core API (implements the abstract contract) ---- - /** - * The sole pressure gate: count the next request's prefix, derived history, - * and system prompt. Above threshold, retain a recent tool-balanced tail and - * compact the head, reconsolidating any prior automatic checkpoint. Returns - * `null` when no safe or necessary range exists. + * Check replayed pressure for the provisional pre-step envelope and compact + * a tool-balanced head until it falls below the effective model threshold. + * A genuinely model-less router-first step skips this provisional check; + * naming an unconfigured model throws the token meter's typed error. + * @param agent - agent whose session and provisional model are measured. + * @param fullSystemPrompt - current assembled system prompt override. + * @param sessionPrefix - current request-only prefix override. + * @param signal - live step cancellation signal forwarded to summarization. + * @returns the latest compaction result, or `null` when no check/work applies. */ override async compactIfNeeded( agent: Agent, @@ -288,47 +122,51 @@ export class BasicCompactService extends CompactService { sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise { - const session = agent.session - const threshold = Math.floor(this.config.contextWindow * this.config.thresholdRatio) - let result: CompactionResult | null = null - for (let attempt = 0; attempt <= this.config.compactionRetries; attempt++) { - const totalTokens = this.estimatePressure(session, fullSystemPrompt, sessionPrefix) - if (totalTokens < threshold) return result + const model = effectiveModel(agent) + if (model === undefined || model.length === 0) return null + const meter = this.ctx.tokenMeter.resolve(model) + const policy = this._modelConfig(meter) + const requestHeader = provisionalHeader(model, agent.session, fullSystemPrompt, sessionPrefix) + const threshold = Math.floor(policy.contextWindow * policy.thresholdRatio) + let measurement = meter.measure(agent.session, requestHeader) + if (measurement.totalTokens < threshold) return null - const range = this._compactableRange(session) + let result: CompactionResult | null = null + for (let attempt = 0; attempt <= this.config.compactionRetries; attempt += 1) { + const surface = meter.measureSurface(agent.session) + if (surface.logRevision !== measurement.logRevision) { + throw new Error( + `compaction: pressure revision ${measurement.logRevision} does not match surface revision ${surface.logRevision}`, + ) + } + const range = selectCompactableRange(agent.session, surface, policy.retainTokens) if (range === null) { - /* v8 ignore else -- defensive for non-standard subclass mutations; the concrete replace keeps a compactable head checkpoint. */ + /* v8 ignore else -- concrete replacement preserves a compactable checkpoint; subclass hooks cannot mutate it. */ if (result === null) return null - /* v8 ignore next -- paired with the ignored defensive branch above. */ + /* v8 ignore next -- paired with the defensive post-success branch above. */ break } - - result = await this.compactRegion(session, range.start, range.end, agent, signal) + result = await this.compactRegion(agent.session, range.start, range.end, agent, signal) + measurement = meter.measure(agent.session, requestHeader) + if (measurement.totalTokens < threshold) return result } - const totalTokens = this.estimatePressure(session, fullSystemPrompt, sessionPrefix) - if (totalTokens < threshold) return result - throw new Error( `compaction still above threshold after ${this.config.compactionRetries + 1} compaction attempts ` - + `(${totalTokens} estimated tokens >= threshold ${threshold})`, + + `(${measurement.totalTokens} estimated tokens >= threshold ${threshold})`, ) } /** - * Estimated token pressure of the NEXT request: the session prefix - * (`EpochHeader.messagePrefix` — request-only messages the loop sends in - * front of the derived history, composed before the pre-step seam and - * handed to the gate), the derived history, and the system prompt. - * @param session - the session whose next request is being estimated. - * @param fullSystemPrompt - the assembled system prompt (counts toward pressure). - * @param sessionPrefix - the instance's composed session prefix (counts toward pressure). - * @returns the estimated token total the next request will carry. + * Compact one inclusive positional surface range using the effective + * conversation model for all retention and shrink pricing. + * @param session - session whose surface is mutated. + * @param start - inclusive first surface-node seq. + * @param end - inclusive last surface-node seq. + * @param agent - agent used by the summarizer and model resolver. + * @param signal - optional summarization cancellation signal. + * @returns the successful durable compaction result. */ - estimatePressure(session: Session, fullSystemPrompt: string, sessionPrefix: readonly Message[]): number { - return this.estimateTokens([...sessionPrefix, ...session.deriveMessages()], fullSystemPrompt) - } - override async compactRegion( session: Session, start: number, @@ -336,214 +174,26 @@ export class BasicCompactService extends CompactService { agent: Agent, signal?: AbortSignal, ): Promise { - // Resolve by surface position: a newer replacement seq may occupy an older slot. - const nodes = session.surface.nodes - const startIdx = nodes.findIndex(n => n.seq === start) - const endIdx = nodes.findIndex(n => n.seq === end) - if (startIdx === -1) throw new Error(`compactRegion: start seq ${start} not found in surface`) - if (endIdx === -1) throw new Error(`compactRegion: end seq ${end} not found in surface`) - if (startIdx > endIdx) { - throw new Error(`compactRegion: start seq ${start} (position ${startIdx}) is after end seq ${end} (position ${endIdx}) on the surface`) - } - - // Both range edges must preserve assistant tool-call/result pairing. - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const startNode = nodes[startIdx]! - if (!toolPairingBalancedBefore(session, startNode)) { - throw new Error(`compactRegion: start seq ${start} is not a balanced boundary (would split a step's tool-call/result pair)`) - } - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const endNode = nodes[endIdx]! - if (!toolPairingBalancedAfter(session, endNode)) { - throw new Error(`compactRegion: end seq ${end} is not a balanced boundary (would split a step, or the step is still open)`) - } - - if (this._isCompactionInProgress(session)) { - throw new Error('compaction already in progress') - } - - // Compaction's events (compact/* and the replacement user/message) must be turn-enclosed: - // the session-log contract rejects any plugin event appended outside an open turn. - const openTurn = this._openTurn(session) - if (openTurn === null) { - throw new Error('compactRegion: no open turn — compaction events must be enclosed in a turn') - } - // Slice the ordered surface nodes [startIdx, endIdx] inclusive — the - // shadowed range is positional, so this is the set the replace op covers. - const shadowedSeqs = nodes.slice(startIdx, endIdx + 1).map(n => n.seq) - - // --- Acquire lock --- - const startEvent = session.append('compact/start', { turn: openTurn }) - - try { - // --- Extract text and summarize --- - const text = renderTranscript(session.events, shadowedSeqs) - const { summary, model, maxTokens } = await this.summarize(text, agent, signal) - - // Estimate token count of the shadowed content for provenance. - let shadowedTokenCount = 0 - for (const seq of shadowedSeqs) { - // seq comes from a surface node — always a valid log index by construction. - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - shadowedTokenCount += this.estimateEventTokens(session.events[seq]!) - } - const framedSummary = this._frameSummary(summary) - const framedSummaryTokenCount = this.estimateContentTokens(framedSummary) - if (framedSummaryTokenCount >= shadowedTokenCount) { - throw new Error( - `summary is not smaller than the shadowed content (${framedSummaryTokenCount} estimated framed tokens >= ${shadowedTokenCount})`, - ) - } - // --- Provenance record (log-only) --- - const summaryEvent = session.append('compact/summary', { - summary, - shadowedRange: { start, end }, - shadowedSeqs, - shadowedTokenCount, - model, - ...maxTokens !== undefined ? { maxTokens } : {}, - }) - - // --- Surface replacement --- The user/message directly shadows all compacted surface - // nodes with a single replace op. - session.append('user/message', { - content: framedSummary, - source: { kind: 'plugin', plugin: 'compact' }, - }, { - surfaceOp: { op: 'replace', start, end }, - sourceEventSeqs: [startEvent.seq, summaryEvent.seq, ...shadowedSeqs], - }) - - // --- Release lock (log-only) --- - // Appended LAST so the lock brackets the WHOLE operation: a crash between - // compact/start and here leaves a detectable orphaned lock (a compact/start - // with no matching compact/end) rather than a compact/end that falsely - // claims compaction finished before the surface replacement landed. - const endEvent = session.append('compact/end', { turn: openTurn }) - - return { - startSeq: startEvent.seq, - summarySeq: summaryEvent.seq, - endSeq: endEvent.seq, - summary, - shadowedRange: { start, end }, - shadowedSeqs, - shadowedTokenCount, - } - } catch (error: unknown) { - // Always release the lock — append compact/end with the error so a - // wedged lock is impossible. - const msg = error instanceof Error ? error.message : String(error) - session.append('compact/end', { turn: openTurn, error: msg }) - throw error + const model = effectiveModel(agent) + if (model === undefined || model.length === 0) { + throw new Error('compactRegion: no routed or configured conversation model is available for token pricing') } + const meter = this.ctx.tokenMeter.resolve(model) + this._modelConfig(meter) + return compactSurfaceRegion({ + meter, + summarize: (text, owner, abort) => this.summarize(text, owner, abort), + }, session, start, end, agent, signal) } - // ---- Internal helpers ---- - - /** - * Frame the raw summary blocks into the content that lands on the surface: - * a checkpoint preamble (so a resuming model reads it as a checkpoint, not a - * fresh user request) followed by the summary wrapped in - * {@link SUMMARY_OPEN_TAG}/{@link SUMMARY_CLOSE_TAG}. The tags make a prior - * checkpoint detectable in the transcript on the next compaction cycle, which - * triggers the merge rule in the summarization prompt. The raw, unframed - * `summary` is preserved separately on the `compact/summary` provenance event. - */ - private _frameSummary(summary: readonly ContentBlock[]): ContentBlock[] { - return [ - { type: 'text', text: `${CHECKPOINT_PREAMBLE}\n\n${SUMMARY_OPEN_TAG}` }, - ...summary, - { type: 'text', text: SUMMARY_CLOSE_TAG }, - ] - } - - /** - * Whether a compaction is currently in progress for `session` — an unmatched `compact/start` - * (no later `compact/end`) WITHIN the current turn. - */ - private _isCompactionInProgress(session: Session): boolean { - const events = session.events - for (let i = events.length - 1; i >= 0; i--) { - // Index bounded by i >= 0 and i < events.length — never undefined. - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const e = events[i]! - if (e.type === 'compact/start') return true - if (e.type === 'compact/end') break - // A turn/end bounds the scan: anything before it belongs to a prior - // (closed) turn and cannot be an in-progress compaction of THIS turn. - if (e.type === 'turn/end') break + /** Resolve and memoize one lazy default/override model policy. */ + private _modelConfig(meter: ModelTokenMeter): ResolvedModelCompactConfig { + let modelConfig = this.modelConfigs.get(meter.model) + if (modelConfig === undefined) { + modelConfig = resolveModelConfig(this.config, meter) + this.modelConfigs.set(meter.model, modelConfig) } - return false - } - - /** Resolve the next head-anchored compactable surface range, or `null`. */ - private _compactableRange(session: Session): { start: number; end: number } | null { - const nodes = session.surface.nodes - if (nodes.length === 0) return null - - const events = session.events - const retainBudget = this.config.retainTokens - - // Walk tail→head summing per-node token estimates. `keepFromIdx` is the - // index of the OLDEST node we retain verbatim; everything strictly older - // (`[0, keepFromIdx - 1]`) is the compactable range. - let accumulated = 0 - let keepFromIdx = nodes.length // nothing retained yet - for (let i = nodes.length - 1; i >= 0; i--) { - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const node = nodes[i]! - const event = events[node.seq] - /* v8 ignore next -- node.seq is a surface-node seq, always a valid log index by construction */ - if (event) accumulated += this.estimateEventTokens(event) - keepFromIdx = i - if (accumulated >= retainBudget) break - } - - // The whole surface fits the retain budget — nothing to compact. - if (keepFromIdx === 0) return null - - // Round the cutoff to a tool-pairing boundary: if the cut before `nodes[keepFromIdx]` is - // unbalanced (an unanswered tool-call sits before it — i.e. it is mid-step), extend the - // retained side head-ward until the cut is balanced, so the compacted range ends without - // splitting an assistant↔result pair. - while (keepFromIdx > 0) { - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - if (toolPairingBalancedBefore(session, nodes[keepFromIdx]!)) break - keepFromIdx -= 1 - } - if (keepFromIdx === 0) return null - - // The compacted range is [head … keepFromIdx - 1], anchored at the head. - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const firstSeq = nodes[0]!.seq - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const cutoffSeq = nodes[keepFromIdx - 1]!.seq - return { start: firstSeq, end: cutoffSeq } - } - - /** Keep only text; checkpoints cannot contain reasoning or orphan tool calls. */ - private _textOnly(blocks: readonly ContentBlock[]): ContentBlock[] { - return blocks.filter((block): block is Extract => block.type === 'text') - } - - /** - * The turn number of the currently OPEN turn — a `turn/start` not yet - * followed by its `turn/end` — or `null` if the session has no open turn. - * - * Compaction's events must be enclosed in a turn, so scanning back from the - * tail: a `turn/start` means that turn is open (return it); a `turn/end` means - * the most recent turn already closed (return null). The whole compaction - * sequence (compact/start … compact/end) is stamped with this turn. - */ - private _openTurn(session: Session): number | null { - for (let i = session.events.length - 1; i >= 0; i--) { - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const e = session.events[i]! - if (e.type === 'turn/start') return e.data.turn - if (e.type === 'turn/end') return null - } - return null + return modelConfig } } diff --git a/packages/compact/compact-basic/src/region.ts b/packages/compact/compact-basic/src/region.ts new file mode 100644 index 0000000000..1bc9b7b0a7 --- /dev/null +++ b/packages/compact/compact-basic/src/region.ts @@ -0,0 +1,196 @@ +/** + * Surface retention selection and the log-recorded compaction transaction. + * + * @module @deepseek-ai/dsh-compact-basic/region + */ + +import { + renderTranscript, + toolPairingBalancedAfter, + toolPairingBalancedBefore, +} from '@deepseek-ai/dsh-compact' +import type { CompactionResult } from '@deepseek-ai/dsh-compact' +import type { ModelTokenMeter, TokenSurfaceMeasurement } from '@deepseek-ai/dsh-token-meter' +import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' +import type { Agent } from '@deepseek-ai/dsh-agent' +import { frameSummary } from './summarizer.ts' +import type { SummaryResult } from './summarizer.ts' + +interface RegionDependencies { + readonly meter: ModelTokenMeter + summarize(text: string, agent: Agent, signal?: AbortSignal): Promise +} + +/** + * Resolve the next head-anchored range while retaining a priced recent tail + * and never splitting an assistant tool-call/result pair. + * @param session - session supplying authoritative current surface positions. + * @param pricedSurface - same-revision surface measurement from the conversation meter. + * @param retainTokens - minimum recent tail budget retained verbatim. + * @returns the inclusive positional seq range to compact, or `null`. + */ +export function selectCompactableRange( + session: Session, + pricedSurface: TokenSurfaceMeasurement, + retainTokens: number, +): { start: number; end: number } | null { + const pricedNodes = pricedSurface.nodes + if (pricedNodes.length === 0) return null + + const surfaceNodes = session.surface.nodes + if (surfaceNodes.length !== pricedNodes.length + || surfaceNodes.some((node, index) => node.seq !== pricedNodes[index]?.seq)) { + throw new Error('compaction: token-meter surface does not match the current session surface') + } + + let accumulated = 0 + let keepFromIdx = pricedNodes.length + for (let index = pricedNodes.length - 1; index >= 0; index -= 1) { + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + accumulated += pricedNodes[index]!.tokens + keepFromIdx = index + if (accumulated >= retainTokens) break + } + if (keepFromIdx === 0) return null + + while (keepFromIdx > 0) { + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + if (toolPairingBalancedBefore(session, surfaceNodes[keepFromIdx]!)) break + keepFromIdx -= 1 + } + if (keepFromIdx === 0) return null + + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + const first = surfaceNodes[0]! + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + const cutoff = surfaceNodes[keepFromIdx - 1]! + return { start: first.seq, end: cutoff.seq } +} + +/** + * Validate and compact one positional surface span. + * @param dependencies - conversation meter and dynamically dispatched summarizer hook. + * @param session - session whose surface is mutated. + * @param start - inclusive first surface-node seq. + * @param end - inclusive last surface-node seq. + * @param agent - agent used by the summarizer. + * @param signal - optional summarization cancellation signal. + * @returns the successful durable compaction result. + */ +export async function compactSurfaceRegion( + dependencies: RegionDependencies, + session: Session, + start: number, + end: number, + agent: Agent, + signal?: AbortSignal, +): Promise { + const nodes = session.surface.nodes + const startIdx = nodes.findIndex(node => node.seq === start) + const endIdx = nodes.findIndex(node => node.seq === end) + if (startIdx === -1) throw new Error(`compactRegion: start seq ${start} not found in surface`) + if (endIdx === -1) throw new Error(`compactRegion: end seq ${end} not found in surface`) + if (startIdx > endIdx) { + throw new Error( + `compactRegion: start seq ${start} (position ${startIdx}) is after end seq ${end} (position ${endIdx}) on the surface`, + ) + } + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + if (!toolPairingBalancedBefore(session, nodes[startIdx]!)) { + throw new Error(`compactRegion: start seq ${start} is not a balanced boundary (would split a step's tool-call/result pair)`) + } + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + if (!toolPairingBalancedAfter(session, nodes[endIdx]!)) { + throw new Error(`compactRegion: end seq ${end} is not a balanced boundary (would split a step, or the step is still open)`) + } + + const tail = inspectTurnTail(session.events) + if (tail.compactionInProgress) throw new Error('compaction already in progress') + if (tail.turn === null) { + throw new Error('compactRegion: no open turn — compaction events must be enclosed in a turn') + } + + const shadowedSeqs = nodes.slice(startIdx, endIdx + 1).map(node => node.seq) + const startEvent = session.append('compact/start', { turn: tail.turn }) + try { + // Capture after the lock event so any later durable append, including a + // log-only one, invalidates the async selection before replacement. + const lockedSurface = dependencies.meter.measureSurface(session) + const selected = lockedSurface.nodes.slice(startIdx, endIdx + 1) + if (selected.length !== shadowedSeqs.length + || selected.some((node, index) => node.seq !== shadowedSeqs[index])) { + throw new Error('compaction: selected surface changed before summarization began') + } + const shadowedTokenCount = selected.reduce((total, node) => total + node.tokens, 0) + const text = renderTranscript(session.events, shadowedSeqs) + const { summary, model, maxTokens } = await dependencies.summarize(text, agent, signal) + + const currentSurface = dependencies.meter.measureSurface(session) + if (currentSurface.logRevision !== lockedSurface.logRevision) { + throw new Error('compaction: session log changed during summarization') + } + const framedSummary = frameSummary(summary) + const framedSummaryTokenCount = dependencies.meter.estimateMessage({ + role: 'user', + content: framedSummary, + }) + if (framedSummaryTokenCount >= shadowedTokenCount) { + throw new Error( + `summary is not smaller than the shadowed content (${framedSummaryTokenCount} estimated framed tokens >= ${shadowedTokenCount})`, + ) + } + + const summaryEvent = session.append('compact/summary', { + summary, + shadowedRange: { start, end }, + shadowedSeqs, + shadowedTokenCount, + model, + ...maxTokens === undefined ? {} : { maxTokens }, + }) + session.append('user/message', { + content: framedSummary, + source: { kind: 'plugin', plugin: 'compact' }, + }, { + surfaceOp: { op: 'replace', start, end }, + sourceEventSeqs: [startEvent.seq, summaryEvent.seq, ...shadowedSeqs], + }) + const endEvent = session.append('compact/end', { turn: tail.turn }) + return { + startSeq: startEvent.seq, + summarySeq: summaryEvent.seq, + endSeq: endEvent.seq, + summary, + shadowedRange: { start, end }, + shadowedSeqs, + shadowedTokenCount, + } + } catch (error: unknown) { + const message = error instanceof Error ? error.message : String(error) + session.append('compact/end', { turn: tail.turn, error: message }) + throw error + } +} + +/** Inspect the current turn boundary and latest compaction bracket once. */ +function inspectTurnTail( + events: readonly SessionEvent[], +): { turn: number | null; compactionInProgress: boolean } { + let compactionInProgress = false + let compactionStateKnown = false + for (let index = events.length - 1; index >= 0; index -= 1) { + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + const event = events[index]! + if (!compactionStateKnown) { + if (event.type === 'compact/start') { + compactionInProgress = true + compactionStateKnown = true + } else if (event.type === 'compact/end') { + compactionStateKnown = true + } + } + if (event.type === 'turn/start') return { turn: event.data.turn, compactionInProgress } + if (event.type === 'turn/end') return { turn: null, compactionInProgress } + } + return { turn: null, compactionInProgress } +} diff --git a/packages/compact/compact-basic/src/summarizer.ts b/packages/compact/compact-basic/src/summarizer.ts new file mode 100644 index 0000000000..359421f0f5 --- /dev/null +++ b/packages/compact/compact-basic/src/summarizer.ts @@ -0,0 +1,153 @@ +/** + * Default one-shot summarization and durable checkpoint framing. + * + * @module @deepseek-ai/dsh-compact-basic/summarizer + */ + +import type { Context } from 'cordis' +import { BlockAssembler } from '@deepseek-ai/dsh-llm' +import type { ContentBlock, FinishReason, GenerateOptions } from '@deepseek-ai/dsh-llm' +import type { Agent } from '@deepseek-ai/dsh-agent' +import type { ResolvedConfig } from './types.ts' + +/** Tags wrapping the structured summary inside the landed checkpoint node. */ +const SUMMARY_OPEN_TAG = '' +const SUMMARY_CLOSE_TAG = '' + +/** Fixed structure required from the auxiliary summarization call. */ +const SUMMARIZE_SYSTEM_PROMPT = [ + 'You are a compaction engine for an AI coding assistant. Condense the conversation transcript into a structured checkpoint that lets another model resume the work with no loss of essential context.', + '', + 'Output EXACTLY the Markdown structure below: keep every section, in order. Use terse bullets, not prose paragraphs. Write "(none)" for an empty section — never drop a section.', + '', + '## Primary Request and Intent', + "- [the user's original and evolving goals; quote verbatim where the exact wording matters]", + '', + '## Key Technical Concepts', + '- [technologies, frameworks, patterns, and conventions in play]', + '', + '## Files and Code', + '- [exact path: why it matters, key changes or snippets]', + '', + '## Errors and Fixes', + '- [error: how it was resolved, plus any related user feedback]', + '', + '## Pending Tasks', + '- [explicitly requested work not yet completed]', + '', + '## Current Work', + '- [precisely what was in progress at this checkpoint]', + '', + '## Next Step', + '- [the single next action, directly in line with the most recent request, or "(none)"]', + '', + '## Critical Context', + '- [decisions and their rationale, constraints, user preferences, open questions, data needed to continue]', + '', + 'Rules:', + '- Preserve exact file paths, commands, error strings, identifiers, and function signatures.', + '- Capture user feedback and explicit instructions faithfully, especially corrections.', + '- Do NOT mention this summarization process or that the context was compacted.', + `- If the transcript already contains a ${SUMMARY_OPEN_TAG} block, it is a PRIOR checkpoint. Do not copy it forward verbatim: preserve still-true facts, drop stale ones, and merge newer information into a single consolidated summary under the same structure.`, +].join('\n') + +/** Framing that makes the replacement user message established context. */ +const CHECKPOINT_PREAMBLE = + 'This is an automatically generated checkpoint condensing an earlier span of the conversation to free up context. Treat the captured context as established background and build on it without restating it. Continue the task directly from the messages that follow, without acknowledging this checkpoint.' + +/** Safe summary content plus the exact auxiliary call envelope recorded in provenance. */ +export interface SummaryResult { + summary: ContentBlock[] + model: string + maxTokens?: number +} + +/** + * Run the default direct `ctx.llm.stream()` summarization call. + * @param ctx - context providing the LLM service. + * @param config - resolved backend configuration. + * @param text - rendered transcript region to summarize. + * @param agent - supplies routed-model history, fallback model, and session id. + * @param signal - optional cancellation forwarded to the adapter. + * @returns safe text-only summary blocks and exact call provenance. + */ +export async function summarizeWithLlm( + ctx: Context, + config: ResolvedConfig, + text: string, + agent: Agent, + signal?: AbortSignal, +): Promise { + const latestModel = agent.session.requestHeader()?.config.model + const model = config.summarizationModel || latestModel || agent.options.model || '' + if (model.length === 0) { + throw new Error( + 'no model available for summarization: set BasicCompactConfig.summarizationModel, route one request, or set AgentOptions.model', + ) + } + + const assembler = new BlockAssembler() + const options: GenerateOptions = { + model, + messages: [{ + role: 'user', + content: [{ type: 'text', text: `Summarize this conversation history:\n\n${text}\n\nSummary:` }], + }], + system: SUMMARIZE_SYSTEM_PROMPT, + maxTokens: config.maxTokens, + sessionId: agent.session.id, + ...signal === undefined ? {} : { signal }, + } + for await (const chunk of ctx.llm.stream(options)) assembler.push(chunk) + const error = finishError(assembler.finish) + if (error !== undefined) throw error + + const summary = textOnly(assembler.message().content) + if (!summary.some(block => block.text.trim().length > 0)) { + throw new Error('summarization produced no text summary content') + } + return { summary, model, maxTokens: config.maxTokens } +} + +/** + * Wrap raw summary blocks in the durable checkpoint framing. + * @param summary - safe text-only model output. + * @returns content for the synthesized replacement user message. + */ +export function frameSummary(summary: readonly ContentBlock[]): ContentBlock[] { + return [ + { type: 'text', text: `${CHECKPOINT_PREAMBLE}\n\n${SUMMARY_OPEN_TAG}` }, + ...summary, + { type: 'text', text: SUMMARY_CLOSE_TAG }, + ] +} + +/** Map a terminal summarization finish to its fail-closed error. */ +function finishError(finish: FinishReason): Error | undefined { + switch (finish.kind) { + case 'error': { + const error = new Error(finish.message) as Error & { code?: string } + if (finish.code !== undefined) error.code = finish.code + return error + } + case 'aborted': { + const error = new Error('summarization stream aborted') as Error & { code?: string } + error.code = 'ABORTED' + return error + } + case 'max-tokens': { + const error = new Error('summarization truncated at the token cap (incomplete checkpoint)') as Error & { code?: string } + error.code = 'MAX_TOKENS' + return error + } + default: + return undefined + } +} + +/** Keep only text blocks before synthesizing a user message. */ +function textOnly( + blocks: readonly ContentBlock[], +): Array> { + return blocks.filter((block): block is Extract => block.type === 'text') +} diff --git a/packages/compact/compact-basic/src/types.ts b/packages/compact/compact-basic/src/types.ts index 05169286d7..44ff06435d 100644 --- a/packages/compact/compact-basic/src/types.ts +++ b/packages/compact/compact-basic/src/types.ts @@ -1,94 +1,44 @@ /** - * Configuration vocabulary for the basic compaction backend. - * - * Every tunable lives here, in the implementation — the abstract contract - * (`@deepseek-ai/dsh-compact`) carries no config, because thresholds and - * retention policy are HOW decisions a different backend would make - * differently. + * Configuration vocabulary for the replay-aware basic compaction backend. * * @module @deepseek-ai/dsh-compact-basic/types */ -/** - * Backend configuration. Every knob is REQUIRED except `auto` and - * `charsPerToken`: there is no concrete data yet to justify default - * thresholds/budgets, so a consumer must state each value explicitly rather - * than inherit a guessed default. `auto` alone defaults to `true` - * (auto-compaction is the intended posture), and `charsPerToken` defaults to - * the English-text heuristic its estimator was calibrated on. - */ +/** Optional pressure and retention policy for one metered model. */ +export interface ModelCompactConfig { + /** Compact at this fraction of the model's configured context window. Defaults to `0.8`. */ + thresholdRatio?: number + /** Recent surface tokens retained verbatim. Defaults to `floor(contextWindow * 0.16)`. */ + retainTokens?: number +} + +/** Basic compaction configuration; every common field has a deployment default. */ export interface BasicCompactConfig { - /** Context window size in tokens. */ - contextWindow: number - /** Compact when estimated token usage exceeds this fraction of context window. */ - thresholdRatio: number - /** Number of tokens of recent context to retain during compaction. */ - retainTokens: number - /** Model to use for summarization (`''` — uses the agent's model). */ - summarizationModel: string - /** Provider generation cap for the summarization call. */ - maxTokens: number - /** Extra compaction attempts when the first compacted surface is still over threshold. */ - compactionRetries: number - /** Enable automatic compaction on the `agent/pre-step` seam (default true). */ + /** Field-wise pressure/retention overrides keyed by configured token-meter model name. */ + models?: Record + /** Summary model; `''` resolves the latest routed model, then `AgentOptions.model`. Defaults to `''`. */ + summarizationModel?: string + /** Provider generation cap for summarization. Defaults to `8192`. */ + maxTokens?: number + /** Extra attempts after the first compaction when pressure remains above threshold. Defaults to `1`. */ + compactionRetries?: number + /** Enable the automatic `agent/pre-step` pressure listener. Defaults to `true`. */ auto?: boolean - /** - * Text density for the token estimator: estimated tokens = chars / - * `charsPerToken`. Defaults to 4 (typical English text). A CJK-heavy - * deployment should set ~1-2 — CJK runs at roughly 1-2 chars per token, so - * the default UNDERestimates several-fold and compaction fires far too late. - * May be fractional. - */ - charsPerToken?: number } -/** Resolved config with `auto` and `charsPerToken` defaulted. */ -export type ResolvedConfig = Required - -/** - * Default `auto`/`charsPerToken` when unset and reject nonsensical numeric knobs. - * - * @param config - the raw, unresolved backend config. - * @returns the validated config with `auto` and `charsPerToken` defaulted. - */ -export function resolveConfig(config: BasicCompactConfig): ResolvedConfig { - const resolved: ResolvedConfig = { auto: true, charsPerToken: 4, ...config } - - assertPositiveInteger('contextWindow', resolved.contextWindow) - assertRatio('thresholdRatio', resolved.thresholdRatio) - assertNonNegativeInteger('retainTokens', resolved.retainTokens) - assertPositiveInteger('maxTokens', resolved.maxTokens) - assertNonNegativeInteger('compactionRetries', resolved.compactionRetries) - assertPositiveFinite('charsPerToken', resolved.charsPerToken) - if (typeof resolved.summarizationModel !== 'string') { - throw new Error('BasicCompactConfig: summarizationModel must be a string.') - } - if (typeof resolved.auto !== 'boolean') { - throw new Error('BasicCompactConfig: auto must be a boolean.') - } - return resolved +/** Validated top-level defaults plus detached per-model partial overrides. */ +export interface ResolvedConfig { + readonly models: Readonly>> + readonly summarizationModel: string + readonly maxTokens: number + readonly compactionRetries: number + readonly auto: boolean } -function assertPositiveInteger(name: string, value: number): void { - if (!Number.isInteger(value) || value <= 0) { - throw new Error(`BasicCompactConfig: ${name} (${value}) must be a positive integer.`) - } -} - -function assertNonNegativeInteger(name: string, value: number): void { - if (!Number.isInteger(value) || value < 0) { - throw new Error(`BasicCompactConfig: ${name} (${value}) must be a non-negative integer.`) - } -} - -function assertPositiveFinite(name: string, value: number): void { - if (typeof value !== 'number' || !Number.isFinite(value) || value <= 0) { - throw new Error(`BasicCompactConfig: ${name} (${value}) must be a positive finite number.`) - } -} - -function assertRatio(name: string, value: number): void { - if (typeof value !== 'number' || !Number.isFinite(value) || value <= 0 || value > 1) { - throw new Error(`BasicCompactConfig: ${name} (${value}) must be a number in (0, 1].`) - } +/** Fully resolved pressure/retention policy for one effective model. */ +export interface ResolvedModelCompactConfig { + readonly model: string + readonly contextWindow: number + readonly thresholdRatio: number + readonly retainTokens: number } diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 8c5cc183c1..4feb981237 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -1,1682 +1,797 @@ -import { describe, expect, it } from 'vitest' +import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' +import BasicCompactService, { + resolveConfig, + resolveModelConfig, +} from '@deepseek-ai/dsh-compact-basic' import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic' +import { selectCompactableRange } from '@deepseek-ai/dsh-compact-basic/src/region.ts' +import type { CompactionResult } from '@deepseek-ai/dsh-compact' +import LlmService, { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' import type { ContentBlock, GenerateOptions, Message, StreamChunk } from '@deepseek-ai/dsh-llm' -import { CallId, LlmAdapter, LlmService } from '@deepseek-ai/dsh-llm' -import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' -import type { SessionEvent, SurfaceEvent } from '@deepseek-ai/dsh-session' -import * as Invariants from '@deepseek-ai/dsh-invariants' +import { Session, SessionId } from '@deepseek-ai/dsh-session' +import TokenMeterService, { + TOKEN_METER_MODEL_UNCONFIGURED, + TokenMeterError, +} from '@deepseek-ai/dsh-token-meter' import type { Agent } from '@deepseek-ai/dsh-agent' -/** A never-aborted signal for the required `compactIfNeeded`/listener arg. */ const SIGNAL = new AbortController().signal +const MODEL = 'test-model' -/** - * Baseline config with every required knob set. `BasicCompactConfig` has no - * defaults for the numeric/model knobs (only `auto` defaults), so each test - * builds a complete config via `cfg()` and overrides only the knob under test. - */ -const TEST_CONFIG: BasicCompactConfig = { - contextWindow: 128000, - thresholdRatio: 0.8, - retainTokens: 20480, - summarizationModel: '', - maxTokens: 8192, - compactionRetries: 1, -} - -/** A complete config with `overrides` applied over the baseline. */ -function cfg(overrides: Partial = {}): BasicCompactConfig { - return { ...TEST_CONFIG, ...overrides } -} - -/** Long enough that the real checkpoint preamble is smaller than two fixture messages. */ -const LONG_FIXTURE_TEXT = ' Detailed fixture context that makes framed checkpoint compaction genuinely shrinking.'.repeat(20) - -/** - * A BasicCompactService with summarize() stubbed (no real model call) and a - * predictable token estimate, for deterministic unit tests of the algorithm. - */ -class TestCompactService extends BasicCompactService { - private readonly summaryOutputs = new WeakSet() - /** Boundary/unit tests use tiny fixtures; keep framing from dominating them unless a test opts out. */ - estimateFramedSummariesCheaply = true - /** Track calls to summarize for test assertions. */ - summarizeCalls: { text: string; model: string }[] = [] - /** The fixed summary to return. */ - mockSummary: ContentBlock[] = [{ type: 'text', text: 'Test summary of compacted content.' }] - /** Per-call summaries; when set, each summarize() call shifts one value. */ - mockSummaryQueue: ContentBlock[][] = [] - /** If set, summarize() throws this error. */ - summarizeError: Error | null = null - - override estimateContentTokens(blocks: readonly ContentBlock[]): number { - if (this.summaryOutputs.has(blocks)) return blocks.length * 2 - if (this.estimateFramedSummariesCheaply && isFramedCheckpoint(blocks)) return blocks.length * 2 - // 10 tokens per block — predictable for retention/threshold math. - return blocks.length * 10 - } - - override async summarize(text: string, agent: Agent): Promise<{ summary: ContentBlock[]; model: string; maxTokens?: number }> { - const model = this.config.summarizationModel || agent.options.model || '' - this.summarizeCalls.push({ text, model }) - if (this.summarizeError) throw this.summarizeError - const summary = this.mockSummaryQueue.shift() ?? this.mockSummary - this.summaryOutputs.add(summary) - return { summary, model } - } -} - -function isFramedCheckpoint(blocks: readonly ContentBlock[]): boolean { - const first = blocks[0] - const last = blocks[blocks.length - 1] - return first?.type === 'text' - && first.text.includes('') - && last?.type === 'text' - && last.text === '' -} - -/** Create a test service with a throwaway context (auto disabled — no model). */ -function createTestService(overrides: Partial = {}): TestCompactService { - return new TestCompactService(new Context(), cfg({ auto: false, ...overrides })) -} - -/** Build closed turns plus an open compaction turn unless `leaveOpen` is false. */ -function multiTurnSession(turns: number, messagesPerTurn: number = 2, opts: { leaveOpen?: boolean } = {}): Session { - const leaveOpen = opts.leaveOpen ?? true - const s = new Session(SessionId('test')) - for (let t = 1; t <= turns; t++) { - s.append('turn/start', { turn: t, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: t, step: 1 }) - for (let m = 0; m < messagesPerTurn; m++) { - s.append('user/message', { - content: [{ type: 'text', text: `turn ${t} user message ${m + 1}.${LONG_FIXTURE_TEXT}` }], - source: { kind: 'user' }, - }, { surfaceOp: 'append' }) - s.append('assistant/message', { - turn: t, step: 1, - content: [{ type: 'text', text: `turn ${t} assistant response ${m + 1}.${LONG_FIXTURE_TEXT}` }], - }, { surfaceOp: 'append' }) - } - s.append('step/end', { turn: t, step: 1 }) - s.append('turn/end', { turn: t, reason: { kind: 'completed' } }) - } - // Open one more turn so compaction's events are turn-enclosed, as they are - // when the loop runs the auto-compaction listener mid-turn. - if (leaveOpen) { - s.append('turn/start', { turn: turns + 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - } - return s -} - -/** Build a session with tool calls for richer extraction tests. */ -function sessionWithTools(): Session { - const s = new Session(SessionId('tools')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - s.append('user/message', { - content: [{ type: 'text', text: 'read file x' }], - source: { kind: 'user' }, - }, { surfaceOp: 'append' }) - s.append('assistant/message', { - turn: 1, step: 1, - content: [ - { type: 'text', text: 'Let me read that file.' }, - { type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{"command":"cat x"}' }, - ], - }, { surfaceOp: 'append' }) - s.append('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'bash', arguments: '{"command":"cat x"}' }) - s.append('tool/result', { - turn: 1, step: 1, callId: CallId('c1'), - content: [{ type: 'text', text: 'hello world' }], - isError: false, - }, { surfaceOp: 'append' }) - s.append('assistant/message', { - turn: 1, step: 1, - content: [{ type: 'text', text: 'The file contains: hello world' }], - }, { surfaceOp: 'append' }) - s.append('step/end', { turn: 1, step: 1 }) - s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - // Open a trailing turn so compaction's events are turn-enclosed (as they are - // when the loop runs the auto-compaction listener mid-turn). - s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) - return s -} - -/** - * Build a session of `turns` turns, each a SINGLE step containing an - * assistant/message that issues a tool-call plus its tool/result — the real - * multi-node-step shape (a step is two surface nodes: the assistant and the - * result). Each turn is preceded by a user/message. Used to exercise - * step-alignment: a region boundary must not fall between the assistant and its - * result. - */ -function toolTurnSession(turns: number): Session { - const s = new Session(SessionId('tools-multi')) - for (let t = 1; t <= turns; t++) { - s.append('turn/start', { turn: t, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('user/message', { - content: [{ type: 'text', text: `turn ${t} request` }], - source: { kind: 'user' }, - }, { surfaceOp: 'append' }) - s.append('step/start', { turn: t, step: 1 }) - s.append('assistant/message', { - turn: t, step: 1, - content: [ - { type: 'text', text: `turn ${t} calling tool` }, - { type: 'tool-call', id: CallId(`c${t}`), name: 'bash', arguments: '{"command":"ls"}' }, - ], - }, { surfaceOp: 'append' }) - s.append('tool/call', { turn: t, step: 1, callId: CallId(`c${t}`), name: 'bash', arguments: '{"command":"ls"}' }) - s.append('tool/result', { - turn: t, step: 1, callId: CallId(`c${t}`), - content: [{ type: 'text', text: `turn ${t} output` }], - isError: false, - }, { surfaceOp: 'append' }) - s.append('step/end', { turn: t, step: 1 }) - s.append('turn/end', { turn: t, reason: { kind: 'completed' } }) - } - // Open a trailing turn so compaction's events are turn-enclosed. - s.append('turn/start', { turn: turns + 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - return s -} - -/** - * Assert the derived transcript has NO orphaned tool-result: every - * `tool-result` block's `toolCallId` must be matched by a preceding `tool-call` - * block in an earlier (assistant) message. A dangling tool-result is exactly - * what splitting a step at compaction produces, and every provider rejects it. - */ -function expectNoOrphanToolResults(messages: Message[]): void { - const seenCallIds = new Set() - for (const msg of messages) { - for (const block of msg.content) { - if (block.type === 'tool-call') seenCallIds.add(block.id) - if (block.type === 'tool-result') { - expect(seenCallIds.has(block.toolCallId), - `orphaned tool-result for callId ${block.toolCallId} (no preceding tool-call)`).toBe(true) - } - } - } -} - -describe('BasicCompactService step-alignment (never split a tool-call/result pair)', () => { - it('compactIfNeeded rounds the retained boundary head-ward to keep a whole step (no orphaned tool-result)', async () => { - // Retain the recent tail while the older assistant/result pairs compact as - // whole units; no boundary may orphan a result. - const svc = createTestService({ contextWindow: 280, thresholdRatio: 0.5, retainTokens: 55 }) - const session = toolTurnSession(3) - - const result = await compactIfNeeded(svc, session, '', 'm', SIGNAL) - expect(result).not.toBeNull() - expect(result!.shadowedSeqs.length).toBeGreaterThan(0) - // No dangling tool-result: every compacted/retained step stayed whole. - expectNoOrphanToolResults(session.deriveMessages()) - // The most-recent step's result is retained verbatim (still on the surface). - const lastResultSeq = session.events.findLast(e => e.type === 'tool/result')!.seq - expect(result!.shadowedSeqs).not.toContain(lastResultSeq) - }) - - it('compactIfNeeded returns null when the only compactable region is an un-splittable single step', async () => { - // The only candidate cut is inside one assistant/result pair; with no safe - // compactable prefix, decline rather than split it. - const s = new Session(SessionId('one-step')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { - turn: 1, step: 1, - content: [{ type: 'text', text: 'calling' }, { type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], - }, { surfaceOp: 'append' }) - s.append('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'bash', arguments: '{}' }) - s.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'out' }], isError: false }, { surfaceOp: 'append' }) - s.append('step/end', { turn: 1, step: 1 }) - // Turn stays open. - - const svc = createTestService({ contextWindow: 100, thresholdRatio: 0.1, retainTokens: 5 }) - const result = await compactIfNeeded(svc, s, '', 'm', SIGNAL) - expect(result).toBeNull() - expect(s.events.some(e => e.type === 'compact/start')).toBe(false) - }) - - it('compactRegion rejects a start that splits a step (unbalanced boundary)', async () => { - const svc = createTestService() - const session = toolTurnSession(1) - const nodes = session.surface.nodes // [user, asst(tool-call), result] - const userSeq = nodes[0]!.seq - const resultSeq = nodes[2]!.seq - // start = the tool/result: its issuing assistant precedes it IN THE SAME STEP, - // so starting here would orphan that assistant's tool-call. end is fine (user). - await expect(compactRegion(svc, session, resultSeq, resultSeq, 'm')) - .rejects.toThrow(/start seq .* is not a balanced boundary/) - expect(userSeq).toBeLessThan(resultSeq) // sanity: ordering as expected - }) - - it('compactRegion rejects an end that splits a step (unbalanced boundary)', async () => { - const svc = createTestService() - const session = toolTurnSession(1) - const nodes = session.surface.nodes - const userSeq = nodes[0]!.seq - const asstSeq = nodes[1]!.seq - // end = the assistant/message: its tool/result follows IN THE SAME STEP, so - // ending here would strand that result. start is fine (the pre-step user). - await expect(compactRegion(svc, session, userSeq, asstSeq, 'm')) - .rejects.toThrow(/end seq .* is not a balanced boundary/) - }) - - it('compactRegion rejects an end inside an open tail step', async () => { - const svc = createTestService() - const s = new Session(SessionId('open-tail')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('user/message', { content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { - turn: 1, step: 1, - content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], - }, { surfaceOp: 'append' }) - const nodes = s.surface.nodes // [user, asst] - const userSeq = nodes[0]!.seq - const asstSeq = nodes[1]!.seq - await expect(compactRegion(svc, s, userSeq, asstSeq, 'm')) - .rejects.toThrow(/end seq .* is not a balanced boundary/) - }) - - it('compactRegion accepts step-aligned boundaries (pre-step user → last result of a closed step)', async () => { - const svc = createTestService() - const session = toolTurnSession(2) - const nodes = session.surface.nodes // [user1, asst1, res1, user2, asst2, res2] - const startSeq = nodes[0]!.seq // pre-step user1 (free boundary) - const endSeq = nodes[2]!.seq // res1 = last node of turn 1's closed step - const result = await compactRegion(svc, session, startSeq, endSeq, 'm') - expect(result.shadowedRange).toEqual({ start: startSeq, end: endSeq }) - expectNoOrphanToolResults(session.deriveMessages()) - }) - - it('compactRegion accepts a single inter-step node (start === end on a pre-step user/message)', async () => { - const svc = createTestService() - const session = toolTurnSession(1) - const nodes = session.surface.nodes - const userSeq = nodes[0]!.seq // pre-step user: free boundary both ways - const result = await compactRegion(svc, session, userSeq, userSeq, 'm') - expect(result.shadowedRange).toEqual({ start: userSeq, end: userSeq }) - }) - - it('compactRegion accepts an injection-turn context node (no step at all)', async () => { - const svc = createTestService() - const s = new Session(SessionId('inject')) - // An idle inject(): turn/start → context/message, NO step. A later turn is - // open so compaction's events are turn-enclosed. - s.append('turn/start', { turn: 1, trigger: { kind: 'injection', source: { kind: 'user' } } }) - s.append('context/message', { content: [{ type: 'text', text: 'ctx' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) - const nodes = s.surface.nodes - const ctxSeq = nodes[0]!.seq - const result = await compactRegion(svc, s, ctxSeq, ctxSeq, 'm') - expect(result.shadowedRange).toEqual({ start: ctxSeq, end: ctxSeq }) - }) -}) - -describe('BasicCompactService.estimateEventTokens', () => { - it('returns 0 for non-message events (boundary, chunk, step/end, tool/call)', () => { - const svc = createTestService() - expect(svc.estimateEventTokens({ type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'step/start', seq: 1, time: 2, data: { turn: 1, step: 1 } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'assistant/chunk', seq: 2, time: 3, data: { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'h' } } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'step/end', seq: 3, time: 4, data: { turn: 1, step: 1 } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'tool/call', seq: 4, time: 5, data: { turn: 1, step: 1, callId: CallId('c1'), name: 'read', arguments: '{}' } })).toBe(0) - }) - - it('returns estimate for message-producing events', () => { - const svc = createTestService() - const userEvent: SessionEvent = { type: 'user/message', seq: 0, time: 1, data: { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } } } - expect(svc.estimateEventTokens(userEvent)).toBe(10) - - const asstEvent: SessionEvent = { type: 'assistant/message', seq: 1, time: 2, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }, { type: 'text', text: 'b' }] } } - expect(svc.estimateEventTokens(asstEvent)).toBe(20) - - const toolEvent: SessionEvent = { type: 'tool/result', seq: 2, time: 3, data: { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'output' }], isError: false } } - expect(svc.estimateEventTokens(toolEvent)).toBe(10) - }) -}) - -describe('BasicCompactService.estimateTokens', () => { - it('sums token estimates across messages', () => { - const svc = createTestService() - const messages: Message[] = [ - { role: 'user', content: [{ type: 'text', text: 'hello' }] }, - { role: 'assistant', content: [{ type: 'text', text: 'hi' }, { type: 'text', text: 'there' }] }, - ] - // 1 block * 10 + 4 (role) + 2 blocks * 10 + 4 (role) = 10 + 4 + 20 + 4 = 38 - expect(svc.estimateTokens(messages)).toBe(38) - }) - - it('includes system prompt in the estimate', () => { - const svc = createTestService() - const messages: Message[] = [ - { role: 'user', content: [{ type: 'text', text: 'hi' }] }, - ] - const systemPrompt = 'You are a helpful assistant.' - // 1 block * 10 + 4 (role) + ceil(28/4) = 10 + 4 + 7 = 21 - expect(svc.estimateTokens(messages, systemPrompt)).toBe(21) - }) -}) - -describe('BasicCompactService.compactRegion', () => { - it('shadows surface nodes and inserts a summary via user/message', async () => { - const svc = createTestService() - const session = multiTurnSession(3, 1) // 3 turns, 2 surface nodes each = 6 nodes - - const nodes = session.surface.nodes - expect(nodes.length).toBe(6) - - const firstSeq = nodes[0]!.seq - const secondSeq = nodes[1]!.seq - const result = await compactRegion(svc, session, firstSeq, secondSeq, 'test-model') - - expect(result.shadowedSeqs).toEqual([firstSeq, secondSeq]) - expect(result.shadowedRange.start).toBe(firstSeq) - expect(result.shadowedRange.end).toBe(secondSeq) - expect(result.summary).toEqual(svc.mockSummary) - - const events = session.events - const startEvent = events.findLast(e => e.type === 'compact/start') - const summaryEvent = events.findLast(e => e.type === 'compact/summary') - const endEvent = events.findLast(e => e.type === 'compact/end') - expect(startEvent).toBeDefined() - expect(summaryEvent).toBeDefined() - expect(endEvent).toBeDefined() - // The provenance record carries the summarize call's envelope, so "which - // model wrote this summary" is answerable from the log alone. - expect(summaryEvent?.type === 'compact/summary' && summaryEvent.data.model).toBe('test-model') - - // compact/* events are log-only — no surfaceOp (type system enforces this). - const startRaw = startEvent as unknown as { surfaceOp?: unknown } - expect(startRaw.surfaceOp).toBeUndefined() - - // The user/message carries the replace surfaceOp. - const userMsg = events.findLast(e => e.type === 'user/message')! - const surfaceUserMsg = userMsg as SurfaceEvent - expect(surfaceUserMsg.surfaceOp).toEqual({ op: 'replace', start: firstSeq, end: secondSeq }) - expect(surfaceUserMsg.sourceEventSeqs).toContain(startEvent!.seq) - expect(surfaceUserMsg.sourceEventSeqs).toContain(summaryEvent!.seq) - expect(surfaceUserMsg.sourceEventSeqs).toContain(firstSeq) - expect(surfaceUserMsg.sourceEventSeqs).toContain(secondSeq) - // compact/end is appended AFTER the replacement (the lock brackets the whole - // op), so the replacement cannot reference it — sourceEventSeqs may only - // reference earlier seqs. - expect(surfaceUserMsg.sourceEventSeqs).not.toContain(endEvent!.seq) - expect(endEvent!.seq).toBeGreaterThan(userMsg.seq) - - // Surface now has: summary user/message + retained 4 nodes = 5 nodes. - const newNodes = session.surface.nodes - expect(newNodes.length).toBe(5) - expect(newNodes[0]!.seq).toBe(userMsg.seq) - - // deriveMessages() produces the framed summary as a user-role message: - // a checkpoint preamble + tag-wrapped summary blocks. - const derived = session.deriveMessages() - expect(derived.length).toBe(5) - expect(derived[0]!.role).toBe('user') - const framed = derived[0]!.content - expect(framed[0]).toMatchObject({ type: 'text' }) - expect((framed[0] as { text: string }).text).toContain('') - expect(framed).toContainEqual(svc.mockSummary[0]) - expect((framed[framed.length - 1] as { text: string }).text).toBe('') - }) - - it('throws when start or end are not surface nodes', async () => { - const svc = createTestService() - const session = multiTurnSession(1, 1) - await expect(compactRegion(svc, session, 999, 1000, 'm')) - .rejects.toThrow(/start seq 999 not found in surface/) - }) - - it('throws when start is positioned after end on the surface', async () => { - const svc = createTestService() - const session = multiTurnSession(2, 1) - const nodes = session.surface.nodes - await expect(compactRegion(svc, session, nodes[1]!.seq, nodes[0]!.seq, 'm')) - .rejects.toThrow(/is after end seq .* on the surface/) - }) - - it('throws when compaction is already in progress', async () => { - const svc = createTestService() - const session = multiTurnSession(2, 1) - const nodes = session.surface.nodes - session.append('compact/start', { turn: 2 }) - await expect(compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm')) - .rejects.toThrow(/compaction already in progress/) - }) - - it('appends compact/end with error on summarize failure', async () => { - const svc = createTestService() - svc.summarizeError = new Error('model unavailable') - const session = multiTurnSession(2, 1) - const nodes = session.surface.nodes - - await expect(compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm')) - .rejects.toThrow('model unavailable') - - const endEvent = session.events.findLast(e => e.type === 'compact/end') - expect(endEvent).toBeDefined() - // multiTurnSession(2,…) closes turns 1-2 and leaves turn 3 open; compaction - // stamps the open turn. - expect(endEvent!.data).toMatchObject({ turn: 3, error: 'model unavailable' }) - - // No replace-op user/message was appended (summarize failed). - const userMsgsAfter = session.events.filter(e => e.type === 'user/message') - const replaceMsgs = userMsgsAfter.filter((e) => { - const se = e as unknown as { surfaceOp?: unknown } - return se.surfaceOp !== undefined && typeof se.surfaceOp !== 'string' - }) - expect(replaceMsgs.length).toBe(0) - }) - - it('extracts conversation text for summarization', async () => { - const svc = createTestService() - const session = multiTurnSession(1, 2) - const nodes = session.surface.nodes - - await compactRegion(svc, session, nodes[0]!.seq, nodes[nodes.length - 1]!.seq, 'm') - - expect(svc.summarizeCalls.length).toBe(1) - const { text, model } = svc.summarizeCalls[0]! - expect(model).toBe('m') - expect(text).toContain('User: turn 1 user message 1') - expect(text).toContain('Assistant: turn 1 assistant response 1') - }) - - it('frames the landed summary with a checkpoint preamble and tags, keeping raw provenance', async () => { - const svc = createTestService() - svc.mockSummary = [{ type: 'text', text: 'STRUCTURED SUMMARY' }] - const session = multiTurnSession(3, 1) - const nodes = session.surface.nodes - - const result = await compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm') - - // Provenance (compact/summary) carries the RAW, unframed summary. - expect(result.summary).toEqual([{ type: 'text', text: 'STRUCTURED SUMMARY' }]) - const summaryEvent = session.events.findLast(e => e.type === 'compact/summary')! - expect(summaryEvent.data).toMatchObject({ summary: [{ type: 'text', text: 'STRUCTURED SUMMARY' }] }) - - // The landed surface node is framed: preamble + tag-wrapped summary. - const landed = session.deriveMessages()[0]!.content - expect((landed[0] as { text: string }).text).toContain('checkpoint') - expect((landed[0] as { text: string }).text).toContain('') - expect(landed).toContainEqual({ type: 'text', text: 'STRUCTURED SUMMARY' }) - expect((landed[landed.length - 1] as { text: string }).text).toBe('') - }) - - it('extracts tool-call and tool-result context', async () => { - const svc = createTestService() - const session = sessionWithTools() - const nodes = session.surface.nodes - - const firstSeq = nodes[0]!.seq - const lastSeq = nodes[nodes.length - 1]!.seq - await compactRegion(svc, session, firstSeq, lastSeq, 'm') - - expect(svc.summarizeCalls.length).toBe(1) - const { text } = svc.summarizeCalls[0]! - expect(text).toContain('read file x') - expect(text).toContain('bash') - expect(text).toContain('Tool result') - }) -}) - -describe('BasicCompactService.compactIfNeeded', () => { - it('returns null when tokens are under threshold', async () => { - const svc = createTestService({ contextWindow: 128000, thresholdRatio: 0.8 }) - const session = multiTurnSession(1, 1) - expect(await compactIfNeeded(svc, session, '', 'm', SIGNAL)).toBeNull() - }) - - it('compacts when tokens exceed threshold', async () => { - const svc = createTestService({ contextWindow: 100, thresholdRatio: 0.5, retainTokens: 10 }) - const session = multiTurnSession(3, 1) // 6 surface nodes, 10 tokens each = 60 - - const result = await compactIfNeeded(svc, session, '', 'm', SIGNAL) - expect(result).not.toBeNull() - expect(result!.shadowedSeqs.length).toBeGreaterThan(0) - }) - - it('counts the session prefix toward pressure (every request carries it in front of the history)', async () => { - const svc = createTestService({ contextWindow: 200, thresholdRatio: 0.5, retainTokens: 10 }) - const session = multiTurnSession(3, 1) // 6 derived messages ≈ 84 estimated tokens — under the 100 threshold alone - expect(await compactIfNeeded(svc, session, '', 'm', SIGNAL)).toBeNull() - - // The loop composes the agent/session-prefix product before the pre-step - // seam and hands it to the gate; it rides every request, so pressure must - // include it — the same history now crosses the threshold. - const sessionPrefix: Message[] = [ - { role: 'user', content: [{ type: 'text', text: `opener one.${LONG_FIXTURE_TEXT}` }] }, - { role: 'user', content: [{ type: 'text', text: `opener two.${LONG_FIXTURE_TEXT}` }] }, - ] - const result = await compactIfNeeded(svc, session, '', 'm', SIGNAL, sessionPrefix) - expect(result).not.toBeNull() - // The prefix itself is NOT history: compaction shadowed surface nodes only. - expect(sessionPrefix).toHaveLength(2) - }) - - it('returns the first compaction result when a zero-retry pass converges after the loop', async () => { - // With compactionRetries=0 there is no next-loop threshold check after the - // first mutation, so the success path is the post-loop `return result`. - const svc = createTestService({ - contextWindow: 100, - thresholdRatio: 0.7, - retainTokens: 10, - compactionRetries: 0, - }) - const session = multiTurnSession(3, 1) // 6 derived messages = 84 estimated tokens. - - const result = await compactIfNeeded(svc, session, '', 'm', SIGNAL) - - expect(result).not.toBeNull() - expect(session.events.filter(e => e.type === 'compact/summary')).toHaveLength(1) - expect(svc.estimateTokens(session.deriveMessages(), '')).toBeLessThan(70) - }) - - it('walks tail→head and retains nodes within token budget', async () => { - const svc = createTestService({ contextWindow: 350, thresholdRatio: 0.2, retainTokens: 15 }) - const session = multiTurnSession(5, 1) // 10 surface nodes = ~100 tokens - - const result = await compactIfNeeded(svc, session, '', 'm', SIGNAL) - expect(result).not.toBeNull() - const nodes = session.surface.nodes - expect(result!.shadowedSeqs.length).toBeGreaterThan(0) - expect(result!.shadowedSeqs).not.toContain(nodes[nodes.length - 1]!.seq) - }) - - it('returns null when the whole surface fits the retain budget (over threshold by role/system overhead)', async () => { - // Role overhead pushes the request above its 48-token threshold, but the - // raw four-node retention walk remains below retainTokens=45, so all fit. - const svc = createTestService({ contextWindow: 480, thresholdRatio: 0.1, retainTokens: 45 }) - const session = multiTurnSession(2, 1) - expect(await compactIfNeeded(svc, session, '', 'm', SIGNAL)).toBeNull() - }) - - it('compacts a runaway turn: its early CLOSED steps summarize while recent steps stay verbatim', async () => { - // Completed early steps of the open turn remain eligible; protecting the - // whole turn would make a runaway turn impossible to compact. - const svc = createTestService({ contextWindow: 800, thresholdRatio: 0.1, retainTokens: 25 }) - const s = new Session(SessionId('runaway')) - // ONE open turn with 5 closed steps; each step is [asst(tool-call), result]. - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('user/message', { content: [{ type: 'text', text: 'do a big multi-step task' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - for (let step = 1; step <= 5; step++) { - s.append('step/start', { turn: 1, step }) - s.append('assistant/message', { - turn: 1, step, - content: [{ type: 'text', text: `step ${step}` }, { type: 'tool-call', id: CallId(`c${step}`), name: 'bash', arguments: '{}' }], - }, { surfaceOp: 'append' }) - s.append('tool/call', { turn: 1, step, callId: CallId(`c${step}`), name: 'bash', arguments: '{}' }) - s.append('tool/result', { turn: 1, step, callId: CallId(`c${step}`), content: [{ type: 'text', text: `out ${step}` }], isError: false }, { surfaceOp: 'append' }) - s.append('step/end', { turn: 1, step }) - } - // The turn stays OPEN (no turn/end) — the model is mid-turn, about to run - // step 6. Surface: user + 5×[asst, result] = 11 nodes. - const nodesBefore = s.surface.nodes.length - expect(nodesBefore).toBe(11) - - const result = await compactIfNeeded(svc, s, '', 'm', SIGNAL) - expect(result).not.toBeNull() - // Early steps of the SAME open turn were shadowed (impossible under layer 2). - expect(result!.shadowedSeqs.length).toBeGreaterThan(0) - // The most-recent step's tool result is retained verbatim (still on surface). - const lastResultSeq = s.events.findLast(e => e.type === 'tool/result')!.seq - expect(result!.shadowedSeqs).not.toContain(lastResultSeq) - expect(s.surface.nodes.some(n => n.seq === lastResultSeq)).toBe(true) - // No orphaned tool-result survives (whole-step boundaries respected). - expectNoOrphanToolResults(s.deriveMessages()) - }) - - it('returns null for an empty surface', async () => { - const svc = createTestService({ contextWindow: 100, thresholdRatio: 0.5, retainTokens: 10 }) - const session = new Session(SessionId('empty')) - expect(await compactIfNeeded(svc, session, '', 'm', SIGNAL)).toBeNull() - }) - - it('compacts again after a prior summary node heads the surface (the summary stays eligible)', async () => { - // Head-anchored recompaction must include the previous summary and retained context. - const svc = createTestService({ contextWindow: 800, thresholdRatio: 0.1, retainTokens: 25 }) - const s = multiTurnSession(4, 1) // turns 1-4 closed, turn 5 open (no surface yet) - - const first = await compactIfNeeded(svc, s, '', 'm', SIGNAL) - expect(first).not.toBeNull() - // The summary node now heads the surface with a fresh high seq. - const summaryHeadSeq = s.surface.nodes[0]!.seq - const turn5StartSeq = s.events.filter(e => e.type === 'turn/start').at(-1)!.seq - expect(summaryHeadSeq).toBeGreaterThan(turn5StartSeq) - - // Append a verbatim node in the open turn (a step's output), still over - // threshold, then compact again — the older summary + closed turns compact, - // the fresh nodes are retained. - s.append('step/start', { turn: 5, step: 1 }) - s.append('user/message', { content: [{ type: 'text', text: 'turn 5 work' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 5, step: 1, content: [{ type: 'text', text: 'reply 5' }] }, { surfaceOp: 'append' }) - s.append('step/end', { turn: 5, step: 1 }) - - const second = await compactIfNeeded(svc, s, '', 'm', SIGNAL) - expect(second).not.toBeNull() - expect(second!.shadowedSeqs.length).toBeGreaterThan(0) - // The fresh open-turn nodes were NOT compacted. - const turn5UserSeq = s.events.find(e => e.type === 'user/message' && e.data.content.some(b => b.type === 'text' && b.text === 'turn 5 work'))!.seq - expect(second!.shadowedSeqs).not.toContain(turn5UserSeq) - }) - - it('re-compacts smaller summaries until the post-compaction surface drops below threshold', async () => { - const svc = createTestService({ - contextWindow: 100, - thresholdRatio: 0.5, - retainTokens: 10, - compactionRetries: 2, - }) - svc.estimateFramedSummariesCheaply = false - svc.mockSummaryQueue = [ - Array.from({ length: 4 }, (_, index) => ({ type: 'text', text: `first ${index}` })), - [{ type: 'text', text: 'second' }], - ] - const session = multiTurnSession(4, 1) - - const result = await compactIfNeeded(svc, session, '', 'm', SIGNAL) - - expect(result).not.toBeNull() - expect(svc.summarizeCalls).toHaveLength(2) - expect(session.events.filter(e => e.type === 'compact/summary')).toHaveLength(2) - expect(svc.estimateTokens(session.deriveMessages(), '')).toBeLessThan(50) - }) - - it('throws after the configured re-compaction attempts still leave the surface above threshold', async () => { - const svc = createTestService({ - contextWindow: 100, - thresholdRatio: 0.5, - retainTokens: 10, - compactionRetries: 1, - }) - svc.estimateFramedSummariesCheaply = false - svc.mockSummaryQueue = [ - Array.from({ length: 4 }, (_, index) => ({ type: 'text', text: `first ${index}` })), - Array.from({ length: 3 }, (_, index) => ({ type: 'text', text: `second ${index}` })), - ] - const session = multiTurnSession(4, 1) - - await expect(compactIfNeeded(svc, session, '', 'm', SIGNAL)) - .rejects.toThrow(/still above threshold after 2 compaction attempts/) - expect(svc.summarizeCalls).toHaveLength(2) - }) -}) - -describe('BasicCompactService replay equivalence', () => { - it('produces identical deriveMessages() after seeding from compacted log', async () => { - const svc = createTestService() - const session = multiTurnSession(3, 1) - const nodes = session.surface.nodes - - await compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm') - const derived = session.deriveMessages() - - const replayed = new Session(SessionId('replay'), [...session.events]) - expect(replayed.deriveMessages()).toEqual(derived) - }) -}) - -describe('BasicCompactService blocking (compaction in progress)', () => { - it('detects in-progress compaction from unmatched compact/start', async () => { - const svc = createTestService() - const session = multiTurnSession(1, 1) - session.append('compact/start', { turn: 1 }) - const nodes = session.surface.nodes - // Whole step (user → assistant) is a step-aligned region, so the call reaches - // the in-progress check rather than being rejected for splitting a step. - await expect(compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm')) - .rejects.toThrow(/compaction already in progress/) - }) - - it('allows compaction after compact/end is appended', async () => { - const svc = createTestService() - const session = multiTurnSession(2, 1) - const nodes = session.surface.nodes - session.append('compact/start', { turn: 1 }) - session.append('compact/end', { turn: 1 }) - const result = await compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm') - expect(result).toBeDefined() - }) - - it('is not wedged by an orphaned compact/start from a prior (now-closed) turn', async () => { - // An orphaned start in a closed repaired turn is stale; only the current - // turn participates in the in-progress lock. - const svc = createTestService() - const s = new Session(SessionId('stale-lock')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - s.append('user/message', { content: [{ type: 'text', text: 'turn 1' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'reply 1' }] }, { surfaceOp: 'append' }) - s.append('compact/start', { turn: 1 }) // ← orphaned: no matching compact/end - s.append('step/end', { turn: 1, step: 1 }) - s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) // repair closed the turn - // A new open turn. - s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) - const nodes = s.surface.nodes - - // The stale start is before the turn/end, so it is NOT seen as in-progress. - const result = await compactRegion(svc, s, nodes[0]!.seq, nodes[1]!.seq, 'm') - expect(result).toBeDefined() - }) -}) - -describe('BasicCompactService token estimation (char/4 heuristic)', () => { - it('estimates text blocks with char/4 + overhead', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) - // 'this is a somewhat longer text block' = 36 → ceil(36/4)+4 = 13; 'short' = 5 → 2+4 = 6 - const blocks: ContentBlock[] = [ - { type: 'text', text: 'this is a somewhat longer text block' }, - { type: 'text', text: 'short' }, - ] - expect(svc.estimateContentTokens(blocks)).toBe(19) - }) - - it('estimates reasoning blocks same as text', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) - // 'thinking about this...' = 22 → ceil(22/4)+4 = 10 - expect(svc.estimateContentTokens([{ type: 'reasoning', text: 'thinking about this...' }])).toBe(10) - }) - - it('estimates tool-call blocks from name + arguments', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) - // 'bash' = 4 → 1; '{"command":"ls"}' = 16 → 4; + 4 overhead = 9 - expect(svc.estimateContentTokens([ - { type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{"command":"ls"}' }, - ])).toBe(9) - }) - - it('estimates tool-result blocks recursively', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) - // inner text 5 → 2+4 = 6; outer 6 + 4 overhead = 10 - expect(svc.estimateContentTokens([ - { type: 'tool-result', toolCallId: CallId('c1'), content: [{ type: 'text', text: 'hello' }], isError: false }, - ])).toBe(10) - }) - - it('returns 0 for empty content blocks', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) - expect(svc.estimateContentTokens([])).toBe(0) - }) - - it('honors a configured charsPerToken (fractional densities included)', () => { - // 'this is a somewhat longer text block' = 36 chars. - const blocks: ContentBlock[] = [{ type: 'text', text: 'this is a somewhat longer text block' }] - // charsPerToken 2: ceil(36/2)+4 = 22 — a CJK-density config doubles the estimate. - const dense = new BasicCompactService(new Context(), cfg({ auto: false, charsPerToken: 2 })) - expect(dense.estimateContentTokens(blocks)).toBe(22) - // Fractional density is legal: ceil(36/1.5)+4 = 28. - const fractional = new BasicCompactService(new Context(), cfg({ auto: false, charsPerToken: 1.5 })) - expect(fractional.estimateContentTokens(blocks)).toBe(28) - // The system-prompt term scales with the same knob: 36-char prompt at density 2 → ceil(36/2) = 18. - expect(dense.estimateTokens([], 'this is a somewhat longer text block')).toBe(18) - }) -}) - -describe('BasicCompactService HMR safety', () => { - it('registers as ctx.compact', () => { - const ctx = new Context() - void new BasicCompactService(ctx, cfg({ auto: false })) - expect(ctx.compact).toBeDefined() - expect(ctx.compact).toBeInstanceOf(BasicCompactService) - }) - - it('disposing the plugin fiber unregisters ctx.compact', async () => { - // Mount through the real plugin fiber (the Loader path), then dispose it and confirm the - // service registration is torn down. - const ctx = new Context() - await ctx.plugin(LlmService) - const fiber = await ctx.plugin(BasicCompactService, cfg({ auto: false })) - expect(ctx.get('compact')).toBeInstanceOf(BasicCompactService) - - await fiber.dispose() - expect(ctx.get('compact')).toBeUndefined() - }) -}) - -describe('BasicCompactService config validation', () => { - it('rejects invalid numeric config values', () => { - expect(() => new BasicCompactService(new Context(), cfg({ auto: false, contextWindow: 0 }))) - .toThrow(/contextWindow .* positive integer/) - expect(() => new BasicCompactService(new Context(), cfg({ auto: false, thresholdRatio: 0 }))).toThrow(/thresholdRatio .* \(0, 1\]/) - expect(() => new BasicCompactService(new Context(), cfg({ auto: false, thresholdRatio: 1.1 }))).toThrow(/thresholdRatio .* \(0, 1\]/) - expect(() => new BasicCompactService(new Context(), cfg({ auto: false, retainTokens: -1 }))) - .toThrow(/retainTokens .* non-negative integer/) - expect(() => new BasicCompactService(new Context(), cfg({ auto: false, maxTokens: 0 }))).toThrow(/maxTokens .* positive integer/) - expect(() => new BasicCompactService(new Context(), cfg({ auto: false, compactionRetries: -1 }))) - .toThrow(/compactionRetries .* non-negative integer/) - expect(() => new BasicCompactService( - new Context(), cfg({ auto: false, summarizationModel: 1 } as unknown as Partial), - )).toThrow(/summarizationModel must be a string/) - expect(() => new BasicCompactService(new Context(), cfg({ auto: 'no' } as unknown as Partial))) - .toThrow(/auto must be a boolean/) - expect(() => new BasicCompactService(new Context(), cfg({ auto: false, charsPerToken: 0 }))) - .toThrow(/charsPerToken .* positive finite number/) - expect(() => new BasicCompactService(new Context(), cfg({ auto: false, charsPerToken: Number.NaN }))) - .toThrow(/charsPerToken .* positive finite number/) - }) - - it('accepts a large retain budget because convergence is enforced dynamically', () => { - expect(() => new BasicCompactService(new Context(), cfg({ - auto: false, - contextWindow: 1000, - thresholdRatio: 0.5, - retainTokens: 900, - }))).not.toThrow() - }) - - it('the default config is valid', () => { - expect(() => new BasicCompactService(new Context(), cfg({ auto: false }))).not.toThrow() - }) -}) - -/** An adapter that emits a fixed summary text, for exercising the real summarize() path. */ -class ScriptedAdapter extends LlmAdapter { - lastOptions: GenerateOptions | null = null - constructor(private summaryText: string) { - super() - } - - async * stream(options: GenerateOptions): AsyncIterable { - this.lastOptions = options - yield { type: 'block-start', index: 0, blockType: 'text' } - yield { type: 'text-delta', index: 0, text: this.summaryText } - yield { type: 'finish', reason: { kind: 'stop' } } - } -} - -/** An adapter that emits arbitrary content blocks, preserving reasoning/text shape. */ -class BlocksAdapter extends LlmAdapter { - lastOptions: GenerateOptions | null = null - constructor(private blocks: readonly ContentBlock[]) { - super() - } - - async * stream(options: GenerateOptions): AsyncIterable { - this.lastOptions = options - for (const [index, block] of this.blocks.entries()) { - yield { type: 'block-start', index, blockType: block.type } - switch (block.type) { - case 'text': - yield { type: 'text-delta', index, text: block.text } - break - case 'reasoning': - yield { type: 'reasoning-delta', index, text: block.text } - break - default: - yield { type: 'block-end', index, block } - } - } - yield { type: 'finish', reason: { kind: 'stop' } } - } -} - -/** Wire a real LlmService + arbitrary-block adapter into a context. */ -async function ctxWithBlocks(blocks: readonly ContentBlock[], model = 'test-model'): Promise<{ ctx: Context; adapter: BlocksAdapter }> { +function createContext( + models: Record = { + [MODEL]: { contextWindow: 100, charsPerToken: 1_000 }, + }, +): Context { const ctx = new Context() - await ctx.plugin(LlmService) - const adapter = new BlocksAdapter(blocks) - ctx.llm.registerAdapter([model], adapter) - return { ctx, adapter } -} - -/** Wire a real LlmService + scripted adapter into a context. */ -async function ctxWithModel(summaryText: string, model = 'test-model'): Promise<{ ctx: Context; adapter: ScriptedAdapter }> { - const ctx = new Context() - await ctx.plugin(LlmService) - const adapter = new ScriptedAdapter(summaryText) - ctx.llm.registerAdapter([model], adapter) - return { ctx, adapter } -} - -/** An adapter whose stream ends with a finish chunk of the given reason (no content). */ -class FinishOnlyAdapter extends LlmAdapter { - constructor(private reason: StreamChunk & { type: 'finish' }) { - super() - } - - async * stream(): AsyncIterable { - yield this.reason - } -} - -/** Wire a real LlmService + finish-only adapter into a context. */ -async function ctxWithFinish(reason: (StreamChunk & { type: 'finish' })['reason'], model = 'test-model'): Promise { - const ctx = new Context() - await ctx.plugin(LlmService) - ctx.llm.registerAdapter([model], new FinishOnlyAdapter({ type: 'finish', reason })) + void new TokenMeterService(ctx, { models }) return ctx } -/** A minimal Agent stub carrying just session + options (enough for the listeners). */ -function stubAgent(session: Session, model?: string): Agent { - return { session, options: { model } } as unknown as Agent +function agent(session: Session, model?: string): Agent { + return { session, options: model === undefined ? {} : { model } } as Agent } -function compactIfNeeded( - svc: BasicCompactService, - session: Session, - fullSystemPrompt: string, - model: string, - signal: AbortSignal, - sessionPrefix: readonly Message[] = [], -) { - return svc.compactIfNeeded(stubAgent(session, model), fullSystemPrompt, sessionPrefix, signal) -} - -function compactRegion( - svc: BasicCompactService, - session: Session, - start: number, - end: number, - model: string, - signal?: AbortSignal, -) { - return svc.compactRegion(session, start, end, stubAgent(session, model), signal) -} - -function summarize(svc: BasicCompactService, text: string, model: string) { - return svc.summarize(text, stubAgent(new Session(SessionId('summary')), model)) -} - -describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { - it('summarizes via the registered adapter and returns its content', async () => { - const { ctx, adapter } = await ctxWithModel('SUMMARY TEXT') - const svc = new BasicCompactService(ctx, cfg({ auto: false, maxTokens: 512 })) - - const { summary, model, maxTokens } = await summarize(svc, 'User: hi\n\nAssistant: hello', 'test-model') - expect(summary).toEqual([{ type: 'text', text: 'SUMMARY TEXT' }]) - // The returned envelope reports what the call actually used — the caller - // logs it on compact/summary (the reconstructability RFC). - expect(model).toBe('test-model') - expect(maxTokens).toBe(512) - // The fixed system prompt and maxTokens flow through. - expect(adapter.lastOptions!.system).toContain('compaction engine') - expect(adapter.lastOptions!.system).toContain('## Next Step') - expect(adapter.lastOptions!.maxTokens).toBe(512) - expect(adapter.lastOptions!.sessionId).toBe(SessionId('summary')) - expect(adapter.lastOptions!.messages[0]!.content[0]).toMatchObject({ type: 'text' }) - }) - - it('uses maxTokens as the summarization provider cap', async () => { - const { ctx, adapter } = await ctxWithModel('SUMMARY TEXT') - const svc = new BasicCompactService(ctx, cfg({ - auto: false, - maxTokens: 50, - })) - - await summarize(svc, 'User: hi', 'test-model') - - expect(adapter.lastOptions!.maxTokens).toBe(50) - }) - - it('keeps only text blocks in the stored summary (drops reasoning and tool-call)', async () => { - const { ctx } = await ctxWithBlocks([ - { type: 'reasoning', text: 'private chain of thought' }, - { type: 'text', text: 'PUBLIC SUMMARY' }, - // A model reply can carry a tool-call; it must not survive into the - // synthesized user/message summary as an orphaned call. - { type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }, - ]) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) - - const { summary } = await summarize(svc, 'User: hi', 'test-model') - - expect(summary).toEqual([{ type: 'text', text: 'PUBLIC SUMMARY' }]) - }) - - it('throws when no text block remains after filtering', async () => { - const { ctx } = await ctxWithBlocks([{ type: 'reasoning', text: 'private only' }]) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) - - await expect(summarize(svc, 'User: hi', 'test-model')).rejects.toThrow(/no text summary content/) - }) - - it('throws when no model is provided', async () => { - const { ctx } = await ctxWithModel('x') - const svc = new BasicCompactService(ctx, cfg({ auto: false })) - await expect(summarize(svc, 'text', '')).rejects.toThrow(/no model available/) - }) - - it('rethrows when the stream ends with a finish-error chunk', async () => { - const ctx = await ctxWithFinish({ kind: 'error', message: 'provider 401', code: 'UNAUTHORIZED' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) - await expect(summarize(svc, 'text', 'test-model')).rejects.toMatchObject({ message: 'provider 401', code: 'UNAUTHORIZED' }) - }) - - it('rethrows a finish-error chunk without a code (code stays undefined)', async () => { - const ctx = await ctxWithFinish({ kind: 'error', message: 'opaque failure' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) - const error = await summarize(svc, 'text', 'test-model').then(() => null, (e: unknown) => e as Error & { code?: string }) - expect(error?.message).toBe('opaque failure') - expect(error?.code).toBeUndefined() - }) - - it('rethrows when the stream ends with a finish-aborted chunk', async () => { - const ctx = await ctxWithFinish({ kind: 'aborted' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) - await expect(summarize(svc, 'text', 'test-model')).rejects.toMatchObject({ message: 'summarization stream aborted', code: 'ABORTED' }) - }) - - it('fails closed on a max-tokens finish (an incomplete checkpoint must not commit)', async () => { - const ctx = await ctxWithFinish({ kind: 'max-tokens' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) - await expect(summarize(svc, 'text', 'test-model')).rejects.toMatchObject({ code: 'MAX_TOKENS' }) - }) - - it('compactRegion leaves the surface intact when summarization hits max-tokens', async () => { - const ctx = await ctxWithFinish({ kind: 'max-tokens' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) - const session = multiTurnSession(2, 1) - const before = [...session.surface.nodes] - const nodes = session.surface.nodes - - await expect(compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'test-model')) - .rejects.toMatchObject({ code: 'MAX_TOKENS' }) - - // No replacement landed — the surface is byte-identical, and the lock was - // released with the error (compact/end carries it). - expect(session.surface.nodes).toEqual(before) - const endEvent = session.events.findLast(e => e.type === 'compact/end')! - const endData = endEvent.data as { error?: string } - expect(endData.error).toContain('truncated') - }) - - it('compactRegion uses the real summarizer end-to-end', async () => { - const { ctx } = await ctxWithModel('CONDENSED') - const svc = new BasicCompactService(ctx, cfg({ auto: false })) - const session = multiTurnSession(2, 1) - const nodes = session.surface.nodes - - const result = await compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'test-model') - expect(result.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) - // The raw summary is wrapped in the checkpoint framing on the surface. - expect(session.deriveMessages()[0]!.content).toContainEqual({ type: 'text', text: 'CONDENSED' }) - }) - - it('rejects a summary that is not smaller than the shadowed content', async () => { - const svc = createTestService({ auto: false }) - const session = multiTurnSession(2, 1) - const nodes = session.surface.nodes - svc.mockSummary = Array.from({ length: 20 }, (_, index) => ({ type: 'text', text: `large ${index}` })) - - await expect(compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm')) - .rejects.toThrow(/summary is not smaller than the shadowed content/) - expect(session.events.some(e => e.type === 'compact/summary')).toBe(false) - }) - - it('rejects when the framed checkpoint is not smaller than the shadowed content', async () => { - const svc = createTestService({ auto: false }) - svc.estimateFramedSummariesCheaply = false - const session = new Session(SessionId('framed-nonshrinking')) - session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - session.append('step/start', { turn: 1, step: 1 }) - session.append('user/message', { content: [{ type: 'text', text: 'tiny user' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'tiny assistant' }] }, { surfaceOp: 'append' }) - session.append('step/end', { turn: 1, step: 1 }) - session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) - const before = [...session.surface.nodes] - const nodes = session.surface.nodes - - await expect(compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm')) - .rejects.toThrow(/summary is not smaller than the shadowed content/) - expect(session.events.some(e => e.type === 'compact/summary')).toBe(false) - expect(session.surface.nodes).toEqual(before) - }) -}) - -describe('BasicCompactService auto-compaction (agent/pre-step listener)', () => { - /** Fire the agent/pre-step serial checkpoint as the loop does. */ - function firePreStep(ctx: Context, agent: Agent, step: number, fullSystemPrompt: string): Promise { - return ctx.serial('agent/pre-step', agent, 1, step, fullSystemPrompt, [], SIGNAL) - } - - it('compacts (mutating the surface) when over threshold', async () => { - const { ctx } = await ctxWithModel('SUMMARY') - void new BasicCompactService(ctx, cfg({ contextWindow: 200, thresholdRatio: 0.5, retainTokens: 20 })) - const session = multiTurnSession(5, 1) // 10 surface nodes - const agent = stubAgent(session, 'test-model') - const before = session.surface.nodes.length - - await firePreStep(ctx, agent, 1, '') - - // The surface shrank in place, and a summary checkpoint landed. - expect(session.surface.nodes.length).toBeLessThan(before) - expect(session.events.some(e => e.type === 'compact/summary')).toBe(true) - // The re-derived head message is the framed summary checkpoint. - expect(session.deriveMessages()[0]!.content).toContainEqual({ type: 'text', text: 'SUMMARY' }) - }) - - it('logs compaction details when auto-compaction returns a converged result', async () => { - const ctx = new Context() - const infos: string[] = [] - ctx.logger.info = ((msg: string) => void infos.push(msg)) as typeof ctx.logger.info - void new TestCompactService(ctx, cfg({ - contextWindow: 100, - thresholdRatio: 0.7, - retainTokens: 10, - compactionRetries: 0, - })) - const session = multiTurnSession(3, 1) - const agent = stubAgent(session, 'test-model') - - await firePreStep(ctx, agent, 1, '') - - expect(session.events.filter(e => e.type === 'compact/summary')).toHaveLength(1) - expect(infos.some(msg => msg.includes('compaction: shadowed'))).toBe(true) - expect(infos.some(msg => msg.includes('estimated tokens after compaction'))).toBe(true) - }) - - it('compacts mid-turn on steps after the first (the surface grows within a turn)', async () => { - const { ctx } = await ctxWithModel('SUMMARY') - void new BasicCompactService(ctx, cfg({ contextWindow: 100, thresholdRatio: 0.5, retainTokens: 10 })) - const session = multiTurnSession(3, 1) // over the 0.5 threshold - const agent = stubAgent(session, 'test-model') - - // A step-2 checkpoint (a tool-heavy turn's later step) must still compact — - // the surface accumulated assistant/message + tool/result nodes since step 1. - await firePreStep(ctx, agent, 2, '') - expect(session.events.some(e => e.type === 'compact/start')).toBe(true) - }) - - it('does nothing when under threshold', async () => { - const { ctx } = await ctxWithModel('SUMMARY') - void new BasicCompactService(ctx, cfg({ contextWindow: 128000, thresholdRatio: 0.8 })) - const session = multiTurnSession(1, 1) - const agent = stubAgent(session, 'test-model') - - await firePreStep(ctx, agent, 1, '') - expect(session.events.some(e => e.type === 'compact/start')).toBe(false) - }) - - it('leaves the surface intact when compaction fails (summarize rejects)', async () => { - // No adapter registered for this model → summarize() rejects → caught, the - // surface is untouched (the loop derives the full history). - const ctx = new Context() - await ctx.plugin(LlmService) - void new BasicCompactService(ctx, cfg({ contextWindow: 300, thresholdRatio: 0.1, retainTokens: 10 })) - const session = multiTurnSession(3, 1) - const agent = stubAgent(session, 'missing-model') - const before = session.surface.nodes.length - - await firePreStep(ctx, agent, 1, '') - // No summary landed; the surface is unchanged. - expect(session.events.some(e => e.type === 'compact/summary')).toBe(false) - expect(session.surface.nodes.length).toBe(before) - }) - - it('does not register the listener when auto is false', async () => { - const { ctx } = await ctxWithModel('SUMMARY') - void new BasicCompactService(ctx, cfg({ auto: false, contextWindow: 100, thresholdRatio: 0.1, retainTokens: 5 })) - const session = multiTurnSession(3, 1) - const agent = stubAgent(session, 'test-model') - - await firePreStep(ctx, agent, 1, '') - expect(session.events.some(e => e.type === 'compact/start')).toBe(false) - }) - - it('summarization is interceptable at llm/stream (model routing for direct calls)', async () => { - const { ctx, adapter } = await ctxWithModel('ROUTED SUMMARY', 'routed-model') - // One-shot summaries bypass agent/request but remain mutable at llm/stream; - // adapter selection happens after the waterfall rewrite. - ctx.on('llm/stream', (options, next) => { - options.model = 'routed-model' - return next() - }) - void new BasicCompactService(ctx, cfg({ contextWindow: 200, thresholdRatio: 0.5, retainTokens: 20 })) - const session = multiTurnSession(5, 1) - const agent = stubAgent(session, 'agent-model') - - await ctx.serial('agent/pre-step', agent, 1, 1, '', [], SIGNAL) - - expect(adapter.lastOptions?.model).toBe('routed-model') - expect(session.events.some(e => e.type === 'compact/summary')).toBe(true) - expect(session.deriveMessages()[0]!.content).toContainEqual({ type: 'text', text: 'ROUTED SUMMARY' }) - }) - - it('removes the auto pre-step listener when the plugin fiber is disposed', async () => { - const { ctx } = await ctxWithModel('SUMMARY') - const fiber = await ctx.plugin(BasicCompactService, cfg({ - contextWindow: 200, - thresholdRatio: 0.5, - retainTokens: 20, - })) - const session = multiTurnSession(5, 1) - const agent = stubAgent(session, 'test-model') - - await fiber.dispose() - await firePreStep(ctx, agent, 1, '') - - expect(session.events.some(e => e.type === 'compact/start')).toBe(false) - expect(ctx.get('compact')).toBeUndefined() - }) -}) - -describe('BasicCompactService transcript rendering (delegated to dsh-compact)', () => { - it('renders reasoning, context, and steering messages', async () => { - const svc = createTestService() - const s = new Session(SessionId('rich')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - s.append('context/message', { - content: [{ type: 'text', text: 'project context here' }], - source: { kind: 'user' }, - }, { surfaceOp: 'append' }) - s.append('assistant/message', { - turn: 1, step: 1, - content: [{ type: 'reasoning', text: 'thinking hard' }, { type: 'text', text: 'answer' }], - }, { surfaceOp: 'append' }) - s.append('steering/message', { - turn: 1, - content: [{ type: 'text', text: 'steer this way' }], - source: { kind: 'user' }, - }, { surfaceOp: 'append' }) - s.append('step/end', { turn: 1, step: 1 }) - s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) - - const nodes = s.surface.nodes - await compactRegion(svc, s, nodes[0]!.seq, nodes[nodes.length - 1]!.seq, 'm') - - const { text } = svc.summarizeCalls[0]! - expect(text).toContain('[Context: project context here]') - expect(text).toContain('[reasoning: thinking hard]') - expect(text).toContain('[Steering: steer this way]') - }) - - it('labels tool errors distinctly from tool results', async () => { - const svc = createTestService() - const s = new Session(SessionId('toolerr')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - s.append('user/message', { content: [{ type: 'text', text: 'run it' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { - turn: 1, step: 1, - content: [{ type: 'tool-call', id: CallId('c9'), name: 'bash', arguments: '{}' }], - }, { surfaceOp: 'append' }) - s.append('tool/call', { turn: 1, step: 1, callId: CallId('c9'), name: 'bash', arguments: '{}' }) - s.append('tool/result', { - turn: 1, step: 1, callId: CallId('c9'), - content: [{ type: 'text', text: 'boom failure' }], - isError: true, - }, { surfaceOp: 'append' }) - s.append('step/end', { turn: 1, step: 1 }) - s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) - - const nodes = s.surface.nodes - await compactRegion(svc, s, nodes[0]!.seq, nodes[nodes.length - 1]!.seq, 'm') - expect(svc.summarizeCalls[0]!.text).toContain('Tool error (call c9): boom failure') - }) -}) - -describe('BasicCompactService edge cases', () => { - it('renders bare and nested tool-result placeholders and unknown blocks', async () => { - const svc = createTestService() - const s = new Session(SessionId('toolresult')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - // assistant/message carrying a nested tool-result block, an unknown block, - // and the tool-call that the following tool/result answers (so the surface - // is tool-pairing balanced). - s.append('assistant/message', { - turn: 1, step: 1, - content: [ - { type: 'tool-result', toolCallId: CallId('n1'), content: [{ type: 'chart', data: 'x' } as unknown as ContentBlock] }, - { type: 'custom-widget', payload: 'x' } as unknown as ContentBlock, - { type: 'tool-call', id: CallId('b1'), name: 'bash', arguments: '{}' }, - ], - }, { surfaceOp: 'append' }) - // tool/result whose content is itself only non-text → bare '[tool-result]'. - s.append('tool/call', { turn: 1, step: 1, callId: CallId('b1'), name: 'bash', arguments: '{}' }) - s.append('tool/result', { - turn: 1, step: 1, callId: CallId('b1'), - content: [{ type: 'tool-result', toolCallId: CallId('inner'), content: [] }], - isError: false, - }, { surfaceOp: 'append' }) - s.append('step/end', { turn: 1, step: 1 }) - s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) - - const nodes = s.surface.nodes - await compactRegion(svc, s, nodes[0]!.seq, nodes[nodes.length - 1]!.seq, 'm') - const { text } = svc.summarizeCalls[0]! - expect(text).toContain('[tool-result: [chart]]') // nested tool-result with content - expect(text).toContain('[custom-widget]') // unknown block placeholder - expect(text).toContain('Tool result (call b1): [tool-result]') // empty nested → bare placeholder - }) - - it('estimates unknown block types via JSON length (default branch)', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) - // A block whose type is none of the known kinds — exercises the default arm. - const unknown = { type: 'custom-widget', payload: 'some data' } as unknown as ContentBlock - expect(svc.estimateContentTokens([unknown])).toBeGreaterThan(0) - }) - - it('auto-compaction reports bounded retry exhaustion after committing a smaller summary', async () => { - const { ctx } = await ctxWithModel('SUMMARY') - const warnings: string[] = [] - ctx.logger.warn = ((msg: string) => void warnings.push(msg)) as typeof ctx.logger.warn - void new BasicCompactService(ctx, cfg({ - contextWindow: 300, - thresholdRatio: 0.1, - retainTokens: 5, - compactionRetries: 0, - })) - const session = multiTurnSession(4, 1) - const agent = stubAgent(session, 'test-model') - - await ctx.serial('agent/pre-step', agent, 1, 1, '', [], SIGNAL) - expect(session.events.some(e => e.type === 'compact/summary')).toBe(true) - // The surface was mutated; the head message is the framed summary checkpoint. - expect(session.deriveMessages()[0]!.content).toContainEqual({ type: 'text', text: 'SUMMARY' }) - expect(warnings.some(w => w.includes('still above threshold after 1 compaction attempts'))).toBe(true) - }) - - it('rejects compaction when no turn is open (compaction events must be turn-enclosed)', async () => { - const svc = createTestService() - // A session whose only turn has CLOSED — scanning back from the tail hits - // turn/end before any turn/start, so there is no open turn to enclose - // compaction's compact/* + replacement events, which the log contract forbids. - const s = new Session(SessionId('noturn')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - s.append('user/message', { content: [{ type: 'text', text: 'orphan' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'reply' }] }, { surfaceOp: 'append' }) - s.append('step/end', { turn: 1, step: 1 }) - s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - const nodes = s.surface.nodes - - await expect(compactRegion(svc, s, nodes[0]!.seq, nodes[1]!.seq, 'm')) - .rejects.toThrow(/no open turn/) - // The lock was never acquired — no compact/start landed. - expect(s.events.some(e => e.type === 'compact/start')).toBe(false) - }) - - it('rejects compaction on a session with no turn boundaries at all', async () => { - const svc = createTestService() - // No turn events whatsoever — the open-turn scan falls through to the end - // of the log and finds none, so compaction is rejected (its events have no - // turn to enclose them). - const s = new Session(SessionId('turnless')) - s.append('user/message', { content: [{ type: 'text', text: 'orphan' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - const nodes = s.surface.nodes - - await expect(compactRegion(svc, s, nodes[0]!.seq, nodes[0]!.seq, 'm')) - .rejects.toThrow(/no open turn/) - expect(s.events.some(e => e.type === 'compact/start')).toBe(false) - }) - - it('compactIfNeeded returns null for empty surface even when over threshold', async () => { - const svc = createTestService({ contextWindow: 1000, thresholdRatio: 0.1, retainTokens: 5 }) - const session = new Session(SessionId('empty-but-pressured')) - // No surface nodes, but a large system prompt pushes the estimate over threshold. - const bigPrompt = 'x'.repeat(800) // ceil(800/4) = 200 tokens >> threshold 100 - expect(await compactIfNeeded(svc, session, bigPrompt, 'm', SIGNAL)).toBeNull() - }) - - it('compactRegion throws when end is not a surface node (start valid)', async () => { - const svc = createTestService() - const session = multiTurnSession(1, 1) - const nodes = session.surface.nodes - await expect(compactRegion(svc, session, nodes[0]!.seq, 9999, 'm')) - .rejects.toThrow(/end seq 9999 not found in surface/) - }) - - it('compactRegion stringifies a non-Error thrown by summarize', async () => { - const svc = createTestService() - // Throw a non-Error value to exercise the String(error) branch in the catch. - svc.summarizeError = 'plain string failure' as unknown as Error - const session = multiTurnSession(1, 1) - const nodes = session.surface.nodes - - // Whole step (user → assistant): a step-aligned region that reaches summarize. - await expect(compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'm')).rejects.toBe('plain string failure') - const endEvent = session.events.findLast(e => e.type === 'compact/end')! - expect(endEvent.data).toMatchObject({ error: 'plain string failure' }) - }) - - it('auto-compaction listener stringifies a non-Error and proceeds', async () => { - const { ctx } = await ctxWithModel('SUMMARY') - const warnings: string[] = [] - ctx.logger.warn = ((msg: string) => void warnings.push(msg)) as typeof ctx.logger.warn - const svc = new TestCompactService(ctx, cfg({ contextWindow: 300, thresholdRatio: 0.1, retainTokens: 10 })) - svc.summarizeError = 'boom' as unknown as Error - const session = multiTurnSession(3, 1) - const agent = stubAgent(session, 'test-model') - const before = session.surface.nodes.length - - await ctx.serial('agent/pre-step', agent, 1, 1, '', [], SIGNAL) - // The failure was swallowed; the surface is untouched and a warning logged. - expect(session.surface.nodes.length).toBe(before) - expect(session.events.some(e => e.type === 'compact/summary')).toBe(false) - expect(warnings.some(w => w.includes('compaction failed: boom'))).toBe(true) - }) - - it('auto-compaction listener takes the result-null branch (nothing to compact)', async () => { - const { ctx } = await ctxWithModel('SUMMARY') - // A large system prompt pushes the listener's estimate over threshold, but - // retainTokens is huge so compactIfNeeded walks everything and returns null. - // threshold = floor(2000*0.1) = 200; invariant: 5 + 150 = 155 ≤ 200. - const svc = new TestCompactService(ctx, cfg({ contextWindow: 2000, thresholdRatio: 0.1, retainTokens: 150 })) - const session = multiTurnSession(2, 1) - const agent = stubAgent(session, 'test-model') - const bigSystem = 'x'.repeat(900) // ceil(900/4)=225 > threshold 200 - - await ctx.serial('agent/pre-step', agent, 1, 1, bigSystem, [], SIGNAL) - expect(session.events.some(e => e.type === 'compact/start')).toBe(false) - expect(svc.summarizeCalls.length).toBe(0) - }) - - it('skips messages whose extracted text is empty across all kinds', async () => { - const svc = createTestService() - const s = new Session(SessionId('empties')) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - s.append('user/message', { content: [{ type: 'text', text: '' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'reasoning', text: '' }] }, { surfaceOp: 'append' }) - s.append('context/message', { content: [], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('steering/message', { turn: 1, content: [{ type: 'text', text: '' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('step/end', { turn: 1, step: 1 }) - // Keep the log pairing-valid while the empty result covers the final message kind. - s.append('step/start', { turn: 1, step: 2 }) - s.append('assistant/message', { - turn: 1, step: 2, - content: [{ type: 'tool-call', id: CallId('z1'), name: 'bash', arguments: '{}' }], - }, { surfaceOp: 'append' }) - s.append('tool/call', { turn: 1, step: 2, callId: CallId('z1'), name: 'bash', arguments: '{}' }) - s.append('tool/result', { turn: 1, step: 2, callId: CallId('z1'), content: [], isError: false }, { surfaceOp: 'append' }) - s.append('step/end', { turn: 1, step: 2 }) - s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) - - const nodes = s.surface.nodes - await compactRegion(svc, s, nodes[0]!.seq, nodes[nodes.length - 1]!.seq, 'm') - expect(svc.summarizeCalls[0]!.text).toBe('Assistant: [tool-call: bash({})]') - }) - - it('renders non-text blocks as type-tagged placeholders across all message kinds', async () => { - const svc = createTestService() - const s = new Session(SessionId('placeholders')) - // A plugin-added block type (merge-extensible ContentBlockMap) — the - // placeholder path must cover every message kind, not just assistant. - const chart = (id: string): ContentBlock => ({ type: 'chart', data: id } as unknown as ContentBlock) - s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - s.append('step/start', { turn: 1, step: 1 }) - // user/message with only a plugin-added block → '[chart]' placeholder. - s.append('user/message', { content: [chart('y')], source: { kind: 'user' } }, { surfaceOp: 'append' }) - // assistant/message with a plugin-added block AND the tool-call its - // tool/result answers (so the surface is tool-pairing balanced). - s.append('assistant/message', { - turn: 1, step: 1, - content: [ - chart('z'), - { type: 'tool-call', id: CallId('e1'), name: 'bash', arguments: '{}' }, - ], - }, { surfaceOp: 'append' }) - // tool/result with a plugin-added block → '[chart]' placeholder. - s.append('tool/call', { turn: 1, step: 1, callId: CallId('e1'), name: 'bash', arguments: '{}' }) - s.append('tool/result', { turn: 1, step: 1, callId: CallId('e1'), content: [chart('r')], isError: false }, { surfaceOp: 'append' }) - // context/message and steering/message with plugin-added content. - s.append('context/message', { content: [chart('c')], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('steering/message', { turn: 1, content: [chart('s')], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('step/end', { turn: 1, step: 1 }) - s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - s.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) - - const nodes = s.surface.nodes - await compactRegion(svc, s, nodes[0]!.seq, nodes[nodes.length - 1]!.seq, 'm') - const { text } = svc.summarizeCalls[0]! - // Every non-text block surfaces as a placeholder rather than being dropped. - expect(text).toContain('User: [chart]') - expect(text).toContain('Assistant: [chart]') - expect(text).toContain('Tool result (call e1): [chart]') - expect(text).toContain('[Context: [chart]]') - expect(text).toContain('[Steering: [chart]]') - }) - -}) - -describe('BasicCompactService positional range (surface seqs are not monotonic after a replace)', () => { - it('compacts a second region after the first replace lands a high-seq summary at the head position', async () => { - // Replacement makes surface seqs non-monotonic. The next region is a - // positional span even when startSeq > endSeq. - const svc = createTestService({ auto: false }) - const session = multiTurnSession(4, 1) - - // A replacement puts its high-seq summary at the surface head. - const nodes0 = session.surface.nodes - const first = await compactRegion(svc, session, nodes0[0]!.seq, nodes0[1]!.seq, 'm') - - const nodes1 = session.surface.nodes - expect(nodes1[0]!.seq).toBeGreaterThanOrEqual(first.summarySeq) - expect(nodes1[0]!.seq).toBeGreaterThan(nodes1[1]!.seq) - - const startSeq = nodes1[0]!.seq - const endSeq = nodes1[2]!.seq - expect(startSeq).toBeGreaterThan(endSeq) - const second = await compactRegion(svc, session, startSeq, endSeq, 'm') - - // Selection follows surface positions, not sequence-number order. - expect(second.shadowedSeqs).toEqual([nodes1[0]!.seq, nodes1[1]!.seq, nodes1[2]!.seq]) - const finalNodes = session.surface.nodes - expect(finalNodes[0]!.seq).toBeGreaterThanOrEqual(second.summarySeq) - expect(session.deriveMessages().length).toBe(finalNodes.length) - }) - - it('extracts the second-compaction transcript in surface order, not log-seq order', async () => { - const svc = createTestService({ auto: false }) - const session = multiTurnSession(3, 1) - - // Put a high-seq summary at the head; log order would place retained older nodes first. - const n0 = session.surface.nodes - await compactRegion(svc, session, n0[0]!.seq, n0[1]!.seq, 'm') - - const n1 = session.surface.nodes - svc.summarizeCalls = [] - await compactRegion(svc, session, n1[0]!.seq, n1[2]!.seq, 'm') - - // Extraction must match surface and `deriveMessages()` order. - const { text } = svc.summarizeCalls[0]! - const checkpointIdx = text.indexOf('compacted-summary') - const olderIdx = text.indexOf('turn 2 user') - expect(checkpointIdx).toBeGreaterThanOrEqual(0) - expect(olderIdx).toBeGreaterThan(checkpointIdx) - }) -}) - -describe('BasicCompactService llm inject (real plugin-load path)', () => { - it('declares llm in static inject so a sibling fiber can resolve ctx.llm', () => { - // summarize() reads ctx.llm; the inject lets the cordis ctx proxy resolve a sibling - // LlmService when this service is mounted as its own plugin fiber. - expect(BasicCompactService.inject).toContain('llm') - }) - - it('resolves ctx.llm and summarizes when mounted as a sibling plugin of LlmService', async () => { - const ctx = new Context() - await ctx.plugin(LlmService) - ctx.llm.registerAdapter(['test-model'], new ScriptedAdapter('CONDENSED')) - // Mount the service through its real plugin fiber (NOT new …(rootCtx)), so - // the sibling-fiber ctx.llm resolution actually exercises the inject. - const fiber = await ctx.plugin(BasicCompactService, cfg({ auto: false })) - - const svc = ctx.compact as BasicCompactService - const session = multiTurnSession(2, 1) - const nodes = session.surface.nodes - const result = await compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'test-model') - expect(result.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) - - // Tear the fiber down so this test owns no leaked registration; the - // dedicated cleanup assertion lives in the "HMR safety" suite. - await fiber.dispose() - expect(ctx.get('compact')).toBeUndefined() - }) -}) - -describe('BasicCompactService under the real invariants plugin', () => { - /** - * Drive compaction through a session whose `session/event` listeners include - * the real dev-mode invariants plugin (as a real app loads it via agent-core). - * The invariants throw on append, so a passing run proves the compaction - * sequence is contract-valid: every event is turn-enclosed, and the positional - * replace op is accepted even when the surface is no longer seq-ordered. - */ - async function setup(): Promise<{ ctx: Context; session: Session; svc: BasicCompactService }> { - const ctx = new Context() - await ctx.plugin(SessionStore) - await ctx.plugin(Invariants) - await ctx.plugin(LlmService) - ctx.llm.registerAdapter(['test-model'], new ScriptedAdapter('CONDENSED')) - await ctx.plugin(BasicCompactService, cfg({ auto: false })) - const session = ctx.sessions.create() - return { ctx, session, svc: ctx.compact as BasicCompactService } - } - - /** Append one closed turn of [user, assistant] surface nodes via the store. */ - function closedTurn(session: Session, turn: number): void { +/** Closed two-message turns followed by one open turn for durable compaction events. */ +function conversation(turns = 4, text = 'fixture'): Session { + const session = new Session(SessionId(`conversation-${turns}`)) + for (let turn = 1; turn <= turns; turn += 1) { session.append('turn/start', { turn, trigger: { kind: 'message', source: { kind: 'user' } } }) + session.append('user/message', { + content: [{ type: 'text', text: `${text} user ${turn}` }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) session.append('step/start', { turn, step: 1 }) - session.append('user/message', { content: [{ type: 'text', text: `turn ${turn} user.${LONG_FIXTURE_TEXT}` }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - session.append('assistant/message', { turn, step: 1, content: [{ type: 'text', text: `turn ${turn} assistant.${LONG_FIXTURE_TEXT}` }] }, { surfaceOp: 'append' }) + session.append('assistant/message', { + turn, + step: 1, + content: [{ type: 'text', text: `${text} assistant ${turn}` }], + }, { surfaceOp: 'append' }) session.append('step/end', { turn, step: 1 }) session.append('turn/end', { turn, reason: { kind: 'completed' } }) } + session.append('turn/start', { + turn: turns + 1, + trigger: { kind: 'message', source: { kind: 'user' } }, + }) + return session +} - it('runs a turn-enclosed compaction whose positional replace the invariants accept', async () => { - const { session, svc } = await setup() - closedTurn(session, 1) - closedTurn(session, 2) - // Open turn 3, as the loop has when the auto-compaction listener fires. - session.append('turn/start', { turn: 3, trigger: { kind: 'message', source: { kind: 'user' } } }) +function toolConversation(): Session { + const session = new Session(SessionId('tools')) + for (let turn = 1; turn <= 3; turn += 1) { + const callId = CallId(`call-${turn}`) + session.append('turn/start', { turn, trigger: { kind: 'message', source: { kind: 'user' } } }) + session.append('user/message', { + content: [{ type: 'text', text: `request ${turn} `.repeat(300) }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + session.append('step/start', { turn, step: 1 }) + session.append('assistant/message', { + turn, + step: 1, + content: [ + { type: 'text', text: `calling ${turn} `.repeat(300) }, + { type: 'tool-call', id: callId, name: 'read', arguments: '{}' }, + ], + }, { surfaceOp: 'append' }) + session.append('tool/call', { turn, step: 1, callId, name: 'read', arguments: '{}' }) + session.append('tool/result', { + turn, + step: 1, + callId, + content: [{ type: 'text', text: `result ${turn} `.repeat(300) }], + isError: false, + }, { surfaceOp: 'append' }) + session.append('step/end', { turn, step: 1 }) + session.append('turn/end', { turn, reason: { kind: 'completed' } }) + } + session.append('turn/start', { turn: 4, trigger: { kind: 'message', source: { kind: 'user' } } }) + return session +} - const nodes = session.surface.nodes - // No invariant throws here: compact/* + the replacement are all in turn 3. - const result = await compactRegion(svc, session, nodes[0]!.seq, nodes[1]!.seq, 'test-model') - expect(result.shadowedSeqs.length).toBe(2) - expect(session.surface.nodes[0]!.seq).toBeGreaterThan(session.surface.nodes[1]!.seq) +class TestCompactService extends BasicCompactService { + summary: ContentBlock[] = [{ type: 'text', text: 'small checkpoint' }] + summaryModel = 'summary-model' + error: unknown + mutateDuringSummary: (() => void) | undefined + calls: Array<{ text: string; signal: AbortSignal | undefined }> = [] + + override async summarize( + text: string, + _agent: Agent, + signal?: AbortSignal, + ): Promise<{ summary: ContentBlock[]; model: string; maxTokens?: number }> { + this.calls.push({ text, signal }) + this.mutateDuringSummary?.() + if (this.error !== undefined) throw this.error + return { summary: this.summary, model: this.summaryModel, maxTokens: 123 } + } +} + +function service( + config: BasicCompactConfig = { auto: false }, + ctx = createContext(), +): TestCompactService { + return new TestCompactService(ctx, config) +} + +async function compactIfNeeded( + compact: BasicCompactService, + session: Session, + model: string | undefined = MODEL, + system = '', + prefix: readonly Message[] = [], +): Promise { + return compact.compactIfNeeded(agent(session, model), system, prefix, SIGNAL) +} + +describe('compact configuration and defaults', () => { + it('uses low-friction common and per-profile defaults', () => { + const ctx = createContext({ + [MODEL]: { contextWindow: 100, charsPerToken: 1_000 }, + large: { contextWindow: 1_000, charsPerToken: 4 }, + }) + const resolved = resolveConfig({}, ctx.tokenMeter) + + expect(resolved).toEqual({ + models: {}, + summarizationModel: '', + maxTokens: 8192, + compactionRetries: 1, + auto: true, + }) + expect(resolveModelConfig(resolved, ctx.tokenMeter.resolve(MODEL))).toEqual({ + model: MODEL, + contextWindow: 100, + thresholdRatio: 0.8, + retainTokens: 16, + }) + expect(resolveModelConfig(resolved, ctx.tokenMeter.resolve('large')).retainTokens).toBe(160) + expect(Object.isFrozen(resolved)).toBe(true) }) - it('accepts a second compaction over the non-monotonic surface left by the first', async () => { - const { session, svc } = await setup() - closedTurn(session, 1) - closedTurn(session, 2) - closedTurn(session, 3) - session.append('turn/start', { turn: 4, trigger: { kind: 'message', source: { kind: 'user' } } }) + it('merges threshold and retention overrides field-wise', () => { + const ctx = createContext() + const thresholdOnly = resolveConfig({ + models: { [MODEL]: { thresholdRatio: 0.5 } }, + }, ctx.tokenMeter) + expect(resolveModelConfig(thresholdOnly, ctx.tokenMeter.resolve(MODEL))).toMatchObject({ + thresholdRatio: 0.5, + retainTokens: 16, + }) - const n0 = session.surface.nodes - await compactRegion(svc, session, n0[0]!.seq, n0[1]!.seq, 'test-model') + const retentionOnly = resolveConfig({ + models: { [MODEL]: { retainTokens: 7 } }, + }, ctx.tokenMeter) + expect(resolveModelConfig(retentionOnly, ctx.tokenMeter.resolve(MODEL))).toMatchObject({ + thresholdRatio: 0.8, + retainTokens: 7, + }) + }) - // Surface head now carries a higher seq than the older retained nodes. A - // second compaction spanning [head … a later closed-step end] must pass the - // invariants' positional replace check even though startSeq > endSeq. - const n1 = session.surface.nodes - expect(n1[0]!.seq).toBeGreaterThan(n1[2]!.seq) - const second = await compactRegion(svc, session, n1[0]!.seq, n1[2]!.seq, 'test-model') - expect(second.shadowedSeqs).toEqual([n1[0]!.seq, n1[1]!.seq, n1[2]!.seq]) + it('validates common values and model policy invariants', () => { + const ctx = createContext() + const bad = [ + [{ maxTokens: 0 }, /maxTokens/], + [{ compactionRetries: -1 }, /compactionRetries/], + [{ auto: 'yes' }, /auto must be a boolean/], + [{ summarizationModel: 1 }, /summarizationModel must be a string/], + [{ models: null }, /models must be an object/], + [{ models: { [MODEL]: null } }, /must be an object/], + [{ models: { [MODEL]: { thresholdRatio: 0 } } }, /number in \(0, 1\]/], + [{ models: { [MODEL]: { thresholdRatio: 1.1 } } }, /number in \(0, 1\]/], + [{ models: { [MODEL]: { retainTokens: -1 } } }, /non-negative integer/], + [{ models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 50 } } }, /less than threshold/], + ] as Array<[unknown, RegExp]> + + for (const [config, pattern] of bad) { + expect(() => resolveConfig(config as BasicCompactConfig, ctx.tokenMeter)).toThrow(pattern) + } + }) + + it('rejects an override for an unknown meter profile with the exact typed error', () => { + const ctx = createContext() + expect(() => resolveConfig({ models: { missing: { retainTokens: 1 } } }, ctx.tokenMeter)) + .toThrow(expect.objectContaining({ + code: TOKEN_METER_MODEL_UNCONFIGURED, + model: 'missing', + })) + }) +}) + +describe('pressure measurement and retention', () => { + const compactConfig: BasicCompactConfig = { + auto: false, + models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + } + + it('skips the provisional check only when no routed or fallback model exists', async () => { + const compact = service(compactConfig) + const session = conversation() + expect(await compact.compactIfNeeded(agent(session), '', [], SIGNAL)).toBeNull() + expect(compact.calls).toHaveLength(0) + }) + + it('throws for a named unconfigured model instead of swallowing it', async () => { + const compact = service(compactConfig) + await expect(compactIfNeeded(compact, conversation(), 'missing')) + .rejects.toMatchObject({ code: TOKEN_METER_MODEL_UNCONFIGURED, model: 'missing' }) + }) + + it('does nothing below threshold and compacts a priced head above threshold', async () => { + const compact = service(compactConfig) + expect(await compactIfNeeded(compact, conversation(2))).toBeNull() + + const session = conversation(4) + const result = await compactIfNeeded(compact, session) + expect(result).not.toBeNull() + expect(result?.shadowedSeqs.length).toBeGreaterThan(2) + expect(session.surface.nodes.length).toBeLessThan(8) + }) + + it('counts the current prompt and request prefix without putting either on the surface', async () => { + const compact = service({ + auto: false, + models: { [MODEL]: { thresholdRatio: 0.7, retainTokens: 9 } }, + }) + const session = conversation(2, 'x'.repeat(2_000)) + expect(await compactIfNeeded(compact, session)).toBeNull() + + const prefix: Message[] = [{ + role: 'user', + content: [{ type: 'text', text: 'p'.repeat(10_000) }], + }] + const result = await compactIfNeeded(compact, session, MODEL, 's'.repeat(5_000), prefix) + expect(result).not.toBeNull() + expect(prefix).toHaveLength(1) + expect(session.events.some(event => event.type === 'context/message')).toBe(false) + }) + + it('uses the latest logged routed model instead of AgentOptions.model', async () => { + const ctx = createContext({ + actual: { contextWindow: 100, charsPerToken: 1_000 }, + fallback: { contextWindow: 10_000, charsPerToken: 1_000 }, + }) + const compact = service({ + auto: false, + models: { actual: { thresholdRatio: 0.5, retainTokens: 18 } }, + }, ctx) + const session = conversation(4) + session.append('request/header', { + header: { config: { model: 'actual' } }, + reason: 'initial', + }) + + const result = await compactIfNeeded(compact, session, 'fallback') + expect(result).not.toBeNull() + }) + + it('declines when envelope pressure is high but the surface has no compactable range', async () => { + const compact = service(compactConfig) + const empty = new Session(SessionId('empty')) + expect(await compactIfNeeded(compact, empty, MODEL, 'x'.repeat(100_000))).toBeNull() + + const retained = conversation(1) + expect(await compactIfNeeded(compact, retained, MODEL, 'x'.repeat(100_000))).toBeNull() + }) + + it('detects scalar/surface revision disagreement', async () => { + const ctx = createContext() + const meter = ctx.tokenMeter.resolve(MODEL) + const original = meter.measureSurface.bind(meter) + vi.spyOn(meter, 'measureSurface').mockImplementation((session) => { + const measurement = original(session) + return { ...measurement, logRevision: measurement.logRevision - 1 } + }) + const compact = service(compactConfig, ctx) + + await expect(compactIfNeeded(compact, conversation(4))).rejects.toThrow(/revision/) + }) + + it('bounds retries when a shrinking checkpoint remains above threshold', async () => { + const compact = service({ + auto: false, + compactionRetries: 0, + models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + }) + compact.summary = Array.from({ length: 7 }, (_, index) => ({ + type: 'text', + text: `summary ${index}`, + })) + + await expect(compactIfNeeded(compact, conversation(4))) + .rejects.toThrow(/still above threshold after 1 compaction attempts/) + }) + + it('rounds a retention cut head-ward to preserve tool-call/result pairing', async () => { + const compact = service({ + auto: false, + models: { [MODEL]: { thresholdRatio: 0.8, retainTokens: 8 } }, + }) + const session = toolConversation() + const result = await compactIfNeeded(compact, session) + expect(result).not.toBeNull() + + const messages = session.deriveMessages() + const calls = new Set() + for (const message of messages) { + for (const block of message.content) { + if (block.type === 'tool-call') calls.add(block.id) + if (block.type === 'tool-result') expect(calls.has(block.toolCallId)).toBe(true) + } + } + }) + + it('rejects a priced surface that is not the current positional surface', () => { + const ctx = createContext() + const session = conversation(2) + const priced = ctx.tokenMeter.resolve(MODEL).measureSurface(session) + expect(() => selectCompactableRange(session, { + ...priced, + nodes: priced.nodes.slice(1), + }, 1)).toThrow(/does not match/) + }) + + it('declines when rounding a cut would consume the only tool pair', () => { + const ctx = createContext() + const session = new Session(SessionId('one-tool-pair')) + const callId = CallId('only') + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + session.append('step/start', { turn: 1, step: 1 }) + session.append('assistant/message', { + turn: 1, + step: 1, + content: [{ type: 'tool-call', id: callId, name: 'read', arguments: '{}' }], + }, { surfaceOp: 'append' }) + session.append('tool/call', { turn: 1, step: 1, callId, name: 'read', arguments: '{}' }) + session.append('tool/result', { + turn: 1, + step: 1, + callId, + content: [{ type: 'text', text: 'result' }], + isError: false, + }, { surfaceOp: 'append' }) + session.append('step/end', { turn: 1, step: 1 }) + + const priced = ctx.tokenMeter.resolve(MODEL).measureSurface(session) + expect(selectCompactableRange(session, priced, 1)).toBeNull() + }) +}) + +describe('compaction region transaction', () => { + it('lands a framed, replayable checkpoint with exact pricing provenance', async () => { + const compact = service() + const session = conversation(3) + const before = session.surface.nodes + const result = await compact.compactRegion( + session, + before[0]!.seq, + before[3]!.seq, + agent(session, MODEL), + SIGNAL, + ) + + expect(result.shadowedSeqs).toEqual(before.slice(0, 4).map(node => node.seq)) + expect(result.shadowedTokenCount).toBeGreaterThan(0) + expect(compact.calls[0]).toMatchObject({ signal: SIGNAL }) + expect(compact.calls[0]?.text).toContain('fixture user 1') + const summary = session.events.findLast(event => event.type === 'compact/summary') + expect(summary?.data).toMatchObject({ + shadowedSeqs: result.shadowedSeqs, + shadowedTokenCount: result.shadowedTokenCount, + model: 'summary-model', + maxTokens: 123, + }) + const head = session.deriveMessages()[0]! + expect(head.content[0]?.type).toBe('text') + expect(head.content[0]?.type === 'text' ? head.content[0].text : '').toContain('') + expect(head.content.at(-1)).toEqual({ type: 'text', text: '' }) + + const replay = new Session(SessionId('replay'), [...session.events]) + expect(replay.deriveMessages()).toEqual(session.deriveMessages()) + }) + + it.each([ + ['start missing', 9_001, undefined, /start seq 9001 not found/], + ['end missing', undefined, 9_002, /end seq 9002 not found/], + ])('rejects %s', async (_label, startOverride, endOverride, pattern) => { + const compact = service() + const session = conversation(2) + const nodes = session.surface.nodes + await expect(compact.compactRegion( + session, + startOverride ?? nodes[0]!.seq, + endOverride ?? nodes[1]!.seq, + agent(session, MODEL), + )).rejects.toThrow(pattern) + }) + + it('rejects reversed and tool-unbalanced positional boundaries', async () => { + const compact = service() + const plain = conversation(2) + const nodes = plain.surface.nodes + await expect(compact.compactRegion( + plain, + nodes[2]!.seq, + nodes[1]!.seq, + agent(plain, MODEL), + )).rejects.toThrow(/is after end/) + + const tools = toolConversation() + const toolNodes = tools.surface.nodes + await expect(compact.compactRegion( + tools, + toolNodes[2]!.seq, + toolNodes[4]!.seq, + agent(tools, MODEL), + )).rejects.toThrow(/start seq .* not a balanced boundary/) + await expect(compact.compactRegion( + tools, + toolNodes[0]!.seq, + toolNodes[1]!.seq, + agent(tools, MODEL), + )).rejects.toThrow(/end seq .* not a balanced boundary/) + }) + + it('requires an open turn and an idle compaction bracket', async () => { + const compact = service() + const closed = conversation(1) + closed.append('turn/end', { turn: 2, reason: { kind: 'completed' } }) + const nodes = closed.surface.nodes + await expect(compact.compactRegion( + closed, + nodes[0]!.seq, + nodes[1]!.seq, + agent(closed, MODEL), + )).rejects.toThrow(/no open turn/) + + const locked = conversation(1) + locked.append('compact/start', { turn: 2 }) + const lockedNodes = locked.surface.nodes + await expect(compact.compactRegion( + locked, + lockedNodes[0]!.seq, + lockedNodes[1]!.seq, + agent(locked, MODEL), + )).rejects.toThrow(/already in progress/) + }) + + it('rejects a session with no turn boundary at all', async () => { + const compact = service() + const session = new Session(SessionId('turnless')) + session.append('user/message', { + content: [{ type: 'text', text: 'orphan' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + const node = session.surface.nodes[0]! + + await expect(compact.compactRegion( + session, + node.seq, + node.seq, + agent(session, MODEL), + )).rejects.toThrow(/no open turn/) + }) + + it('rejects a meter snapshot that changed before summarization began', async () => { + const ctx = createContext() + const meter = ctx.tokenMeter.resolve(MODEL) + const original = meter.measureSurface.bind(meter) + vi.spyOn(meter, 'measureSurface').mockImplementationOnce((session) => { + const measurement = original(session) + return { ...measurement, nodes: measurement.nodes.slice(1) } + }) + const compact = service({ auto: false }, ctx) + const session = conversation(2) + const nodes = session.surface.nodes + + await expect(compact.compactRegion( + session, + nodes[0]!.seq, + nodes[2]!.seq, + agent(session, MODEL), + )).rejects.toThrow(/selected surface changed/) + }) + + it('records summarizer failures without mutating the surface', async () => { + const compact = service() + compact.error = new Error('summary unavailable') + const session = conversation(2) + const before = session.surface.nodes + + await expect(compact.compactRegion( + session, + before[0]!.seq, + before[2]!.seq, + agent(session, MODEL), + )).rejects.toThrow('summary unavailable') + expect(session.surface.nodes).toEqual(before) + expect(session.events.findLast(event => event.type === 'compact/end')?.data) + .toMatchObject({ error: 'summary unavailable' }) + }) + + it('stringifies non-Error failures in the durable end bracket', async () => { + const compact = service() + compact.error = 'plain failure' + const session = conversation(2) + const nodes = session.surface.nodes + await expect(compact.compactRegion( + session, + nodes[0]!.seq, + nodes[2]!.seq, + agent(session, MODEL), + )).rejects.toBe('plain failure') + expect(session.events.findLast(event => event.type === 'compact/end')?.data) + .toMatchObject({ error: 'plain failure' }) + }) + + it('rejects concurrent durable appends before committing the replacement', async () => { + const compact = service() + const session = conversation(2) + compact.mutateDuringSummary = () => { + session.append('request/header', { + header: { config: { model: MODEL } }, + reason: 'initial', + }) + } + const nodes = session.surface.nodes + + await expect(compact.compactRegion( + session, + nodes[0]!.seq, + nodes[2]!.seq, + agent(session, MODEL), + )).rejects.toThrow(/session log changed/) + expect(session.events.some(event => event.type === 'compact/summary')).toBe(false) + }) + + it('rejects a non-shrinking framed summary under the conversation meter', async () => { + const compact = service() + compact.summary = Array.from({ length: 20 }, (_, index) => ({ + type: 'text', + text: `verbose ${index}`, + })) + const session = conversation(2) + const nodes = session.surface.nodes + + await expect(compact.compactRegion( + session, + nodes[0]!.seq, + nodes[2]!.seq, + agent(session, MODEL), + )).rejects.toThrow(/summary is not smaller/) + expect(session.events.some(event => event.type === 'compact/summary')).toBe(false) + }) + + it('requires a conversation model for pricing', async () => { + const compact = service() + const session = conversation(1) + const nodes = session.surface.nodes + await expect(compact.compactRegion( + session, + nodes[0]!.seq, + nodes[1]!.seq, + agent(session), + )).rejects.toThrow(/no routed or configured conversation model/) + }) +}) + +class ScriptedAdapter extends LlmAdapter { + lastOptions: GenerateOptions | undefined + + constructor( + private readonly blocks: readonly ContentBlock[], + private readonly finish: (StreamChunk & { type: 'finish' })['reason'] = { kind: 'stop' }, + ) { + super() + } + + override async * stream(options: GenerateOptions): AsyncIterable { + this.lastOptions = options + for (const [index, block] of this.blocks.entries()) { + yield { type: 'block-start', index, blockType: block.type } + if (block.type === 'text') { + yield { type: 'text-delta', index, text: block.text } + } else if (block.type === 'reasoning') { + yield { type: 'reasoning-delta', index, text: block.text } + } else { + yield { type: 'block-end', index, block } + } + } + yield { type: 'finish', reason: this.finish } + } +} + +async function summarizerHarness( + blocks: readonly ContentBlock[], + finish?: (StreamChunk & { type: 'finish' })['reason'], + model = MODEL, + config: BasicCompactConfig = { auto: false }, +): Promise<{ ctx: Context; adapter: ScriptedAdapter; compact: BasicCompactService }> { + const ctx = new Context() + await ctx.plugin(LlmService) + void new TokenMeterService(ctx, { models: { [model]: { contextWindow: 100 } } }) + const adapter = new ScriptedAdapter(blocks, finish) + ctx.llm.registerAdapter([model], adapter) + const compact = new BasicCompactService(ctx, config) + return { ctx, adapter, compact } +} + +describe('default one-shot summarizer', () => { + it('uses configured model/default cap, forwards cancellation, and keeps only safe text', async () => { + const { adapter, compact } = await summarizerHarness([ + { type: 'reasoning', text: 'private' }, + { type: 'text', text: 'public summary' }, + { type: 'tool-call', id: CallId('unexpected'), name: 'x', arguments: '{}' }, + ], undefined, MODEL, { + auto: false, + summarizationModel: MODEL, + maxTokens: 321, + }) + const session = conversation(1) + const output = await compact.summarize('transcript', agent(session, 'fallback'), SIGNAL) + + expect(output).toEqual({ + summary: [{ type: 'text', text: 'public summary' }], + model: MODEL, + maxTokens: 321, + }) + expect(adapter.lastOptions).toMatchObject({ + model: MODEL, + maxTokens: 321, + signal: SIGNAL, + sessionId: session.id, + }) + expect(adapter.lastOptions?.system).toContain('## Primary Request and Intent') + }) + + it('resolves latest routed model before AgentOptions.model', async () => { + const { adapter, compact } = await summarizerHarness([{ type: 'text', text: 'summary' }], undefined, 'routed') + const session = conversation(1) + session.append('request/header', { + header: { config: { model: 'routed' } }, + reason: 'initial', + }) + const output = await compact.summarize('history', agent(session, 'fallback')) + expect(output.model).toBe('routed') + expect(adapter.lastOptions?.model).toBe('routed') + }) + + it('fails clearly when no summarization model can be resolved', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + void new TokenMeterService(ctx) + const compact = new BasicCompactService(ctx, { auto: false }) + await expect(compact.summarize('history', agent(new Session(SessionId('model-less'))))) + .rejects.toThrow(/no model available for summarization/) + }) + + it.each([ + [{ kind: 'error', message: 'provider failed', code: 'PROVIDER' }, 'PROVIDER', /provider failed/], + [{ kind: 'error', message: 'opaque' }, undefined, /opaque/], + [{ kind: 'aborted' }, 'ABORTED', /aborted/], + [{ kind: 'max-tokens' }, 'MAX_TOKENS', /token cap/], + ] as Array<[(StreamChunk & { type: 'finish' })['reason'], string | undefined, RegExp]>) ( + 'rejects terminal finish %#', + async (finish, code, pattern) => { + const { compact } = await summarizerHarness([], finish) + let thrown: unknown + try { + await compact.summarize('history', agent(conversation(1), MODEL)) + } catch (error: unknown) { + thrown = error + } + expect(thrown).toBeInstanceOf(Error) + expect((thrown as Error).message).toMatch(pattern) + expect((thrown as Error & { code?: string }).code).toBe(code) + }, + ) + + it('rejects empty or reasoning-only successful output', async () => { + const { compact } = await summarizerHarness([{ type: 'reasoning', text: 'private' }]) + await expect(compact.summarize('history', agent(conversation(1), MODEL))) + .rejects.toThrow(/no text summary content/) + }) +}) + +describe('automatic listener and loader composition', () => { + function preStep(ctx: Context, owner: Agent): Promise { + return ctx.serial('agent/pre-step', owner, 1, 1, '', [], SIGNAL) + } + + it('compacts above threshold and remains idle below it', async () => { + const ctx = createContext() + const compact = new TestCompactService(ctx, { + models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + }) + const pressured = conversation(4) + await preStep(ctx, agent(pressured, MODEL)) + expect(pressured.events.some(event => event.type === 'compact/summary')).toBe(true) + + const small = conversation(1) + await preStep(ctx, agent(small, MODEL)) + expect(small.events.some(event => event.type === 'compact/start')).toBe(false) + expect(compact.calls).toHaveLength(1) + }) + + it('warns and continues after operational failures, including non-Errors', async () => { + const ctx = createContext() + const warnings: string[] = [] + ctx.logger.warn = ((message: string) => void warnings.push(message)) as typeof ctx.logger.warn + const compact = new TestCompactService(ctx, { + models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + }) + compact.error = 'temporary failure' + const session = conversation(4) + + await expect(preStep(ctx, agent(session, MODEL))).resolves.toBeUndefined() + expect(warnings).toContainEqual(expect.stringContaining('temporary failure')) + expect(session.events.some(event => event.type === 'compact/summary')).toBe(false) + }) + + it('propagates a named unknown-model configuration failure', async () => { + const ctx = createContext() + void new TestCompactService(ctx) + await expect(preStep(ctx, agent(conversation(4), 'missing'))).rejects.toMatchObject({ + code: TOKEN_METER_MODEL_UNCONFIGURED, + model: 'missing', + }) + }) + + it('auto:false installs no listener', async () => { + const ctx = createContext() + void new TestCompactService(ctx, { + auto: false, + models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + }) + const session = conversation(4) + await preStep(ctx, agent(session, MODEL)) + expect(session.events.some(event => event.type === 'compact/start')).toBe(false) + }) + + it('loads and disposes the real zero-config service stack', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + const meterFiber = await ctx.plugin(TokenMeterService) + const compactFiber = await ctx.plugin(BasicCompactService, { auto: false }) + + expect(ctx.tokenMeter.resolve('deepseek-v4-flash').contextWindow).toBe(128_000) + expect(ctx.get('compact')).toBeInstanceOf(BasicCompactService) + await compactFiber.dispose() + expect(ctx.get('compact')).toBeUndefined() + await meterFiber.dispose() + expect(ctx.get('tokenMeter')).toBeUndefined() + }) + + it('removes its automatic listener with the plugin fiber', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(TokenMeterService, { + models: { [MODEL]: { contextWindow: 100, charsPerToken: 1_000 } }, + }) + const fiber = await ctx.plugin(TestCompactService, { + models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + }) + await fiber.dispose() + + const session = conversation(4) + await preStep(ctx, agent(session, MODEL)) + expect(session.events.some(event => event.type === 'compact/start')).toBe(false) + }) +}) + +describe('typed unknown-model boundary', () => { + it('uses TokenMeterError identity rather than message matching', () => { + const ctx = createContext() + let thrown: unknown + try { + ctx.tokenMeter.resolve('missing') + } catch (error: unknown) { + thrown = error + } + expect(thrown).toBeInstanceOf(TokenMeterError) + expect(thrown).toMatchObject({ code: TOKEN_METER_MODEL_UNCONFIGURED }) }) }) diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index 49fb99acec..cc1111c5f1 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -11,6 +11,7 @@ import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' +import TokenMeterService from '@deepseek-ai/dsh-token-meter' import type { SurfaceEvent } from '@deepseek-ai/dsh-session' /** @@ -20,13 +21,7 @@ import type { SurfaceEvent } from '@deepseek-ai/dsh-session' * surface-position semantics rather than raw-log scanning. */ -const TOKENS_PER_BLOCK = 10 - class ReproCompactService extends BasicCompactService { - override estimateContentTokens(blocks: readonly ContentBlock[]): number { - return blocks.length * TOKENS_PER_BLOCK - } - override async summarize(): Promise<{ summary: ContentBlock[]; model: string }> { return { summary: [{ type: 'text', text: 'CHECKPOINT SUMMARY' }], model: 'stub' } } @@ -67,6 +62,9 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) + await ctx.plugin(TokenMeterService, { + models: { mock: { contextWindow: 64, charsPerToken: 1_000 } }, + }) ctx.llm.registerAdapter(['mock'], new StepwiseToolAdapter(toolSteps)) ctx.tools.register(defineTool({ name: 'work', @@ -80,9 +78,7 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr // fires within the runaway turn. const compact = new ReproCompactService(ctx, { auto: true, - contextWindow: 64, - thresholdRatio: 0.5, - retainTokens: 20, + models: { mock: { thresholdRatio: 0.5, retainTokens: 20 } }, summarizationModel: '', maxTokens: 8192, compactionRetries: 1, diff --git a/packages/compact/compact-basic/tests/loader-composition.spec.ts b/packages/compact/compact-basic/tests/loader-composition.spec.ts new file mode 100644 index 0000000000..ff6320c05f --- /dev/null +++ b/packages/compact/compact-basic/tests/loader-composition.spec.ts @@ -0,0 +1,66 @@ +import { mkdtemp, rm, writeFile } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { pathToFileURL } from 'node:url' +import { afterEach, describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import Loader from '@cordisjs/plugin-loader' +import Include from '@cordisjs/plugin-include' +import LlmService from '@deepseek-ai/dsh-llm' +import TokenMeterService from '@deepseek-ai/dsh-token-meter' +import BasicCompactService from '@deepseek-ai/dsh-compact-basic' + +let root: string | undefined +let context: Context | undefined + +afterEach(async () => { + await context?.fiber.dispose() + context = undefined + if (root !== undefined) await rm(root, { recursive: true, force: true }) + root = undefined +}) + +describe('real Loader composition', () => { + it('loads the zero-config token-meter then compact-basic YAML pair', async () => { + root = await mkdtemp(join(tmpdir(), 'dsh-token-meter-loader-')) + const configPath = join(root, 'cordis.yml') + await writeFile(configPath, [ + "- name: '@deepseek-ai/dsh-llm'", + "- name: '@deepseek-ai/dsh-token-meter'", + "- name: '@deepseek-ai/dsh-compact-basic'", + '', + ].join('\n')) + + context = new Context() + context.baseUrl = pathToFileURL(root).href + '/' + await context.plugin(Loader) + context.loader.builtins.include = Include + const modules = new Map([ + ['@deepseek-ai/dsh-llm', LlmService], + ['@deepseek-ai/dsh-token-meter', TokenMeterService], + ['@deepseek-ai/dsh-compact-basic', BasicCompactService], + ]) + context.loader.internal = { + version: 'v2', + async import(specifier: string) { + if (!modules.has(specifier)) throw new Error(`unexpected Loader import: ${specifier}`) + return modules.get(specifier) + }, + } as unknown as NonNullable + await context.loader.create({ + name: 'cordis:include', + config: { path: pathToFileURL(configPath).href }, + }) + await context.loader.await() + + const unloaded = [...context.loader.entries()] + .filter(entry => entry.fiber === undefined && !entry.disabled) + .map(entry => entry.options.name) + expect(unloaded).toEqual([]) + expect(context.tokenMeter.resolve('deepseek-v4-flash')).toMatchObject({ + contextWindow: 128_000, + charsPerToken: 4, + }) + expect(context.get('compact')).toBeInstanceOf(BasicCompactService) + }) +}) diff --git a/packages/compact/compact-basic/tsconfig.json b/packages/compact/compact-basic/tsconfig.json index 075c64cb61..0103ad82a8 100644 --- a/packages/compact/compact-basic/tsconfig.json +++ b/packages/compact/compact-basic/tsconfig.json @@ -8,7 +8,9 @@ "references": [ { "path": "../../../vendor/cosmokit" }, { "path": "../../../vendor/cordis" }, + { "path": "../../../vendor/schemastery" }, { "path": "../../llm/llm" }, + { "path": "../../llm/token-meter" }, { "path": "../../core/session" }, { "path": "../../core/agent" }, { "path": "../compact" } diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index 5b59893561..bbaeff0b17 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -7,14 +7,14 @@ This package is the interface tier of the compaction capability, split so each c | Package | Role | |---|---| | `@deepseek-ai/dsh-compact` (this) | the interface: abstract service + `compact/*` events + `CompactionResult` + tool-pairing boundary helpers + the shared transcript renderer (`renderTranscript`/`renderContentBlocks`) | -| `@deepseek-ai/dsh-compact-basic` | a backend: chars-per-token estimation (`charsPerToken`, default 4) + token-budget retention + `llm.stream()` summarization | +| `@deepseek-ai/dsh-compact-basic` | a backend: `ctx.tokenMeter` pressure + token-budget retention + `llm.stream()` summarization | | `@deepseek-ai/dsh-tool-compact` (deferred) | the model-facing `/compact` tool over `ctx.compact` | Unlike the bash seam, this interface depends on `@deepseek-ai/dsh-session` and `@deepseek-ai/dsh-llm` — the contract's verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so they cannot be expressed without naming those packages. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). ## Service API (`ctx.compact`) -Both methods are **abstract** — the backend owns the entire strategy (token estimation, retention policy, event sequencing, summarization). +Both methods are **abstract** — the backend owns trigger policy, retention, event sequencing, and summarization. Reusable request measurement is a separate service, [`ctx.tokenMeter`](../../llm/token-meter/README.md), rather than part of this interface. | Member | Semantics | |---|---| @@ -53,7 +53,7 @@ The `compact/*` events extend `SessionEventMap` (merge-extensible) via declarati ## Implementing a backend -Subclass `CompactService`, implement `compactIfNeeded` and `compactRegion`, and load the subclass as a plugin — it registers as `ctx.compact`. A tokenizer-, template-, or model-backed implementation can live as a sibling package without changing callers. +Subclass `CompactService`, implement `compactIfNeeded` and `compactRegion`, and load the subclass as a plugin — it registers as `ctx.compact`. A template- or model-backed implementation can live as a sibling package without changing callers or the shared token meter. ## Model Experience diff --git a/packages/compact/compact/src/index.ts b/packages/compact/compact/src/index.ts index 12eb77b362..6d32ad0159 100644 --- a/packages/compact/compact/src/index.ts +++ b/packages/compact/compact/src/index.ts @@ -29,10 +29,11 @@ declare module 'cordis' { } /** - * Abstract compaction service. Implementations own token estimation, retention, - * and summarization, but a successful run must replace the selected surface span - * with one summary node and prevent concurrent compaction of the same session. - * Load one implementation per context as `ctx.compact`. + * Abstract compaction service. Implementations own trigger policy, retention, + * and summarization, and may consume a separate measurement service. A + * successful run replaces the selected surface span with one summary node and + * prevents concurrent compaction of the same session. Load one implementation + * per context as `ctx.compact`. */ export abstract class CompactService extends Service { constructor(ctx: Context) { diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 22b1d8dc79..9e726d2e3a 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -214,6 +214,13 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'async assemble(context: AssembleContext = {}): Promise', ], }, + { + key: 'tokenMeter', + summary: 'Concrete registry and replay owner for all configured model meters.', + methods: [ + 'resolve(model: string): ModelTokenMeter', + ], + }, { key: 'tools', summary: 'Tool registry and execution pipeline.', @@ -669,6 +676,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'DiffResultView', declaration: 'export interface DiffResultView {\n card: \'diff\';\n title?: string;\n diffs: FileDiff[];\n}', }, + { + name: 'EpochHeader', + declaration: 'export interface EpochHeader {\n config: LlmCallConfig;\n system?: string;\n tools?: ToolSchema[];\n messagePrefix?: Message[];\n}', + }, { name: 'FileDiff', declaration: 'export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n}', @@ -737,6 +748,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'HookContext', declaration: 'export interface HookContext {\n content: ContentBlock[];\n source: MessageSource;\n}', }, + { + name: 'LlmCallConfig', + declaration: 'export interface LlmCallConfig {\n model: string;\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n}', + }, { name: 'Message', declaration: 'export interface Message {\n role: \'system\' | \'user\' | \'assistant\';\n content: ContentBlock[];\n}', @@ -749,6 +764,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'MessageSourceMap', declaration: 'export interface MessageSourceMap {\n user: {\n kind: \'user\';\n };\n plugin: {\n kind: \'plugin\';\n plugin: string;\n };\n}', }, + { + name: 'ModelTokenMeter', + declaration: 'export interface ModelTokenMeter {\n readonly model: string;\n readonly contextWindow: number;\n readonly charsPerToken: number;\n measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement;\n measureSurface(session: Session): TokenSurfaceMeasurement;\n estimateMessage(message: Message): number;\n}', + }, { name: 'OwnerToken', declaration: 'export type OwnerToken = Branded<\'OwnerToken\'>;', @@ -941,6 +960,22 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'TodoItem', declaration: 'export interface TodoItem {\n content: string;\n status: \'pending\' | \'in_progress\' | \'completed\';\n}', }, + { + name: 'TokenMeasurement', + declaration: 'export interface TokenMeasurement {\n readonly model: string;\n readonly logRevision: number;\n readonly baseline: TokenMeasurementBaseline;\n readonly surfaceDeltaTokens: number;\n readonly totalTokens: number;\n}', + }, + { + name: 'TokenMeasurementBaseline', + declaration: 'export type TokenMeasurementBaseline = {\n readonly kind: \'none\';\n readonly tokens: 0;\n} | {\n readonly kind: \'estimated\';\n readonly tokens: number;\n} | {\n readonly kind: \'usage\';\n readonly tokens: number;\n readonly usage: Readonly;\n};', + }, + { + name: 'TokenSurfaceMeasurement', + declaration: 'export interface TokenSurfaceMeasurement {\n readonly model: string;\n readonly logRevision: number;\n readonly totalTokens: number;\n readonly nodes: readonly TokenSurfaceNode[];\n}', + }, + { + name: 'TokenSurfaceNode', + declaration: 'export interface TokenSurfaceNode {\n readonly seq: number;\n readonly tokens: number;\n}', + }, { name: 'TokenUsage', declaration: 'export interface TokenUsage {\n inputTokens: number;\n outputTokens: number;\n cacheReadTokens?: number;\n cacheWriteTokens?: number;\n reasoningTokens?: number;\n}', diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 91ed9d5049..99aef8b9cf 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -50,6 +50,8 @@ Configured agents start automatically. `cwd` applies only to fresh sessions; `re The driver owns one agent for its lifetime. It records turn, step, request, stream, and tool boundaries in the session log; live extension events coordinate policy around those durable facts. The [architecture turn flow](../../../docs/architecture.md#turn-flow) and generated [event catalog](../../../docs/cordis-catalog/events.md) are the authoritative sequence and signatures. +Every provider call that reaches a successful finish appends one `assistant/message` completion anchor after `agent/step-result`, including content-less calls and `max-tokens` finishes. The anchor records exact chunk provenance (`[]` for a stream with no chunks) and usage when available; empty content stays out of derived message history while those replay facts remain durable. + Plugin failure ends the current turn, not the loop. Cancellation clears pending work and aborts the current step without leaking to the next prompt. Terminal continuation stops remain authoritative through turn close and durability flush. ### What belongs to plugins diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 18eca40cc1..af42d8ff6a 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -528,15 +528,14 @@ async function runStep( if (assembler.finish.kind === 'max-tokens') { let message: Message = withoutToolCalls(assembler.message()) message = withoutToolCalls(await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message))) - // Preserve usage even when max-token truncation produced no content. - if (message.content.length > 0 || assembler.usage) { - // The finish chunk guarantees non-empty provenance here. - session.append( - 'assistant/message', - { turn, step, content: message.content, ...(assembler.usage ? { usage: assembler.usage } : {}) }, - { surfaceOp: 'append', sourceEventSeqs: chunkSeqs }, - ) - } + // Every successful call records its completion anchor. Empty content is + // skipped by deriveMessages(), while exact chunk provenance lets replay + // distinguish a known empty provider stream from unrecorded provenance. + session.append( + 'assistant/message', + { turn, step, content: message.content, ...(assembler.usage ? { usage: assembler.usage } : {}) }, + { surfaceOp: 'append', sourceEventSeqs: chunkSeqs }, + ) return { hadToolCalls: false, finish: assembler.finish } } @@ -544,14 +543,14 @@ async function runStep( let message: Message = assembler.message() message = await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message)) - // Empty messages exist only to carry usage; omit empty provenance. - if (message.content.length > 0 || assembler.usage) { - session.append( - 'assistant/message', - { turn, step, content: message.content, ...(assembler.usage ? { usage: assembler.usage } : {}) }, - { surfaceOp: 'append', ...(chunkSeqs.length > 0 ? { sourceEventSeqs: chunkSeqs } : {}) }, - ) - } + // Every successful call records its completion anchor. A present empty + // source set means the provider stream was known to contain no chunks; + // omission remains the conservative legacy/unrecorded representation. + session.append( + 'assistant/message', + { turn, step, content: message.content, ...(assembler.usage ? { usage: assembler.usage } : {}) }, + { surfaceOp: 'append', sourceEventSeqs: chunkSeqs }, + ) // Tool execution stays sequential; recheck abort around each normalized result. const toolCalls = message.content.filter(block => block.type === 'tool-call') diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 8130d4b893..4b2d9df1d3 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -1075,9 +1075,10 @@ describe('tool result call identity', () => { }) }) -describe('surface: assistant/message omits sourceEventSeqs when no chunks streamed', () => { - it('a step-result listener injecting content over an empty stream appends with surfaceOp but no sourceEventSeqs', async () => { - // Injected result content with no chunks must omit empty sourceEventSeqs. +describe('surface: assistant/message records exact empty provenance when no chunks streamed', () => { + it('a step-result listener injecting content over an empty stream records sourceEventSeqs []', async () => { + // The explicit empty source set distinguishes a known empty provider + // stream from legacy events whose provenance was not recorded. const adapter = new MockAdapter([[]]) const ctx = await harness(adapter) await ctx.plugin(Invariants) @@ -1094,7 +1095,7 @@ describe('surface: assistant/message omits sourceEventSeqs when no chunks stream const recorded = agent.session.events.find(e => e.type === 'assistant/message')! expect(recorded.type).toBe('assistant/message') expect(recorded.surfaceOp).toBe('append') - expect(recorded.sourceEventSeqs).toBeUndefined() + expect(recorded.sourceEventSeqs).toEqual([]) // The injected content reaches derived history. expect(JSON.stringify(agent.session.deriveMessages())).toContain('injected') }) diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index fb686928b1..f282301a2b 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -717,10 +717,9 @@ describe('agent loop', () => { }) }) - it('appends no assistant/message for a max-tokens step with empty content and no usage', async () => { - // A max-tokens step truncated to a dropped tool call AND with no usage chunk has nothing to - // record: empty content and no accounting → no assistant/message (the empty-content host - // exists only to carry usage). + it('appends an empty completion anchor for a max-tokens step with no usage', async () => { + // The truncated tool call is dropped from durable content, while the + // successful provider call still needs an exact replay anchor. const callId = CallId('c1') const adapter = new MockAdapter([[ { type: 'block-start', index: 0, blockType: 'tool-call' }, @@ -744,14 +743,19 @@ describe('agent loop', () => { await waitForIdle(ctx, agent) expect(reasons).toEqual([{ kind: 'max-tokens' }]) - expect(agent.session.events.some(e => e.type === 'assistant/message')).toBe(false) + const assistant = agent.session.events.find(e => e.type === 'assistant/message')! + expect(assistant.type === 'assistant/message' && assistant.data).toEqual({ + turn: 1, + step: 1, + content: [], + }) + expect(assistant.sourceEventSeqs?.length).toBeGreaterThan(0) expect(agent.session.deriveMessages()).toEqual([{ role: 'user', content: [{ type: 'text', text: 'go' }] }]) }) - it('appends no assistant/message for a normal stop finish with empty content and no usage', async () => { - // A clean `stop` finish that streamed nothing assembled (no blocks) and - // carried no usage chunk has nothing to record: the content-or-usage guard - // on the normal step path suppresses a pure trace-only empty assistant/message. + it('appends an empty completion anchor for a normal stop with no usage', async () => { + // A clean content-less call stays absent from derived messages but remains + // a durable successful-call boundary for replay consumers. const adapter = new MockAdapter([[{ type: 'finish', reason: { kind: 'stop' } }]]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) @@ -763,7 +767,13 @@ describe('agent loop', () => { await waitForIdle(ctx, agent) expect(reasons).toEqual([{ kind: 'completed' }]) - expect(agent.session.events.some(e => e.type === 'assistant/message')).toBe(false) + const assistant = agent.session.events.find(e => e.type === 'assistant/message')! + expect(assistant.type === 'assistant/message' && assistant.data).toEqual({ + turn: 1, + step: 1, + content: [], + }) + expect(assistant.sourceEventSeqs?.length).toBe(1) expect(agent.session.deriveMessages()).toEqual([{ role: 'user', content: [{ type: 'text', text: 'go' }] }]) }) diff --git a/packages/core/session/README.md b/packages/core/session/README.md index 2540f988c7..3a079fe860 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -66,7 +66,7 @@ Also defines `TurnTriggerMap` and `TurnEndReasonMap` (merge-extensible sum types Every `SessionEvent` carries two optional top-level fields (structural metadata): -- `sourceEventSeqs?: number[]` — seq numbers of provenance sources (e.g., the `assistant/chunk` seqs behind an `assistant/message`, or the shadowed nodes behind a compaction replace node). +- `sourceEventSeqs?: number[]` — seq numbers of provenance sources (e.g., the `assistant/chunk` seqs behind an `assistant/message`, or the shadowed nodes behind a compaction replace node). On `assistant/message`, a present `[]` records a known empty provider stream, while omission means legacy or otherwise unrecorded provenance; other surface events require a non-empty list when this field is present. - `surfaceOp?: SurfaceOp` — how this event entered the surface. Absent for non-surface events (boundaries, chunks, usage, errors). ### Metadata types (`types.ts`) diff --git a/packages/core/session/src/types.ts b/packages/core/session/src/types.ts index f4f42062fd..da31751f95 100644 --- a/packages/core/session/src/types.ts +++ b/packages/core/session/src/types.ts @@ -331,6 +331,12 @@ export type SurfaceOp = */ export interface SurfaceIntent { surfaceOp: SurfaceOp + /** + * Complete known provenance source set. `assistant/message` may use a + * present empty array for a known empty provider stream; omission means its + * provenance was not recorded. Other surface events require a non-empty set + * when this field is present. + */ sourceEventSeqs?: number[] } @@ -359,7 +365,9 @@ export type SessionEvent = { /** * Seq numbers of events that are provenance sources of this event * (e.g. the `assistant/chunk` seqs that built an `assistant/message`, - * or the surface nodes shadowed by a compaction replace node). + * or the surface nodes shadowed by a compaction replace node). An + * `assistant/message` may carry a present empty array for a known empty + * provider stream; omission means unrecorded provenance. */ sourceEventSeqs?: number[] /** How this event entered the surface; absent for non-surface events. */ diff --git a/packages/llm/README.md b/packages/llm/README.md index 3fc5c9cf9e..f4d9dd82cb 100644 --- a/packages/llm/README.md +++ b/packages/llm/README.md @@ -5,7 +5,8 @@ The LLM seam and its provider adapters. The interface package (`llm`) owns the a | Package | Role | ctx key | |---|---|---| | `llm/` | Abstract LLM service + content-block vocabulary + chunk assembler | `ctx.llm` | +| `token-meter/` | Replay-aware, per-model request and surface token measurement | `ctx.tokenMeter` | | `llm-deepseek/` | DeepSeek API adapter (hand-rolled fetch/SSE) | (registers on `ctx.llm`) | | `llm-pi-ai/` | DeepSeek adapter via `@earendil-works/pi-ai` (design twin) | (registers on `ctx.llm`) | -The interface lives at `llm/llm/`; adapters are flat siblings under the group. A new provider adapter joins here and registers on `ctx.llm` without touching the interface. See [twin LLM adapters](../../docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md) for why two adapters exist. +The interface lives at `llm/llm/`; adapters and the reusable token meter are flat siblings under the group. A new provider adapter joins here and registers on `ctx.llm` without touching the interface. See [twin LLM adapters](../../docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md) for why two adapters exist and the [replay token meter RFC](../../docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md) for measurement ownership. diff --git a/packages/llm/token-meter/README.md b/packages/llm/token-meter/README.md new file mode 100644 index 0000000000..e50ee84b3b --- /dev/null +++ b/packages/llm/token-meter/README.md @@ -0,0 +1,57 @@ +# @deepseek-ai/dsh-token-meter + +Replay-aware token measurement through `ctx.tokenMeter`. The service binds one stable meter to each configured model and advances isolated per-model/per-session folds from the durable session log. Compaction consumes it today; other pressure-sensitive plugins can reuse the same accounting without depending on `CompactService`. + +## Profiles and configuration + +The built-in `deepseek-v4-flash` and `deepseek-v4-pro` profiles each use a 128,000-token context window and four characters per estimated token. `models` merges overrides field-by-field, so changing only density keeps the built-in window. A custom model requires `contextWindow`; its `charsPerToken` defaults to `4`. + +| Key | Default | Contract | +|---|---:|---| +| `models..contextWindow` | `128000` | Positive integer provider capacity. | +| `models..charsPerToken` | `4` | Positive finite heuristic density. | + +Resolving an unknown model throws `TokenMeterError` with code `TOKEN_METER_MODEL_UNCONFIGURED` and preserves the exact model name. Direct-construction profile validation uses `TOKEN_METER_INVALID_CONFIG`; Loader mounts first apply the package's Schemastery shape validation. There is no universal fallback window. + +## Measurement contract + +`ctx.tokenMeter.resolve(model)` returns a `ModelTokenMeter` with three operations: + +- `measure(session, requestHeader?)` returns scalar request pressure at one consumed-log revision. +- `measureSurface(session)` returns current surface nodes and their per-node prices at the same kind of revision. +- `estimateMessage(message)` prices one detached message under that profile. + +Measurements are detached and deeply immutable. A caller that needs a consistent scalar/surface decision compares their `logRevision` values instead of copying the full history on every read. + +The fold tracks request headers and deltas, step boundaries, surface appends and replacements, successful assistant messages, provider usage, and assistant-chunk provenance. Provider usage is reused only when the handle's model and the canonical request envelope match the successful-call anchor. Otherwise the complete current envelope and surface are repriced under the requested model. Surface changes remain signed relative to a matching anchor, including negative deltas after shrinking replacements. + +Usage accounting sums disjoint input, cache-read, cache-write, and output buckets; reasoning is not added again. Every successful call records an assistant anchor, including content-less calls. An explicit empty provenance list means a known empty provider stream, while absent legacy provenance conservatively treats the durable assistant output as provider output. + +## Composition + +```yaml +- name: '@deepseek-ai/dsh-token-meter' +- name: '@deepseek-ai/dsh-compact-basic' +``` + +Both plugins have usable defaults for the bundled DeepSeek profiles. Custom deployments can override only the fields that differ: + +```yaml +- name: '@deepseek-ai/dsh-token-meter' + config: + models: + deepseek-v4-flash: + charsPerToken: 2 + local-model: + contextWindow: 32768 +``` + +## Model Experience + +Indirectly, through consumers such as `dsh-compact-basic`; the service itself adds no prompt, message, schema, tool, or model call. + +## Known Limitations and Deferred Work + +- **Heuristic density still needs maintenance** — message content without provider usage is priced by configured character density plus structural overhead, not an exact provider tokenizer. CJK-heavy or provider-specific formats may need profile overrides. +- **Provider usage is only reusable for an identical canonical envelope** — prompt, prefix, tools, or call-config changes deliberately fall back to full heuristic repricing. +- **Legacy provenance is conservative** — assistant messages without `sourceEventSeqs` cannot distinguish provider output from listener rewrites, so the fold avoids claiming a known empty or exact chunk stream. diff --git a/packages/llm/token-meter/package.json b/packages/llm/token-meter/package.json new file mode 100644 index 0000000000..30031b0b2e --- /dev/null +++ b/packages/llm/token-meter/package.json @@ -0,0 +1,37 @@ +{ + "name": "@deepseek-ai/dsh-token-meter", + "description": "Replay-aware per-model token measurement service (ctx.tokenMeter) for the DeepSeek Harness", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", + "cordis": "^4.0.0-rc.7" + }, + "dependencies": { + "schemastery": "^3.18.0" + }, + "devDependencies": { + "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", + "cordis": "^4.0.0-rc.7" + } +} diff --git a/packages/llm/token-meter/src/index.ts b/packages/llm/token-meter/src/index.ts new file mode 100644 index 0000000000..19d700ac96 --- /dev/null +++ b/packages/llm/token-meter/src/index.ts @@ -0,0 +1,193 @@ +/** + * Replay token-meter service with model-specific context capacity and pricing. + * + * @module @deepseek-ai/dsh-token-meter + */ + +import { Context, Service } from 'cordis' +import z from 'schemastery' +import { HarnessError, deepFreeze } from '@deepseek-ai/dsh-llm' +import type { Session } from '@deepseek-ai/dsh-session' +import { ReplayModelTokenMeter } from './replay.ts' +import type { ModelTokenProfile } from './replay.ts' +import type { + ModelTokenMeter, + ModelTokenMeterConfig, + TokenMeterConfig, +} from './types.ts' + +export type * from './types.ts' + +/** Exact error code for resolving a model without a configured profile. */ +export const TOKEN_METER_MODEL_UNCONFIGURED = 'TOKEN_METER_MODEL_UNCONFIGURED' + +/** Exact error code for invalid token-meter configuration. */ +export const TOKEN_METER_INVALID_CONFIG = 'TOKEN_METER_INVALID_CONFIG' + +/** Closed machine-routable token-meter failure taxonomy. */ +export type TokenMeterErrorCode = + | typeof TOKEN_METER_MODEL_UNCONFIGURED + | typeof TOKEN_METER_INVALID_CONFIG + +/** Built-in DeepSeek model profiles available with zero configuration. */ +const BUILTIN_TOKEN_PROFILES: Readonly>> = deepFreeze({ + 'deepseek-v4-flash': { + model: 'deepseek-v4-flash', + contextWindow: 128_000, + charsPerToken: 4, + }, + 'deepseek-v4-pro': { + model: 'deepseek-v4-pro', + contextWindow: 128_000, + charsPerToken: 4, + }, +}) + +/** Typed token-meter failure with the affected model preserved for callers. */ +export class TokenMeterError extends HarnessError { + declare readonly code: TokenMeterErrorCode + /** Exact model name involved in this error, when applicable. */ + readonly model: string | undefined + + constructor(message: string, code: TokenMeterErrorCode, model?: string, options?: ErrorOptions) { + super(message, code, options) + this.name = 'TokenMeterError' + this.model = model + } +} + +declare module 'cordis' { + interface Context { + tokenMeter: TokenMeterService + } +} + +/** Validate and detach all configured model profiles. */ +function resolveProfiles(config: TokenMeterConfig): readonly ModelTokenProfile[] { + const profiles = new Map() + for (const profile of Object.values(BUILTIN_TOKEN_PROFILES)) { + profiles.set(profile.model, { ...profile }) + } + + const configuredValue: unknown = config.models + const configuredModels = configuredValue === undefined ? {} : configuredValue + if (typeof configuredModels !== 'object' + || configuredModels === null + || Array.isArray(configuredModels)) { + throw new TokenMeterError( + 'TokenMeterConfig: models must be an object', + TOKEN_METER_INVALID_CONFIG, + ) + } + + for (const [model, override] of Object.entries(configuredModels as Record)) { + if (model.length === 0) { + throw new TokenMeterError( + 'TokenMeterConfig: model names must not be empty', + TOKEN_METER_INVALID_CONFIG, + model, + ) + } + assertProfileObject(model, override) + const builtIn = profiles.get(model) + const contextWindow = override.contextWindow ?? builtIn?.contextWindow + const charsPerToken = override.charsPerToken ?? builtIn?.charsPerToken ?? 4 + if (contextWindow === undefined) { + throw new TokenMeterError( + `TokenMeterConfig: custom model "${model}" requires contextWindow`, + TOKEN_METER_INVALID_CONFIG, + model, + ) + } + assertPositiveInteger(model, 'contextWindow', contextWindow) + assertPositiveFinite(model, 'charsPerToken', charsPerToken) + profiles.set(model, { model, contextWindow, charsPerToken }) + } + + for (const profile of profiles.values()) { + assertPositiveInteger(profile.model, 'contextWindow', profile.contextWindow) + assertPositiveFinite(profile.model, 'charsPerToken', profile.charsPerToken) + } + return deepFreeze([...profiles.values()].map(profile => ({ ...profile }))) +} + +function assertProfileObject(model: string, value: unknown): asserts value is ModelTokenMeterConfig { + if (typeof value !== 'object' || value === null || Array.isArray(value)) { + throw new TokenMeterError( + `TokenMeterConfig: profile "${model}" must be an object`, + TOKEN_METER_INVALID_CONFIG, + model, + ) + } +} + +function assertPositiveInteger(model: string, name: string, value: number): void { + if (!Number.isInteger(value) || value <= 0) { + throw new TokenMeterError( + `TokenMeterConfig: ${model}.${name} (${value}) must be a positive integer`, + TOKEN_METER_INVALID_CONFIG, + model, + ) + } +} + +function assertPositiveFinite(model: string, name: string, value: number): void { + if (typeof value !== 'number' || !Number.isFinite(value) || value <= 0) { + throw new TokenMeterError( + `TokenMeterConfig: ${model}.${name} (${value}) must be a positive finite number`, + TOKEN_METER_INVALID_CONFIG, + model, + ) + } +} + +/** Concrete registry and replay owner for all configured model meters. */ +export class TokenMeterService extends Service { + static Config: z = z.object({ + models: z.dict(z.object({ + contextWindow: z.number(), + charsPerToken: z.number(), + })), + }) + + private readonly meters = new Map() + + constructor(ctx: Context, config: TokenMeterConfig = {}) { + super(ctx, 'tokenMeter') + for (const profile of resolveProfiles(config)) { + this.meters.set(profile.model, new ReplayModelTokenMeter(profile)) + } + + // Readers catch up independently, while eager observation bounds ordinary + // read latency. A reader in an earlier listener consumes the new event; + // this listener then sees the same revision and performs no duplicate fold. + ctx.on('session/event', (session) => { + this._observe(session) + }) + } + + /** + * Resolve one stable model-bound replay handle. + * @param model - exact routed model name. + * @throws {@link TokenMeterError} with `TOKEN_METER_MODEL_UNCONFIGURED` when no profile exists. + * @returns the configured handle for this model. + */ + resolve(model: string): ModelTokenMeter { + const meter = this.meters.get(model) + if (meter === undefined) { + throw new TokenMeterError( + `token meter has no profile for model "${model}"`, + TOKEN_METER_MODEL_UNCONFIGURED, + model, + ) + } + return meter + } + + /** Advance every configured model's isolated replay fold. */ + private _observe(session: Session): void { + for (const meter of this.meters.values()) meter.observeIfActive(session) + } +} + +export default TokenMeterService diff --git a/packages/llm/token-meter/src/replay.ts b/packages/llm/token-meter/src/replay.ts new file mode 100644 index 0000000000..8b4af52dc5 --- /dev/null +++ b/packages/llm/token-meter/src/replay.ts @@ -0,0 +1,367 @@ +/** + * Model-bound transactional replay of request headers, surface mutations, and + * successful-call token anchors. + * + * @module @deepseek-ai/dsh-token-meter/replay + */ + +import { BlockAssembler, deepFreeze } from '@deepseek-ai/dsh-llm' +import type { ContentBlock, Message, TokenUsage } from '@deepseek-ai/dsh-llm' +import type { EpochHeader, Session, SessionEvent, SurfaceEvent } from '@deepseek-ai/dsh-session' +import { applyHeaderDelta, canonicalHeader, headerEquals, isSurfaceEvent } from '@deepseek-ai/dsh-session' +import type { + ModelTokenMeter, + TokenMeasurement, + TokenMeasurementBaseline, + TokenSurfaceMeasurement, + TokenSurfaceNode, +} from './types.ts' + +/** Internal validated pricing profile. */ +export interface ModelTokenProfile { + readonly model: string + readonly contextWindow: number + readonly charsPerToken: number +} + +/** Per-block structural overhead for JSON framing and type tags. */ +const BLOCK_OVERHEAD = 4 + +/** Role-field framing overhead added to every priced message. */ +const ROLE_OVERHEAD = 4 + +interface UsageAnchor { + readonly header: EpochHeader + readonly surfaceTokens: number + readonly baseline: Exclude +} + +interface ReplayState { + consumedEvents: number + header: EpochHeader | undefined + surface: TokenSurfaceNode[] + surfaceTokens: number + stepStart: { turn: number; step: number; surfaceTokens: number } | undefined + anchor: UsageAnchor | undefined +} + +interface PreparedSurfaceMutation { + readonly tokens: number + commit(state: ReplayState): void +} + +/** Sum disjoint provider usage buckets without double-counting reasoning output. */ +function usageTokens(usage: TokenUsage): number { + return usage.inputTokens + + (usage.cacheReadTokens ?? 0) + + (usage.cacheWriteTokens ?? 0) + + usage.outputTokens +} + +/** One configured model's replay fold, weakly isolated by session identity. */ +export class ReplayModelTokenMeter implements ModelTokenMeter { + readonly model: string + readonly contextWindow: number + readonly charsPerToken: number + + private readonly states = new WeakMap() + + constructor(profile: ModelTokenProfile) { + this.model = profile.model + this.contextWindow = profile.contextWindow + this.charsPerToken = profile.charsPerToken + } + + /** + * Advance an already-read model/session fold without creating unused state. + * @param session - session whose durable tail advanced. + */ + observeIfActive(session: Session): void { + if (this.states.has(session)) this._sync(session) + } + + /** @inheritdoc */ + estimateMessage(message: Message): number { + return this._estimateContent(message.content) + ROLE_OVERHEAD + } + + /** @inheritdoc */ + measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement { + const state = this._sync(session) + const header = requestHeader === undefined + ? state.header + : canonicalHeader(requestHeader) + const anchor = state.anchor + + let baseline: TokenMeasurementBaseline + let surfaceDeltaTokens: number + if (anchor !== undefined && header !== undefined && headerEquals(anchor.header, header)) { + baseline = anchor.baseline + surfaceDeltaTokens = state.surfaceTokens - anchor.surfaceTokens + } else if (header === undefined && state.surfaceTokens === 0) { + baseline = { kind: 'none', tokens: 0 } + surfaceDeltaTokens = 0 + } else { + baseline = { + kind: 'estimated', + tokens: this._estimateHeader(header) + state.surfaceTokens, + } + surfaceDeltaTokens = 0 + } + + return deepFreeze(structuredClone({ + model: this.model, + logRevision: state.consumedEvents, + baseline, + surfaceDeltaTokens, + totalTokens: Math.max(0, baseline.tokens + surfaceDeltaTokens), + })) + } + + /** @inheritdoc */ + measureSurface(session: Session): TokenSurfaceMeasurement { + const state = this._sync(session) + return deepFreeze(structuredClone({ + model: this.model, + logRevision: state.consumedEvents, + totalTokens: state.surfaceTokens, + nodes: state.surface, + })) + } + + /** Catch one session's fold up to the current durable tail. */ + private _sync(session: Session): ReplayState { + let state = this.states.get(session) + if (state === undefined) { + state = { + consumedEvents: 0, + header: undefined, + surface: [], + surfaceTokens: 0, + stepStart: undefined, + anchor: undefined, + } + this.states.set(session, state) + } + + while (state.consumedEvents < session.events.length) { + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- contiguous session seqs index the durable log + const event = session.events[state.consumedEvents]! + this._foldEvent(session, state, event) + state.consumedEvents += 1 + } + return state + } + + /** + * Validate and prepare every fallible part before mutating replay state. + * A malformed event therefore remains the next unread event on every retry + * instead of applying a partial surface mutation twice. + */ + private _foldEvent(session: Session, state: ReplayState, event: SessionEvent): void { + let nextHeader = state.header + let nextStepStart = state.stepStart + let nextAnchor = state.anchor + + switch (event.type) { + case 'request/header': + nextHeader = canonicalHeader(event.data.header) + break + case 'request/header-delta': + if (state.header === undefined) { + throw new Error(`token meter: request/header-delta at seq ${event.seq} has no preceding header`) + } + nextHeader = applyHeaderDelta(state.header, event.data) + break + case 'step/start': + if (state.stepStart !== undefined) { + throw new Error( + `token meter: step/start at seq ${event.seq} arrived before turn ${state.stepStart.turn}/step ${state.stepStart.step} ended`, + ) + } + nextStepStart = { ...event.data, surfaceTokens: state.surfaceTokens } + break + case 'step/end': + if (state.stepStart === undefined + || state.stepStart.turn !== event.data.turn + || state.stepStart.step !== event.data.step) { + throw new Error(`token meter: step/end at seq ${event.seq} has no matching step/start boundary`) + } + nextStepStart = undefined + break + default: + break + } + + const surface = isSurfaceEvent(event) + ? this._prepareSurfaceMutation(session, state, event) + : undefined + + if (event.type === 'assistant/message' && nextHeader?.config.model === this.model) { + const stepStart = state.stepStart + if (stepStart === undefined + || stepStart.turn !== event.data.turn + || stepStart.step !== event.data.step) { + throw new Error(`token meter: assistant/message at seq ${event.seq} has no matching step/start boundary`) + } + + // assistant/message is surface-mandatory at every append/seed boundary. + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + const eventTokens = surface!.tokens + if (event.data.usage !== undefined) { + const providerAssistantTokens = this._estimateProviderAssistant( + session, + event, + eventTokens, + ) + nextAnchor = { + header: nextHeader, + surfaceTokens: stepStart.surfaceTokens + providerAssistantTokens, + baseline: { + kind: 'usage', + tokens: usageTokens(event.data.usage), + usage: event.data.usage, + }, + } + } else { + const anchorSurfaceTokens = stepStart.surfaceTokens + eventTokens + nextAnchor = { + header: nextHeader, + surfaceTokens: anchorSurfaceTokens, + baseline: { + kind: 'estimated', + tokens: this._estimateHeader(nextHeader) + anchorSurfaceTokens, + }, + } + } + } + + state.header = nextHeader + state.stepStart = nextStepStart + if (surface !== undefined) surface.commit(state) + state.anchor = nextAnchor + } + + /** Validate one surface operation and return its allocation-light commit. */ + private _prepareSurfaceMutation( + session: Session, + state: ReplayState, + event: SurfaceEvent, + ): PreparedSurfaceMutation { + const tokens = this._estimateSurfaceEvent(session, event) + const op = event.surfaceOp + if (op === 'append') { + return { + tokens, + commit(target) { + target.surface.push({ seq: event.seq, tokens }) + target.surfaceTokens += tokens + }, + } + } + + const startIdx = state.surface.findIndex(node => node.seq === op.start) + const endIdx = state.surface.findIndex(node => node.seq === op.end) + if (startIdx === -1 || endIdx === -1 || startIdx > endIdx) { + throw new Error( + `token meter: replace at seq ${event.seq} has invalid current range ${op.start}-${op.end}`, + ) + } + const removedTokens = state.surface + .slice(startIdx, endIdx + 1) + .reduce((total, node) => total + node.tokens, 0) + return { + tokens, + commit(target) { + target.surface.splice(startIdx, endIdx - startIdx + 1, { seq: event.seq, tokens }) + target.surfaceTokens += tokens - removedTokens + }, + } + } + + /** Price one current surface event exactly as it projects to a request. */ + private _estimateSurfaceEvent(session: Session, event: SurfaceEvent): number { + const message = session.deriveEventMessage(event) + return message === null ? 0 : this.estimateMessage(message) + } + + /** + * Reassemble provider output from exact chunk provenance for a usage anchor. + * Missing legacy provenance conservatively treats the durable output as the + * provider output; explicit empty provenance prices a known empty stream. + */ + private _estimateProviderAssistant( + session: Session, + event: SessionEvent<'assistant/message'>, + durableEventTokens: number, + ): number { + const sourceSeqs = event.sourceEventSeqs + if (sourceSeqs === undefined) return durableEventTokens + + const assembler = new BlockAssembler() + const seen = new Set() + for (const seq of sourceSeqs) { + if (seq >= event.seq) { + throw new Error(`token meter: assistant/message at seq ${event.seq} source seq ${seq} is not earlier`) + } + if (seen.has(seq)) { + throw new Error(`token meter: assistant/message at seq ${event.seq} repeats source seq ${seq}`) + } + seen.add(seq) + // Session construction validates contiguous seqs, and the explicit + // earlier-than-assistant check above therefore guarantees existence. + const source = session.events[seq] + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + const sourceEvent = source! + if (sourceEvent.type !== 'assistant/chunk') { + throw new Error(`token meter: assistant/message at seq ${event.seq} source seq ${seq} is not assistant/chunk`) + } + if (sourceEvent.data.turn !== event.data.turn || sourceEvent.data.step !== event.data.step) { + throw new Error(`token meter: assistant/message at seq ${event.seq} source seq ${seq} belongs to another step`) + } + assembler.push(sourceEvent.data.chunk) + } + const providerMessage = assembler.message() + return providerMessage.content.length === 0 ? 0 : this.estimateMessage(providerMessage) + } + + /** Price content blocks recursively under this model's density profile. */ + private _estimateContent(blocks: readonly ContentBlock[]): number { + let tokens = 0 + for (const block of blocks) { + switch (block.type) { + case 'text': + case 'reasoning': + tokens += Math.ceil(block.text.length / this.charsPerToken) + BLOCK_OVERHEAD + break + case 'tool-call': + tokens += Math.ceil(block.name.length / this.charsPerToken) + + Math.ceil(block.arguments.length / this.charsPerToken) + + BLOCK_OVERHEAD + break + case 'tool-result': + tokens += this._estimateContent(block.content) + BLOCK_OVERHEAD + break + default: + // ContentBlockMap is merge-extensible; unknown blocks retain a + // conservative structural JSON price under the selected profile. + tokens += BLOCK_OVERHEAD + Math.ceil(JSON.stringify(block).length / this.charsPerToken) + } + } + return tokens + } + + /** Price the canonical non-surface request envelope. */ + private _estimateHeader(header: EpochHeader | undefined): number { + if (header === undefined) return 0 + let tokens = 0 + for (const message of header.messagePrefix ?? []) tokens += this.estimateMessage(message) + if (header.system !== undefined) { + tokens += Math.ceil(header.system.length / this.charsPerToken) + ROLE_OVERHEAD + } + if (header.tools !== undefined && header.tools.length > 0) { + tokens += Math.ceil(JSON.stringify(header.tools).length / this.charsPerToken) + BLOCK_OVERHEAD + } + return tokens + } +} diff --git a/packages/llm/token-meter/src/types.ts b/packages/llm/token-meter/src/types.ts new file mode 100644 index 0000000000..e9b7e812c1 --- /dev/null +++ b/packages/llm/token-meter/src/types.ts @@ -0,0 +1,101 @@ +/** + * Public configuration and measurement vocabulary for replay token metering. + * + * @module @deepseek-ai/dsh-token-meter/types + */ + +import type { Message, TokenUsage } from '@deepseek-ai/dsh-llm' +import type { EpochHeader, Session } from '@deepseek-ai/dsh-session' + +/** Optional pricing fields for one configured model. */ +export interface ModelTokenMeterConfig { + /** Provider context-window capacity in tokens. Required for a custom model. */ + contextWindow?: number + /** Heuristic text density in characters per token. Defaults to `4`. */ + charsPerToken?: number +} + +/** Token-meter plugin configuration. */ +export interface TokenMeterConfig { + /** Built-in field overrides and custom model profiles, keyed by routed model name. */ + models?: Record +} + +/** The baseline from which a signed surface delta produces current pressure. */ +export type TokenMeasurementBaseline = + | { readonly kind: 'none'; readonly tokens: 0 } + | { readonly kind: 'estimated'; readonly tokens: number } + | { readonly kind: 'usage'; readonly tokens: number; readonly usage: Readonly } + +/** Detached immutable scalar pressure at one consumed session-log revision. */ +export interface TokenMeasurement { + /** Model profile used for every heuristic component. */ + readonly model: string + /** Number of durable events consumed; equal to the next unread event seq. */ + readonly logRevision: number + /** Provider or heuristic anchor used for this measurement. */ + readonly baseline: TokenMeasurementBaseline + /** Signed repricing of current surface content relative to the baseline anchor. */ + readonly surfaceDeltaTokens: number + /** Non-negative current request-and-response pressure. */ + readonly totalTokens: number +} + +/** One token-priced node in the current ordered session surface. */ +export interface TokenSurfaceNode { + /** Durable sequence number of the surface event. */ + readonly seq: number + /** Heuristic tokens for the exact message projected by this node. */ + readonly tokens: number +} + +/** Detached immutable priced surface at one consumed session-log revision. */ +export interface TokenSurfaceMeasurement { + /** Model profile used to price every node. */ + readonly model: string + /** Number of durable events consumed; equal to the next unread event seq. */ + readonly logRevision: number + /** Total heuristic tokens across the current surface. */ + readonly totalTokens: number + /** Current surface nodes in positional head-to-tail order. */ + readonly nodes: readonly TokenSurfaceNode[] +} + +/** A model-bound replay meter returned by {@link TokenMeterService.resolve}. */ +export interface ModelTokenMeter { + /** Routed model name bound to this handle. */ + readonly model: string + /** Provider context-window capacity in tokens. */ + readonly contextWindow: number + /** Heuristic text density in characters per token. */ + readonly charsPerToken: number + + /** + * Measure current request pressure through the session's durable tail. + * + * Provider usage is reused only when its routed model and canonical request + * envelope match `requestHeader`; otherwise the complete envelope and + * surface are heuristically repriced for this handle's model. + * + * @param session - session to replay through its current durable tail. + * @param requestHeader - optional effective request envelope replacing the latest logged header. + * @returns a detached deeply immutable pressure measurement. + */ + measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement + + /** + * Price the current surface for retention and replacement decisions. + * + * @param session - session to replay through its current durable tail. + * @returns a detached deeply immutable positional surface measurement. + */ + measureSurface(session: Session): TokenSurfaceMeasurement + + /** + * Heuristically price one model-visible message. + * + * @param message - message to price without mutation. + * @returns content and role-framing tokens under this model profile. + */ + estimateMessage(message: Message): number +} diff --git a/packages/llm/token-meter/tests/token-meter.spec.ts b/packages/llm/token-meter/tests/token-meter.spec.ts new file mode 100644 index 0000000000..1012d5c15e --- /dev/null +++ b/packages/llm/token-meter/tests/token-meter.spec.ts @@ -0,0 +1,603 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import { CallId } from '@deepseek-ai/dsh-llm' +import type { ContentBlock, Message, TokenUsage } from '@deepseek-ai/dsh-llm' +import SessionStore, { Session, SessionId, canonicalHeader } from '@deepseek-ai/dsh-session' +import type { EpochHeader } from '@deepseek-ai/dsh-session' +import TokenMeterService, { + TOKEN_METER_INVALID_CONFIG, + TOKEN_METER_MODEL_UNCONFIGURED, + TokenMeterError, +} from '@deepseek-ai/dsh-token-meter' +import type { ModelTokenMeter, TokenMeterConfig } from '@deepseek-ai/dsh-token-meter' + +function header(model: string, extras: Omit = {}): EpochHeader { + return canonicalHeader({ config: { model }, ...extras }) +} + +function textMessage(text: string, role: Message['role'] = 'user'): Message { + return { role, content: [{ type: 'text', text }] } +} + +function appendHeader(session: Session, value: EpochHeader): void { + session.append('request/header', { header: value, reason: 'initial' }) +} + +interface SuccessfulCallOptions { + turn?: number + step?: number + providerText?: string + durableText?: string + usage?: TokenUsage + provenance?: 'exact' | 'empty' | 'absent' +} + +function appendSuccessfulCall( + session: Session, + value: EpochHeader, + options: SuccessfulCallOptions = {}, +): void { + const turn = options.turn ?? 1 + const step = options.step ?? 1 + const providerText = options.providerText ?? 'provider answer' + const durableText = options.durableText ?? providerText + const provenance = options.provenance ?? 'exact' + session.append('step/start', { turn, step }) + appendHeader(session, value) + + const sources: number[] = [] + if (provenance === 'exact') { + const chunks = [ + { type: 'block-start' as const, index: 0, blockType: 'text' as const }, + { type: 'text-delta' as const, index: 0, text: providerText }, + { type: 'block-end' as const, index: 0, block: { type: 'text' as const, text: providerText } }, + ...options.usage === undefined ? [] : [{ type: 'usage' as const, usage: options.usage }], + { type: 'finish' as const, reason: { kind: 'stop' as const } }, + ] + for (const chunk of chunks) { + sources.push(session.append('assistant/chunk', { turn, step, chunk }).seq) + } + } + + const intent = provenance === 'absent' + ? { surfaceOp: 'append' as const } + : { surfaceOp: 'append' as const, sourceEventSeqs: provenance === 'empty' ? [] : sources } + session.append('assistant/message', { + turn, + step, + content: durableText.length === 0 ? [] : [{ type: 'text', text: durableText }], + ...options.usage === undefined ? {} : { usage: options.usage }, + }, intent) + session.append('step/end', { turn, step }) +} + +function meter(config: TokenMeterConfig = {}): TokenMeterService { + return new TokenMeterService(new Context(), config) +} + +describe('TokenMeterService configuration and registration', () => { + it('provides immutable zero-config DeepSeek profiles', () => { + const service = meter() + expect(service.resolve('deepseek-v4-flash')).toMatchObject({ + model: 'deepseek-v4-flash', + contextWindow: 128_000, + charsPerToken: 4, + }) + expect(service.resolve('deepseek-v4-pro')).toMatchObject({ + model: 'deepseek-v4-pro', + contextWindow: 128_000, + charsPerToken: 4, + }) + }) + + it('merges built-in overrides field-wise and defaults custom density', () => { + const service = meter({ + models: { + 'deepseek-v4-flash': { charsPerToken: 2 }, + custom: { contextWindow: 32_000 }, + }, + }) + expect(service.resolve('deepseek-v4-flash')).toMatchObject({ contextWindow: 128_000, charsPerToken: 2 }) + expect(service.resolve('deepseek-v4-pro')).toMatchObject({ contextWindow: 128_000, charsPerToken: 4 }) + expect(service.resolve('custom')).toMatchObject({ contextWindow: 32_000, charsPerToken: 4 }) + }) + + it('throws a typed exact-code error for unknown models', () => { + const service = meter() + let thrown: unknown + try { + service.resolve('unconfigured-model') + } catch (error: unknown) { + thrown = error + } + expect(thrown).toBeInstanceOf(TokenMeterError) + expect(thrown).toMatchObject({ + code: TOKEN_METER_MODEL_UNCONFIGURED, + model: 'unconfigured-model', + }) + expect((thrown as Error).message).toContain('unconfigured-model') + }) + + it.each([ + [{ models: null }, /models must be an object/], + [{ models: [] }, /models must be an object/], + [{ models: { custom: {} } }, /requires contextWindow/], + [{ models: { '': { contextWindow: 1 } } }, /must not be empty/], + [{ models: { custom: { contextWindow: 0 } } }, /positive integer/], + [{ models: { custom: { contextWindow: 1.5 } } }, /positive integer/], + [{ models: { custom: { contextWindow: 1, charsPerToken: 0 } } }, /positive finite/], + [{ models: { custom: { contextWindow: 1, charsPerToken: Number.NaN } } }, /positive finite/], + [{ models: { custom: null } }, /must be an object/], + [{ models: { custom: [] } }, /must be an object/], + ] as unknown as Array<[TokenMeterConfig, RegExp]>)('rejects invalid profile config %#', (config, pattern) => { + let thrown: unknown + try { + meter(config) + } catch (error: unknown) { + thrown = error + } + expect(thrown).toBeInstanceOf(TokenMeterError) + expect(thrown).toMatchObject({ code: TOKEN_METER_INVALID_CONFIG }) + expect((thrown as Error).message).toMatch(pattern) + }) + + it('registers and unregisters ctx.tokenMeter with its plugin fiber', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + const fiber = await ctx.plugin(TokenMeterService) + expect(ctx.get('tokenMeter')).toBeInstanceOf(TokenMeterService) + await fiber.dispose() + expect(ctx.get('tokenMeter')).toBeUndefined() + }) +}) + +describe('ModelTokenMeter pricing', () => { + it('prices every built-in content shape and merge-extended blocks', () => { + const handle = meter({ models: { custom: { contextWindow: 100, charsPerToken: 2 } } }).resolve('custom') + const blocks: ContentBlock[] = [ + { type: 'text', text: 'abcd' }, + { type: 'reasoning', text: 'ab' }, + { type: 'tool-call', id: CallId('c'), name: 'read', arguments: '{"x":1}' }, + { + type: 'tool-result', + toolCallId: CallId('c'), + content: [{ type: 'text', text: 'xy' }], + isError: false, + }, + { type: 'future-block', payload: 'abcd' } as unknown as ContentBlock, + ] + const estimated = handle.estimateMessage({ role: 'assistant', content: blocks }) + expect(estimated).toBeGreaterThan(30) + expect(handle.estimateMessage(textMessage('abcd'))).toBe(10) + }) + + it('returns a detached deeply immutable empty measurement', () => { + const handle = meter().resolve('deepseek-v4-flash') + const session = new Session(SessionId('empty')) + const result = handle.measure(session) + expect(result).toEqual({ + model: 'deepseek-v4-flash', + logRevision: 0, + baseline: { kind: 'none', tokens: 0 }, + surfaceDeltaTokens: 0, + totalTokens: 0, + }) + expect(Object.isFrozen(result)).toBe(true) + expect(Object.isFrozen(result.baseline)).toBe(true) + expect(() => { + ;(result as { totalTokens: number }).totalTokens = 1 + }).toThrow(TypeError) + }) + + it('keeps earlier scalar and surface snapshots detached from later replay', () => { + const handle = meter().resolve('deepseek-v4-flash') + const session = new Session(SessionId('detached')) + session.append('user/message', { + content: [{ type: 'text', text: 'first' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + const scalar = handle.measure(session) + const surface = handle.measureSurface(session) + const scalarCopy = structuredClone(scalar) + const surfaceCopy = structuredClone(surface) + + session.append('user/message', { + content: [{ type: 'text', text: 'second' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + expect(handle.measure(session).logRevision).toBe(2) + expect(handle.measureSurface(session).nodes).toHaveLength(2) + expect(scalar).toEqual(scalarCopy) + expect(surface).toEqual(surfaceCopy) + expect(scalar.logRevision).toBe(1) + expect(surface.nodes).toHaveLength(1) + }) + + it('prices header, prefix, tools, and surface when no reusable usage exists', () => { + const handle = meter().resolve('deepseek-v4-flash') + const session = new Session(SessionId('heuristic')) + session.append('user/message', { + content: [{ type: 'text', text: 'question' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + appendHeader(session, header('deepseek-v4-flash', { + system: 'system', + messagePrefix: [textMessage('prefix')], + tools: [{ name: 'read', description: 'read', parameters: { type: 'object' } }], + })) + const result = handle.measure(session) + expect(result.baseline.kind).toBe('estimated') + expect(result.totalTokens).toBeGreaterThan(handle.measureSurface(session).totalTokens) + expect(result.logRevision).toBe(session.events.length) + }) +}) + +describe('replay anchors and surface folds', () => { + const USAGE: TokenUsage = { + inputTokens: 20, + cacheReadTokens: 3, + cacheWriteTokens: 4, + outputTokens: 7, + reasoningTokens: 6, + } + + it('uses disjoint provider usage and signed durable-output rewrites', () => { + const handle = meter().resolve('deepseek-v4-flash') + const session = new Session(SessionId('usage')) + session.append('user/message', { + content: [{ type: 'text', text: 'before' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + appendSuccessfulCall(session, header('deepseek-v4-flash'), { + providerText: 'short', + durableText: 'a much longer rewritten durable assistant answer', + usage: USAGE, + }) + const result = handle.measure(session) + expect(result.baseline).toMatchObject({ kind: 'usage', tokens: 34, usage: USAGE }) + expect(result.surfaceDeltaTokens).toBeGreaterThan(0) + expect(result.totalTokens).toBe(34 + result.surfaceDeltaTokens) + expect(() => { + ;((result.baseline as { usage: { inputTokens: number } }).usage.inputTokens) = 1 + }).toThrow(TypeError) + }) + + it('uses an estimated anchor when provider usage is absent', () => { + const handle = meter().resolve('deepseek-v4-flash') + const session = new Session(SessionId('missing-usage')) + appendSuccessfulCall(session, header('deepseek-v4-flash', { system: 's' }), { + providerText: 'provider', + durableText: 'rewritten', + }) + const anchored = handle.measure(session) + expect(anchored.baseline.kind).toBe('estimated') + expect(anchored.surfaceDeltaTokens).toBe(0) + session.append('user/message', { + content: [{ type: 'text', text: 'later' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + const advanced = handle.measure(session) + expect(advanced.surfaceDeltaTokens).toBeGreaterThan(0) + }) + + it('distinguishes explicit empty provenance from absent legacy provenance', () => { + const explicit = new Session(SessionId('explicit-empty')) + const legacy = new Session(SessionId('legacy-absent')) + appendSuccessfulCall(explicit, header('deepseek-v4-flash'), { + durableText: 'listener injected text', + providerText: '', + usage: USAGE, + provenance: 'empty', + }) + appendSuccessfulCall(legacy, header('deepseek-v4-flash'), { + durableText: 'listener injected text', + providerText: '', + usage: USAGE, + provenance: 'absent', + }) + const handle = meter().resolve('deepseek-v4-flash') + expect(handle.measure(explicit).surfaceDeltaTokens).toBeGreaterThan(0) + expect(handle.measure(legacy).surfaceDeltaTokens).toBe(0) + }) + + it('preserves one model anchor across another model success and reuses it after switching back', () => { + const service = meter({ + models: { + alpha: { contextWindow: 1000 }, + beta: { contextWindow: 1000, charsPerToken: 2 }, + }, + }) + const alpha = service.resolve('alpha') + const beta = service.resolve('beta') + const session = new Session(SessionId('switch')) + const alphaHeader = header('alpha', { system: 'same envelope' }) + appendSuccessfulCall(session, alphaHeader, { usage: USAGE, providerText: 'alpha' }) + expect(alpha.measure(session).baseline.kind).toBe('usage') + + appendSuccessfulCall(session, header('beta'), { + turn: 1, + step: 2, + usage: { inputTokens: 100, outputTokens: 50 }, + providerText: 'beta response', + }) + expect(alpha.measure(session).baseline.kind).toBe('estimated') + expect(beta.measure(session).baseline).toMatchObject({ kind: 'usage', tokens: 150 }) + + appendHeader(session, alphaHeader) + const switchedBack = alpha.measure(session) + expect(switchedBack.baseline).toMatchObject({ kind: 'usage', tokens: 34 }) + expect(switchedBack.surfaceDeltaTokens).toBeGreaterThan(0) + }) + + it('invalidates usage for any canonical envelope change or explicit override', () => { + const handle = meter().resolve('deepseek-v4-flash') + const session = new Session(SessionId('envelope')) + const anchoredHeader = header('deepseek-v4-flash', { system: 'one' }) + appendSuccessfulCall(session, anchoredHeader, { usage: USAGE }) + expect(handle.measure(session, { ...anchoredHeader, tools: [] }).baseline.kind).toBe('usage') + expect(handle.measure(session, header('deepseek-v4-flash', { system: 'two' })).baseline.kind) + .toBe('estimated') + expect(handle.measure(session, header('deepseek-v4-pro', { system: 'one' })).baseline.kind) + .toBe('estimated') + expect(handle.measure(session, { + ...anchoredHeader, + config: { ...anchoredHeader.config, temperature: 0.2 }, + }).baseline.kind).toBe('estimated') + expect(handle.measure(session, { + ...anchoredHeader, + messagePrefix: [textMessage('prefix')], + }).baseline.kind).toBe('estimated') + expect(handle.measure(session, { + ...anchoredHeader, + tools: [{ name: 'read', description: 'read', parameters: { type: 'object' } }], + }).baseline.kind).toBe('estimated') + }) + + it('folds valid header deltas into the effective envelope', () => { + const session = new Session(SessionId('header-delta')) + appendHeader(session, header('deepseek-v4-flash')) + session.append('request/header-delta', { config: { model: 'deepseek-v4-pro' } }) + const result = meter().resolve('deepseek-v4-flash').measure(session) + expect(result.baseline.kind).toBe('estimated') + expect(result.logRevision).toBe(2) + }) + + it('replays seeded append and replace operations with signed deltas', () => { + const service = meter() + const original = new Session(SessionId('surface-original')) + appendSuccessfulCall(original, header('deepseek-v4-flash'), { + usage: USAGE, + providerText: 'long provider answer '.repeat(100), + }) + original.append('user/message', { + content: [{ type: 'text', text: 'new tail' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + const seeded = new Session(SessionId('surface-seeded'), original.events) + const handle = service.resolve('deepseek-v4-flash') + const before = handle.measureSurface(seeded) + const beforeScalar = handle.measure(seeded) + expect(before.nodes).toHaveLength(2) + expect(beforeScalar.surfaceDeltaTokens).toBeGreaterThan(0) + + const first = seeded.surface.nodes[0]!.seq + seeded.append('user/message', { + content: [{ type: 'text', text: 'replacement' }], + source: { kind: 'plugin', plugin: 'test' }, + }, { surfaceOp: { op: 'replace', start: first, end: first }, sourceEventSeqs: [first] }) + const after = handle.measureSurface(seeded) + const afterScalar = handle.measure(seeded) + expect(after.nodes).toHaveLength(2) + expect(after.nodes[0]!.seq).toBe(seeded.events.length - 1) + expect(after.logRevision).toBe(seeded.events.length) + expect(Object.isFrozen(after.nodes)).toBe(true) + expect(Object.isFrozen(after.nodes[0])).toBe(true) + expect(afterScalar.surfaceDeltaTokens).toBeLessThan(0) + expect(before.nodes).toHaveLength(2) + expect(before.logRevision).toBe(original.events.length) + expect(beforeScalar.surfaceDeltaTokens).toBeGreaterThan(0) + }) + + it('prices an empty assistant surface anchor as zero', () => { + const session = new Session(SessionId('empty-assistant')) + appendSuccessfulCall(session, header('deepseek-v4-flash'), { + providerText: '', + durableText: '', + provenance: 'empty', + }) + const surface = meter().resolve('deepseek-v4-flash').measureSurface(session) + const assistant = session.events.find(event => event.type === 'assistant/message')! + expect(surface.nodes).toEqual([{ seq: assistant.seq, tokens: 0 }]) + expect(surface.totalTokens).toBe(0) + }) +}) + +describe('malformed replay and listener lifecycle', () => { + function expectRepeatedFailure(handle: ModelTokenMeter, session: Session, pattern: RegExp): void { + expect(() => handle.measure(session)).toThrow(pattern) + expect(() => handle.measure(session)).toThrow(pattern) + } + + it('rejects a header delta before any snapshot transactionally', () => { + const session = new Session(SessionId('bad-delta')) + session.append('request/header-delta', { config: { model: 'deepseek-v4-flash' } }) + expectRepeatedFailure(meter().resolve('deepseek-v4-flash'), session, /no preceding header/) + }) + + it('rejects a matching-model assistant without its step boundary transactionally', () => { + const session = new Session(SessionId('bad-step')) + appendHeader(session, header('deepseek-v4-flash')) + session.append('assistant/message', { + turn: 1, + step: 1, + content: [{ type: 'text', text: 'bad' }], + }, { surfaceOp: 'append', sourceEventSeqs: [] }) + expectRepeatedFailure(meter().resolve('deepseek-v4-flash'), session, /no matching step\/start/) + }) + + it('clears completed step boundaries and rejects overlapping or late step events', () => { + const overlapping = new Session(SessionId('overlapping-step')) + overlapping.append('step/start', { turn: 1, step: 1 }) + overlapping.append('step/start', { turn: 1, step: 2 }) + expectRepeatedFailure( + meter().resolve('deepseek-v4-flash'), + overlapping, + /arrived before turn 1\/step 1 ended/, + ) + + const late = new Session(SessionId('late-assistant')) + late.append('step/start', { turn: 1, step: 1 }) + appendHeader(late, header('deepseek-v4-flash')) + late.append('step/end', { turn: 1, step: 1 }) + late.append('assistant/message', { + turn: 1, + step: 1, + content: [], + }, { surfaceOp: 'append', sourceEventSeqs: [] }) + expectRepeatedFailure( + meter().resolve('deepseek-v4-flash'), + late, + /no matching step\/start/, + ) + + const mismatchedEnd = new Session(SessionId('mismatched-end')) + mismatchedEnd.append('step/start', { turn: 1, step: 1 }) + mismatchedEnd.append('step/end', { turn: 1, step: 2 }) + expectRepeatedFailure( + meter().resolve('deepseek-v4-flash'), + mismatchedEnd, + /step\/end .* no matching step\/start/, + ) + }) + + it('rejects invalid assistant provenance', () => { + const cases: Array<{ + name: string + appendSource(session: Session): number[] + pattern: RegExp + }> = [ + { + name: 'non-chunk', + appendSource(session) { + return [session.append('user/message', { + content: [{ type: 'text', text: 'x' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }).seq] + }, + pattern: /is not assistant\/chunk/, + }, + { + name: 'wrong-step', + appendSource(session) { + return [session.append('assistant/chunk', { + turn: 1, + step: 2, + chunk: { type: 'finish', reason: { kind: 'stop' } }, + }).seq] + }, + pattern: /belongs to another step/, + }, + ] + for (const testCase of cases) { + const session = new Session(SessionId(`bad-source-${testCase.name}`)) + session.append('step/start', { turn: 1, step: 1 }) + appendHeader(session, header('deepseek-v4-flash')) + const sourceEventSeqs = testCase.appendSource(session) + session.append('assistant/message', { + turn: 1, + step: 1, + content: [{ type: 'text', text: 'bad' }], + usage: { inputTokens: 1, outputTokens: 1 }, + }, { surfaceOp: 'append', sourceEventSeqs }) + expect(() => meter().resolve('deepseek-v4-flash').measure(session)).toThrow(testCase.pattern) + } + }) + + it('rejects repeated and non-earlier assistant provenance', () => { + const duplicate = new Session(SessionId('duplicate-source')) + duplicate.append('step/start', { turn: 1, step: 1 }) + appendHeader(duplicate, header('deepseek-v4-flash')) + const source = duplicate.append('assistant/chunk', { + turn: 1, + step: 1, + chunk: { type: 'finish', reason: { kind: 'stop' } }, + }).seq + duplicate.append('assistant/message', { + turn: 1, + step: 1, + content: [], + usage: { inputTokens: 1, outputTokens: 0 }, + }, { surfaceOp: 'append', sourceEventSeqs: [source, source] }) + expect(() => meter().resolve('deepseek-v4-flash').measure(duplicate)).toThrow(/repeats source seq/) + + const future = new Session(SessionId('future-source')) + future.append('step/start', { turn: 1, step: 1 }) + appendHeader(future, header('deepseek-v4-flash')) + future.append('assistant/message', { + turn: 1, + step: 1, + content: [], + usage: { inputTokens: 1, outputTokens: 0 }, + }, { surfaceOp: 'append', sourceEventSeqs: [99] }) + expect(() => meter().resolve('deepseek-v4-flash').measure(future)).toThrow(/is not earlier/) + }) + + it('does not partially apply a malformed assistant replacement', () => { + const session = new Session(SessionId('transactional-replace')) + session.append('user/message', { + content: [{ type: 'text', text: 'head' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + appendHeader(session, header('deepseek-v4-flash')) + const head = session.events[0]!.seq + session.append('assistant/message', { + turn: 1, + step: 1, + content: [{ type: 'text', text: 'replacement' }], + }, { surfaceOp: { op: 'replace', start: head, end: head }, sourceEventSeqs: [head] }) + expectRepeatedFailure( + meter().resolve('deepseek-v4-flash'), + session, + /no matching step\/start/, + ) + }) + + it('rejects corrupt replacement ranges without advancing the replay cursor', () => { + const session = new Session(SessionId('bad-replace')) + session.append('user/message', { + content: [{ type: 'text', text: 'head' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + session.append('user/message', { + content: [{ type: 'text', text: 'bad' }], + source: { kind: 'user' }, + }, { surfaceOp: { op: 'replace', start: 99, end: 99 }, sourceEventSeqs: [0] }) + expectRepeatedFailure(meter().resolve('deepseek-v4-flash'), session, /invalid current range/) + }) + + it('handles earlier-reader catch-up, eager observation, and service reload', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + let handle: ModelTokenMeter | undefined + const revisions: number[] = [] + ctx.on('session/event', (session) => { + if (handle !== undefined) revisions.push(handle.measure(session).logRevision) + }) + const firstFiber = await ctx.plugin(TokenMeterService) + handle = ctx.tokenMeter.resolve('deepseek-v4-flash') + const session = ctx.sessions.create(SessionId('listener-order')) + handle.measure(session) + session.append('user/message', { + content: [{ type: 'text', text: 'one' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + expect(revisions).toEqual([1]) + expect(handle.measure(session).logRevision).toBe(1) + + await firstFiber.dispose() + const secondFiber = await ctx.plugin(TokenMeterService) + handle = ctx.tokenMeter.resolve('deepseek-v4-flash') + expect(handle.measure(session).logRevision).toBe(1) + await secondFiber.dispose() + }) +}) diff --git a/packages/llm/token-meter/tsconfig.json b/packages/llm/token-meter/tsconfig.json new file mode 100644 index 0000000000..5e1604e02f --- /dev/null +++ b/packages/llm/token-meter/tsconfig.json @@ -0,0 +1,27 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../../vendor/cosmokit" + }, + { + "path": "../../../vendor/cordis" + }, + { + "path": "../../../vendor/schemastery" + }, + { + "path": "../../llm/llm" + }, + { + "path": "../../core/session" + } + ] +} diff --git a/packages/support/invariants/README.md b/packages/support/invariants/README.md index 54fb26b333..49974c94dd 100644 --- a/packages/support/invariants/README.md +++ b/packages/support/invariants/README.md @@ -32,6 +32,7 @@ Session log (per session): - **steps nest in turns** — `step/start` opens a step in the open turn; `step/end` closes the matching step. - **chunks belong to an open step** — `step/start` precedes its `assistant/chunk`s. - **a `tool/result` needs a prior `tool/call`** — but NOT the converse: a `tool/call` may have no result (a thrown tool-execution pipeline step ends the turn with no `tool/result`, which is legal). +- **provenance sources are valid and unambiguous** — `sourceEventSeqs` contains unique earlier known seqs; only `assistant/message` may carry an explicit empty list, which denotes a known empty provider stream rather than absent legacy provenance. Agent status (per agent): diff --git a/packages/support/invariants/src/index.ts b/packages/support/invariants/src/index.ts index 8da5429b06..7e39564227 100644 --- a/packages/support/invariants/src/index.ts +++ b/packages/support/invariants/src/index.ts @@ -118,8 +118,8 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr } } if (se.sourceEventSeqs !== undefined) { - if (se.sourceEventSeqs.length === 0) { - throw new InvariantError('sourceEventSeqs must not be empty when present') + if (se.sourceEventSeqs.length === 0 && event.type !== 'assistant/message') { + throw new InvariantError('sourceEventSeqs must not be empty except on assistant/message') } const unique = new Set(se.sourceEventSeqs) if (unique.size !== se.sourceEventSeqs.length) { diff --git a/packages/support/invariants/tests/invariants.spec.ts b/packages/support/invariants/tests/invariants.spec.ts index 0212501114..ce535262ba 100644 --- a/packages/support/invariants/tests/invariants.spec.ts +++ b/packages/support/invariants/tests/invariants.spec.ts @@ -487,13 +487,17 @@ describe('surface invariants', () => { // no throw — well-formed replace op }) - it('rejects empty sourceEventSeqs', async () => { + it('accepts known-empty assistant provenance and rejects empty provenance elsewhere', async () => { const { ctx } = await setup() const session = ctx.sessions.create() session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + session.append('step/start', { turn: 1, step: 1 }) expect(() => { session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [] }) - }).toThrow(InvariantError) + }).not.toThrow() + expect(() => { + session.append('user/message', { content: [], source: { kind: 'user' } }, { surfaceOp: 'append', sourceEventSeqs: [] }) + }).toThrow(/must not be empty except on assistant\/message/) }) it('rejects duplicate sourceEventSeqs', async () => { diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index b40b8e69db..46bf3eba6f 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -217,7 +217,17 @@ importers: version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) packages/compact/compact-basic: + dependencies: + schemastery: + specifier: ^3.18.0 + version: 3.18.0 devDependencies: + '@cordisjs/plugin-include': + specifier: workspace:^ + version: link:../../../vendor/include + '@cordisjs/plugin-loader': + specifier: workspace:^ + version: link:../../../vendor/loader '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent @@ -239,12 +249,15 @@ importers: '@deepseek-ai/dsh-system-prompt': specifier: workspace:^ version: link:../../core/system-prompt + '@deepseek-ai/dsh-token-meter': + specifier: workspace:^ + version: link:../../llm/token-meter '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools cordis: specifier: ^4.0.0-rc.7 - version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) + version: 4.0.0-rc.7(@cordisjs/plugin-include@vendor+include)(@cordisjs/plugin-loader@vendor+loader) packages/context/time-context: dependencies: @@ -724,6 +737,22 @@ importers: specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) + packages/llm/token-meter: + dependencies: + schemastery: + specifier: ^3.18.0 + version: 3.18.0 + devDependencies: + '@deepseek-ai/dsh-llm': + specifier: workspace:^ + version: link:../llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + cordis: + specifier: ^4.0.0-rc.7 + version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) + packages/sandbox/sandbox: devDependencies: '@deepseek-ai/dsh-llm': @@ -1856,6 +1885,9 @@ importers: '@deepseek-ai/dsh-timeout-policy': specifier: workspace:^ version: link:../../packages/timeout/timeout-policy + '@deepseek-ai/dsh-token-meter': + specifier: workspace:^ + version: link:../../packages/llm/token-meter '@deepseek-ai/dsh-tool-ask-user': specifier: workspace:^ version: link:../../packages/ui/tool-ask-user diff --git a/python/sdk-runtime/package.json b/python/sdk-runtime/package.json index cff5eda404..049db0f57c 100644 --- a/python/sdk-runtime/package.json +++ b/python/sdk-runtime/package.json @@ -30,6 +30,7 @@ "@deepseek-ai/dsh-jsonrpc": "workspace:^", "@deepseek-ai/dsh-jsonrpc-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-token-meter": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", "@deepseek-ai/dsh-llm-pi-ai": "workspace:^", "@deepseek-ai/dsh-permission": "workspace:^", diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index a6660f7cd3..71fe28fbe0 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -84,6 +84,14 @@ const SERVICE_ROLES: ServiceRole[] = [ consumers: ['agent-loop', 'compact-basic'], note: 'Adapters register provider implementations; the loop and compaction call the provider-neutral stream service.', }, + { + key: 'tokenMeter', + pkg: 'token-meter', + title: 'Replay token measurement', + mode: 'core', + consumers: ['compact-basic'], + note: 'Owns isolated per-model/session replay folds; pressure consumers share immutable revisioned measurements.', + }, { key: 'sessions', pkg: 'session', @@ -823,6 +831,8 @@ function renderLifecycle(): string { ` Driver-->>SDK: ${mermaidCode('agent/status')} idle`, '```', '', + 'The `assistant/message` edge records every successful provider call, including content-less and `max-tokens` finishes. Empty content stays out of derived history while the durable anchor retains usage and exact chunk provenance, including an explicit empty source set.', + '', 'SDK users that need replayable transcript data should consume `session/event`; `agent/*` is the live coordination surface for queue/status, prompt interception, request shaping, steering, continuation, and errors.', '', ...maintenanceFooter(maintenance), diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index 7b83f1004e..75f0e9bf12 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -30,6 +30,10 @@ { "doc": "docs/core-data-structures/llm-streaming.md", "symbol": "ContentBlockMap", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/llm-streaming.md", "symbol": "AppIdentity", "source": "packages/llm/llm/src/attribution.ts" }, + { "doc": "docs/core-data-structures/token-meter.md", "symbol": "TokenMeasurement", "source": "packages/llm/token-meter/src/types.ts" }, + { "doc": "docs/core-data-structures/token-meter.md", "symbol": "TokenSurfaceNode", "source": "packages/llm/token-meter/src/types.ts" }, + { "doc": "docs/core-data-structures/token-meter.md", "symbol": "TokenSurfaceMeasurement", "source": "packages/llm/token-meter/src/types.ts" }, + { "doc": "docs/core-data-structures/session.md", "symbol": "SessionEventMap", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "EpochHeader", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "TodoItem", "source": "packages/core/session/src/types.ts" }, diff --git a/scripts/verify-package-readme-model-experience.ts b/scripts/verify-package-readme-model-experience.ts index dc8d11a6c2..d4e5e00608 100644 --- a/scripts/verify-package-readme-model-experience.ts +++ b/scripts/verify-package-readme-model-experience.ts @@ -47,6 +47,7 @@ const SENTENCE_MODEL_EXPERIENCE: Readonly> = { 'packages/fs/fs-local': { kind: 'indirect', reason: 'The provider backend delegates model rendering to dsh-tool-fs.' }, 'packages/hooks/hook-protocol': { kind: 'indirect', reason: 'Only the hook bridge plugins render decoded hook output to a model.' }, 'packages/llm/llm': { kind: 'none', reason: 'The adapter registry forwards already-assembled requests unchanged.' }, + 'packages/llm/token-meter': { kind: 'indirect', reason: 'The measurement service leaves model-visible changes to its consumers.' }, 'packages/sandbox/sandbox-local': { kind: 'indirect', reason: 'The provider backend delegates model rendering to dsh-bash-sandbox and dsh-tool-bash.' }, 'packages/session-query/session-query': { kind: 'none', reason: 'The trusted query service exposes cloned records only to callers and registers no model surface.' }, 'packages/skill/skill': { kind: 'indirect', reason: 'The provider registry delegates model rendering to dsh-tool-skill.' }, diff --git a/tsconfig.build.json b/tsconfig.build.json index 591955b260..fc5bbf9a5f 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -13,6 +13,7 @@ { "path": "./packages/util/brand" }, { "path": "./packages/util/timeout" }, { "path": "./packages/llm/llm" }, + { "path": "./packages/llm/token-meter" }, { "path": "./packages/core/session" }, { "path": "./packages/core/scope" }, { "path": "./packages/session-persistence/session-persistence" }, diff --git a/tsconfig.json b/tsconfig.json index e97a8295a5..b79d0e338c 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -24,6 +24,7 @@ { "path": "./packages/util/brand" }, { "path": "./packages/util/timeout" }, { "path": "./packages/llm/llm" }, + { "path": "./packages/llm/token-meter" }, { "path": "./packages/core/session" }, { "path": "./packages/core/scope" }, { "path": "./packages/session-persistence/session-persistence" }, From 649865043db86045ece6d586f2b0cdb9c2c13268 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 14:59:20 +0800 Subject: [PATCH 139/359] docs: preserve prose cleanup in session simplification --- docs/cordis-catalog/events.md | 54 +- docs/core-data-structures/core.md | 19 +- docs/event-producer-consumer.md | 26 +- docs/persistence-catalog.md | 36 +- .../2026-07-05-reconstructable-requests.md | 2 +- .../2026-06-18-compaction-capability-seam.md | 14 +- .../feature/2026-07-06-explicit-tool-order.md | 6 +- .../implemented/feature/2026-07-06-sandbox.md | 45 +- packages/compact/compact-basic/src/index.ts | 201 +------ .../compact-basic/tests/compact-basic.spec.ts | 86 +-- packages/core/agent-loop/src/loop.ts | 481 +++-------------- packages/core/agent-loop/src/request-log.ts | 24 +- packages/core/agent/src/types.ts | 494 +++--------------- packages/core/session/README.md | 2 +- packages/core/session/src/tool-pairing.ts | 71 +-- packages/core/session/src/types.ts | 168 ++---- .../core/session/tests/tool-pairing.spec.ts | 43 +- packages/llm/llm/src/call-config.ts | 27 +- packages/support/acp-snapshot/src/suite.ts | 118 +---- 19 files changed, 377 insertions(+), 1540 deletions(-) diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 4e77ab89e2..aa87ea66d7 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -15,7 +15,7 @@ Dispatch modes: **emit** (fire-and-forget), **waterfall** (each listener gets `n ### `agent/created` — emit -An agent's fully composed scoped world was published in the AgentRegistry. Its session is already live in the session store. Setup is composition-only by contract; the subsequent `agent/session-start` boundary is the first supported place to inject or queue startup work. A synchronous listener throw vetoes publication and rollback emits the matching disposal edges; returned-promise rejection is observed and logged but cannot retroactively veto this synchronous boundary. A synchronous listener that requests the advanced registry detach does not remove the entry immediately: removal and the paired `agent/disposed` edge wait until the creation dispatch unwinds, so no later creation listener observes a disposal that preceded its own creation callback. +A fully configured agent and live session were published. Setup is composition-only; `agent/session-start` is the first startup-driving seam. Synchronous listener failure vetoes publication, while returned-promise rejection is reported. Detach requested during dispatch waits until every creation listener has observed the stable entry. ```ts cordis-catalog 'agent/created'(this: Scoped, agent: Agent): void @@ -23,11 +23,11 @@ An agent's fully composed scoped world was published in the AgentRegistry. Its s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:316`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:139`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit -An agent was removed from the registry. The concrete AgentLoop lifecycle emits this only after its driver and any in-flight turn reach quiescence; a custom agent registered through the public registry owns its own driver contract, which the registry cannot infer. Ordered teardown may still be detaching the session and unwinding scoped registrations when this runs. +An agent left the registry; AgentLoop emits this after driver quiescence but before session detachment and scoped-registration unwind. Custom registry users own their driver-ordering contract. ```ts cordis-catalog 'agent/disposed'(this: Scoped, agent: Agent): void @@ -35,7 +35,7 @@ An agent was removed from the registry. The concrete AgentLoop lifecycle emits t Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:331`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:148`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -47,13 +47,11 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:605`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:283`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial -Awaited pre-step surface-mutation checkpoint, fired once per step AFTER `turn/start` (and after the prior step closed) but BEFORE this step's `step/start` — so anything a listener appends lands OUTSIDE the step, between `turn/start`/`step/end` and the upcoming `step/start`. `step` is the number of the step about to start. The loop awaits `ctx.serial('agent/pre-step', …)` after assembling the system prompt, then opens the step and derives the request history ONCE from whatever the surface now holds. This is where compaction belongs: it mutates the session surface in place (shadowing an older range with a summary node) with its log-only `compact/*` records cleanly outside any step, and the single subsequent derive reflects the mutation — so there is no double-derive and no listener can see (or be expected to act on) an assembled `messages` array that does not exist yet. - -Serial (awaited in registration order), not a waterfall: a listener mutates the surface as a side effect; there is nothing to transform, but the loop must wait for the mutation to complete before opening the step and deriving. Cordis `serial` bails early if a listener returns a bail value; this event is typed and documented as `void`, so listeners must not return a semantic veto value. `fullSystemPrompt` is the assembled prompt a listener needs to measure pressure (the system prompt counts toward the budget), and `sessionPrefix` is the instance's composed agent/session-prefix product for the same reason — every request carries it in front of the derived history, and it is composed BEFORE this seam fires precisely so a pressure gate counts the prefix the request will actually send (never a stale logged one). `signal` cancels any in-flight work a listener starts (e.g. a summarization model call). Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered through `agent.ctx` fires only for that agent's dispatches; a listener on a plain plugin context fires for every agent. The dispatch `this` is the scope carrier (`Scoped`), built by the emitting side via `scopeTarget`/`agentEvents`. +Awaited serial checkpoint for session-surface mutation after prompt assembly and before `step/start`; appends land outside the pending step. The loop derives history once afterward, so compaction records and replacements are included without rewriting an assembled request. The prompt and prefix are the exact pressure inputs for that request, and `signal` cancels listener work. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. ```ts cordis-catalog 'agent/pre-step'(this: Scoped, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void @@ -61,11 +59,11 @@ Serial (awaited in registration order), not a waterfall: a listener mutates the Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:438`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:202`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall -Waterfall: decide what happens to ONE drained queued message before it becomes a `user/message` — allow (optionally rewriting the prompt bytes or attaching `additionalContext`) or block it. Fires inside the already-open turn, per drained message. Maps onto Claude Code's `UserPromptSubmit` hook. Call `next()` to delegate to the default (allow unchanged), or return a PromptDecision without calling `next()` to short-circuit. +Allow, rewrite, or block one drained prompt before it becomes a user message. Call `next()` for the unchanged default. ```ts cordis-catalog 'agent/prompt-submit'(this: Scoped, agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise): Promise @@ -73,11 +71,11 @@ Waterfall: decide what happens to ONE drained queued message before it becomes a Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:456`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:212`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit -A message entered the agent's inbox (queued or steering). Content and the resolved source are the detached, deeply-frozen values retained by the inbox. `source` has defaults applied and is not the caller's raw options. +Detached, frozen content entered the agent's inbox. Source defaults have already been applied, so these are the exact values retained for the log. ```ts cordis-catalog 'agent/queued'(this: Scoped, agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void @@ -85,11 +83,11 @@ A message entered the agent's inbox (queued or steering). Content and the resolv Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:360`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:167`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall -Waterfall: shape the step's call configuration — model switching, sampling overrides — by returning a replacement LlmCallConfig (the frozen seed is the config the loop would otherwise use). Config is ALL a listener shapes here: every request is a pure function of the session log (the reconstructability RFC), so model-visible content flows through the log channels — `inject()`, steering, prompt-submit `additionalContext`, prompt sections via `system-prompt/assemble`, or the header-logged session prefix via agent/session-prefix — never through request mutation, and the loop records whatever config the request actually uses as a `request/header` event before dispatch. The step's messages are already snapshotted when this fires (the `step/start` boundary): an `inject()` from a listener here lands in the log but joins the NEXT request. For surface mutation that must precede the snapshot (compaction), use agent/pre-step. Call `next()` to delegate, or return an LlmCallConfig without it to short-circuit. +Replace the frozen call configuration. Model-visible content must use logged channels; this seam cannot mutate messages. Injection here joins the next request because the current step boundary is already fixed. ```ts cordis-catalog 'agent/request'(this: Scoped, agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise): Promise @@ -97,15 +95,11 @@ Waterfall: shape the step's call configuration — model switching, sampling ove Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:485`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:224`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall -Waterfall: compose the SESSION PREFIX — request-only messages placed in front of the ENTIRE derived history (directly after the provider's system slot) on every request this loop instance sends. Fired ONCE per loop instance, lazily before its first step's agent/pre-step seam — BEFORE the pre-step so a token-pressure gate (compaction) counts the prefix this instance will actually send, never a previous instance's logged one. The composed result is deep-frozen, recorded as `EpochHeader.messagePrefix` on the instance's anchoring `'initial'`/`'resume'` header snapshot, and reused verbatim for every subsequent request — never recomputed mid-session, so the provider prefix cache holds by construction (a process restart or `ctx.agents.resume()` is a new instance: it recomposes, and any drift lands attributably on the `'resume'` snapshot). Composition runs outside the step, before the boundary snapshot: a composing listener's session append joins the CURRENT request's derived history. A composition interrupted by a cancel/dispose landing inside the waterfall is discarded — never cached, logged, or sent — and the next turn recomposes under a live signal, so an abort-aware listener's degraded fallback cannot leak into later requests. - -This is the home for session-stable openers the model must always see but that must NOT become durable history — a skills catalog, an AGENTS.md digest, a workspace baseline: `Session.deriveMessages()` never returns the prefix, and the header events are its only durable record, so the request stays reconstructable from the log. Content that CHANGES mid-session belongs in the append-only history channels instead — `agent.inject()`, a `tools/post-execute` decision's `additionalContext`, prompt-submit `additionalContext` — each a durable `context/message` paid once and prefix-cached thereafter. - -The seed is a frozen empty list; a contributing listener returns a NEW array — never an in-place push. The canonical contribution is a PREPEND, `[mine, ...await next()]`: the waterfall unwinds innermost-first (the LAST-registered listener's `next()` resolves first), so prepending yields registration order on the wire, and every plugin using it composes deterministically. The append form `[...await next(), mine]` is legal but places a contribution AFTER every later-registered plugin's — reverse registration order when all contributors append. Call `next()` to delegate, or return a list without it to short-circuit. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered through `agent.ctx` fires only for that agent's dispatches; a listener on a plain plugin context fires for every agent. The dispatch `this` is the scope carrier (`Scoped`), built by the emitting side via `scopeTarget`/`agentEvents`. +Compose request-only messages placed before derived history. The frozen result is computed once per loop instance, logged on its anchoring request header, and reused so the provider prefix remains stable. Interrupted composition is discarded. Composition precedes the first `agent/pre-step` and request boundary, so listener appends join the current request and pressure accounting sees the composed prefix. Changing context belongs in history; contributors should prepend to `await next()` to preserve registration order. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. ```ts cordis-catalog 'agent/session-prefix'(this: Scoped, agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise): Promise @@ -113,11 +107,11 @@ The seed is a frozen empty list; a contributing listener returns a NEW array — Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:537`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:239`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit -The agent's session lifecycle began, fired once before its first turn. `source` says why (SessionStartSource: fresh startup, a resumed persisted session, …). A pure NOTIFICATION (emit, not waterfall): a listener cannot veto by returning a decision or throwing. A listener that wants to seed context does so via `agent.inject()` (a `context/message` the first request sees). A lifecycle owner can still dispose its structural ownership edge during this notification; publication rechecks liveness and then aborts before the driver starts. +The session lifecycle began, once before the first turn. Use `agent.inject()` to seed model-facing context. This is a notification, not a veto; disposal requested by a lifecycle owner is rechecked before the driver starts. ```ts cordis-catalog 'agent/session-start'(this: Scoped, agent: Agent, source: SessionStartSource): void @@ -125,11 +119,11 @@ The agent's session lifecycle began, fired once before its first turn. `source` Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:381`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:180`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit -Agent status changed (`idle` ⇄ `running`, or → `disposed`). Drive lifecycle off this transition, never off a status you just requested — `send()` does not flip status to `running` before it returns. +Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does not enter `running` synchronously; drive lifecycle from this event. ```ts cordis-catalog 'agent/status'(this: Scoped, agent: Agent, status: AgentStatus): void @@ -137,7 +131,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). Drive lifecycle Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:345`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:157`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -149,11 +143,11 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:552`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:250`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall -Waterfall: override the turn-continuation decision via a typed ContinuationDecision. The loop's `defaultDecision` is `continue` when the step had tool calls or steering was injected, else `stop`. Listeners force-continue (`/goal`, `/loop` — optionally attaching a `reason` recorded as next-step steering) or force-stop (budget guards). Call `next()` to delegate to the default, or return a decision to override. +Override whether the turn continues. The default continues after tool calls or steering and stops otherwise; a continue reason becomes steering. ```ts cordis-catalog 'agent/turn-continuation'(this: Scoped, agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise): Promise @@ -161,11 +155,11 @@ Waterfall: override the turn-continuation decision via a typed ContinuationDecis Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:570`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:260`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial -Serial terminal-stop checkpoint after the ordinary `agent/turn-continuation` waterfall, any `continue.reason`, and the pending-steering continuation override have been folded. A listener returns `{ action: 'stop' }` to make this turn terminal, or `undefined` to abstain. Terminal stop is monotonic: listener order and steering cannot resume the turn, and pending steering is discarded rather than becoming another step or turn. +Monotonic terminal-stop checkpoint after continuation and steering are folded; a stop remains authoritative through turn close and flush: steering queued in that window is discarded, while ordinary sends survive. ```ts cordis-catalog 'agent/turn-stop'(this: Scoped, agent: Agent, turn: number): ContinuationStop | undefined @@ -173,7 +167,7 @@ Serial terminal-stop checkpoint after the ordinary `agent/turn-continuation` wat Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:588`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:270`](../../packages/core/agent/src/types.ts) ## `approval/*` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index ee49134b7c..c68ab6c923 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -157,17 +157,8 @@ interface GenerateOptions { stop?: string[] signal?: AbortSignal /** - * The id of the session this request belongs to — stamped by the agent loop - * from `agent.session.id`. Adapters ignore it; it lets an `llm/stream` listener - * route a call by WHICH session issued it (the replay adapter keys its per-call - * cursor by session, so a parent and its in-process subagent — each with its - * own session on one context — replay from their own recorded scripts). - * - * Typed as `Branded<'SessionId'>` rather than importing `SessionId` from - * `dsh-session`: that package imports `Message` from here, so importing its - * `SessionId` back would cycle. `SessionId` IS `Branded<'SessionId'>`, so a - * real session id assigns with no cast. (A future ids package could own the - * brand and dissolve this note.) + * Session identity stamped by the loop for listener routing. Adapters ignore + * it; replay uses it to keep concurrent parent and child cursors independent. */ sessionId?: Branded<'SessionId'> } @@ -354,7 +345,9 @@ interface Agent { } ``` -`AgentStatus` is `'idle' | 'running' | 'disposed'`. `AgentId` is a branded string. `AgentOptions` (`model?`) is merge-extensible — plugins add creation options by declaration merging. Persona is not an agent option: the `dsh-system-prompt` config supplies the global default, and an agent-scoped `deployment:persona` section may shadow it. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, serial `agent/pre-step`/`agent/turn-stop` checkpoints, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits. +`AgentStatus` is `'idle' | 'running' | 'disposed'`, and `AgentId` is branded. `AgentOptions` is merge-extensible and currently includes `model?`. Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default. + +The [event taxonomy](../architecture.md#event) owns the `agent/*` lifecycle, checkpoint, and waterfall contracts. Turn and step boundaries are durable session events rather than agent emits. ## Interception decisions @@ -397,7 +390,7 @@ type ContinuationStop = Extract type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact' ``` -`agent/session-prefix` composes the session prefix — a plain `Message[]`, no dedicated payload type. Fired ONCE per loop instance, lazily on its first request: the composed list is deep-frozen, recorded as the header's `messagePrefix` ([the request envelope](#the-request-envelope-llmcallconfig-and-the-logged-header)), and placed in front of the ENTIRE derived history on every request the instance sends — the home for session-stable openers like a skills catalog or an AGENTS.md digest, never returned by `deriveMessages()`. Reuse is structural, so the prefix cannot drift mid-session (resume = a new instance = a recompose); content that changes mid-session goes through the append-only history channels instead (`agent.inject()`, `tools/post-execute` / prompt-submit `additionalContext`). Not a Decision union: the seam contributes content instead of vetoing, so the shape is the contribution itself. +`agent/session-prefix` composes a `Message[]` once per loop instance. The deep-frozen result is recorded in the request header and prepended to every derived history, making it the home for session-stable openers. A resumed instance recomposes; mid-session changes use append-only context channels. The waterfall returns content directly because it contributes rather than decides. ## `ToolDefinition` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 27b891b2f3..d1a097fe24 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,19 +7,19 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:316`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:331`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:605`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:438`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:456`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:360`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:485`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:537`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:381`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:345`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:552`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:570`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:588`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:139`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:148`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:283`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:202`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:212`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:167`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:224`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:239`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:180`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:157`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:250`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:260`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:270`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:59`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:68`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index 22534a9bfa..516527f137 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -57,7 +57,7 @@ Raw stream chunk — token-level replay fidelity. Types: [StreamChunk](core-data-structures/llm-streaming.md) -Source: [`packages/core/session/src/types.ts:287`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:208`](../packages/core/session/src/types.ts) #### `assistant/message` — surface @@ -69,7 +69,7 @@ Assembled assistant message for one step (derived history uses this). Carries th Types: [ContentBlock](core-data-structures/core.md) · [TokenUsage](core-data-structures/llm-streaming.md) -Source: [`packages/core/session/src/types.ts:294`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:215`](../packages/core/session/src/types.ts) ### `bash/*` @@ -129,7 +129,7 @@ In-session context injection (file-change notices, subdir AGENTS.md, skill conte Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:285`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:206`](../packages/core/session/src/types.ts) ### `hook/*` @@ -169,7 +169,7 @@ Source: [`packages/ui/permission/src/index.ts:33`](../packages/ui/permission/src #### `prompt/blocked` — log-only -A queued prompt an `agent/prompt-submit` listener VETOED — the durable record of a blocked prompt and why. Appended in place of the `user/message` the prompt would have become, so the block survives replay even in a MIXED batch where another queued prompt is allowed (there the turn does not end `rejected`, so the boundary reason alone would not preserve it). `content` is the original prompt the listener rejected; `reason` is the veto text (PromptDecision `block.reason`). NOT a SurfaceEventType: a blocked prompt produces no LLM message and never reaches `deriveMessages()`. +Durable record of a prompt veto and its reason. It is log-only: the blocked prompt never enters the model-visible surface, including in a mixed batch. ```ts persistence-catalog 'prompt/blocked': { content: ContentBlock[]; source: MessageSource; reason: string } @@ -177,19 +177,19 @@ A queued prompt an `agent/prompt-submit` listener VETOED — the durable record Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:279`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:200`](../packages/core/session/src/types.ts) ### `request/*` #### `request/header` — log-only -Full snapshot of the EpochHeader the NEXT request is built under, with the RequestHeaderReason it was recorded whole. Appended by the loop inside the step, before dispatch, on a loop instance's first request-building step (`'initial'`/`'resume'`) or when a later request's header changes (`'change'`); always records what the request actually used, post-`agent/request`. Reconstruction reads the latest snapshot. NOT a SurfaceEventType: it produces no LLM message — it is the request envelope, logged so every request is a pure function of the session log (the reconstructability RFC). +Full header for the next request, appended inside its step before dispatch. It is log-only; the latest snapshot reconstructs the request header. ```ts persistence-catalog 'request/header': { header: EpochHeader; reason: RequestHeaderReason } ``` -Source: [`packages/core/session/src/types.ts:338`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:240`](../packages/core/session/src/types.ts) ### `steering/*` @@ -203,7 +203,7 @@ Steering content injected between steps of a running turn. Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:312`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:233`](../packages/core/session/src/types.ts) ### `step/*` @@ -215,7 +215,7 @@ Closes step `step` of turn `turn`. 'step/end': { turn: number; step: number } ``` -Source: [`packages/core/session/src/types.ts:266`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:193`](../packages/core/session/src/types.ts) #### `step/start` — log-only @@ -225,15 +225,13 @@ Opens step `step` of turn `turn` — one model call plus the tool executions it 'step/start': { turn: number; step: number } ``` -Source: [`packages/core/session/src/types.ts:264`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:191`](../packages/core/session/src/types.ts) ### `todo/*` #### `todo/write` — log-only -The agent's whole todo list, carried as a full snapshot and replaced wholesale on each write — the current list is the most recent `todo/write` (last-write-wins on replay, no fold). Appended by an owning agent via `session.append('todo/write', { todos })`. - -NOT a SurfaceEventType: it produces no LLM message and never reaches `deriveMessages()`, so it carries no `surfaceOp` and stays off the surface — it is durable, replayable UI state, distinct from the conversation history. It is a `SessionEventMap` member riding the existing `session/event` emit, not a first-class Cordis `interface Events` notification, so it has no cordis-catalog row. +Whole-list snapshot; latest write wins on replay. Log-only UI state; never derived history. ```ts persistence-catalog 'todo/write': { todos: TodoItem[] } @@ -241,7 +239,7 @@ NOT a SurfaceEventType: it produces no LLM message and never reaches `deriveMess Types: [TodoItem](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:326`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:235`](../packages/core/session/src/types.ts) ### `tool/*` @@ -255,7 +253,7 @@ The model requested one tool invocation: `name` with the raw `arguments` JSON st Types: [CallId](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:300`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:221`](../packages/core/session/src/types.ts) #### `tool/code-dispatch` — log-only @@ -279,7 +277,7 @@ A completed tool call's model-facing result, plus an optional tool-private `meta Types: [CallId](core-data-structures/core.md) · [ContentBlock](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:310`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:231`](../packages/core/session/src/types.ts) ### `turn/*` @@ -293,7 +291,7 @@ Closes turn `turn` with the TurnEndReason that ended it. The loop fires the awai Types: [TurnEndReason](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:262`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:189`](../packages/core/session/src/types.ts) #### `turn/start` — log-only @@ -305,7 +303,7 @@ Opens turn `turn`. `trigger` records what started it — a drained message batch Types: [TurnTrigger](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:256`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:183`](../packages/core/session/src/types.ts) ### `user/*` @@ -319,4 +317,4 @@ A user-visible prompt (queued message drained at turn start). Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:268`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:195`](../packages/core/session/src/types.ts) diff --git a/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md b/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md index 38f5a690c6..a5bc946af4 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md +++ b/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md @@ -4,7 +4,7 @@ Status: implemented ## Problem -Two gaps shared one root. First, provider KV caching (DeepSeek context caching) is prefix-based — a request pays full price only for the tokens after the longest stored prefix it matches — yet nothing in the request pipeline stated, checked, or measured prefix stability: every registered [`PromptSection`](../../../../packages/core/system-prompt/src/index.ts) happened to be static, the tool set happened not to change mid-session, no listener happened to rewrite requests. A single time-interpolating section would have silently multiplied context cost, and no test or metric would have moved. Second, and deeper: the session log — the system's single source of truth — could not actually answer *what the model saw*. It recorded every message but never the system prompt, the tool schemas, or even which model; the mutable `agent/request` waterfall handed listeners the whole `GenerateOptions` to rewrite per call; replay equivalence was therefore a property of the plugin population, not of the design. +The request pipeline did not guarantee prefix stability for provider caching, and the session log could not reconstruct what the model saw. It omitted model, system prompt, and tool schemas while allowing per-call request rewrites. Cache behavior and replay equivalence therefore depended on whichever plugins happened to be loaded. The reference shape for the happy path is MiniCode's `LLMClient`: a stateful conversation client, appended to — never rebuilt — as the conversation advances, resetting only when the system prompt, tool set, or compaction genuinely changes what the model must see. The design question this RFC answers is how to get that discipline without giving up event-sourcing. diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index e0835dcaa6..a9efbee2b4 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -34,7 +34,7 @@ An earlier draft put the full algorithm (the retention walk, token-summing, text ### Auto-compaction runs on `agent/pre-step`, a dedicated surface-mutation seam -Compaction is a **surface mutation**, not a request transform — and that distinction is the seam it belongs on. The loop's request lifecycle, per step, is: assemble the system prompt → open the step → derive the message history from the surface → run the `agent/request` waterfall → call the model. An earlier cut wedged compaction into the `agent/request` waterfall, which forced two problems: (1) the loop had already derived `messages` from the *stale* surface, so the listener had to mutate the surface and then *re-derive* and overwrite `request.messages` — a double-derive whose only purpose was to undo the premature first derive; and (2) `agent/request` also carries downstream-injected context a listener might have added to `request.messages`, which compaction cannot act on (it can only compact the surface), inviting the confusion of measuring tokens compaction can't shed. +Compaction mutates the session surface, so it runs before the step opens and before messages are derived. `agent/request` remains a call-config transform and never needs to rebuild history after a surface change. The fix is a dedicated loop seam, **`agent/pre-step`** (`@mode serial`), fired by the loop *after* system assembly and *before* the step opens (`step/start`): @@ -62,7 +62,7 @@ A runaway turn thus compacts exactly like any other history: its early *closed* ### Head-anchoring: one auto checkpoint, always at the head -`compactIfNeeded` always anchors the compacted range at the surface **head** (`nodes[0]`). After a first compaction lands a summary node at the head, the *second* compaction's range starts at that summary node and re-summarizes it together with the steps accumulated since — so the surface holds **at most one** auto-generated checkpoint, always at the head, re-consolidated each cycle (the backend's checkpoint-merge prompt makes this a cheap incremental merge — see below). This is *why* `CompactionResult.shadowedRange` is a **surface-position span, not a numeric seq interval**: after a replace lands a fresh high-seq summary node at an older range's position, `start` can be numerically **greater** than `end`. The range is resolved positionally (index into the ordered node list and slice), and `shadowedSeqs` is the authoritative set in surface order. (Manual `compactRegion` may target any aligned mid-range and so *can* leave several checkpoints; the checkpoint framing does not claim everything after it is recent.) +Auto-compaction always starts at the surface head, merging the prior checkpoint with newly compacted history so only one automatic checkpoint remains. `shadowedRange` is therefore positional rather than a numeric sequence interval: a newer summary sequence may occupy an older surface position. `shadowedSeqs` records the authoritative surface order. Manual mid-range compaction may leave multiple checkpoints. ### Approximate convergence invariant @@ -85,7 +85,7 @@ compact/end → log-only. Releases the lock (carries `error` on a recoverab ### Checkpoint framing + incremental merge (backend-private) -The landed `user/message` is not the raw summary: the backend wraps it in a checkpoint preamble (so a resuming model reads it as established background, not a fresh request) and `…` tags. The tags make a prior checkpoint detectable on the next cycle, and the summarization prompt then instructs the model to *merge it in place* (preserve still-true facts, drop stale) rather than re-summarize verbatim — a cheap incremental merge that needs no extra log/event machinery. The raw, unframed summary stays on the `compact/summary` provenance event. This framing is entirely a **backend HOW decision** — the contract only promises "a single replace `user/message` carries the (possibly framed) summary; the raw summary lives on `compact/summary`." A template or remote backend may frame differently or not at all. +The basic backend wraps the summary as established checkpoint context and tags it for incremental merging on the next cycle. The raw summary remains on `compact/summary`. Framing is backend policy; the seam promises only that one replacement user message carries the possibly framed summary. ### Blocking via a log-recorded lock, plus a crash/recoverable failure taxonomy @@ -121,7 +121,7 @@ Two failure paths, both documented: ## Testing -- **Unit** (`dsh-compact-basic`): the whole-unit retention walk, the convergence-invariant throw, both failure paths (`compact/end` with/without `error`), head-anchoring producing a non-monotonic `shadowedRange`, decline-on-open-tail, crash-orphan inertness, and the **runaway-turn regression** — a single oversized open turn compacts its early closed steps (proven to fail on the layer-2 protection it replaced). Driven through the real `dsh-invariants` plugin and the real Loader/inject path. -- **Loop** (`dsh-agent-loop`): `agent/pre-step` fires once per step, after `turn/start` and before `step/start`, awaited; a surface mutation in a `pre-step` listener lands outside the step and is reflected in the single derived request. -- **With-key e2e** (`examples/coding-agent`): a real model + real bash session with a lowered `contextWindow`/`retainTokens` triggers compaction mid-session; the test verifies the WORLD (a `compact/start…end` pair landed, the surface shrank, the agent still completed the task after compaction). This is compaction's first real-world exercise and the runaway-survival net. -- **Snapshot (deferred, named gap)**: a full-transcript snapshot of a runaway-turn compaction is NOT yet possible — `dsh-llm-replay` derives one model call per `(turn, step)` from `assistant/chunk` events, but the summarization call records no `assistant/chunk`s and carries no `sessionId` (it binds to the anonymous cursor and claims a non-existent extra script). Covering it needs net-new replay infrastructure (record/replay an interleaved summarization call) and is scheduled as a follow-up rather than discovered mid-build. +- **Unit:** Real Loader and invariant plugins cover whole-unit retention, convergence failure, both `compact/end` outcomes, head anchoring, open-tail refusal, inert crash orphans, and compacting closed steps inside one oversized open turn. +- **Loop:** Tests pin one awaited `agent/pre-step` per step between `turn/start` and `step/start`; a surface mutation there lands outside the step and appears in the single derived request. +- **With-key e2e:** A real model and bash session with lowered limits triggers compaction, records a complete `compact/start…end` pair, shrinks the surface, and finishes the task. +- **Snapshot gap:** Runaway-turn compaction cannot yet replay because the summarization call records no `assistant/chunk` events or `sessionId`; interleaved summarization-call replay remains follow-up work. diff --git a/docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md b/docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md index 048c359948..05fa373433 100644 --- a/docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md +++ b/docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md @@ -4,7 +4,7 @@ Status: implemented ## Problem -The order of the tool list a model call carries — `request/header.tools` on the session log and `GenerateOptions.tools` on the wire — was an emergent artifact: the tool registry returns schemas in registration order, the system-prompt assembly concatenates providers in registration order, and the loop logged and dispatched the result verbatim. Registration order is plugin load order, and plugin load order is a race: the cordis loader imports every `cordis.yml` entry concurrently, so which tool plugin registers first depends on module-import completion timing. The plugin dependency relation cannot rescue this — it is a partial order under which independent tool plugins (e.g. `tool-subagent` vs `tool-todo`) are incomparable, so both interleavings are legal linearizations. This stopped being theoretical when a CI runner resolved the race differently from every recording machine: snapshot goldens pinned one permutation of `request/header.tools`, the `node 22.18` CI leg produced the other, and 5/5 snapshot tests failed on a diff that was pure array reordering. Tool order is part of the request bytes (prompt-cache stability, potentially model behavior) and, since the reconstructability contract, part of the durable session log — it must be a decision, not a residue. +Model-facing tool order followed plugin registration order, which depends on concurrent module loading for otherwise independent plugins. That race produced different request headers in CI and snapshot recordings. Because order affects request bytes, caching, and the durable header, it needs an explicit deterministic policy. ## Decision @@ -17,7 +17,7 @@ The system-prompt assembly owns the canonical model-facing tool order, exactly w - The list must contain the rest entry exactly once and no duplicate names. - When `toolOrder` is unset, the canonical order is plain lexicographic name order (code-unit comparison, locale-independent), so determinism requires no configuration. -The policy is applied where the list is born: `assemble()`, before the `system-prompt/assemble` waterfall. The assembly canonicalizes the tools it collects from providers the same way it sorts sections by their `order` field — on the initial assembly, killing the registration-order entropy at its source. The waterfall therefore starts from one deterministic list; when a listener leaves that order intact, the loop's `EpochHeader`, the `request/header` event, the deep-frozen request, and the dev invariant's cross-check inherit it with no new loop change. +`assemble()` canonicalizes provider tools before the `system-prompt/assemble` waterfall, removing registration-order variance at its source. The waterfall starts from this deterministic list; unchanged order then flows into the request header, frozen request, and reconstruction checks without loop-specific ordering logic. Scope is deliberately narrow: this fixes the REGISTRATION-ORDER race, not plugin behavior. A `system-prompt/assemble` listener may still add, remove, or rearrange tools — same as it may edit sections after their sort — and owns the determinism of what it emits; the waterfall contract already demands deterministic listeners (the reconstructability invariant would catch a listener that diverges between build and replay). @@ -46,4 +46,4 @@ Config plumbing follows the `persona` precedent, and `toolOrder` sits beside it: ## Testing -Unit tests on `dsh-system-prompt` pin the ordering semantics (lexicographic default, listed/rest placement, unknown-name rejection at assembly, reserved tool-name rejection, stable handling of shared names, provider-order independence), the pre-waterfall contract (listeners observe the canonical list; a listener-appended tool is not re-sorted), and each invalid-list rejection at load. Loop-level tests assert the `request/header` fold carries the canonical order for scrambled registration orders (identical across permutations), that a configured `toolOrder` reaches both the logged header and the dispatched deep-frozen request, that the frozen loop-built envelope survives to the adapter, and that an unregistered `toolOrder` name fails the turn with a balanced `error` `turn/end`, an `agent/error`, no step, no logged header, and no dispatched request. Forwarding is asserted at every level that exposes the key (`dsh-agent-core`, `dsh-stdio-agent`, `dsh-acp-agent`). The snapshot tier replays all scenarios while only the pinned `text-turn` header carries the full canonical tool list; non-pinning fixtures continue to compare through `{{tools}}`. +System-prompt tests cover lexicographic default order, listed/rest placement, provider-order independence, shared names, invalid lists, unknown or reserved names, the canonical pre-waterfall list, and the rule that listener-added tools are not re-sorted. Loop tests pin identical logged and dispatched order across registration permutations, forwarding through agent-core and both apps, deep-frozen requests, and balanced turn failure with no step, header, or adapter call for an unknown configured name. Snapshot replay keeps the full canonical list only in the pinned `text-turn` header; other fixtures continue to use `{{tools}}`. diff --git a/docs/rfc/implemented/feature/2026-07-06-sandbox.md b/docs/rfc/implemented/feature/2026-07-06-sandbox.md index 58321fbf81..bb3684e1b7 100644 --- a/docs/rfc/implemented/feature/2026-07-06-sandbox.md +++ b/docs/rfc/implemented/feature/2026-07-06-sandbox.md @@ -38,30 +38,13 @@ The swap is invisible to every consumer of `ctx.bash`: the bash tools, hook comm Misconfiguration fails loud: `mode` outside the closed vocabulary is rejected at plugin load, and a host with no usable backend throws the structured `SANDBOX_UNAVAILABLE` — at `confine()` before the command ever spawns — rather than degrading to unconfined execution. `runnerCommand` on `dsh-sandbox-local` is the operator's explicit assertion of a bwrap-compatible runner (chain and probes skipped); it doubles as the deterministic fake-runner seam for keyless tests. -What the model then experiences: denied file effects come back as result facts with a `[sandbox: file access denied under mode]` marker plus standing instructions not to retry around them; under a confining executor the schema offers `sandbox_permissions` + `justification` for the one-approval escalated retry (validated strictly wider than the session's effective mode at execution); the system prompt deliberately does NOT state the sandbox mode — the model learns the boundary from the marker (which names the mode) when it hits it, instead of preemptively refusing work a standing declaration discourages. What an ACP editor experiences: one `Permissions` config-option select per session (advertised when the `dsh-permission` preset layer is composed; each preset bundles a sandbox mode and an approval policy and writes through to both knob events — a knob state outside the table derives a switch-away-only `custom` current), switchable at runtime; a sandbox switch simply changes what subsequent commands may do, while an approval-policy switch to `'never'` is stated in the prompt and narrated. - -The product path, concretely (the escalation arc is verbatim from the recorded `escalation-approved` scenario; the denial leg is pinned on the real-kernel e2e tier): - -``` -tool/result … [sandbox: file access denied under read-only mode] ← the write RAN; the kernel refused it -tool/call bash {"command": "printf 'escalated\n' > escalated.txt && cat escalated.txt", - "sandbox_permissions": "workspace-write", - "justification": "the user asked to write escalated.txt in the workspace"} - → the editor is prompted on this very call (session/request_permission through the approval seam); Allow once -tool/result "escalated" — THIS call ran under workspace-write and its result facts say so; the session stays read-only -``` - -Reject instead and nothing executes: the result is the verbatim `the user rejected escalating this command to "workspace-write"`, and the teaching makes that final — no re-ask. +Denied file effects return a `[sandbox: file access denied under mode]` marker and instructions not to work around the denial. A confining executor adds paired `sandbox_permissions` and `justification` fields for one approved retry that must be strictly wider than the session's effective mode. A grant widens only that retry; rejection executes nothing, returns `the user rejected escalating this command to ""`, and permits no re-ask. The prompt does not announce sandbox mode, avoiding preemptive refusal. When `dsh-permission` is composed, ACP exposes one `Permissions` select whose presets write both knob events; unmatched knobs appear as switch-away-only `custom`. Only a switch to the deterministic `'never'` approval policy is stated in the prompt and narrated. ### Design detail -#### Grounding — verified against the code +#### Scope grounding -- Runtime OS subprocesses exist at exactly two sites: the `ctx.bash` seam's single spawn (`packages/bash/bash-local/src/run.ts`; hook commands flow through `ctx.bash`, so bash confinement covers them transitively) and `subagent-acp`'s child agents (`packages/subagent/subagent-acp/src/run.ts`) — the second consumer that makes a shared seam due rather than preemptive under the [capability seams RFC](../architecture/2026-06-13-capability-seams.md)'s "don't split preemptively" rule. -- Everything else executes inside the harness process (fs is in-process `node:fs`, web is in-process `fetch`, every `ToolDefinition.execute()` closes over `ctx`): an OS sandbox wraps `execve` and cannot wrap an in-process function call, so "sandbox any tool" is policy at each tool's seam, never a mechanical transport change. -- `tools/pre-execute` (`allow`/`deny`/`ask`) exists, with `ask` serviced by [the approval seam](2026-07-06-approval-seam.md); the fs intent gates are version guards with no mode input yet. -- `dsh-bash`'s request/spec split (`BashExecRequest` → `resolve()` → `BashExecSpec`) carries per-call fields the way escalation needs — `owner` is the template: request-optional, spec required-but-nullable, carried verbatim — and the result types already speak `SandboxMode`, so a per-call policy field adds no dependency edge. -- The pinned-header snapshot design means a schema/description change churns at most one pinning fixture per suite, and the escalation fields are advertised only under a sandboxing executor — so they live in exactly one pinned header, the acp example suite's `permission-switching` fixture. +OS subprocess confinement applies to the bash executor, including hook commands, and later to ACP subagent children. Filesystem, web, and other tools execute in-process and require policy at their own seams; an argv wrapper cannot confine a function closing over `ctx`. The existing bash request/spec split carries per-call overrides, while `tools/pre-execute` and the approval seam own the human decision. #### The seam: `ctx.sandbox` @@ -75,33 +58,33 @@ Left open, for the phase that needs them: whether network restriction arrives as #### Local backends and the shipped launcher -`dsh-sandbox-local` selects BY PLATFORM, once per lifetime, and caches the verdict: each platform names its runner chain, a chain of one is selected directly — probing arbitrates between candidates, and a sole candidate leaves nothing to arbitrate — and a chain of several is probed FUNCTIONALLY in preference order (build and enforce a real profile, never `--version` — a present-but-unusable `bwrap` must fail its probe). Linux: `bwrap` first (its mount profile is closest to the mode vocabulary: whole tree read-only, fresh `/dev`+`/proc`, `workspace-write` adds an ephemeral `/tmp` and rebinds the workspace root; deliberately no `--unshare-pid` and no network claim), else the npm-distributed `landlock-run` Landlock launcher. darwin: `sandbox-exec` speaking a Seatbelt (SBPL) profile — allow-default with `(deny file-write*)` plus write allow-lists, every granted root canonicalized because Seatbelt matches resolved paths (`/tmp` IS `/private/tmp`) — unprobed, the sole candidate. A platform with no chain fails closed at `confine()`; an unprobed runner that turns out unusable fails closed at EXECUTION instead — it refuses to run the command, and every wrap carries `runnerFailureSignatures` (the runner's own error prefix, which also matches the shell's runner-not-found message) so the consumer classifies that as a SANDBOX failure, never a task failure: on either path the command neither runs unconfined nor slips through as a plain failure. A non-empty `runnerCommand` config is the operator's assertion of a runner that fully enforces the bwrap-shaped profile — chain and probes skipped; it doubles as the deterministic fake-runner seam for keyless tests. It is not exempt from fail-closed execution: its wrap carries argv0-scoped outer-shell failure shapes (`exec: : not found`, `: No such file or directory`, `: Permission denied`) as its runner-failure dialect, so a missing or unexecutable configured runner classifies as a sandbox failure like every other rung — never as a failing command, and never as a denial. +`dsh-sandbox-local` selects one platform runner per provider lifetime and caches the verdict. Linux functionally probes `bwrap` then Landlock; macOS uses Seatbelt. Unsupported platforms and unusable runners fail closed. Each wrap carries backend-specific denial and runner-failure signatures so `dsh-bash-sandbox` can distinguish a denied file effect from a broken sandbox. `runnerCommand` skips selection as an operator assertion of a bwrap-shaped runner, but missing or unexecutable commands still classify as sandbox failure and never run the payload unconfined. The launcher is a ~300-line C program (plain C11 over the raw Landlock UAPI — no libraries beyond a statically linked musl, so the audit surface is that one file plus the kernel's stable syscall contract): `--ro ` / `--rw ` grants, `--`, the wrapped argv; it installs the ruleset on itself and `exec`s (rulesets are inherited across `execve`, and it sets `no_new_privs` before restricting); `--probe` enforces a maximal ruleset in a short-lived child and exits 0 only when the kernel actually enforces; launcher failures exit 125 without exec'ing. -The launcher lives in its own repository and reaches the harness as the npm package family [`node-addon-landlock-run`](https://www.npmjs.com/package/node-addon-landlock-run) (the per-platform-package pattern of `node-addon-require-builtin` and esbuild): an entry package — `dsh-sandbox-local`'s one runtime dependency — plus per-platform binary packages selected at install time by npm's `os`/`cpu` fields. The entry package owns the launcher's CLI contract end to end (`launcherPath()` resolution with a never-existing fallback, the functional `probe()`, `grantArgs()` flag spelling), versioned together with the binary so probe-report parsing can never drift against it; the harness keeps only the policy side, `landlockProfileArgs()` mapping the mode vocabulary to grants. Native-only per-architecture builds, pack gates (binary presence, executability, ELF architecture), and the byte-pinned publish rehearsal are that repository's release pipeline; this repo's Landlock CI legs install the published family from the registry — the true consumer path — and prove real-kernel confinement through it. +The Landlock launcher ships through [`node-addon-landlock-run`](https://www.npmjs.com/package/node-addon-landlock-run), with platform binaries selected by npm. That package owns path resolution, probing, and CLI flags; the harness maps sandbox modes to grants. Versioning the entry point with its binaries keeps probe parsing and launch syntax aligned. FIXME: Revisit the separate-repository boundary and try to maintain the launcher source and its platform package family inside this monorepo, so the native release surface and harness contract evolve together. -Profile parity is honest rather than identical: under Landlock, `read-only` grants `--ro /` plus `--rw /dev/null` (the node, not `/dev` — the host's `/dev/shm` is a persistent shared tmpfs), and `workspace-write` grants the HOST `/tmp` where bwrap's is ephemeral; under Seatbelt, `read-only` likewise grants only the `/dev/null` literal, and `workspace-write` grants the host `/tmp` plus the per-user darwin temp dir (`os.tmpdir()` — the platform's real temp area for mkstemp-family tools; omitting it would deny what the mode promises). Every wrap carries the rung's denial dialect (`denialSignatures`: EROFS text under bwrap, EACCES under Landlock, EPERM under Seatbelt) so consumers match the active backend rather than a cross-runner union. Enforcement is honest per ABI level: an older kernel enforces the subset its ABI governs (path truncate is ungoverned before ABI v3), the probe's report line distinguishes the cases, and every confined result carries the structured `enforcement: 'full' | 'partial'` fact — refusing partial enforcement would deny the fallback to precisely the older-kernel hosts that need it. The bwrap and Seatbelt profiles govern every promised file effect by construction, so their passing probes always report `full`. +Backend profiles share the mode contract but differ in necessary host grants. Landlock and Seatbelt allow only `/dev/null` in read-only mode; workspace-write also permits their required host temp roots. Each wrap carries backend-specific denial signatures. Landlock reports partial enforcement on older ABIs that cannot govern every operation, while successful bwrap and Seatbelt profiles report full enforcement. #### The bash consumer -`dsh-bash-sandbox` extends `LocalBashExecutor` (spawn mechanics, process-group kills, spill files, background tasks, credential scrub inherited verbatim) and hands `ctx.sandbox` the exact `['bash', '-c', command]` argv it is about to spawn. A sandbox denial is a RESULT FACT, not an error: the command RAN and the kernel refused a file operation, so `result.sandbox.denied` is orthogonal to `exitCode`/`signal`. Classification is conservative text inference over the collected stderr tail against the WRAP's own dialect, so a backend is never credited with a denial text its kernel does not speak (bare EPERM under a Linux runner names non-file boundaries the mode vocabulary does not govern); the known residual false positive is non-sandbox text in the active dialect (an ssh auth failure under Landlock, a refused `kill` under Seatbelt), and a structured runner signal wins once one exists. A RUNNER failure is the opposite of a denial and outranks it in classification (a runner's error text can itself contain denial words): the wrap's `runnerFailureSignatures` matching a failed run means the sandbox broke and the command NEVER RAN — the foreground path re-throws it as the structured `SANDBOX_UNAVAILABLE` error (the late twin of the confine-time throw, carrying the runner's first stderr line), a settled background task stamps `sandbox.runnerFailed` and `bash_output` renders its own marker — so a broken sandbox can never read as a failing command. +`dsh-bash-sandbox` reuses local process execution and asks `ctx.sandbox` to wrap the exact bash argv. A kernel denial is a result fact independent of exit status and is inferred only from the selected wrap's stderr dialect. Runner failure outranks denial because it means the command never ran: foreground calls throw `SANDBOX_UNAVAILABLE`, while settled background tasks set `sandbox.runnerFailed` for `bash_output`. This keeps broken confinement distinct from both task failure and an enforced denial. The model's view is result facts only: the static tool description explains the denial marker (`[sandbox: file access denied under mode]`), encourages attempting commands that may be denied, and forbids retrying around a denial; when the escalation fields are advertised, a denied result additionally carries the escalation hint itself, so the sanctioned same-turn retry is prompted at the decision point rather than depending on the model recalling the description (§ Escalation). No prompt section states the sandbox mode (§ Per-session modes). #### Escalation: one approved wider retry after a denial -The seam level is mechanism only. `BashExecRequest` carries `sandboxMode?: SandboxMode`, an explicit per-call policy input; `BashExecSpec` carries it required-but-nullable (the `owner` pattern: a forgotten field is a visible `undefined`, and `resolve()` is the one explicit defaulting step); `BashExecutor` exposes the capability fact `get sandboxMode(): SandboxMode | undefined` — `undefined` in the base class, the configured mode in `SandboxBashExecutor` — so the tool layer can advertise only what the mounted executor honors: composition truth, not configuration. The seam honors ANY explicit mode, including a narrower one; the wider-only ladder is escalation policy and lives in the tool. A non-sandboxing executor (`dsh-bash-local`) carries the field verbatim and confines nothing — the field reaching it means the caller bypassed the tool's gate, and its honest behavior stays unconfined execution, not a guess at enforcement it does not have. +`BashExecRequest.sandboxMode` is an optional per-call input; resolved specs make the field explicit. `BashExecutor.sandboxMode` advertises whether the mounted executor can honor it, so only a confining composition exposes escalation. The seam accepts any explicit mode; the tool owns the wider-only escalation rule. Non-sandboxing executors remain honestly unconfined. `SandboxBashExecutor.resolve()` stamps the effective mode — escalation grant > session override > configured default — so `run()`/`start()` read the spec, never the config. The `danger-full-access` branch, the confine call, and the result facts all key off the spec's mode, and the per-task facts map carries each task's mode alongside its wrap facts (`notifyTaskDone()` stamps from the map entry): one escalated call — foreground or background — reports the mode it ACTUALLY ran under while every neighbor keeps its own. -The tool gate advertises two extra parameters exactly when `ctx.bash.sandboxMode` reports a confining mode at registration: `sandbox_permissions`, an enum of the closed escalation-target vocabulary — `workspace-write`/`danger-full-access`, every mode a session could ever escalate TO — and `justification`, required together with it. The enum is deliberately NOT cut down to the modes wider than the executor's DEFAULT: schemas are registry-global while the effective mode is per-session and switchable, so a default-relative ladder strands a session overridden NARROWER than the default (with a `danger-full-access` default and a `read-only` override it would advertise nothing at all — confined, but with no lever). Strict widening is instead enforced at EXECUTION against the call's effective mode (session override ?? executor default): a request that is not strictly wider fails closed with its own text and prompts no one. An escalating call resolves approval BEFORE anything executes — no `ctx.approval` composed, or no agent on the execution, fails closed with its own text; otherwise `ctx.approval.request({ agent, toolName: 'bash', callId, reason, signal })` with the audit-self-contained reason `escalate sandbox to ${mode}: ${justification}`, while the UI attaches the prompt to the already-streamed call (the command is visible there; the approval RFC's no-arguments rule holds). The four outcomes map to distinct results: `allowed-once` stamps `sandboxMode` onto the bash request and proceeds; `rejected`, `cancelled`, and `unavailable` each produce their own error text, so the model can tell a human "no" from a dismissed prompt from a missing channel. The grant is consumed by the very call that asked; nothing is stored. +When a confining executor is mounted, `bash` advertises paired `sandbox_permissions` and `justification` fields. The schema exposes the full closed escalation vocabulary because effective mode is per-session; execution rejects any target that is not strictly wider than that call's effective mode. Approval resolves before execution. `allowed-once` stamps the granted mode onto only that request, while `rejected`, `cancelled`, `unavailable`, a missing approval service, or a missing agent all fail closed with distinct results. No grant is persisted. -The tool description teaches — and a denied result itself prompts — the SAME-TURN flow when the fields exist: on a denial a wider mode would cure, escalate immediately in that turn by retrying the exact command once with `sandbox_permissions` (the narrowest mode that suffices) + `justification`, without detouring through chat to ask first — the approval prompt raised by the retry IS how the user consents. Never speculatively: an escalation is grounded in a real denial — normally the one the command just hit, up front only when the session already denied the same access — and a prompt stating approvals are disabled turns the exception off entirely; a rejected escalation is final for that command. Denial-grounding is deliberately model discipline plus human judgment, not harness bookkeeping — the human sees the exact command and justification on the prompt (see Alternatives for why hard-matching is rejected). No new session events anywhere: the attempt is an ordinary `tool/call` whose logged arguments carry the two fields, the decision is the approval seam's `approval/asked`/`approval/decided` pair, the outcome is an ordinary `tool/result` whose sandbox facts name the mode it ran under. The asker lives in `dsh-tool-bash`, NOT the executor: a transport seam has no `agent`, no `callId`, and no business asking humans questions. +Escalation is a same-turn retry of the denied command with the narrowest sufficient `sandbox_permissions` and a `justification`; the approval prompt is the consent step. It must be grounded in an actual denial, except when the session already observed the same denied access, and a disabled or rejected approval ends that command. The retry, approval decision, and result use existing tool and approval events. `dsh-tool-bash` owns the ask because the executor seam has neither the agent nor call id required for user interaction. -Left open, recorded for the phase that picks them up: what a grant's scope identity is beyond the sandbox mode — the exact call, a path, a command prefix, the session, a time window — the question `allow_always` grant storage must answer before that option can be advertised; how cancellation behaves while an approval prompt is pending; and how escalation is defined for `run_in_background` denials that arrive via `bash_output`. +Left open, recorded for the phase that picks them up: what a grant's scope identity is beyond the sandbox mode — the exact call, a path, a command prefix, the session, a time window — the question `allow_always` grant storage must answer before that option can be advertised; and how escalation is defined for `run_in_background` denials that arrive via `bash_output`. #### Per-session modes: the session log as the store @@ -198,15 +181,13 @@ Costs and accepted limits: - **The model may over-ask.** Escalating without denial grounding, or picking `danger-full-access` where `workspace-write` suffices: the description steers and the enum forces the ladder, but the human prompt is the actual gate; the `approval/asked` reasons make over-asking auditable, and a `prepend` policy answerer can auto-reject patterns a deployment never wants. - **The advertised target set is static while the effective mode is per-session** (schemas are registry-global) — a session already at the widest mode is still offered the fields. Harmless by construction: the strict-wider check at execution, not the enum, is the safety boundary — a non-widening request fails with its own text and never prompts anyone. - **A granted escalation is not a working sandbox.** An unavailable backend still fails closed even for a granted escalation to a confining mode — at `confine()` when the platform has no chain or every probe fails, at execution when an unprobed sole runner refuses (classified as a sandbox failure, not a command failure) — while a granted `danger-full-access` run never touches the provider at all: there the grant, not the probe, is the authority. -- **An idle switch lives in bridge memory until the next turn anchors it.** A crash in that window reverts it (reported honestly on `session/load`), and a session that never runs another turn never persists it — accepted, with the loop-owned idle commit turn named as future work if durability becomes a requirement. +- **An idle switch lives in bridge memory until the next prompt submission anchors it.** A crash in that window reverts it (reported on `session/load`), and a session that never submits another prompt never persists it — accepted, with a loop-owned idle commit turn left as future work if durability becomes required. - **The approval narrator's restart baseline parses prompt prose.** The closed candidate sentence is owned by the writing module itself, so a wording change is a coordinated writer+parser edit in one file; a session whose headers predate the section silently adopts the current policy without a notice. - **The approval section is still a dynamic prompt surface** (a `'never'` switch breaks provider prompt-prefix caching for that session). Accepted: policy switches are rare, and a model acting on a stale `'never'` is worse. The sandbox knob no longer touches the prompt at all. - **The model may hold a stale belief about the sandbox mode** (nothing announces a switch). Accepted deliberately: the next attempt's marker or success corrects it, and the observed failure mode of announcing — preemptive refusal — is worse than one wasted retry. ## FAQ -Behavioral and usage questions only — every "why not X?" design question lives in [Alternatives considered](#alternatives-considered), whose job is exactly that. - - **A command came back with `[sandbox: file access denied under read-only mode]` — did it fail?** It RAN, and the kernel refused a file effect: the denial is a result fact orthogonal to exit code. The teaching forbids retrying around it; the one sanctioned move is the same command retried once with an escalation request. - **How is a BROKEN sandbox told apart from a failing command?** Runner failure outranks denial in classification: a failed run matching the wrap's `runnerFailureSignatures` means the command NEVER ran — foreground re-throws the structured `SANDBOX_UNAVAILABLE` with the runner's stderr line, a background task stamps `sandbox.runnerFailed` and renders its own marker. A broken sandbox can never read as a failing command, and the command never runs unconfined. - **What happens on a platform with no backend — Windows today?** `confine()` throws the fail-closed `SANDBOX_UNAVAILABLE` and the command never spawns; `win32` is a reserved EMPTY chain, pinned by test to fail closed identically until a Windows runner fills it (§ Deferred phases). @@ -214,7 +195,7 @@ Behavioral and usage questions only — every "why not X?" design question lives - **Does the sandbox restrict network or process visibility?** No — `SandboxMode` claims FILE effects only; the bwrap profile deliberately does not unshare pid, and no backend claims network. Whether network restriction becomes its own knob is left open in § The seam. - **Which tools actually run confined?** OS subprocesses through `ctx.bash` — the bash tools, and hook commands transitively. fs/web/todo execute in-process, where an `execve` wrapper is mechanically meaningless; their `read-only` semantics arrive with the cross-family deferred phase, and until then the contract says bash-only honestly. - **Does a granted escalation persist, or cover background tasks?** Neither: the grant is consumed by the very call that asked (foreground or background), that one call reports the mode it actually ran under, and every neighbor keeps its own. How escalation should be DEFINED for a background denial that only surfaces later via `bash_output` is left open in § Escalation. -- **When does an editor's mode switch take effect?** Mid-turn: appended immediately, honored by the very next call's stamp. Idle: held on the bridge's session record, anchored at the next turn's `agent/prompt-submit`, with N flips coalescing to at most one event (none if net-zero); a crash before anchoring reverts it and `session/load` reports the truth. The model is not told — its next command simply behaves under the new mode. +- **When does an editor's mode switch take effect?** Mid-turn: appended immediately, honored by the very next call's stamp. Idle: held on the bridge's session record, anchored at the next `agent/prompt-submit` inside its open turn, with N flips coalescing to at most one event (none if net-zero); a crash before anchoring reverts it and `session/load` reports the truth. The model is not told — its next command simply behaves under the new mode. - **What survives a restart — and what if the operator changed the config default while the process was down?** Overrides replay from the session log (`effective = fold ?? config`), so a resumed session keeps its modes with zero catch-up machinery; a default that drifted offline changes behavior the same way a switch does (the approval policy, being stated, is additionally narrated with operator/config attribution). - **What does `enforcement: 'partial'` on a result mean?** The selected backend enforces the subset its kernel ABI governs — e.g. Landlock before ABI v3 does not govern path truncate — and says so structurally instead of refusing the host; the probe's report line distinguishes the cases. The bwrap and Seatbelt profiles govern every promised file effect by construction, so they always report `full`. diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index 0b0300472c..c879dabfa1 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -1,31 +1,8 @@ /** - * `BasicCompactService`: the first implementation of the - * `@deepseek-ai/dsh-compact` seam. It owns the entire compaction strategy: - * - * - **Token estimation** — chars/`charsPerToken` heuristic (config, default 4) - * with per-block structural overhead. - * - **Retention policy** — walk surface nodes tail→head, keep recent nodes up - * to a token budget, compact everything older. The cutoff is snapped forward - * to the next balanced tool-pairing boundary so a compacted region never - * splits a step's tool-call/result pair (an open tail step is never crossed — - * compaction declines and retries once it closes). - * - **Summarization** — a direct one-shot `ctx.llm.stream()` call assembled - * via `BlockAssembler` with a fixed condense-the-history system prompt; - * NOT a loop step, so `agent/request` never fires — interception happens - * at `llm/stream` like any other direct call. - * - **Surface mutation** — a single `user/message` replace node carries the - * summary; `compact/*` events are log-only lock + provenance records. - * - **Auto-compaction** — an `agent/pre-step` listener delegates to - * {@link BasicCompactService.compactIfNeeded} before EVERY step (so a - * tool-heavy turn that grows the surface mid-turn still compacts); it owns the - * sole token-pressure check. - * - * A different backend (real tokenizer, template summarizer, turn-count - * retention) either subclasses this and overrides the {@link - * BasicCompactService.estimateContentTokens} / {@link - * BasicCompactService.summarize} hooks, or implements the abstract - * {@link CompactService} from scratch. - * + * Basic compaction backend. It estimates request pressure, retains a recent + * tool-balanced surface tail, summarizes the older head through a one-shot model + * call, and replaces that head with one checkpoint. Auto-compaction runs before + * every step so a growing turn can compact its earlier closed steps. * @module @deepseek-ai/dsh-compact-basic */ @@ -54,15 +31,8 @@ const SUMMARY_OPEN_TAG = '' const SUMMARY_CLOSE_TAG = '' /** - * The summarization system prompt: instructs the model to condense the - * conversation into a fixed, fully-populated structure rather than freeform - * bullets. The fixed structure guarantees coverage of the things a resuming - * model needs (original intent, pending work, the next step, critical context) - * and is stable across compaction cycles, so a prior checkpoint can be merged - * in place. The final rule keys off {@link SUMMARY_OPEN_TAG}: when the - * transcript already contains a prior checkpoint, the model consolidates rather - * than re-summarizing it verbatim (a cheap incremental-merge that needs no - * extra log/event machinery — the tag travels on the summary surface node). + * Fixed summary structure for resumable checkpoints. A tagged prior checkpoint + * is merged with newer history instead of copied forward verbatim. */ const SUMMARIZE_SYSTEM_PROMPT = [ 'You are a compaction engine for an AI coding assistant. Condense the conversation transcript into a structured checkpoint that lets another model resume the work with no loss of essential context.', @@ -100,29 +70,13 @@ const SUMMARIZE_SYSTEM_PROMPT = [ `- If the transcript already contains a ${SUMMARY_OPEN_TAG} block, it is a PRIOR checkpoint. Do not copy it forward verbatim: preserve still-true facts, drop stale ones, and merge newer information into a single consolidated summary under the same structure.`, ].join('\n') -/** - * Framing prepended to the landed summary so a resuming model reads it as a - * checkpoint rather than a fresh user request, and continues the task from it. - * It summarizes an earlier span of the conversation; the messages that follow - * are the continuation. Because region compaction can be invoked manually, a - * surface may hold several checkpoints, so the framing does NOT claim that - * everything after it is recent or verbatim — only that the captured context - * should be built on, not restated. - */ +/** Framing that makes a landed summary established context rather than a new request. */ const CHECKPOINT_PREAMBLE = 'This is an automatically generated checkpoint condensing an earlier span of the conversation to free up context. Treat the captured context as established background and build on it without restating it. Continue the task directly from the messages that follow, without acknowledging this checkpoint.' /** - * Map a terminal `FinishReason` to the error a SUMMARIZATION must throw, or - * `undefined` for an acceptable finish. `FinishReason` is merge-extensible. - * - * Compaction fails CLOSED on a truncated summary: `error`, `aborted`, AND - * `max-tokens` all raise. Unlike an ordinary agent turn — where `max-tokens` is - * a normal "the model hit its budget" outcome the loop keeps — a summary cut off - * at the token cap is an INCOMPLETE checkpoint, and committing it would shadow - * (discard) the real history it summarizes. Raising here keeps the original - * surface intact (the caller appends `compact/end` with the error and the auto - * path proceeds with full history). `stop`/future kinds are accepted. + * Map a terminal summary failure to an error. A max-token finish is rejected + * because committing an incomplete checkpoint would shadow the full history. */ function finishError(finish: FinishReason): Error | undefined { switch (finish.kind) { @@ -164,25 +118,8 @@ export class BasicCompactService extends CompactService { this.config = resolveConfig(config) if (this.config.auto) { - // Auto-compaction: delegate to compactIfNeeded before EVERY step. This is - // LOAD-BEARING for runaway-turn survival: a tool-heavy ReAct turn appends - // an assistant/message and a tool/result per step, so the surface (and the - // derived token count) grows WITHIN a turn. The only moment to rescue a - // turn that alone approaches the window is the next step's pre-step - // checkpoint; gating to a turn's first step would let a runaway turn - // overflow before the next turn's check. The listener owns NO threshold - // logic — compactIfNeeded is the single place that decides whether to - // compact, and its in-progress lock serializes concurrent attempts. - // - // It runs on `agent/pre-step` (a serial surface-mutation checkpoint fired - // AFTER turn/start but BEFORE step/start), NOT `agent/request`: compaction - // mutates the session surface, and the loop derives the request `messages` - // AFTER this fires — so a single derive already reflects the compaction, - // with no double-derive and no need to rewrite an already-assembled - // `messages` array. Firing pre-step (outside any open step) keeps the - // log-only `compact/*` records and the replacement node cleanly outside a - // step, so a crash mid-compaction leaves an inert orphan the turn-repair - // closes — never a half-open step. + // Check before every step so a single growing turn can compact earlier closed steps. + // This serial pre-step seam mutates the surface outside the pending step. ctx.on('agent/pre-step', async (agent: Agent, _turn: number, _step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal) => { try { const result = await this.compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal) @@ -289,27 +226,9 @@ export class BasicCompactService extends CompactService { } /** - * Summarize conversation text into content blocks via `ctx.llm.stream()` - * assembled through a `BlockAssembler`. A direct one-shot model call, NOT a - * loop step: it does not run the `agent/request` waterfall (that seam shapes - * the loop's conversation requests); per-call - * interception happens at `llm/stream` like any other direct call. The model - * comes from `BasicCompactConfig.summarizationModel`, falling back to the - * agent's own model. - * Override in a subclass for a template or remote summarizer. - * - * Honors the adapter failure contract: an adapter may report a model failure - * by throwing from `stream()` (propagated here) OR by ending the stream with - * a `finish {kind:'error'|'aborted'}` chunk — the latter is re-thrown so a - * provider error never yields an empty summary. - * - * Forwards `signal` into `GenerateOptions.signal` so an abort/dispose tears - * down the in-flight summarization rather than orphaning the model call. - * - * Returns the summary blocks TOGETHER with the call envelope it actually - * used (`model`, `maxTokens`) — the caller logs the envelope on the - * `compact/summary` provenance event, so an overriding subclass (template - * or remote summarizer) reports its own envelope honestly. + * Summarize through a direct one-shot `ctx.llm.stream()` call, not an agent + * step or `agent/request` dispatch. Failure finishes and truncated summaries + * reject; the signal is forwarded and only text reaches the checkpoint. * * @param text - plain-text rendering of the conversation region to condense. * @param agent - supplies the fallback model and the session id stamped on @@ -359,42 +278,10 @@ export class BasicCompactService extends CompactService { // ---- Core API (implements the abstract contract) ---- /** - * The sole token-pressure gate: estimate the NEXT request's pressure — the - * session prefix + the surface-derived history + the system prompt - * ({@link estimatePressure}) — and if it exceeds the threshold - * (`contextWindow * thresholdRatio`), compact - * the oldest surface nodes outside the `retainTokens` budget. The auto- - * compaction listener delegates here rather than pre-checking, so this is the - * only place the decision lives. The prefix counts because every request - * carries it in front of the history (`EpochHeader.messagePrefix`) even - * though it is not derived history — omitting it would under-estimate by - * exactly the prefix and let a deployment at the window edge skip - * compaction, then ship an over-window request. The loop composes the - * prefix BEFORE the pre-step seam and hands it through, so the gate sees - * this instance's actual prefix (never a previous instance's logged one — - * a resumed/forked instance whose contributor grew is gated on the grown - * value from its very first step). Compaction itself can only - * shrink HISTORY: a prefix that alone approaches the window is a - * configuration error no compactor fixes. - * - * Retention is a UNIFORM tail→head walk over the whole surface — turn - * boundaries play NO role. Walking node-by-node from the tail and summing - * token estimates, once the retained total reaches `retainTokens` the cutoff - * is rounded to a balanced tool-pairing boundary: if the cut before the - * retained node is unbalanced (an unanswered tool-call sits before it — i.e. - * it is mid-step), the walk continues head-ward until the cut is balanced so - * the whole step is retained (never splitting a step's tool-calls from their - * results); if it stopped on a free node (a node belonging to no step), that - * cut is already balanced. This always rounds toward retaining MORE (retained - * ≥ `retainTokens`) and is boundary-safe by construction — no separate snap - * pass. - * - * The compacted range is always anchored at the surface HEAD (`nodes[0]`): - * auto-compaction re-consolidates any prior head checkpoint into one fresh - * checkpoint. Declines (`null`) when nothing is over threshold, when the whole - * surface fits the retain budget, or when no balanced cutoff exists in the - * compactable range (its only content is an open tail step — retry once it - * closes). + * The sole pressure gate: count the next request's prefix, derived history, + * and system prompt. Above threshold, retain a recent tool-balanced tail and + * compact the head, reconsolidating any prior automatic checkpoint. Returns + * `null` when no safe or necessary range exists. */ override async compactIfNeeded( agent: Agent, @@ -466,14 +353,7 @@ export class BasicCompactService extends CompactService { throw new Error(`compactRegion: start seq ${start} (position ${startIdx}) is after end seq ${end} (position ${endIdx}) on the surface`) } - // The region must never split a step's assistant-message tool-calls from - // their tool/results (which would orphan one side and produce a transcript - // every provider rejects). A region is safe iff BOTH its edges are balanced - // cuts: the cut before `start`, and the cut after `end`. A node that belongs - // to no step (pre-step user message, inter-step steering, injection context) - // is a balanced (free) boundary; an `end` inside an open (unclosed) tail step - // leaves the cut after it unbalanced (the open tool-call has no result yet), - // so it is rejected. See dsh-session's tool-pairing balance check. + // Both range edges must preserve assistant tool-call/result pairing. const events = session.events if (!isToolPairingBalanced(nodes, events, start)) { throw new Error(`compactRegion: start seq ${start} is not a balanced boundary (would split a step's tool-call/result pair)`) @@ -489,13 +369,8 @@ export class BasicCompactService extends CompactService { throw new Error('compaction already in progress') } - // Compaction's events (compact/* and the replacement user/message) must be - // turn-enclosed: the session-log contract rejects any plugin event appended - // outside an open turn. Auto-compaction satisfies this — it runs on the - // `agent/pre-step` seam, after `turn/start` and before `step/start`, so - // strictly inside the open turn (but outside any step). A manual call on a - // fully-closed session has no turn to enclose the events, so reject rather - // than emit an un-enclosed run. + // Compaction's events (compact/* and the replacement user/message) must be turn-enclosed: + // the session-log contract rejects any plugin event appended outside an open turn. const openTurn = this._openTurn(session) if (openTurn === null) { throw new Error('compactRegion: no open turn — compaction events must be enclosed in a turn') @@ -536,13 +411,8 @@ export class BasicCompactService extends CompactService { ...maxTokens !== undefined ? { maxTokens } : {}, }) - // --- Surface replacement --- - // The user/message directly shadows all compacted surface nodes with a - // single replace op. It is the ONLY surface event in the compaction - // sequence — compact/start, compact/summary, and compact/end are log-only - // (surfaceOp is rejected by the compiler for non-SurfaceEventType). - // The landed content is FRAMED (checkpoint preamble + tag-wrapped summary); - // the compact/summary provenance event above holds the raw model output. + // --- Surface replacement --- The user/message directly shadows all compacted surface + // nodes with a single replace op. session.append('user/message', { content: framedSummary, source: { kind: 'plugin', plugin: 'compact' }, @@ -596,17 +466,8 @@ export class BasicCompactService extends CompactService { } /** - * Whether a compaction is currently in progress for `session` — an unmatched - * `compact/start` (no later `compact/end`) WITHIN the current turn. - * - * The scan is scoped to the current turn: walking back from the tail it stops - * at the first `turn/end` (the boundary closing the prior turn). A - * `compact/start` left orphaned by a crash mid-compaction lives in a turn that - * persistence repair then closes with a synthetic `turn/end`; scoping here so - * that a stale orphan from a PAST turn cannot wedge compaction forever (it sits - * before the nearest `turn/end`, so the scan never reaches it). An in-progress - * compaction's `compact/start` is always in the still-open current turn, - * before any `turn/end`, so it is still detected. + * Whether a compaction is currently in progress for `session` — an unmatched `compact/start` + * (no later `compact/end`) WITHIN the current turn. */ private _isCompactionInProgress(session: Session): boolean { const events = session.events @@ -672,17 +533,7 @@ export class BasicCompactService extends CompactService { return { start: firstSeq, end: cutoffSeq } } - /** - * Keep ONLY text blocks from the model-produced summary before storing it. - * - * The summary lands on the surface as a synthesized `user/message` (see - * {@link _frameSummary}), so the only block type that is both useful and safe - * there is `text`. A model assistant message can otherwise carry `reasoning` - * (private chain-of-thought, must not leak into the durable checkpoint) and - * `tool-call` blocks — and a surviving `tool-call` in a user message would be - * an orphaned call with no matching `tool-result`, exactly the tool-pairing - * breakage compaction works to avoid. Filtering to text drops both. - */ + /** Keep only text; checkpoints cannot contain reasoning or orphan tool calls. */ private _textOnly(blocks: readonly ContentBlock[]): ContentBlock[] { return blocks.filter((block): block is Extract => block.type === 'text') } diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 1a30cc9fc9..44ae51ccad 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -82,15 +82,7 @@ function createTestService(overrides: Partial = {}): TestCom return new TestCompactService(new Context(), cfg({ auto: false, ...overrides })) } -/** - * Build a multi-turn session with surface markers (simulating real agent-loop - * output). Compaction always runs inside an OPEN turn (the loop fires the - * `agent/pre-step` seam after a turn's start and before a step's start), so by - * default the session is left with a trailing open turn: turns `1..turns` - * close, then one more `turn/start` opens with no matching `turn/end`. Pass - * `{ leaveOpen: false }` for a fully-closed session (e.g. to assert that manual - * compaction is rejected when no turn is open). - */ +/** Build closed turns plus an open compaction turn unless `leaveOpen` is false. */ function multiTurnSession(turns: number, messagesPerTurn: number = 2, opts: { leaveOpen?: boolean } = {}): Session { const leaveOpen = opts.leaveOpen ?? true const s = new Session(SessionId('test')) @@ -211,12 +203,8 @@ function expectNoOrphanToolResults(messages: Message[]): void { describe('BasicCompactService step-alignment (never split a tool-call/result pair)', () => { it('compactIfNeeded rounds the retained boundary head-ward to keep a whole step (no orphaned tool-result)', async () => { - // 3 turns, each one step = { assistant(tool-call), tool/result }. Surface - // (9 nodes): user1, asst1, res1, user2, asst2, res2, user3, asst3, res3 — - // 10/20/10 tokens. The tail→head walk retains by whole units; the compacted - // region always ends on a step boundary, so no step's tool-call is split - // from its result. retainTokens=55 keeps the recent tail; the older steps - // compact intact. + // Retain the recent tail while the older assistant/result pairs compact as + // whole units; no boundary may orphan a result. const svc = createTestService({ contextWindow: 280, thresholdRatio: 0.5, retainTokens: 55 }) const session = toolTurnSession(3) @@ -231,12 +219,8 @@ describe('BasicCompactService step-alignment (never split a tool-call/result pai }) it('compactIfNeeded returns null when the only compactable region is an un-splittable single step', async () => { - // The surface is exactly ONE step: [assistant(tool-call), tool/result]. Over - // threshold (by the derived role overhead), the tail→head walk stops with the - // retained boundary at the tool/result — which is NOT a step-aligned start (its - // issuing assistant precedes it in the same step). Rounding head-ward to find a - // clean boundary reaches index 0, so there is no step-aligned cutoff in the - // compactable range: compactIfNeeded declines rather than splitting the step. + // The only candidate cut is inside one assistant/result pair; with no safe + // compactable prefix, decline rather than split it. const s = new Session(SessionId('one-step')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) @@ -605,27 +589,16 @@ describe('BasicCompactService.compactIfNeeded', () => { }) it('returns null when the whole surface fits the retain budget (over threshold by role/system overhead)', async () => { - // threshold = floor(480*0.1) = 48. The 4 surface nodes weigh 10 each (raw 40 - // for the retention walk), but the derived estimate adds 4 role tokens per - // message → 56 ≥ 48, so the threshold check passes and the walk runs. The - // walk accumulates all 40 < retainTokens (45) without crossing the budget, - // so keepFromIdx reaches 0 and compaction declines. + // Role overhead pushes the request above its 48-token threshold, but the + // raw four-node retention walk remains below retainTokens=45, so all fit. const svc = createTestService({ contextWindow: 480, thresholdRatio: 0.1, retainTokens: 45 }) const session = multiTurnSession(2, 1) expect(await compactIfNeeded(svc, session, '', 'm', SIGNAL)).toBeNull() }) it('compacts a runaway turn: its early CLOSED steps summarize while recent steps stay verbatim', async () => { - // The REGRESSION that motivated dropping turn-protection. A single in-flight - // (open) turn has grown past the threshold on its own: several CLOSED steps, - // each [assistant(tool-call), tool/result]. Retention is turn-agnostic, so - // the turn's OWN early closed steps are eligible — they compact while the - // recent tail stays verbatim, and the harness survives. - // - // On the OLD layer-2 code this test FAILS: the entire open turn was retained - // verbatim (protectedIdx = first open-turn node = 0), so compactIfNeeded - // returned null and shadowedSeqs would be empty — the runaway turn could - // never compact and the next model call would overflow the window. + // Completed early steps of the open turn remain eligible; protecting the + // whole turn would make a runaway turn impossible to compact. const svc = createTestService({ contextWindow: 800, thresholdRatio: 0.1, retainTokens: 25 }) const s = new Session(SessionId('runaway')) // ONE open turn with 5 closed steps; each step is [asst(tool-call), result]. @@ -665,12 +638,7 @@ describe('BasicCompactService.compactIfNeeded', () => { }) it('compacts again after a prior summary node heads the surface (the summary stays eligible)', async () => { - // After the first compaction lands a replacement summary node at the head, - // a second compaction (still over threshold) re-consolidates it with newer - // context — head-anchoring means the prior checkpoint is always re-included, - // never stranded. retainTokens=25 leaves a couple of retained nodes after - // the first compaction (so the surface is [summary, …retained], not just - // [summary]). + // Head-anchored recompaction must include the previous summary and retained context. const svc = createTestService({ contextWindow: 800, thresholdRatio: 0.1, retainTokens: 25 }) const s = multiTurnSession(4, 1) // turns 1-4 closed, turn 5 open (no surface yet) @@ -776,10 +744,8 @@ describe('BasicCompactService blocking (compaction in progress)', () => { }) it('is not wedged by an orphaned compact/start from a prior (now-closed) turn', async () => { - // A crash mid-compaction left a compact/start with no compact/end; the turn - // it lived in was later closed (persistence repair appends turn/end). A - // whole-log scan would treat that stale start as an active lock forever. The - // scan is scoped to the current turn, so a NEW turn compacts normally. + // An orphaned start in a closed repaired turn is stale; only the current + // turn participates in the in-progress lock. const svc = createTestService() const s = new Session(SessionId('stale-lock')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) @@ -860,11 +826,8 @@ describe('BasicCompactService HMR safety', () => { }) it('disposing the plugin fiber unregisters ctx.compact', async () => { - // Mount through the real plugin fiber (the Loader path), then dispose it and - // confirm the service registration is torn down. LlmService is mounted first - // so the service's `inject: ['llm']` resolves and the fiber activates. (The - // sibling-fiber ctx.llm resolution this same setup also exercises is covered - // under the "llm inject (real plugin-load path)" suite.) + // Mount through the real plugin fiber (the Loader path), then dispose it and confirm the + // service registration is torn down. const ctx = new Context() await ctx.plugin(LlmService) const fiber = await ctx.plugin(BasicCompactService, cfg({ auto: false })) @@ -1259,11 +1222,8 @@ describe('BasicCompactService auto-compaction (agent/pre-step listener)', () => it('summarization is interceptable at llm/stream (model routing for direct calls)', async () => { const { ctx, adapter } = await ctxWithModel('ROUTED SUMMARY', 'routed-model') - // The summarize call is a direct one-shot model call, not a loop step: it - // does not run agent/request (that seam shapes the loop's conversation - // requests). llm/stream is its interception surface, and a hand-built - // request is not frozen, so mutate-then-next model routing works — the - // adapter resolves AFTER the waterfall, so the rewrite picks the adapter. + // One-shot summaries bypass agent/request but remain mutable at llm/stream; + // adapter selection happens after the waterfall rewrite. ctx.on('llm/stream', (options, next) => { options.model = 'routed-model' return next() @@ -1517,19 +1477,13 @@ describe('BasicCompactService edge cases', () => { const svc = createTestService() const s = new Session(SessionId('empties')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - // Step 1: an empty-text user, an empty-reasoning assistant with NO tool-call - // (balanced: nothing to answer), and empty context/steering — all extract to - // nothing and are skipped. s.append('step/start', { turn: 1, step: 1 }) s.append('user/message', { content: [{ type: 'text', text: '' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'reasoning', text: '' }] }, { surfaceOp: 'append' }) s.append('context/message', { content: [], source: { kind: 'user' } }, { surfaceOp: 'append' }) s.append('steering/message', { turn: 1, content: [{ type: 'text', text: '' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) s.append('step/end', { turn: 1, step: 1 }) - // Step 2: a tool exchange whose tool/result has empty content → empty - // extraction → skipped. The assistant carries the matching tool-call so the - // surface stays tool-pairing balanced; its text extracts to the tool-call - // placeholder (the one surviving line). + // Keep the log pairing-valid while the empty result covers the final message kind. s.append('step/start', { turn: 1, step: 2 }) s.append('assistant/message', { turn: 1, step: 2, @@ -1661,10 +1615,8 @@ describe('BasicCompactService positional range (surface seqs are not monotonic a describe('BasicCompactService llm inject (real plugin-load path)', () => { it('declares llm in static inject so a sibling fiber can resolve ctx.llm', () => { - // summarize() reads ctx.llm; the inject lets the cordis ctx proxy resolve a - // sibling LlmService when this service is mounted as its own plugin fiber. - // Asserting the declaration (and exercising the real mount below) guards the - // resolution that root-ctx unit tests cannot, since they share one fiber. + // summarize() reads ctx.llm; the inject lets the cordis ctx proxy resolve a sibling + // LlmService when this service is mounted as its own plugin fiber. expect(BasicCompactService.inject).toContain('llm') }) diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 711e6fab69..15cc0aa410 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -1,9 +1,7 @@ /** - * The agent loop driver: one `runLoop()` invocation drives one agent for its - * whole lifetime. Error-contained at the turn level — a throwing plugin ends - * the turn, never kills the loop. See the JSDoc on `runLoop()` for the full - * lifecycle pseudo-code. - * + * Drives one agent across queued durable turns. Turn failures are contained so + * later work can run; the session log, not this driver, owns conversation state. + * See docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md. * @module dsh-agent-loop/loop */ @@ -25,33 +23,12 @@ import type { Inbox } from './inbox.ts' /** An Error with an optional machine-readable code (e.g., from LlmError or a throwing plugin). */ type CodedError = Error & { code?: string } -/** - * Normalize an arbitrary thrown value into a coded Error. A real Error passes - * through (its `code`, if any, is preserved by {@link errorData}); a non-Error - * throw is wrapped in a {@link HarnessError} with code `UNKNOWN` and the - * original value chained as `cause`, so a bad throw still carries a routable - * code instead of degrading to a bare message. - */ +/** Normalize thrown values while preserving an existing error code. */ function toError(error: unknown): CodedError { return error instanceof Error ? error : new HarnessError(String(error), 'UNKNOWN', { cause: error }) } -/** - * Map a model-call {@link FinishReason} to the step error it should raise, or - * `undefined` when the step completed normally. - * - * Adapters report provider/transport failures one of two sanctioned ways (see - * the StreamChunk contract in dsh-llm): throw from `stream()` (handled by the - * caller's try/catch), OR end the stream with a finish-error/aborted chunk - * (the only option for adapters that can't throw mid-stream, e.g. - * library-backed ones). This translates the latter into a thrown step error - * so the turn ends error/aborted (the failure recorded on `turn/end.reason`), - * never as a normal `completed` assistant message. - * - * `FinishReason` is merge-extensible (plugins/adapters can add `kind`s), so - * the switch handles the known terminal-failure kinds and treats every other - * kind — `stop`, `tool-calls`, `max-tokens`, future additions — as success. - */ +/** Convert terminal failure finishes into step errors; unknown extensible finishes remain successful. */ function finishError(finish: FinishReason): CodedError | undefined { switch (finish.kind) { case 'error': { @@ -78,19 +55,7 @@ function errorData(err: CodedError): { message: string; code?: string } { return { message: err.message, ...typeof err.code === 'string' ? { code: err.code } : {} } } -/** - * The turn-end contribution of a step's *successful* finish, or `undefined` - * when the step finished ordinarily (a plain `completed`). - * - * {@link finishError} has already converted `error`/`aborted` finishes into - * thrown step errors, so the finishes that reach here are `stop`, - * `tool-calls`, `max-tokens`, or a future merge-extensible kind. Only - * `max-tokens` carries forward as a distinct {@link TurnEndReason}: a step that - * hit the output-token ceiling ended the turn cut-short rather than by the - * model's choice. `stop`/`tool-calls`/unknown kinds contribute nothing beyond - * the default `completed`. {@link runTurn} applies this with the rule "any - * `max-tokens` step in the turn makes the turn end `max-tokens`". - */ +/** Map a successful max-token finish onto the turn reason; other successful finishes add nothing. */ function stepFinishReason(finish: FinishReason): TurnEndReason | undefined { switch (finish.kind) { case 'max-tokens': @@ -103,11 +68,7 @@ function stepFinishReason(finish: FinishReason): TurnEndReason | undefined { } } -/** - * Ambient handles the loop driver receives from the agent. Decouples the - * pure function `runLoop` from the mutable ReactLoopAgent fields, making the - * loop testable without a real agent. - */ +/** Mutable agent controls supplied to the loop driver. */ export interface LoopHandle { /** Native-private agent inbox handed to the driver only at internal startup. */ readonly inbox: Inbox @@ -116,122 +77,37 @@ export interface LoopHandle { /** Resolves when the agent is disposed — unblocks the idle wait. */ disposed: Promise isDisposed(): boolean - /** - * Whether a `cancel()` is pending for the current turn. The driver checks this - * at every decision point where a turn could start or continue (right after - * the idle wait, after the `running` flip, before each step, and at the - * continuation gate) and drops the about-to-run / continuing turn. Reset once - * per loop iteration via {@link clearCancel} after the turn returns, so the - * marker governs exactly one cancellation and never leaks to a later prompt. - */ + /** Whether cancellation is pending for the current loop iteration. */ isCancelled(): boolean - /** - * The resolved reason for the pending cancel (`reason ?? 'cancelled'`), read - * by the marker branches (pre-step / continuation) so a turn dropped where no - * `AbortController` carries the reason still records the caller's - * `cancel(reason)` value — matching the mid-step abort path. Only meaningful - * when {@link isCancelled} is true. - */ + /** Resolved pending-cancellation reason; meaningful only while {@link isCancelled} is true. */ cancelReason(): string /** Clear the cancel marker (called once per iteration after the turn returns). */ clearCancel(): void - /** - * Settle pending `whenIdle()` waiters WITHOUT a status transition. Used by the - * pre-step cancel-skip path: it drops the about-to-run turn and re-parks at the - * idle wait, so no `running→idle` transition fires to settle a `whenIdle()` - * waiter that was registered in the pre-step window — this settles it directly - * (it emits no `agent/status`, so an ACP `agent/status` listener never sees a - * spurious idle that would resolve a freshly-queued prompt as cancelled). - */ + /** Settle idle waiters when pre-running cancellation skips a turn, without emitting `agent/status`. */ settleIdle(): void } /** - * The agent loop. One invocation drives one agent for its whole lifetime: - * - * ``` - * create agent → emit agent/session-start(source) ⟵ once, before turn 1 - * forever: - * wait for queued messages (idle) - * TURN (error-contained — a throwing plugin ends the turn, never the loop): - * 'turn/start'; each queued msg: waterfall agent/prompt-submit ⟵ durable turn boundary (no agent/* mirror) - * allow → session('user/message'…) (+ inject additionalContext) | block → drop - * every prompt blocked → 'turn/end'(rejected), 0 steps - * STEP loop: - * drain steering → session('steering/message') ⟵ catches late steering - * assembly = ctx.systemPrompt.assemble(assembleContextFor(agent)) ⟵ waterfall system-prompt/assemble - * (scope-filtered; scoped sections/tools join); renderPrompt - * (persona section + {{variables}}) IS the full prompt - * prefix ??= waterfall agent/session-prefix ⟵ once per loop instance (first step): frozen - * session prefix; logged on the header, never - * session history (scope-filtered, fused dispatch) - * await events.serial('agent/pre-step', …, prefix) ⟵ surface mutation (compaction) OUTSIDE the step; - * pressure gates see the prefix the request carries - * boundary = session.deriveMessages() ⟵ the reconstruction boundary: snapshot in the - * session('step/start') same sync frame, strictly before step/start - * config = waterfall agent/request(config) ⟵ frozen seed; a returned replacement switches - * session('request/header') ⟵ the header event this request owes the - * log (initial/resume anchor or changed snapshot) - * req = freeze({header..., messages: prefix+boundary, sessionId, signal}) - * stream ctx.llm.stream(req) ⟵ waterfall llm/stream (raw chunks, frozen req) - * session('assistant/chunk') - * msg = waterfall agent/step-result ⟵ BEFORE the log append, so the - * session('assistant/message' {content, usage?}) session records what actually ran - * each tool-call in msg (sequential, abort-checked): - * session('tool/call'); ctx.tools.execute() ⟵ tools/pre-execute (allow/deny/ask) - * → dispatch → tools/post-execute - * session('tool/result') - * append buffered post-execute additionalContext → session('context/message')(s) - * drain steering → session('steering/message') - * session('step/end') ⟵ durable step boundary (no agent/* mirror) - * cont = waterfall agent/turn-continuation ⟵ ContinuationDecision; default - * {action: hadToolCalls||steered ? 'continue':'stop'}; a continue.reason is - * recorded as next-step steering - * if action==stop && steering arrived (step/end/continuation listeners): continue anyway - * terminal = serial agent/turn-stop ⟵ stop or abstain; after all ordinary - * continuation and steering folding - * if terminal: discard pending steering and break - * if action==stop: break - * session('turn/end') ⟵ durable turn boundary (no agent/* mirror) - * await ctx.sessions.flush(session) ⟵ durability checkpoint (store-owned carrier) - * re-enqueue leftover steering as queued ⟵ steering is never stranded - * idle (emit agent/status) unless more queued - * ``` + * Drive queued batches as durable turns until disposal. Plugin failures end the + * current turn without terminating the driver. * @param ctx - the plugin context the loop reaches events (agent/…, session/flush) and services (systemPrompt, llm, tools) through. * @param agent - the agent this invocation drives for its whole lifetime (its inbox, session, and options). * @param handle - the bridge to the agent's mutable state: status/abort setters plus the disposal and cancel-marker reads. */ export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopHandle): Promise { - // Per-instance transmission bookkeeping: whether THIS loop instance has - // anchored the log's header fold yet (its first request logs a - // 'initial'/'resume' request/header snapshot). Everything else the request - // needs is read from the session log itself — the loop holds no - // conversation state (the reconstructability RFC). + // Per-instance prefix and request-header state; conversation history remains in the session log. const transmission = createTransmissionLog() const { session } = agent - // The fused agent-subject dispatcher: every agent/* dispatch below carries - // the agent's scope (an `agent.ctx` listener hears only this agent) with - // the subject injected — one spelling, checked by the dev invariants. + // Fused subject and scope carrier for every agent event below. const events = agentEvents(ctx, agent) while (!handle.isDisposed()) { await handle.inbox.waitForQueued(handle.disposed) if (handle.isDisposed()) break - // Pre-step cancel (window 1): a `cancel()` landed after a `send()` woke the - // idle wait but before we flip to `running`. The cancelled queued/steering - // work is already cleared by `cancel()`. Clear the marker, then: - // - if NOTHING new is queued, drop the about-to-run turn and re-park, - // settling any `whenIdle()` waiter DIRECTLY (no running→idle transition - // fires here to settle it) and WITHOUT emitting `agent/status` (an ACP - // listener must not see a spurious idle that resolves a freshly-queued - // prompt as cancelled); - // - if a NEW prompt was queued AFTER the cancel (a send() that raced in - // before the loop resumed), the marker was for the cancelled work only — - // fall through and run the new prompt's turn. Do NOT settle waiters here: - // a whenIdle() waiter must wait for that new turn's running→idle, not - // resolve before it runs (the quiescence contract). + // Cancellation between wake and `running` skips only the cancelled work; + // a replacement prompt still runs and owns the eventual idle transition. if (handle.isCancelled()) { handle.clearCancel() if (!handle.inbox.hasQueued) { @@ -242,18 +118,8 @@ export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopH handle.setStatus('running') - // Pre-step cancel (window 2): `setStatus('running')` emits `agent/status` - // SYNCHRONOUSLY, so a `running` listener can `cancel()` in the gap between the - // check above and `runTurn`. Mirror window 1: clear the marker, then - // - if NOTHING new is queued, drop the about-to-run turn and transition - // back to `idle` (`running` was already emitted, so a real idle - // transition balances the status AND settles `whenIdle()` waiters); - // - if a NEW prompt was queued AFTER the cancel (a `running` listener that - // cancels then sends), the marker was for the cancelled work only — fall - // through and run the new prompt's turn (status is already `running`), so - // a `whenIdle()` waiter resolves on THAT turn's running→idle, not before - // it runs. Settling here would resolve quiescence while the replacement - // is still queued and unrun (the same early-resolve race window 1 fixes). + // A synchronous `running` listener can cancel before `runTurn`; balance the + // status only when no replacement prompt was queued by that listener. if (handle.isCancelled()) { handle.clearCancel() if (!handle.inbox.hasQueued) { @@ -262,24 +128,13 @@ export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopH } } - // Re-derive the turn number from the log each iteration (do NOT keep a local - // counter): an idle `agent.inject()` can append its own one-shot turn while - // the loop waits above, so the next real turn must continue from whatever - // turn number is actually last in the log — a stale counter would collide. + // Idle injection can add a turn, so derive the next number from the log. const turn = lastTurnNumber(session) + 1 let terminalStopped = false try { terminalStopped = await runTurn(ctx, events, agent, handle, turn, transmission) } catch (error: unknown) { - // Backstop: runTurn rethrows only a PRE-turn throw (the invariant guard - // before turn/start) — no turn/start was appended, so no turn is open and - // none is owed. A session `error` here would land outside any turn (after - // the previous turn/end), where the persistence backend drops it as a - // crash tail (the turn-enclosure RFC). Report via agent/error + the logger only; the - // driver survives and moves on. - // Acceptance and internal dispatch validation can reject before - // turn/start commits. Report that supported pre-turn failure without - // inventing a turn/end for a turn that never opened. + // Pre-turn failure has no durable boundary to close; report it without appending outside a turn. const err = toError(error) ctx.logger.warn(`agent "${agent.id}": turn ${turn} failed before it started: ${err.message}`) try { @@ -287,21 +142,10 @@ export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopH } catch { /* contained: a throwing agent/error listener must not kill the driver */ } } - // Reset the cancel marker UNCONDITIONALLY here, after the turn returns and - // before the next iteration's idle wait. NOT gated on the idle transition - // below: a `send()` that lands during the cancelled turn's flush window makes - // `hasQueued` true at the `setStatus('idle')` guard, so an idle-gated reset - // would never fire and the stale marker would wrongly drop that next prompt's - // turn. Resetting per iteration scopes the marker to exactly the turn that was - // cancelled. + // Reset per iteration, including when a prompt arrives during the flush window. handle.clearCancel() - // Steering that arrived too late to join an ordinary turn (turn-end - // listeners, flush) becomes queued input so it is never stranded. A - // terminal-stop owner is the deliberate exception: discard the steering - // again after the close + flush window so terminal policy cannot be undone - // after its in-turn drain. Ordinary queued sends live in a separate FIFO and - // remain untouched. + // Late steering becomes queued input unless terminal policy stopped the turn. for (const message of handle.inbox.drainSteering()) { if (!terminalStopped) handle.inbox.enqueue(message) } @@ -315,10 +159,7 @@ async function runTurn( ): Promise { const { session } = agent - // --- Pre-turn. A throw here (the invariant guard) is owed NO turn/end — - // turn/start has not been appended — so it propagates to runLoop's backstop - // untouched. The queued messages are drained here but appended AFTER - // turn/start (below), so every event in the log lives inside a turn. + // Drain before opening the turn, but append only after `turn/start`. const queued = handle.inbox.drainQueued() const first = queued[0] /* v8 ignore next 3 -- invariant guard: runLoop only calls runTurn when hasQueued */ @@ -331,28 +172,17 @@ async function runTurn( let errorReported = false let terminalStopped = false - // Close the open step exactly once (idempotent via stepOpen). Post-commit - // session/event observers are contained by Session; a pre-commit validator - // failure still escapes so the outer recovery path may retry the boundary or - // fail loudly without pretending an uncommitted step/end exists. + // Close the committed step once; pre-commit validation failure still escapes. const closeStep = (): void => { if (!stepOpen) return session.append('step/end', { turn, step }) stepOpen = false } - // Record a step/turn failure exactly once: set the error reason (carrying the - // failing `step` — the durable failure lives entirely on turn/end.reason, there - // is no separate session error event) and emit agent/error (contained — trap: a - // throwing agent/error listener must not re-escape and strand the turn). - // Disposal and abort set `reason` directly without calling this (they are not - // failures). + // Record the durable turn failure once and contain the live error notification. const failTurn = (err: CodedError): void => { if (errorReported) return errorReported = true - // The turn is still open here. Post-commit observers cannot escape append, - // and a pre-commit turn/end veto leaves no closing boundary to overwrite. - // Set the reason that the next successful closeTurn will append. reason = { kind: 'error', step, ...errorData(err) } try { events.emit('agent/error', turn, step, err) @@ -362,9 +192,7 @@ async function runTurn( } } - // Close the turn. Post-commit observer failures are contained by Session; - // pre-commit validation failures escape to recovery instead of being mistaken - // for a committed boundary. Turn boundaries are durable session events only. + // Pre-commit validation failure escapes rather than masquerading as a committed boundary. const closeTurn = (): void => { session.append('turn/end', { turn, reason }) } @@ -414,11 +242,7 @@ async function runTurn( } while (true) { - // A fully-blocked batch (every prompt vetoed by prompt-submit) opens a - // zero-step turn that ends `rejected`: break BEFORE the first step so the - // boundary stays balanced (turn/start → turn/end) and the block is a - // durable in-turn fact. `anyAllowed` never changes inside the loop, so this - // only ever fires on the first iteration. + // A fully blocked batch closes its zero-step turn as rejected. if (!anyAllowed) { reason = { kind: 'rejected', reason: lastBlockReason } break @@ -437,48 +261,20 @@ async function runTurn( const abort = new AbortController() handle.setAbort(abort) - // Assemble the system prompt for this step. Done HERE (before step/start) - // because the pre-step seam needs it: compaction measures token pressure - // against the system prompt (it counts toward the budget). runStep reuses - // this same assembly for the request, so the prompt is assembled once per - // step. renderPrompt IS the full prompt — the persona is the order-0 - // section (owned by dsh-system-prompt) and `{{variable}}` - // interpolation happens in the render, so there is no separate join. + // Assemble once before pre-step so pressure checks and the request share the same prompt. const assembly = await ctx.systemPrompt.assemble(assembleContextFor(agent)) const fullSystemPrompt = renderPrompt(assembly) - // Interruption landing after assembly: dispose() or cancel() in a - // turn-start listener (or a listener whose promise resolved before the - // await above) arms either handle.isDisposed() or handle.isCancelled(). - // The Abort was created first, so any concurrent abort also lands on it. - // Drop the about-to-start step WITHOUT running the seam — no step is open - // yet, so end the turn accordingly (disposed wins for an unambiguous - // reason). + // Cancellation or disposal during assembly ends the turn before any step opens. if (handle.isCancelled() || handle.isDisposed()) { handle.setAbort(undefined) reason = handle.isDisposed() ? { kind: 'disposed' } : { kind: 'aborted', reason: handle.cancelReason() } break } - // Compose the session prefix ONCE per loop instance, lazily before the - // instance's first pre-step: request-only messages placed in front of - // the ENTIRE derived history on every request this instance sends. It - // MUST precede the pre-step seam so compaction gates on THIS instance's - // prefix — reading a previous instance's logged prefix would let a - // resumed/forked instance whose contributor grew skip compaction and - // ship an over-window first request. The result is deep-cloned - // (decoupled from listener-held references), deep-frozen, and cached on - // the transmission bookkeeping, so reuse is structural — the prefix - // cannot change mid-session and the provider prefix cache holds by - // construction (resume = a new instance = a recompose, anchored by its - // 'resume' snapshot). The prefix is not session history — the header - // event in runStep is its only durable record - // (EpochHeader.messagePrefix). The frozen empty seed serves both the - // listener chain and the no-listener fallback: a contribution is a - // RETURNED extension of `await next()`, never an in-place push. This - // runs OUTSIDE the step, before the boundary snapshot: a composing - // listener's session append lands before the boundary and joins the - // CURRENT request. + // Compose the request-only prefix once per loop instance before pressure + // checks. It precedes all derived history and is recorded only in the + // request header, not as session history. if (transmission.sessionPrefix === undefined) { const emptyPrefix: Message[] = deepFreeze([]) const composed = await events.waterfall( @@ -486,16 +282,7 @@ async function runTurn( () => Promise.resolve(emptyPrefix), ) - // Interruption landing during prefix composition: mirror the assembly - // window above — drop the about-to-start step without running the - // seam, and DISCARD the composition instead of caching it. An - // abort-aware listener may have returned a degraded fallback under - // the firing signal; committing it would ship a prefix no request - // ever used (and no header ever logged) on this instance's next real - // request. The next turn recomposes under a live signal — the cache - // only ever holds a fully composed prefix. The cache-hit path needs - // no such check: nothing awaits between the assembly check above and - // the pre-step seam. + // Never cache an interrupted composition; the next turn recomposes it. if (handle.isCancelled() || handle.isDisposed()) { handle.setAbort(undefined) reason = handle.isDisposed() ? { kind: 'disposed' } : { kind: 'aborted', reason: handle.cancelReason() } @@ -504,19 +291,7 @@ async function runTurn( transmission.sessionPrefix = deepFreeze(structuredClone(composed)) } - // Pre-step surface-mutation checkpoint (compaction), fired OUTSIDE the - // step: after `turn/start` (and the prior step's close) but before - // `step/start`, so a compaction's log-only `compact/*` records and its - // replacement node land cleanly outside any step (honest structure that - // crash-safety relies on — a dangling `compact/start` sits before the - // synthetic `turn/end` repair appends). Serial (awaited, in order, no - // veto): each listener completes its surface mutation before the next, so - // concurrent listeners cannot interleave their `session.append`s. A - // throwing listener escapes to the outer catch, which closes the (not-yet- - // open) step as a no-op and ends the turn via failTurn — a broken - // pre-step plugin ends the turn, not the loop. The composed session - // prefix rides along so token-pressure listeners count everything the - // request will actually carry. + // Await surface mutations outside the step; pressure checks receive the pending prefix. await events.serial('agent/pre-step', turn, step, fullSystemPrompt, transmission.sessionPrefix, abort.signal) // Interruption landing during the pre-step seam: do not open an empty step. @@ -526,16 +301,8 @@ async function runTurn( break } - // The reconstruction boundary (the reconstructability RFC): the request's - // messages are snapshotted HERE, in the same synchronous frame as the - // step/start append directly below — so the snapshot is exactly the - // derivation over the log prefix strictly before step/start's seq. - // Anything appended later by the request-window inject seam or a - // concurrent task lands after the boundary and joins the NEXT request. - // session/event itself is observe-only: append reentrancy is rejected - // until the current callback list drains. An external reconstructor - // recovers these exact messages by folding the surface over - // events[0..stepStartSeq). + // Snapshot the exact log prefix before step/start: the reconstruction + // boundary. Appends after this synchronous snapshot join the next request. const boundaryMessages = session.deriveMessages() session.append('step/start', { turn, step }) @@ -582,13 +349,7 @@ async function runTurn( break } - // The successful step's finish reason carries forward: a `max-tokens` - // step makes the whole turn end `max-tokens` (the ACP RFC's rule "any - // max-tokens step surfaces as max-tokens"). `stepFinishReason` returns - // `max-tokens` or `undefined`, so a later ordinary step never resets a - // max-tokens turn back to completed, and a never-truncated turn keeps the - // default `completed`. The disposal/abort/error branches above and the - // continuation-window disposal check below override this — they win. + // Preserve max-token completion unless a later disposal, abort, or error wins. const stepReason = stepFinishReason(stepOutcome.finish) if (stepReason) reason = stepReason @@ -610,24 +371,16 @@ async function runTurn( break } - // A forced `continue` may carry model-facing context: record it as - // next-STEP steering (the steering channel), so the continued turn's next - // iteration drains it before its request — the typed twin of the /goal - // step/end-steer pattern. + // A continuation reason becomes next-step steering. if (decision.action === 'continue' && decision.reason) { handle.inbox.steer({ content: decision.reason.content, source: decision.reason.source }) } let shouldContinue = decision.action === 'continue' - // Steering from step/end session-event or continuation listeners (the - // /goal pattern) demands the model see it — it overrides a stop decision; - // the next iteration's drain records it. + // Pending steering overrides an ordinary stop. if (!shouldContinue && handle.inbox.hasSteering) shouldContinue = true - // Terminal policy runs only AFTER the extensible continuation waterfall, - // its optional reason, and late steering have all been folded. Unlike the - // waterfall, this serial seam is monotonic: the first stop bail wins, and - // no later listener or steering override can resurrect the turn. + // Terminal policy is monotonic and runs after ordinary continuation folding. let terminalStop = false try { const stop = await events.serial('agent/turn-stop', turn) @@ -640,19 +393,12 @@ async function runTurn( } if (terminalStop) { terminalStopped = true - // A continuation reason or listener may have queued steering before the - // terminal checkpoint. Discard only steering (never ordinary queued - // prompts) so it cannot become a next step or be re-enqueued as a fresh - // turn by runLoop's late-steering fallback. + // Terminal stop discards steering but preserves ordinary queued prompts. handle.inbox.drainSteering() shouldContinue = false } - // A cancel that landed during the continuation window — after the step's - // AbortController was cleared (setAbort(undefined)) but before the next - // step starts — has no controller to observe it, so the turn-scoped marker - // ends the turn here. cancel() also cleared the steering FIFO, so the - // override above did not re-arm continuation. + // The marker catches cancellation after the step controller was cleared. if (handle.isCancelled()) { reason = { kind: 'aborted', reason: handle.cancelReason() } break @@ -668,19 +414,11 @@ async function runTurn( // Normal / inline-error loop exit: close the turn. closeTurn() } catch (error: unknown) { - // Decide whether this turn opened from the LOG, not a speculative flag. A - // pre-commit validator or acceptance failure leaves no turn/start and owes - // no turn/end, so it propagates to runLoop's backstop. Once turn/start is - // present, this path balances any committed step and records the failure. + // Close only a turn whose start committed to the log. const turnStartLogged = session.events.some(e => e.type === 'turn/start' && e.data.turn === turn) if (!turnStartLogged) throw error closeStep() - // Choose the close reason. Disposal wins only if no error was already - // reported: a turn disposed mid-step sets reason=disposed in the step-error - // branch (without reporting an error), so preserve disposed rather than - // overwrite it. Otherwise a mid-step throw on a live agent is a real - // failure → failTurn. (errorReported is mutated only inside the failTurn - // closure, which the analyzer can't follow, hence the inline lint-disable.) + // Preserve an established disposal reason; otherwise report the failure. if (handle.isDisposed() && !errorReported) { // eslint-disable-line @typescript-eslint/no-unnecessary-condition reason = { kind: 'disposed' } } else { @@ -689,19 +427,11 @@ async function runTurn( closeTurn() } - // Durability checkpoint: persistence plugins drain write-behind buffers. - // A failing persistence plugin is reported but doesn't kill the agent. - // Through the store's flush (the carrier owner), never a raw parallel. + // Flush through the store-owned durability checkpoint without killing the driver on failure. try { await ctx.sessions.flush(session) } catch (error: unknown) { - // The turn is already closed (turn/end appended above) and flush must run - // AFTER turn/end to be a checkpoint — so there is no in-turn position left - // for a session `error` event. Appending one here would land it after the - // last turn/end, where the persistence backend treats it as a crash tail - // and drops it on resume (the turn-enclosure RFC: every event is turn-enclosed). Report - // the failure via agent/error + the logger only; persistence keeps the - // buffered events for the next flush/dispose, so nothing is lost. + // The turn is closed, so report the failed flush live rather than append outside a turn. const err = toError(error) ctx.logger.warn(`agent "${agent.id}": session/flush failed at turn ${turn}: ${err.message}`) try { @@ -722,13 +452,12 @@ function drainSteering(agent: ReactLoopAgent, inbox: Inbox, turn: number): boole return messages.length > 0 } -/** One step: build the request from the boundary snapshot + the step's - * header → compose the session prefix if this instance has none yet → log - * the header event the request owes → stream model → record → execute - * tools. The caller assembles the - * system prompt, fires the `agent/pre-step` seam, snapshots the derivation, - * and opens the step BEFORE calling this, so `boundaryMessages` is exactly - * the surface prefix at step/start and already reflects any compaction. */ +/** + * Run one committed step: transform call config, log the request header, build + * the request from the cached prefix plus the step-boundary snapshot, stream and + * record the response, then execute tools. The caller has already assembled the + * prompt, run `agent/pre-step`, snapshotted history, and opened the step. + */ async function runStep( ctx: Context, events: AgentEventDispatch, @@ -743,40 +472,23 @@ async function runStep( ): Promise<{ hadToolCalls: boolean; finish: FinishReason }> { const { session, options } = agent - // Seed the call config: the first request of THIS loop instance seeds from - // current AgentOptions — explicit options always win over the logged - // baseline, which is what keeps fork model-overrides and resume-time - // reconfiguration correct. Later steps seed from the log's folded header, - // which by then is exactly what this instance last logged. - // One deep-cloned, frozen seed serves BOTH the listener chain and the - // no-listener fallback: structuredClone decouples it from the session's - // cached header fold (a raw reference would let a delegating listener - // mutate the fold in place and silently skip the delta log), and the freeze - // makes in-place shaping unrepresentable — a switch is a RETURNED - // replacement, which the header event below records. + // Seed the first request from agent options and later requests from the logged header; + // detach and freeze so listeners must return an attributable replacement. const seedConfig: LlmCallConfig = deepFreeze(structuredClone(transmission.loggedHeader // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- loggedHeader ⟹ a snapshot is in the log ? session.requestHeader()!.config : { model: options.model ?? '' })) - // Shape the call config: listeners return a replacement to switch model or - // sampling (the seed is frozen — content shaping is not expressible here; - // model-visible content flows through the log channels). The header event - // below records whatever the request ACTUALLY uses, so a listener's switch - // is a logged, reconstructable fact, never silent drift. + // Listener replacements are recorded in the request header before dispatch. const config = await events.waterfall('agent/request', turn, step, seedConfig, () => Promise.resolve(seedConfig)) if (!config.model) { throw new Error(`agent "${agent.id}" has no model: set AgentOptions.model or supply one via the agent/request waterfall`) } - // The session prefix was composed (once per instance) before this step's - // pre-step seam — the caller guarantees it, so the cache is always set here. // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- runTurn composes the prefix before every runStep call const sessionPrefix = transmission.sessionPrefix! - // The request header (the log's request/header snapshots): canonical form, - // recorded before dispatch so the log always explains the request — - // including the session prefix, which no other event carries. + // Record the canonical header, including the otherwise-unlogged prefix, before dispatch. const header = canonicalHeader({ config, ...system ? { system } : {}, @@ -785,11 +497,7 @@ async function runStep( }) recordRequestHeader(session, transmission, header) - // Build and freeze: the request is a pure function of (boundary snapshot, - // logged header) — llm/stream listeners and adapters read it, mutation - // throws. sessionId + frozen is the loop-built marker the dev invariant - // keys on. Message order: header.messagePrefix, then the boundary - // snapshot — the reconstruction equation the invariant recomputes. + // Freeze the logged header plus boundary snapshot; the prefix precedes derived history. const request: GenerateOptions = deepFreeze({ model: header.config.model, messages: [...header.messagePrefix ?? [], ...boundaryMessages], @@ -813,26 +521,16 @@ async function runStep( assembler.push(chunk) } - // Adapters report provider/transport failures one of two sanctioned ways - // (see the StreamChunk contract in dsh-llm): throw from stream() — already - // handled by the caller's try/catch — OR end the stream with a - // finish-error/aborted chunk. finishError() maps the latter to the step - // error to raise (turn ends error/aborted, not a normal completed message). + // Normalize failure finish chunks into the same path as thrown stream errors. const stepError = finishError(assembler.finish) if (stepError) throw stepError if (assembler.finish.kind === 'max-tokens') { let message: Message = withoutToolCalls(assembler.message()) message = withoutToolCalls(await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message))) - // Fire the assistant/message when there is content OR usage: a max-tokens - // step can be cut off with empty content but still carry token accounting, - // and assistant/message is the only host for usage (there is no standalone - // usage event). An empty-content assistant/message is skipped by - // deriveMessages(), so hosting usage on it never injects a spurious assistant - // turn into derived history. + // Preserve usage even when max-token truncation produced no content. if (message.content.length > 0 || assembler.usage) { - // A max-tokens finish is itself a streamed `finish` chunk, so chunkSeqs is - // never empty here — pass the provenance unconditionally. + // The finish chunk guarantees non-empty provenance here. session.append( 'assistant/message', { turn, step, content: message.content, ...(assembler.usage ? { usage: assembler.usage } : {}) }, @@ -842,20 +540,11 @@ async function runStep( return { hadToolCalls: false, finish: assembler.finish } } - // The step-result waterfall runs BEFORE the session append so the log (the - // source of truth for derived history and replay) records the message that - // tool dispatch actually uses. + // Record the post-waterfall message that tool dispatch uses. let message: Message = assembler.message() message = await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message)) - // Same content-or-usage guard as the max-tokens branch: a step that finishes - // with neither assembled content nor usage (e.g. a bare `stop` finish that - // streamed nothing) records no assistant/message — an empty-content message - // exists only to host usage, and deriveMessages() skips it either way, so - // appending one with no usage would be a pure trace-only row. - // - // sourceEventSeqs records the assistant/chunk provenance, but is omitted when - // no chunks streamed (the surface invariant rejects an empty sourceEventSeqs). + // Empty messages exist only to carry usage; omit empty provenance. if (message.content.length > 0 || assembler.usage) { session.append( 'assistant/message', @@ -864,15 +553,9 @@ async function runStep( ) } - // --- Tool execution (sequential; parallel execution is a TODO) --- - // ToolRegistry.execute converts tool failures (including aborts) into - // isError results, so abort is re-checked around every call here. + // Tool execution stays sequential; recheck abort around each normalized result. const toolCalls = message.content.filter(block => block.type === 'tool-call') - // Per-step buffer of `additionalContext` attached by tools/post-execute - // listeners. Appended as context/message(s) only AFTER every tool/result for - // the step, so a multi-call step keeps tool-call/result adjacency - // (interleaving context between a call's result and the next call's would - // break the pairing the next model request relies on). + // Buffer context until all results are appended to preserve call/result adjacency. const pendingContext: HookContext[] = [] for (const call of toolCalls) { /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ @@ -884,12 +567,8 @@ async function runStep( } catch { parsedArguments = call.arguments } - // TODO(pre-tool-input-rewrite): tools/pre-execute deliberately cannot rewrite - // `arguments` — tool/call (the audit record) and assistant/message (the - // model-history source) are logged BEFORE execute, and live consumers (ACP, - // tool-bash presentation) read the pre-execution args, so an execution-only - // rewrite would desync the UI from what ran. Designing that consistently is - // its own proposed RFC (docs/rfc/proposed/feature/…-pre-tool-input-rewrite.md). + // TODO(pre-tool-input-rewrite): Keep logged history and live presentation aligned; + // see docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md. const result = await ctx.tools.execute({ callId: call.id, name: call.name, @@ -899,33 +578,24 @@ async function runStep( }) session.append('tool/result', { turn, step, - // The correlation id MUST be the loop's authoritative call.id (the - // model-transcript id that deriveMessages turns into toolCallId), NOT - // result.callId — a post-execute waterfall listener returning a - // mismatched id would otherwise orphan the call↔result pairing in the - // next model request. A listener-internal id, if ever needed, belongs in - // a separate diagnostic field, never overloaded onto callId. + // Correlation comes from the immutable execution input; the result does + // not duplicate this authoritative transcript identity. callId: call.id, content: result.content, isError: result.isError, ...result.error ? { error: result.error } : {}, - // The tool's private presentation payload (e.g. a result-time diff), - // persisted so a UI bridge reproduces the card on replay. + // Persist tool-owned presentation data for replay. ...result.meta !== undefined ? { meta: result.meta } : {}, }, { surfaceOp: 'append', sourceEventSeqs: [callEvent.seq] }) - // Buffer (don't append yet) any post-execute additionalContext for this call. if (result.additionalContext) pendingContext.push(result.additionalContext) - // signal CAN flip during the await above (abort() inside a tool); - // the analyzer can't see through the await boundary. + // The signal may flip while the tool is awaited. /* v8 ignore start -- signal.reason default unreachable: cancel()/disposal always set it */ // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) /* v8 ignore stop */ } - // Append buffered post-execute context AFTER every tool/result, preserving - // tool-call/result adjacency across the whole batch. inject() appends into the - // open turn (a context/message at its chronological position). + // Append buffered context after the complete result batch. for (const context of pendingContext) { agent.inject(context.content, { source: context.source }) } @@ -948,13 +618,8 @@ export function lastTurnNumber(session: Session): number { } /** - * Whether a turn is currently open in the session log (a `turn/start` with no - * matching later `turn/end`). Decided from the LOG, not agent status: status - * can be `running` while no turn is open (an `agent/status` listener firing - * before `turn/start`, or the post-`turn/end` flush window before status - * returns to idle), so status is not a reliable open-turn signal. Used by - * `inject()` to choose between appending into an open turn vs. wrapping the - * injection in its own one-shot turn (the turn-enclosure RFC). + * Whether the session log has an unmatched `turn/start`. Agent status is not + * sufficient during pre-start and post-end windows. * @param session - the session whose log is inspected. * @returns true when the log's last turn boundary is a `turn/start` with no matching `turn/end` yet. */ diff --git a/packages/core/agent-loop/src/request-log.ts b/packages/core/agent-loop/src/request-log.ts index 94e121d0f6..ea6141fea9 100644 --- a/packages/core/agent-loop/src/request-log.ts +++ b/packages/core/agent-loop/src/request-log.ts @@ -1,11 +1,7 @@ /** - * Per-loop-instance transmission bookkeeping for the reconstructability - * contract: which header event to append before a request so the session log - * always explains the request (the reconstructability RFC). The loop is - * otherwise transmission-stateless — the comparison baseline is the log's own - * folded header (`Session.requestHeader()`), so resume and fork need no - * special path: a fresh loop instance simply logs a `'resume'` snapshot on - * its first request and full changed-header snapshots from there. + * Per-loop-instance request-header bookkeeping for reconstructability. The + * comparison baseline is folded from the session log; a fresh instance anchors + * it with an initial/resume snapshot and later logs full changed snapshots. * * @module dsh-agent-loop/request-log */ @@ -37,18 +33,8 @@ export function createTransmissionLog(): TransmissionLog { } /** - * Append whatever header event this request owes the log, so folding the log - * reproduces the header the request was built under. Exactly one of three - * things happens: - * - * 1. This loop instance has not logged a header yet → a full `request/header` - * snapshot anchors the fold: reason `'initial'` when the log has no header - * events at all (a new conversation), `'resume'` when it does (process - * restart, fork seed — the boundary itself is a recorded fact, so the - * snapshot is appended even when nothing changed). - * 2. The header equals the folded baseline → nothing; the log already - * explains this request. - * 3. It differs → a full snapshot with reason `'change'`. + * Append the full header snapshot owed by this request: initial/resume for the + * instance's first request, nothing when unchanged, or change otherwise. * * @param session - the session whose log explains the request. * @param state - this loop instance's bookkeeping (mutated on first log). diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index a990f0d67d..3aad65a70e 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -1,46 +1,6 @@ /** - * Agent interface and event taxonomy. Every plugin programs against the - * `Agent` handle defined here; the concrete implementation lives in - * `@deepseek-ai/dsh-agent-loop`. - * - * Merge-extensible: `AgentOptions` supports declaration merging for - * plugin-specific creation options. - * - * ## Event-domain semantics (the boundary rule) - * - * The harness has three event domains, each with one job: - * - * - **`session/*`** (`@deepseek-ai/dsh-session`) — the DURABLE, replayable FACT - * log. Owns `SessionEventMap`; every entry is JSON-only (no live objects). - * One `session/event` emit per append, plus the `session/flush` parallel - * durability checkpoint. Answers "what happened, durably/replayably." A - * consumer that wants the live transcript subscribes here. - * - **`agent/*`** (this module) — the LIVE runtime surface. Always carries the - * live `Agent`. Two shapes: INTERCEPTION seams (the `agent/prompt-submit`/ - * `agent/request`/`agent/session-prefix`/`agent/step-result`/ - * `agent/turn-continuation` waterfalls and the serial `agent/pre-step` / - * `agent/turn-stop` checkpoints) that mutate/veto, and TRANSIENT emits - * (`agent/status`, `agent/error`, `agent/created`/ - * `agent/disposed`, `agent/queued`, `agent/session-start`) - * that notify with the `Agent` in hand. Turn/step boundaries are NOT here — - * they are durable `session/event` records. Answers "right now, with the agent - * object — intercept or observe." - * - **`tools/*`** (`@deepseek-ai/dsh-tools`) — the tool registry + execution. - * - * **The rule:** a durable, replayable fact is a SessionEvent; a live - * interception or a transient/live-object signal is an `agent`/`tools` Cordis - * event. A turn/step boundary is a durable fact: it lives in the session log - * and is read off the `session/event` feed — it is NOT mirrored as an `agent/*` - * emit. A consumer that needs the `Agent` handle (or its short id) at a boundary - * keeps a session-id→agent map from `agent/created`/`agent/disposed`. - * See `docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md` - * and `docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md`. - * - * The interception waterfalls here (`agent/prompt-submit`, `agent/request`, - * `agent/step-result`, `agent/turn-continuation`) each return a typed Decision; - * the terminal serial `agent/turn-stop` returns the stop-only subset. The - * convention is pinned by - * `docs/rfc/implemented/feature/2026-06-30-interception-seams.md`. + * Public agent types and live-runtime events. Durable transcript facts and + * turn/step boundaries remain `@deepseek-ai/dsh-session` events. * * @module @deepseek-ai/dsh-agent/types */ @@ -66,38 +26,18 @@ import type { Session } from '@deepseek-ai/dsh-session' declare module '@deepseek-ai/dsh-system-prompt' { interface AssembleContext { - /** - * The agent this assembly is for. The agent loop passes it on every - * per-step assembly (via its `assembleContextFor(agent)` helper, which - * also sets the `scope` field to the same agent — the layer selector - * `dsh-system-prompt` reads); variable providers project per-agent facts - * from it (`options.model` → `{{model}}`, `session.header.cwd` → - * `{{cwd}}`). Optional because a bare `assemble()` (tests, diagnostics) - * has no agent — providers must tolerate its absence. Never set `agent` - * without `scope`: the assembly would silently miss the agent's scoped - * sections/tools (the dev invariants flag it). - */ + /** Agent for this assembly; absent on diagnostics. When present, `scope` must identify the same agent. */ agent?: Agent } } -/** - * Options an agent is created with. The persona is NOT here: the - * dsh-system-prompt config supplies the global default, and a scoped - * `deployment:persona` section may override it for one agent. - * Merge-extensible: plugins declare extra fields via declaration merging. - */ +/** Merge-extensible agent creation options. Persona belongs to system-prompt sections. */ export interface AgentOptions { /** Model name (must have a registered adapter at call time). */ model?: string } -/** - * Options for {@link Agent.send}/{@link Agent.steer}/{@link Agent.inject}. An - * absent `source` resolves to `{ kind: 'user' }`, so a plugin supplying content - * must label itself here or its message is recorded as a user prompt (see - * {@link HookContext} on why that label is load-bearing). - */ +/** Message options; an omitted source resolves to `{ kind: 'user' }`, so plugins must label their own content. */ export interface SendOptions { source?: MessageSource } @@ -110,54 +50,22 @@ export interface SendOptions { */ export type AgentStatus = 'idle' | 'running' | 'disposed' -/** - * Model-facing context an interception listener wants the agent to SEE on the - * next request — the canonical shape behind every "inject extra context" - * decision ({@link PromptDecision}, {@link PostToolDecision}, - * {@link ContinuationDecision}). It is `agent.inject()`ed as a - * `context/message`, so it carries a REQUIRED {@link MessageSource}: `inject()` - * defaults a missing source to `{kind:'user'}`, which would MISLABEL plugin - * context as a user prompt and corrupt derived history. A bridge sets - * `{kind:'plugin', plugin:'…'}`; a native plugin names itself. Required, not - * optional — the label is load-bearing, never defaulted here. - */ +/** Model-facing context injected by a listener; `source` prevents plugin text from being labeled as user input. */ export interface HookContext { content: ContentBlock[] source: MessageSource } /** - * The decision an {@link Agent} `agent/prompt-submit` waterfall listener returns - * for ONE drained queued message, before it becomes a `user/message`. Maps onto - * the Claude Code `UserPromptSubmit` hook's allow/block + `additionalContext`. - * - * - `allow` proceeds with the prompt; optional `content` REPLACES the prompt - * bytes (a rewrite), and optional `additionalContext` is `inject()`ed as a - * separate `context/message` the next request also sees. - * - `block` drops the prompt (it never becomes a `user/message`); `reason` is - * the durable record of why. The loop appends a `prompt/blocked` session event - * (carrying the original content, source, and `reason`) in place of the - * dropped `user/message`, so the veto survives replay even in a MIXED batch - * where a sibling prompt is allowed. A batch whose EVERY prompt is blocked - * additionally opens a zero-step turn that ends with {@link TurnEndReason} - * `rejected` (so the boundary stays balanced and a UI can render "blocked by - * hook"). + * Prompt interception result. `allow.content` replaces the prompt and + * `additionalContext` becomes a separate context message. `block` records a + * durable `prompt/blocked`; an all-blocked batch ends a zero-step rejected turn. */ export type PromptDecision = | { kind: 'allow'; content?: ContentBlock[]; additionalContext?: HookContext } | { kind: 'block'; reason: string } -/** - * The decision an {@link Agent} `agent/turn-continuation` waterfall listener - * returns. The loop computes the default (`continue` when the step had tool - * calls or steering was injected, else `stop`); listeners override it to - * force-continue (`/goal`, `/loop`) or force-stop (budget guards). - * - * A `continue` may carry a `reason`: model-facing context recorded as next-STEP - * steering within the SAME turn (the loop enqueues it through the steering - * channel, so the continued turn's next step sees it). This is the typed twin of - * the existing "steer from a step/end listener" `/goal` pattern. - */ +/** Turn continuation override; a continue reason is recorded as next-step steering in the same turn. */ export type ContinuationDecision = | { action: 'stop' } | { action: 'continue'; reason?: HookContext } @@ -169,47 +77,21 @@ export type ContinuationDecision = */ export type ContinuationStop = Extract -/** - * Why an agent's session lifecycle began, carried by `agent/session-start`. A - * bridge keys its SessionStart hook's matcher on this (Claude Code's - * `startup`/`resume`/`clear`/`compact` source set). `startup` = a fresh create - * (including a seeded/forked create — a seed is NOT a resume); `resume` = a - * persisted session reloaded via `ctx.agents.resume()`. `clear`/`compact` are - * driven by those subsystems (compact = `TODO(compaction)`). - */ +/** Why a session lifecycle began; seeded creates are `startup`, while persisted loads are `resume`. */ export type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact' -/** - * The agent handle — the surface every plugin (UI, hooks, orchestrators) - * programs against. The concrete implementation lives in - * `@deepseek-ai/dsh-agent-loop` (class `ReactLoopAgent`); nothing outside the loop - * package should depend on the implementation. - */ +/** Public agent handle; the concrete driver belongs to `@deepseek-ai/dsh-agent-loop`. */ export interface Agent { readonly id: AgentId readonly options: AgentOptions readonly session: Session readonly status: AgentStatus - /** - * The agent's scope context (`@deepseek-ai/dsh-scope`, key = this agent). - * Registrations through it — tools, prompt sections/variables, event - * listeners, restrictions — are visible to THIS agent only and unwind when - * the agent is disposed; `agent.ctx.on('agent/…')` listeners fire only for - * this agent's dispatches (zero self-filtering). Service resolution through - * it flows through the loop plugin's dependency surface — handing out - * `agent.ctx` hands out that capability. Live for exactly the agent's - * lifetime: registrations after disposal throw Cordis's INACTIVE_EFFECT. - */ + /** Agent-scoped context; its contributions are agent-local, unwind on disposal, and reject registration afterward. */ readonly ctx: Context /** - * Queue a user message. Starts a turn when idle; otherwise waits for the next - * turn. Content and the resolved source are accepted as one detached, - * deeply-frozen lossless-JSON record before notification or enqueue, so - * caller or `agent/queued` listener in-place mutation cannot change later - * log/model input. Throws synchronously when either value is not losslessly - * JSON-serializable; `agent/prompt-submit` may still return an explicit - * replacement. + * Queue detached, frozen lossless-JSON input; starts a turn when idle. + * Invalid input throws synchronously before notification or enqueue. */ send(content: ContentBlock[], options?: SendOptions): void @@ -221,317 +103,137 @@ export interface Agent { steer(content: ContentBlock[], options?: SendOptions): void /** - * Inject in-session context (file-change notices, skill content, cron - * notifications, …): appends a `context/message` session event the next model - * request sees at its chronological position, rendered as tagged synthetic - * context rather than a user prompt. Does not run the model. - * - * Turn-enclosure (the turn-enclosure RFC): an inject while a turn is open joins that turn; - * an inject while idle wraps its `context/message` in a one-shot `injection` - * turn (`turn/start` → `context/message` → `turn/end`) and checkpoints it for - * durability, so every event stays inside a turn and a persistence backend - * never loses a between-turn notice. The idle checkpoint is fire-and-forget - * from this synchronous method, but lifecycle disposal awaits it before - * unregistering the agent or detaching its session. A failing flush is - * reported via `agent/error` (step `0`) and the logger, never thrown into the - * caller. - * - * Live-adapter review has validated the tagged-envelope rendering against - * current DeepSeek behavior; provider-specific mismatches belong in that - * adapter, not in the canonical session vocabulary. + * Append model-facing context without running the model. Idle injection uses + * a one-shot turn and durability checkpoint, while injection during an open + * turn joins it at the current log position. Disposal awaits idle checkpoints; + * flush failures are reported through `agent/error`, not thrown to the caller. */ inject(content: ContentBlock[], options?: SendOptions): void /** - * Cancel ALL pending work for the agent. `cancel()`: - * - * - clears the queued FIFO (un-started prompts never run) and the steering - * FIFO (steering for the cancelled turn is dropped, not re-enqueued); - * - aborts the in-flight step if one is running (the turn ends `aborted`); - * - drops a turn that is about to start (a `cancel()` landing in the - * pre-step window — after a `send()` queued but before the loop flips to - * `running`, or after `running` is emitted but before the first step) so - * that queued prompt does not run and cannot be batched into the cancelled - * turn. - * - * After `cancel()`, `whenIdle()` resolves on the post-cancel quiescent state. - * `cancel()` on an idle agent with nothing queued or running is a safe no-op - * — it does NOT arm anything that would drop a later legitimate prompt. + * Clear queued and steering work, including work waiting to start, and abort + * the active step. The supplied reason is preserved across pre-step and active + * cancellation windows, and `whenIdle()` resolves after cancellation reaches + * quiescence. Idle cancellation is a no-op and does not arm a later cancel. */ cancel(reason?: string): void - /** - * Resolve once the agent has reached quiescence after settling out of - * `running`, or immediately if it is already idle with no queued work. A - * non-owner's quiescence-observation hook: a consumer that does NOT own the - * agent's lifecycle awaits this to proceed only after queued/running work has - * fully stopped, rather than returning while the driver is still streaming or - * about to start a queued turn — without itself tearing the agent down. (A - * lifecycle OWNER does not need it: `AgentHandle.dispose()` already awaits the - * loop-exit promise directly as part of stopping and unregistering. So this is - * for a non-owning observer — e.g. a test awaiting a turn to settle, or a - * monitor — that wants the settle signal but must not dispose the agent.) - * - * "Quiescence", not merely "status changed": a disposed agent emits - * `agent/status('disposed')` from inside its disposer, BEFORE the driver loop - * has unwound — so `whenIdle()` resolving on `disposed` must wait for the loop - * to actually exit (the implementation chains the loop-exit promise), not just - * observe the status flip. A mid-step disposal that never reaches `idle` still - * unblocks the await this way. - */ + /** Resolve at idle quiescence; disposal waits for driver exit rather than only the status transition. */ whenIdle(): Promise - // Subagent delegation is realized on top of this interface by the - // `@deepseek-ai/dsh-subagent` seam, not by a method here: a backend creates - // the child through `ctx.agents.create` (fork seeds the child Session with a - // balanced prefix of the parent's log via `CreateAgentOptions.seed`; spawn - // starts fresh) and drives it as an ordinary Agent handle, so steer() and - // event subscription work uniformly. See docs/core-data-structures/subagent.md. } declare module 'cordis' { interface Events { // ---- lifecycle (emit) ---- /** - * An agent's fully composed scoped world was published in the - * {@link AgentRegistry}. Its session is already live in the session store. - * Setup is composition-only by contract; the subsequent - * `agent/session-start` boundary is the first supported place to inject or - * queue startup work. A synchronous listener throw - * vetoes publication and rollback emits the matching disposal edges; - * returned-promise rejection is observed and logged but cannot - * retroactively veto this synchronous boundary. A synchronous listener - * that requests the advanced registry detach does not remove the entry - * immediately: removal and the paired `agent/disposed` edge wait until the - * creation dispatch unwinds, so no later creation listener observes a - * disposal that preceded its own creation callback. + * A fully configured agent and live session were published. Setup is + * composition-only; `agent/session-start` is the first startup-driving seam. + * Synchronous listener failure vetoes publication, while returned-promise + * rejection is reported. Detach requested during dispatch waits until every + * creation listener has observed the stable entry. * @param agent - the newly registered agent with its live session and completed setup. - * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered - * through `agent.ctx` fires only for that agent's dispatches; a listener on a - * plain plugin context fires for every agent. The dispatch `this` is the - * scope carrier (`Scoped`), built by the emitting side via - * `scopeTarget`/`agentEvents`. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @mode emit */ 'agent/created'(this: Scoped, agent: Agent): void /** - * An agent was removed from the registry. The concrete AgentLoop lifecycle - * emits this only after its driver and any in-flight turn reach quiescence; - * a custom agent registered through the public registry owns its own driver - * contract, which the registry cannot infer. Ordered teardown may still be - * detaching the session and unwinding scoped registrations when this runs. + * An agent left the registry; AgentLoop emits this after driver quiescence + * but before session detachment and scoped-registration unwind. Custom + * registry users own their driver-ordering contract. * @param agent - the exact agent removed from the registry. - * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered - * through `agent.ctx` fires only for that agent's dispatches; a listener on a - * plain plugin context fires for every agent. The dispatch `this` is the - * scope carrier (`Scoped`), built by the emitting side via - * `scopeTarget`/`agentEvents`. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @mode emit */ 'agent/disposed'(this: Scoped, agent: Agent): void /** - * Agent status changed (`idle` ⇄ `running`, or → `disposed`). Drive - * lifecycle off this transition, never off a status you just requested — - * `send()` does not flip status to `running` before it returns. + * Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does + * not enter `running` synchronously; drive lifecycle from this event. * @param agent - the agent whose status flipped. * @param status - the status just entered (the transition's destination). - * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered - * through `agent.ctx` fires only for that agent's dispatches; a listener on a - * plain plugin context fires for every agent. The dispatch `this` is the - * scope carrier (`Scoped`), built by the emitting side via - * `scopeTarget`/`agentEvents`. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @mode emit */ 'agent/status'(this: Scoped, agent: Agent, status: AgentStatus): void /** - * A message entered the agent's inbox (queued or steering). Content and the - * resolved source are the detached, deeply-frozen values retained by the - * inbox. `source` has defaults applied and is not the caller's raw options. + * Detached, frozen content entered the agent's inbox. Source defaults have + * already been applied, so these are the exact values retained for the log. * @param agent - the agent whose inbox received the message. * @param content - the accepted content blocks retained by the inbox. * @param info - the accepted source plus whether it entered as steering. - * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered - * through `agent.ctx` fires only for that agent's dispatches; a listener on a - * plain plugin context fires for every agent. The dispatch `this` is the - * scope carrier (`Scoped`), built by the emitting side via - * `scopeTarget`/`agentEvents`. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @mode emit */ 'agent/queued'(this: Scoped, agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void // ---- session lifecycle (emit) ---- /** - * The agent's session lifecycle began, fired once before its first turn. - * `source` says why ({@link SessionStartSource}: fresh startup, a resumed - * persisted session, …). A pure NOTIFICATION (emit, not waterfall): a - * listener cannot veto by returning a decision or throwing. A listener that - * wants to seed context does so via `agent.inject()` (a `context/message` the - * first request sees). A lifecycle owner can still dispose its structural - * ownership edge during this notification; publication rechecks liveness and - * then aborts before the driver starts. + * The session lifecycle began, once before the first turn. Use + * `agent.inject()` to seed model-facing context. This is a notification, not + * a veto; disposal requested by a lifecycle owner is rechecked before the + * driver starts. * @param agent - the agent whose session lifecycle began. * @param source - why the session started (fresh startup, resume, …). - * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered - * through `agent.ctx` fires only for that agent's dispatches; a listener on a - * plain plugin context fires for every agent. The dispatch `this` is the - * scope carrier (`Scoped`), built by the emitting side via - * `scopeTarget`/`agentEvents`. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @mode emit */ 'agent/session-start'(this: Scoped, agent: Agent, source: SessionStartSource): void - // Turn and step boundaries are NOT mirrored as agent/* emits: a consumer - // that needs them reads the durable `turn/start`/`turn/end`/`step/start`/ - // `step/end` session events off the `session/event` feed (the session log is - // the live transcript feed). See the module doc's three-domain rule and the - // "remove agent boundary mirror events" RFC. + // Turn and step boundaries are durable session events, not agent events. // ---- step/request extension seams (serial + waterfall) ---- /** - * Awaited pre-step surface-mutation checkpoint, fired once per step AFTER - * `turn/start` (and after the prior step closed) but BEFORE this step's - * `step/start` — so anything a listener appends lands OUTSIDE the step, - * between `turn/start`/`step/end` and the upcoming `step/start`. `step` is - * the number of the step about to start. The loop awaits - * `ctx.serial('agent/pre-step', …)` after assembling the system prompt, then - * opens the step and derives the request history ONCE from whatever the - * surface now holds. This is where compaction belongs: it mutates the session - * surface in place (shadowing an older range with a summary node) with its - * log-only `compact/*` records cleanly outside any step, and the single - * subsequent derive reflects the mutation — so there is no double-derive and - * no listener can see (or be expected to act on) an assembled `messages` - * array that does not exist yet. - * - * Serial (awaited in registration order), not a waterfall: a listener - * mutates the surface as a side effect; there is nothing to transform, but - * the loop must wait for the mutation to complete before opening the step - * and deriving. Cordis `serial` bails early if a listener returns a bail - * value; this event is typed and documented as `void`, so listeners must not - * return a semantic veto value. `fullSystemPrompt` is the assembled prompt a - * listener needs to measure pressure (the system prompt counts toward the - * budget), and `sessionPrefix` is the instance's composed - * {@link agent/session-prefix} product for the same reason — every request - * carries it in front of the derived history, and it is composed BEFORE - * this seam fires precisely so a pressure gate counts the prefix the - * request will actually send (never a stale logged one). `signal` cancels - * any in-flight work a listener starts (e.g. a - * summarization model call). - * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered - * through `agent.ctx` fires only for that agent's dispatches; a listener on a - * plain plugin context fires for every agent. The dispatch `this` is the - * scope carrier (`Scoped`), built by the emitting side via - * `scopeTarget`/`agentEvents`. - * @param agent - the agent about to open the step. - * @param turn - the already-open turn this step belongs to. - * @param step - the number of the step about to start. - * @param fullSystemPrompt - the assembled prompt, for measuring token pressure. - * @param sessionPrefix - the instance's frozen session prefix, for the same measurement. - * @param signal - aborts in-flight listener work when the turn is torn down. + * Awaited serial checkpoint for session-surface mutation after prompt + * assembly and before `step/start`; appends land outside the pending step. + * The loop derives history once afterward, so compaction records and + * replacements are included without rewriting an assembled request. The + * prompt and prefix are the exact pressure inputs for that request, and + * `signal` cancels listener work. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @param agent - the agent opening the step. + * @param turn - the open turn number. + * @param step - the pending step number. + * @param fullSystemPrompt - the assembled prompt. + * @param sessionPrefix - the frozen request prefix. + * @param signal - the turn abort signal. * @mode serial */ - // TODO: `fullSystemPrompt`/`sessionPrefix` are a smell on a generic - // per-step seam — compaction - // is their only consumer, so a wide event carries payloads just one listener - // reads. Revisit if no second consumer appears: e.g. hand listeners a lazy - // prompt provider, or move token-pressure measurement behind a - // compaction-specific seam instead of the shared pre-step checkpoint. + // TODO: Move prompt-pressure inputs behind a compaction-specific seam if no second consumer appears. 'agent/pre-step'(this: Scoped, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void /** - * Waterfall: decide what happens to ONE drained queued message before it - * becomes a `user/message` — allow (optionally rewriting the prompt bytes or - * attaching `additionalContext`) or block it. Fires inside the already-open - * turn, per drained message. Maps onto Claude Code's `UserPromptSubmit` hook. - * Call `next()` to delegate to the default (allow unchanged), or return a - * {@link PromptDecision} without calling `next()` to short-circuit. + * Allow, rewrite, or block one drained prompt before it becomes a user + * message. Call `next()` for the unchanged default. * @param agent - the agent draining its inbox. * @param content - the drained message's blocks, as queued. * @param source - the message's resolved source. - * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered - * through `agent.ctx` fires only for that agent's dispatches; a listener on a - * plain plugin context fires for every agent. The dispatch `this` is the - * scope carrier (`Scoped`), built by the emitting side via - * `scopeTarget`/`agentEvents`. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @mode waterfall */ 'agent/prompt-submit'(this: Scoped, agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise): Promise /** - * Waterfall: shape the step's call configuration — model switching, - * sampling overrides — by returning a replacement {@link LlmCallConfig} - * (the frozen seed is the config the loop would otherwise use). Config is - * ALL a listener shapes here: every request is a pure function of the - * session log (the reconstructability RFC), so model-visible content - * flows through the log channels — `inject()`, steering, prompt-submit - * `additionalContext`, prompt sections via `system-prompt/assemble`, or - * the header-logged session prefix via {@link agent/session-prefix} - * — never through request mutation, and the loop records whatever config - * the request actually uses as a `request/header` event before dispatch. - * The step's messages are already snapshotted when this fires (the - * `step/start` boundary): an `inject()` from a listener here lands in the - * log but joins the NEXT request. For surface mutation that must precede - * the snapshot (compaction), use {@link agent/pre-step}. Call `next()` to - * delegate, or return an {@link LlmCallConfig} without it to - * short-circuit. + * Replace the frozen call configuration. Model-visible content must use + * logged channels; this seam cannot mutate messages. Injection here joins + * the next request because the current step boundary is already fixed. * @param agent - the agent making the model call. * @param turn - the open turn number. * @param step - the step whose request this is. * @param config - the config the loop would use (frozen); return a replacement to switch. - * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered - * through `agent.ctx` fires only for that agent's dispatches; a listener on a - * plain plugin context fires for every agent. The dispatch `this` is the - * scope carrier (`Scoped`), built by the emitting side via - * `scopeTarget`/`agentEvents`. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @mode waterfall */ 'agent/request'(this: Scoped, agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise): Promise /** - * Waterfall: compose the SESSION PREFIX — request-only messages placed in - * front of the ENTIRE derived history (directly after the provider's - * system slot) on every request this loop instance sends. Fired ONCE per - * loop instance, lazily before its first step's {@link agent/pre-step} - * seam — BEFORE the pre-step so a token-pressure gate (compaction) counts - * the prefix this instance will actually send, never a previous - * instance's logged one. The composed - * result is deep-frozen, recorded as `EpochHeader.messagePrefix` on the - * instance's anchoring `'initial'`/`'resume'` header snapshot, and reused - * verbatim for every subsequent request — never recomputed mid-session, - * so the provider prefix cache holds by construction (a process restart - * or `ctx.agents.resume()` is a new instance: it recomposes, and any - * drift lands attributably on the `'resume'` snapshot). Composition runs - * outside the step, before the boundary snapshot: a composing listener's - * session append joins the CURRENT request's derived history. A - * composition interrupted by a cancel/dispose landing inside the - * waterfall is discarded — never cached, logged, or sent — and the next - * turn recomposes under a live signal, so an abort-aware listener's - * degraded fallback cannot leak into later requests. - * - * This is the home for session-stable openers the model must always see - * but that must NOT become durable history — a skills catalog, an - * AGENTS.md digest, a workspace baseline: `Session.deriveMessages()` - * never returns the prefix, and the header events are its only durable - * record, so the request stays reconstructable from the log. Content - * that CHANGES mid-session belongs in the append-only history channels - * instead — `agent.inject()`, a `tools/post-execute` decision's - * `additionalContext`, prompt-submit `additionalContext` — each a - * durable `context/message` paid once and prefix-cached thereafter. - * - * The seed is a frozen empty list; a contributing listener returns a NEW - * array — never an in-place push. The canonical contribution is a - * PREPEND, `[mine, ...await next()]`: the waterfall unwinds - * innermost-first (the LAST-registered listener's `next()` resolves - * first), so prepending yields registration order on the wire, and every - * plugin using it composes deterministically. The append form - * `[...await next(), mine]` is legal but places a contribution AFTER - * every later-registered plugin's — reverse registration order when all - * contributors append. Call `next()` to - * delegate, or return a list without it to short-circuit. - * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered - * through `agent.ctx` fires only for that agent's dispatches; a listener on a - * plain plugin context fires for every agent. The dispatch `this` is the - * scope carrier (`Scoped`), built by the emitting side via - * `scopeTarget`/`agentEvents`. + * Compose request-only messages placed before derived history. The frozen + * result is computed once per loop instance, logged on its anchoring request + * header, and reused so the provider prefix remains stable. Interrupted + * composition is discarded. Composition precedes the first `agent/pre-step` + * and request boundary, so listener appends join the current request and + * pressure accounting sees the composed prefix. Changing context belongs in + * history; contributors should prepend to `await next()` to preserve registration order. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @param agent - the agent whose session prefix is being composed. - * @param prefix - the frozen empty seed; return an extended replacement to contribute. - * @param signal - aborts in-flight listener work (e.g. a discovery scan) when the step is torn down. + * @param prefix - the frozen seed; return an extended replacement. + * @param signal - aborts composition when the step is torn down. * @mode waterfall */ 'agent/session-prefix'(this: Scoped, agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise): Promise @@ -542,47 +244,27 @@ declare module 'cordis' { * @param turn - the open turn number. * @param step - the step that produced the message. * @param message - the assistant message as assembled from the stream. - * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered - * through `agent.ctx` fires only for that agent's dispatches; a listener on a - * plain plugin context fires for every agent. The dispatch `this` is the - * scope carrier (`Scoped`), built by the emitting side via - * `scopeTarget`/`agentEvents`. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @mode waterfall */ 'agent/step-result'(this: Scoped, agent: Agent, turn: number, step: number, message: Message, next: () => Promise): Promise /** - * Waterfall: override the turn-continuation decision via a typed - * {@link ContinuationDecision}. The loop's `defaultDecision` is `continue` - * when the step had tool calls or steering was injected, else `stop`. - * Listeners force-continue (`/goal`, `/loop` — optionally attaching a - * `reason` recorded as next-step steering) or force-stop (budget guards). - * Call `next()` to delegate to the default, or return a decision to override. + * Override whether the turn continues. The default continues after tool + * calls or steering and stops otherwise; a continue reason becomes steering. * @param agent - the agent deciding whether to run another step. * @param turn - the turn being continued or stopped. * @param defaultDecision - what the loop would do absent an override. - * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered - * through `agent.ctx` fires only for that agent's dispatches; a listener on a - * plain plugin context fires for every agent. The dispatch `this` is the - * scope carrier (`Scoped`), built by the emitting side via - * `scopeTarget`/`agentEvents`. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @mode waterfall */ 'agent/turn-continuation'(this: Scoped, agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise): Promise /** - * Serial terminal-stop checkpoint after the ordinary - * `agent/turn-continuation` waterfall, any `continue.reason`, and the - * pending-steering continuation override have been folded. A listener - * returns `{ action: 'stop' }` to make this turn terminal, or `undefined` - * to abstain. Terminal stop is monotonic: listener order and steering - * cannot resume the turn, and pending steering is discarded rather than - * becoming another step or turn. + * Monotonic terminal-stop checkpoint after continuation and steering are + * folded; a stop remains authoritative through turn close and flush: + * steering queued in that window is discarded, while ordinary sends survive. * @param agent - the agent whose composed continuation outcome may be stopped. * @param turn - the turn at its terminal-stop checkpoint. - * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered - * through `agent.ctx` fires only for that agent's dispatches; a listener on a - * plain plugin context fires for every agent. The dispatch `this` is the - * scope carrier (`Scoped`), built by the emitting side via - * `scopeTarget`/`agentEvents`. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @mode serial */ 'agent/turn-stop'(this: Scoped, agent: Agent, turn: number): ContinuationStop | undefined @@ -595,11 +277,7 @@ declare module 'cordis' { * @param turn - the turn in which the failure surfaced. * @param step - the step at which the failure surfaced. * @param error - the failure, verbatim. - * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): a listener registered - * through `agent.ctx` fires only for that agent's dispatches; a listener on a - * plain plugin context fires for every agent. The dispatch `this` is the - * scope carrier (`Scoped`), built by the emitting side via - * `scopeTarget`/`agentEvents`. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @mode emit */ 'agent/error'(this: Scoped, agent: Agent, turn: number, step: number, error: Error): void diff --git a/packages/core/session/README.md b/packages/core/session/README.md index 1072809fa1..3f11876c3b 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -75,7 +75,7 @@ Every `SessionEvent` carries two optional top-level fields (structural metadata) ### Extension points - Persistence plugins: subscribe to `session/event` (write-behind) and drain on `session/flush` (awaited) and fiber dispose. A durable backend reads the log and reloads it into a live session; the metadata seam (`SessionHeader`, `session.header`) is what such a backend stores beside the log. -- Replay/fork: `ctx.sessions.create(id, { seed })` seeds a new session with an existing event log. The surface rebuilds deterministically from `surfaceOp` markers in the seeded events. The constructor reads each seed entry once and uses the same one-pass lossless-JSON snapshot and exact surface-metadata shape checks as `append`, then enforces contiguous seqs and deep-freezes every accepted record; a stateful caller, exotic nested value, marker-less or malformed surface event, metadata on a non-surface event, or retained seed reference therefore cannot silently change the reconstructed history. Broader turn-enclosure checks stay in `dsh-invariants` and persistence repair. Ordinary live-session forks use `ctx.sessions.fork(source, boundary?, childSessionId?)`, where `boundary` is the inclusive source event seq to fork through. +- Replay/fork: `create(id, { seed })` validates and freezes a contiguous log and rebuilds its surface. `fork(source, boundary?, childSessionId?)` selects a completed-turn prefix and records lineage. - Compaction: the `dsh-compact-basic` plugin appends a `user/message` with `surfaceOp: { op: 'replace', start, end }` to shadow old surface nodes behind a summary checkpoint. ## Model Experience diff --git a/packages/core/session/src/tool-pairing.ts b/packages/core/session/src/tool-pairing.ts index 8f1b35708f..e7eaae8eaa 100644 --- a/packages/core/session/src/tool-pairing.ts +++ b/packages/core/session/src/tool-pairing.ts @@ -1,36 +1,7 @@ /** - * Tool-pairing balance over a session's SURFACE: is a given cut point in the - * surface a safe edge for a collapsed region (e.g. compaction)? - * - * The invariant a consumer needs: a collapsed region must never separate an - * `assistant/message`'s `tool-call` blocks from their answering `tool/result`s - * — that would leave the rehydrated transcript with a dangling tool-call or an - * orphaned tool-result, which every provider rejects. (This is the - * compaction-time mirror of the crash-recovery imbalance that - * {@link interruptedTurnClosers} repairs on load.) Steps were once used as a - * proxy for this bracketing, but a compaction REWRITES the surface — it lands a - * replacement node at a high log seq whose SURFACE position is the head — so a - * scan over the LOG's `step/*` markers mis-reads such a node's neighbours. The - * pairing the invariant actually protects lives in the surface nodes' own - * content (a `tool-call` block's id, a `tool/result`'s `callId`), which travels - * with the node through any reshaping, so alignment is decided over the surface - * directly. - * - * A **cut** is a gap between two adjacent surface nodes (named by the node it - * sits immediately before), or the after-tail gap (`null`). Walking the surface - * head→tail and assigning each node a delta — `+1` per `tool-call` block on an - * `assistant/message`, `-1` per `tool/result`, `0` otherwise — the depth at a - * cut is the number of still-unanswered tool calls before it. A cut is - * **balanced** when that depth is `0`. A region `[start..end]` is safe to - * collapse iff BOTH its edges are balanced cuts: the cut before `start` and the - * cut after `end`. Nodes that belong to no step (a pre-step `user/message`, an - * inter-step `steering/message`, an injection `context/message`) carry no - * pairing, contribute `0`, and so are free boundaries — exactly as before, but - * now as a consequence of the balance rather than a special case. An open - * trailing step (an assistant whose `tool/result`s have not landed yet) keeps - * the depth positive through the tail, so no cut inside it is balanced — the - * old explicit open-step check falls out of the same counter. - * + * Tool-pairing balance over a session surface. Compaction changes surface + * positions, so safe cuts are derived from tool-call/result content on the + * surface rather than step markers in the append-only log. * @module @deepseek-ai/dsh-session/tool-pairing */ @@ -56,33 +27,14 @@ function nodeDelta(event: SessionEvent): number { } /** - * Whether the surface prefix ending at the given cut has BALANCED tool-call / - * tool-result brackets — i.e. every `tool-call` block on the surface before the - * cut has its answering `tool/result` before the cut too, so the cut is a safe - * edge for a collapsed region (it cannot split an assistant↔result pair). + * Check that a surface cut does not split a tool call from its result. A region + * is safe to collapse only when both edge cuts return true. * - * `nodes` is the surface sequence list in head→tail order (e.g. - * `session.surface.nodes`); `events` is the session log, used to look each - * event up by sequence. `beforeSeq` names the cut by the surface event it - * sits immediately before; the after-tail cut (the whole surface) is `null`, - * as is any `beforeSeq` not present on the surface. - * - * A region `[start..end]` is collapsible iff both edges are balanced cuts: call - * `isToolPairingBalanced(nodes, events, start)` for the cut before `start`, and - * `isToolPairingBalanced(nodes, events, after)` — where `after` is `end`'s - * surface successor (`nodes[index + 1]`), or `null` when `end` is the tail — - * for the cut after `end`. - * - * @param nodes - surface event sequences in head→tail order. - * @param events - the session log each sequence indexes into. - * @param beforeSeq - names the cut (the node it sits immediately before); - * `null` — or any seq not on the surface — means the after-tail cut. - * @returns true when every `tool-call` before the cut is answered before it - * (the unanswered-call depth at the cut is zero). - * @throws if the surface prefix drives the unanswered-call depth negative — a - * `tool/result` with no preceding open `tool-call` on the surface. That is a - * corrupt surface (a structural invariant violation), surfaced loudly here - * rather than silently mis-classifying a boundary. + * @param nodes - surface event sequence numbers in head-to-tail order. + * @param events - the session log indexed by those sequence numbers. + * @param beforeSeq - event immediately after the cut; null or an absent seq means after-tail. + * @returns whether every call before the cut is answered before it. + * @throws if a result appears without a preceding open call. */ export function isToolPairingBalanced( nodes: readonly number[], @@ -99,7 +51,6 @@ export function isToolPairingBalanced( throw new Error(`tool-pairing balance: tool/result at surface seq ${seq} has no matching tool-call (corrupt surface)`) } } - // Reached the after-tail cut (beforeSeq === null, or a seq not on the - // surface): the whole-surface prefix is balanced iff depth returned to 0. + // A missing cut sequence means the after-tail boundary. return depth === 0 } diff --git a/packages/core/session/src/types.ts b/packages/core/session/src/types.ts index c2997c0b47..0b45a2a57d 100644 --- a/packages/core/session/src/types.ts +++ b/packages/core/session/src/types.ts @@ -14,33 +14,17 @@ export function SessionId(id: string): SessionId { } /** - * The on-disk session format version, stamped into every newly-written - * {@link SessionHeader} and enforced by every persistence backend on load. The - * single source of truth for the version — write sites and the load-time check - * all read it. - * - * It is **`0`** deliberately: while the harness is unreleased the on-disk format - * is **unstable / pre-release, with no compatibility implied**. Breaking changes - * to the persisted {@link SessionEventMap} shape (folding fields onto an event, - * removing a variant, …) happen freely and do NOT bump this — v0 absorbs all - * pre-release churn, and a backend simply REJECTS any log not at v0 (there is no - * migration; no persisted user data exists to preserve). A real, monotonically - * bumped version policy begins at the first tagged release, when a specific - * format boundary becomes worth distinguishing. + * The on-disk session format version, stamped into every newly-written {@link SessionHeader} + * and enforced by every persistence backend on load. The single source of truth for the + * version — write sites and the load-time check all read it. + * While the harness is unreleased it is pinned at `0`: no compatibility is + * implied, incompatible logs are rejected, and no migration is provided. A + * monotonic version policy starts with the first tagged release. */ export const SESSION_FORMAT_VERSION = 0 /** - * Immutable session metadata — written once at creation and never rewritten. - * {@link Session} enforces that contract at runtime: it validates and detaches - * the accepted scalar fields, requires this header's id to match the session - * id, and deep-freezes the published record. - * - * Kept SEPARATE from the event log deliberately: format-version, cwd, and - * lineage are storage concerns, not conversation events, so they stay out of - * {@link SessionEventMap} and never reach `deriveMessages()`. Every reference - * system (pi's `version: 3` header, Codex's `SessionMeta`, Claude Code's tail - * metadata) writes such a header. + * Immutable validated storage metadata, kept outside the conversation event log. */ export interface SessionHeader { /** @@ -58,13 +42,8 @@ export interface SessionHeader { /** The session this one was forked from (seed lineage), if any. */ readonly parentSession?: SessionId /** - * How many leading events were INHERITED via a seed rather than produced by - * this session — the seed boundary. Set when a fork seeds a child with a - * prefix of the parent's log (= the seeded prefix length); absent/0 means the - * session produced all its own events. Persisted so a reload reconstructs the - * boundary instead of re-deriving it from the full stored log, and so a replay - * harness can skip the inherited prefix when deriving the child's OWN script - * (the seeded events are the parent's, not this child's model calls). + * How many leading events were inherited through a seed. Persisting this + * boundary lets resume and replay distinguish parent history from child work. */ readonly seedLength?: number } @@ -78,17 +57,8 @@ export interface CreateSessionOptions { /** Events to seed the new session with (replay/fork). */ readonly seed?: readonly SessionEvent[] /** - * Creation metadata. The store reads this plain record and each accepted - * field once, then fills in `version`/`id` and defaults - * `createdAt` to now; the caller supplies the storage-level fields (validated - * absolute `cwd`, `parentSession` lineage, the seed boundary `seedLength`, and - * — when reconstructing a persisted session — the original `createdAt` to - * preserve it). - * - * `seedLength` is EXPLICIT, not inferred from `seed.length`: a reconstruction - * (resume/load) seeds the WHOLE stored log, so its `seed.length` is the full - * length, not the original boundary — the caller must pass the persisted - * boundary back. A fresh fork passes its actual seeded-prefix length. + * Storage metadata read once before publication. `seedLength` is explicit + * because a resumed seed contains the full stored log, not only its inherited prefix. */ readonly meta?: { readonly cwd?: string @@ -119,21 +89,7 @@ export interface TurnTriggerMap { export type TurnTrigger = TurnTriggerMap[keyof TurnTriggerMap] /** - * Why a turn ended. - * Merge-extensible sum type. - * - * `max-tokens` mirrors the model-call `FinishReasonMap` variant (DeepSeek's - * `length`): the turn ended because a step hit the output-token ceiling, not - * because the model chose to stop. The agent-loop surfaces it via the rule - * "any `max-tokens` step in the turn makes the turn end `max-tokens`" (a - * continuation plugin can run further steps after one, but the cut-short fact - * still wins). It is distinct from `completed` so a consumer (e.g. the ACP - * bridge mapping to `StopReason: 'max_tokens'`) can tell a clean stop from a - * truncated one. The next variants to add — when an adapter/loop first emits - * them — are `refusal` and `max_turn_requests` (both named by the ACP RFC as ACP - * stop reasons); no current adapter produces a `refusal` finish (unknown - * DeepSeek finish reasons collapse to `error`), so it is deliberately omitted - * until one does. + * Why a turn ended. Merge-extensible sum type. */ export interface TurnEndReasonMap { completed: { kind: 'completed' } @@ -146,26 +102,16 @@ export interface TurnEndReasonMap { */ error: { kind: 'error'; step: number; message: string; code?: string } disposed: { kind: 'disposed' } + /** At least one step reached its output-token ceiling, even if a plugin continued the turn. */ 'max-tokens': { kind: 'max-tokens' } /** - * The turn's entire prompt batch was BLOCKED before any step ran — every - * drained queued message was vetoed by an `agent/prompt-submit` listener (a - * hook). The turn still opened (so the boundary stays balanced and the block - * is a durable in-turn fact), but ran zero steps. `reason` carries the block - * message from the vetoing decision. Distinct from `aborted` (a user-driven - * cancel) and `error` (a failure): the prompt was rejected by policy, not - * interrupted or broken. A UI renders it as "prompt blocked by hook". + * Policy blocked every prompt before the first step. The zero-step turn still + * records a balanced durable boundary and the veto reason. */ rejected: { kind: 'rejected'; reason: string } /** - * The turn never ended on its own: the process crashed mid-turn and a - * persistence backend later closed the orphaned (open) turn on reload so the - * log stays balanced. SYNTHESIZED by the backend's crash-recovery repair — no - * loop ever emits this. Its events are real (they were durably appended before - * the crash) and are PRESERVED, not discarded: a single turn can be huge in a - * long-horizon task (many steps, large tool output), so truncating it would - * lose real work. The marker records that the turn was cut short, not that the - * model completed it. See the session-persistence RFC. + * A persistence backend closed a crash-orphaned turn on reload. The loop never + * emits this marker, and the events recorded before the crash remain intact. */ interrupted: { kind: 'interrupted' } } @@ -192,14 +138,9 @@ export interface TodoItem { } /** - * The request header: everything about an LLM request besides its derived - * message history — the call configuration plus the rendered system prompt, - * tool schemas, and the session prefix. Logged session state (the - * reconstructability RFC): each changed header is logged as a full - * {@link SessionEventMap} `request/header` snapshot, and taking the latest - * snapshot (`foldRequestHeader`) reconstructs the header any request used. - * Canonical form: an empty system prompt, an empty tool list, and an empty - * prefix are ABSENT fields, matching how requests are built. + * Logged request state outside derived history: call config, system prompt, + * tools, and prefix. The latest full `request/header` snapshot reconstructs it; + * canonical empty optional fields are absent. */ export interface EpochHeader { /** The conversation's call configuration (model + sampling scalars). */ @@ -227,24 +168,10 @@ export interface EpochHeader { export type RequestHeaderReason = 'initial' | 'resume' | 'change' /** - * The session event vocabulary — the append-only source of truth for an - * agent's whole interaction history. The LLM message history is *derived* - * from this log; nothing else is authoritative. Replay = re-derive from the - * same events; trace/telemetry = subscribe to the log. - * - * Merge-extensible: plugins declare extra event types via declaration merging - * (e.g. the compaction plugin adds `'compact/start'`, `'compact/summary'`, - * `'compact/end'`). - * - * Durability contract (what a persistence backend relies on): the durable log - * persists every event verbatim, INCLUDING `assistant/chunk` — `seq` must stay - * contiguous (`seq = log.length`), so chunks cannot be filtered out of the - * canonical log. All `event.data` must be JSON-serializable — `Session.append` - * (and the seed path in the constructor) enforces this at the source (throwing - * on non-serializable data), so a bad event never enters the log and - * `session.events` always equals what a backend can persist. Adding a new event - * type that carries non-serializable data, or that breaks the turn/step nesting - * the invariants plugin checks, is a breaking change to the on-disk format. + * The merge-extensible, append-only source of truth for an agent interaction. + * Message history is derived from this log. Every event is lossless JSON and + * sequence numbers stay contiguous, including raw chunks, so persistence can + * store the canonical log verbatim. */ export interface SessionEventMap { /** @@ -267,14 +194,8 @@ export interface SessionEventMap { /** A user-visible prompt (queued message drained at turn start). */ 'user/message': { content: ContentBlock[]; source: MessageSource } /** - * A queued prompt an `agent/prompt-submit` listener VETOED — the durable - * record of a blocked prompt and why. Appended in place of the `user/message` - * the prompt would have become, so the block survives replay even in a MIXED - * batch where another queued prompt is allowed (there the turn does not end - * `rejected`, so the boundary reason alone would not preserve it). `content` - * is the original prompt the listener rejected; `reason` is the veto text - * ({@link PromptDecision} `block.reason`). NOT a {@link SurfaceEventType}: a - * blocked prompt produces no LLM message and never reaches `deriveMessages()`. + * Durable record of a prompt veto and its reason. It is log-only: the blocked + * prompt never enters the model-visible surface, including in a mixed batch. */ 'prompt/blocked': { content: ContentBlock[]; source: MessageSource; reason: string } /** @@ -310,30 +231,11 @@ export interface SessionEventMap { 'tool/result': { turn: number; step: number; callId: CallId; content: ContentBlock[]; isError: boolean; error?: { name: string; code: string }; meta?: unknown } /** Steering content injected between steps of a running turn. */ 'steering/message': { turn: number; content: ContentBlock[]; source: MessageSource } - /** - * The agent's whole todo list, carried as a full snapshot and replaced - * wholesale on each write — the current list is the most recent `todo/write` - * (last-write-wins on replay, no fold). Appended by an owning agent via - * `session.append('todo/write', { todos })`. - * - * NOT a {@link SurfaceEventType}: it produces no LLM message and never reaches - * `deriveMessages()`, so it carries no `surfaceOp` and stays off the surface — - * it is durable, replayable UI state, distinct from the conversation history. - * It is a `SessionEventMap` member riding the existing `session/event` emit, - * not a first-class Cordis `interface Events` notification, so it has no - * cordis-catalog row. - */ + /** Whole-list snapshot; latest write wins on replay. Log-only UI state; never derived history. */ 'todo/write': { todos: TodoItem[] } /** - * Full snapshot of the {@link EpochHeader} the NEXT request is built under, - * with the {@link RequestHeaderReason} it was recorded whole. Appended by - * the loop inside the step, before dispatch, on a loop instance's first - * request-building step (`'initial'`/`'resume'`) or when a later request's - * header changes (`'change'`); always records what the request actually used, - * post-`agent/request`. Reconstruction reads the latest snapshot. NOT a - * {@link SurfaceEventType}: it produces no LLM message — it is the request - * envelope, logged so every request is a pure function of the session log - * (the reconstructability RFC). + * Full header for the next request, appended inside its step before dispatch. + * It is log-only; the latest snapshot reconstructs the request header. */ 'request/header': { header: EpochHeader; reason: RequestHeaderReason } } @@ -381,16 +283,8 @@ export type SurfaceOp = | { op: 'replace'; start: number; end: number } /** - * Surface metadata passed to {@link Session.append}. - * `surfaceOp` controls how the event enters the ordered surface; - * `sourceEventSeqs` records the seq numbers of events that are provenance - * sources of this one (e.g. the `assistant/chunk` seqs behind an - * `assistant/message`, or the shadowed nodes behind a compaction replacement). - * - * Required for {@link SurfaceEventType} events — every message-producing event - * MUST declare how it enters the surface, because the surface is the sole - * source of derived history. Non-surface event types (`turn/start`, - * `assistant/chunk`, `error`, …) cannot carry surface metadata. + * Surface placement and provenance for {@link Session.append}. Required on + * message-producing events and forbidden on log-only events. */ export interface SurfaceIntent { surfaceOp: SurfaceOp diff --git a/packages/core/session/tests/tool-pairing.spec.ts b/packages/core/session/tests/tool-pairing.spec.ts index 8e7b8b4a03..6f0bed7b63 100644 --- a/packages/core/session/tests/tool-pairing.spec.ts +++ b/packages/core/session/tests/tool-pairing.spec.ts @@ -4,24 +4,8 @@ import { Session, SessionId, isToolPairingBalanced } from '../src/index.ts' import type { SessionEvent } from '../src/index.ts' /** - * Unit coverage for the tool-pairing balance check. It decides whether a CUT in - * the surface (a gap before a given surface node, or the after-tail gap) is a - * safe edge for a collapsed region (compaction): a region must never split an - * `assistant/message`'s tool-calls from their `tool/result`s. A cut is balanced - * when no unanswered tool-call sits before it on the surface. Nodes belonging to - * no step (pre-step user message, inter-step steering, injection context) are - * pairing-neutral, so their cuts are free boundaries. - * - * The fixtures are built through a real {@link Session} so the ordered surface - * sequence list is derived exactly as production does — including the non-monotonic - * surface a `replace` op leaves (a compaction checkpoint at a high log seq - * sitting at the surface head), which is the case the abandoned log-position - * scan mis-classified. - * - * Builders mirror the agent loop's real append order: queued user messages land - * BEFORE `step/start`; within a step the order is `assistant/message` then - * `tool/result`(s); injection turns are a bare `turn/start → context/message → - * turn/end` with no step. + * Tool-pairing cut coverage over real session surfaces, including replacement + * nodes whose surface order differs from append-log order. */ const SURFACE = { surfaceOp: 'append' as const } @@ -182,10 +166,8 @@ describe('isToolPairingBalanced — multiple tool calls in one assistant message }) describe('isToolPairingBalanced — a mid-step injection context/message', () => { - // A background task-done inject() lands a context/message INSIDE an open step, - // between the assistant (with a tool-call) and its tool/result. It is - // pairing-neutral, so the cut on EITHER side of it is unbalanced (the call is - // still open across it) — it is NOT a free boundary in this position. + // The injected context is pairing-neutral, but both adjacent cuts remain + // unbalanced because the tool call is still open across them. function midStepInjection(): Session { const s = new Session(SessionId('mid-inject')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) @@ -236,11 +218,8 @@ describe('isToolPairingBalanced on an injection turn (no step)', () => { }) describe('isToolPairingBalanced — CBR-001: a head checkpoint left by a replace op', () => { - // The case the log-position scan got wrong. After a compaction, a replacement - // user/message lands at a HIGH log seq but sits at the SURFACE head, beside - // the still-open step whose events follow it in the log. It carries no - // tool-call/result pair (just summarized prose), so it must be a balanced cut - // on BOTH sides regardless of its log neighbours. + // A replacement checkpoint has a high log seq but sits at the surface head; + // its cuts are balanced regardless of later raw-log neighbors. function checkpointHeadedSession(): Session { const s = new Session(SessionId('checkpoint')) // A closed turn with a tool step → surface [u1, asst(call), result]. @@ -275,9 +254,8 @@ describe('isToolPairingBalanced — CBR-001: a head checkpoint left by a replace const s = checkpointHeadedSession() const nodes = s.surface.nodes const checkpointSeq = nodes[0]! - // The checkpoint heads the surface, yet a surface node (the open step's - // assistant) follows it in LOG order — the exact split between surface - // position and log position that the log-position scan tripped on. + // The checkpoint heads the surface while the open step's assistant follows + // it in append-log order. const laterSurfaceInLog = s.events.find( e => e.seq > checkpointSeq && nodes.includes(e.seq), ) @@ -291,10 +269,7 @@ describe('isToolPairingBalanced — CBR-001: a head checkpoint left by a replace }) it('end cut after the head checkpoint is balanced (it carries no tool pair)', () => { - // This is the exact assertion the log-position scan failed: the forward log - // scan from the checkpoint reached the open step's assistant/message and - // wrongly reported mid-step. The surface balance sees a neutral node whose - // following cut closes no open call. + // The neutral checkpoint closes no open call at its following surface cut. const s = checkpointHeadedSession() expect(endBalanced(s, s.surface.nodes[0]!)).toBe(true) }) diff --git a/packages/llm/llm/src/call-config.ts b/packages/llm/llm/src/call-config.ts index 19bb95bd12..19ec9fbc3e 100644 --- a/packages/llm/llm/src/call-config.ts +++ b/packages/llm/llm/src/call-config.ts @@ -1,14 +1,8 @@ /** - * The call configuration of a conversation and its comparison/freeze - * utilities. `LlmCallConfig` is the non-content third of the request header - * (see `EpochHeader` in dsh-session): everything about a request besides its - * message content that can undermine provider KV-cache reuse — `model` - * selects the cache namespace outright, and the sampling scalars are treated - * the same way out of caution. It is per-conversation state recorded in the - * session log (the reconstructability RFC), never a silently-drifting - * per-call knob: the `agent/request` waterfall proposes a replacement, and - * the loop logs a real change as a `request/header` snapshot. - * + * Conversation call configuration and freeze utilities. Model and sampling + * values are request-header state that can affect cache reuse; request + * waterfalls replace them and the loop logs changed snapshots instead of + * allowing silent per-call drift. * @module dsh-llm/call-config */ @@ -39,16 +33,9 @@ export function callConfigEquals(a: LlmCallConfig, b: LlmCallConfig): boolean { } /** - * Deep-freeze a value in place so any later mutation throws (ESM code runs in - * strict mode), and return it. The loop freezes every request it builds - * before dispatch — `llm/stream` listeners and adapters read the request, - * never rewrite it, so the wire bytes cannot silently desync from what the - * session log reconstructs. Guards against cycles with a WeakSet: loop-built - * requests hold `structuredClone`d JSON-validated session data, but the - * helper accepts arbitrarily constructed values. One exemption: an - * `AbortSignal` is never entered or frozen — it is the request's live - * cancellation channel, and freezing one breaks `AbortController.abort()` - * outright (Node stores the aborted flag as an own property of the signal). + * Deep-freeze a value in place, guarding cycles, so later mutation throws. + * {@link AbortSignal} objects are deliberately skipped because they are the + * request's live cancellation channel and freezing them breaks abort. * @param value - the value to freeze in place. * @returns the same value, frozen. */ diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts index 523092bf09..945aad156b 100644 --- a/packages/support/acp-snapshot/src/suite.ts +++ b/packages/support/acp-snapshot/src/suite.ts @@ -1,32 +1,14 @@ /** - * The ACP snapshot suite factory (REPLAY by default, keyless). A suite is a - * scenario table plus a snapshots directory: each scenario under - * `//` ships an `input.json` (the client stdin script) and - * a `session.jsonl` fixture; replay boots the real agent subprocess - * (./harness.ts), drives it, and diffs the normalized stdout transcript - * against the committed `stdout.golden.jsonl`. For model scenarios it ALSO - * checks the re-persisted session log — against the `session.jsonl` fixture - * itself, not a separate golden: the fixture doubles as the replay source - * (recorded scenarios) and the expected produced log (both sides normalized - * before comparing). + * Keyless-by-default ACP snapshot suite factory. Each scenario drives the real + * subprocess and compares normalized stdout; comparable session fixtures are + * both replay input and expected output. Record mode refreshes reproducible + * model scenarios from the live API, while refresh mode replays committed + * scripts and rewrites derived artifacts without a key. * - * Request-header content is pinned by exactly ONE scenario per HEADER CLASS — - * scenarios that boot the same config compose the same header. Every JSONL - * fixture scrubs the system prompt to `{{system}}`; each class's pinning - * scenario stores the readable prompt in `system-prompt.golden.md` and keeps its full - * tool schemas in `session.jsonl`, while every other fixture also scrubs tools - * to `{{tools}}`. A per-run uniformity guard compares both artifacts against - * every live header and forbids unrepresented changed headers (see the - * pinned-header RFC, - * docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md). - * - * `pnpm run test:snapshot:record` (DSH_SNAPSHOT=record + -u) re-records the - * `session.jsonl` fixtures against the real API and refreshes the stdout golden - * in one pass. `pnpm run test:snapshot:refresh` (DSH_SNAPSHOT=refresh) instead - * replays the committed model scripts keylessly and writes the current stdout - * + persisted-log goldens back without calling a live LLM. The caller resolves - * that env into {@link SnapshotSuiteOptions} (env reading stays at the suite - * edge, not in this library). + * Exactly one scenario per header-composition class pins tool schemas in JSONL + * and the system prompt in Markdown. Every live header is checked against that + * pin, so session-dependent composition must declare a separate class instead + * of escaping coverage. * * @module @deepseek-ai/dsh-acp-snapshot/suite */ @@ -89,20 +71,8 @@ export interface Scenario { */ childSessions?: number /** - * Whether THIS scenario pins its header class's model-facing request-header - * content. Its actual composed prompt is maintained as a readable - * `system-prompt.golden.md`; its JSONL keeps full tool schemas but stores the prompt - * as `{{system}}`. Every other scenario of the class stores tools as - * `{{tools}}` too ({@link scrubRequestHeaders}). A prompt or tool-schema - * change therefore shows up in one focused artifact per class, not every - * session fixture. One pin per class suffices because - * header composition is class-uniform (parent, spawn child, and fork child - * all compose the same prompt-modulo-cwd and the same tools) — and that - * premise is ASSERTED, not assumed: every non-pinning run's live headers - * must equal its class's pinned fixture's (normalized), so a - * session-dependent header (say, a restricted subagent toolset) fails loud - * until it gets its own pinning scenario. - * Defaults to false. + * Whether this scenario is its header class's sole request-header pin. Its Markdown file owns + * the prompt, its JSONL keeps tool schemas, and every classmate is checked for equality. */ pinsHeader?: boolean /** @@ -161,17 +131,9 @@ export function childFixturePaths(dir: string, childSessions: number): string[] } /** - * Derive the {@link NormalizeContext} for a `session.jsonl` fixture from its own - * header line (`{ type: 'session', id, cwd }`). A committed fixture carries the - * session id and cwd of the run that harvested it — different from the live - * replay run — so normalizing it against the live run's ctx would leave those - * recorded values unscrubbed. Reading them from the header scrubs the fixture's - * own id/cwd to the same `{{sessionId}}`/`{{cwd}}` tokens the replay output gets. - * An authored fixture whose header is already normalized (`id:'{{sessionId}}'`, - * `cwd:'{{cwd}}'`) yields those tokens as the volatile values, so scrubbing them - * is an idempotent no-op. A header with no `cwd` falls back to a sentinel that - * cannot occur in a log (NOT `''`, which `String.split` would match on every - * character boundary and corrupt the output). + * Derive normalization values from a fixture's own session header. Recorded ids and cwd differ + * from the live replay run; the non-empty sentinel for missing cwd avoids accidental empty- + * string replacement. * * @param fixture The committed `session.jsonl` content. * @returns The fixture's own volatile values, ready for {@link normalizeSessionLog}. @@ -383,10 +345,8 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { for (const scenario of scenarios) { describe(`snapshot: ${scenario.name}`, () => { - // In RECORD mode, only re-run the `recorded` (live-API) scenarios; the - // `authored` ones (sidecar-driven errors/cancel) are never re-recorded. - // REFRESH mode is replay-backed and deterministic, so it runs every - // scenario and rewrites the comparable fixtures from that replay run. + // In RECORD mode, only re-run the `recorded` (live-API) scenarios; the `authored` ones + // (sidecar-driven errors/cancel) are never re-recorded. it.skipIf(RECORDING && !scenario.recorded)('matches the goldens', async () => { const dir = join(snapshotsDir, scenario.name) const input = JSON.parse(await readFile(join(dir, 'input.json'), 'utf8')) as InputScript @@ -408,10 +368,9 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { ...scenario.configPath !== undefined ? { configPath: scenario.configPath } : {}, }) - // Scrub every volatile id the run produced: the ACP server-issued session - // id plus every harvested log's recorded id (a subagent child id never - // surfaces over ACP, but it appears in the child's own log header). The - // normalizer's UUID catch-all covers any we don't enumerate. + // Scrub every volatile id the run produced: the ACP server-issued session id plus every + // harvested log's recorded id (a subagent child id never surfaces over ACP, but it + // appears in the child's own log header). const ctx: NormalizeContext = { sessionIds: [ ...result.sessionId !== undefined ? [result.sessionId] : [], @@ -420,15 +379,8 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { cwd: result.cwd, } - // RECORD mode (recorded model scenarios only): persist the freshly-harvested - // live logs back to their fixtures. REFRESH mode does the same from a - // keyless replay run for every comparable log, including authored - // scenarios that live record deliberately skips. The primary goes to - // session.jsonl, each child to session..jsonl in harvest order. A - // Every fixture is written with its system prompt scrubbed. A pinning - // scenario keeps the remaining header content (notably tool schemas); - // every other scenario scrubs that bulk too. Record/refresh therefore - // cannot smuggle prompt text back into JSONL or duplicate schemas. + // Record writes live model fixtures; keyless refresh writes every comparable replayed + // fixture. Pins keep tools but all JSONL files scrub prompt text. const scrub = scenario.pinsHeader === true ? scrubSystemPrompts : scrubRequestHeaders @@ -471,14 +423,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { // A model turn always produces a log worth comparing; a hook scenario can // produce one without a model turn (a `rejected` turn carrying `hook/*`). if (comparesLog) { - // The harvested logs (primary-first) must match their committed fixtures - // 1:1. Each side passes through normalizeSessionLog, scrubbed against ITS - // OWN volatile values — the live run's via `ctx`, the committed fixture's - // via its own header (a committed file cannot share the live run's ids). - // Both sides pass through the scenario's idempotent scrub: every live - // prompt becomes the fixture's `{{system}}`; non-pinning scenarios - // additionally tokenize tools/prefix. The dedicated header guard below - // compares those omitted values against their class's pin artifacts. + // The harvested logs (primary-first) must match their committed fixtures 1:1. expect(result.sessionLogs.length, 'this scenario must persist a session log').toBe(childSessions + 1) for (let i = 0; i < fixtureFiles.length; i++) { const harvested = scrub((result.sessionLogs[i] as HarvestedLog).content) @@ -544,18 +489,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { }) it('every registered scenario has its required fixture files', () => { - // Every scenario has an input script and an stdout golden. EVERY scenario - // also needs `session.jsonl`: the suite boots `llm-replay` with that path - // as the replay source for ALL scenarios (the factory passes - // `fixtureFile: /session.jsonl` unconditionally), and `loadReplayScript` - // throws "fixture not found" when it is absent and no override replaces it. - // A no-model scenario ships a header-only `session.jsonl` (it derives to an - // empty script — no model call is made); a model scenario's fixture also - // doubles as the expected-log artifact the run is diffed against. The - // `replay.override.json` sidecar is matched BOTH ways against the table's - // `overridden` flag: required when set, forbidden when not — the harness - // forwards the file purely on existence, so an unregistered stray sidecar - // would silently replace the derived script. + // Every scenario has an input script and an stdout golden. for (const { name, overridden, childSessions, pinsHeader } of scenarios) { const dir = join(snapshotsDir, name) expect(existsSync(join(dir, 'input.json')), `${name}/input.json`).toBe(true) @@ -574,10 +508,8 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { }) it('exactly one scenario pins the request-header content of each header class', () => { - // Zero pins would drop a class's prompt/schema surface from the suite - // entirely; two would split it. One pin per class is the design - // (pinned-header RFC); WHICH scenario pins is the scenario table's - // reviewable choice. + // Zero pins would drop a class's prompt/schema surface from the suite entirely; two would + // split it. const pins = new Map() for (const scenario of scenarios.filter(s => s.pinsHeader === true)) { const cls = classOf(scenario) From 99dccf559ade20054ab041143d0c6e594904b159 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 15:13:57 +0800 Subject: [PATCH 140/359] fix(compact): preserve replay ownership (PR2 round 2) --- docs/architecture.md | 2 +- .../2026-06-18-compaction-capability-seam.md | 2 +- packages/compact/compact-basic/README.md | 2 +- packages/compact/compact-basic/src/index.ts | 10 ++- .../compact-basic/tests/compact-basic.spec.ts | 20 ++++++ packages/compact/compact/README.md | 4 +- packages/compact/compact/src/index.ts | 12 ++-- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/loop.ts | 61 +++++++++++++---- .../tests/contract-regressions.spec.ts | 68 ++++++++++++++++++- 10 files changed, 154 insertions(+), 29 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index 75a03c474c..1fa0ee377c 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -81,7 +81,7 @@ forever: agent/request (config only) -> log request/header -> llm/stream (frozen) 'assistant/chunk' agent/step-result - 'assistant/message' + 'assistant/message' (transformed content, or an empty successful-call anchor if step-result rejects) each tool call: 'tool/call' tools/pre-execute -> monotonic guards -> tools/execute -> tools/post-execute -> tools/result diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index d5d254cf4a..42b93f1225 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -30,7 +30,7 @@ This is not a coupling smell — it is the contract's domain. The "only cordis" An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the standalone service lets multiple consumers share one model/session replay fold. -`compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` takes required pressure inputs and cancellation. The session comes from the agent. `compactRegion(session, start, end, agent, signal?)` keeps an optional signal for manual callers. The pre-step integration resolves a provisional model from the latest logged request header, then `AgentOptions.model`; a model-less router-only first step skips pressure because `agent/request` can route later. The default summarizer resolves its model from explicit config, the latest logged routed model, then agent options. +`compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` takes required pressure inputs and cancellation. The session comes from the agent. `compactRegion(session, start, end, agent, signal?)` keeps an optional signal for manual callers and requires `session === agent.session`; implementations reject mismatch before model resolution, lock acquisition, summarization, or log mutation. The pre-step integration resolves a provisional model from the latest logged request header, then `AgentOptions.model`; a model-less router-only first step skips pressure because `agent/request` can route later. The default summarizer resolves its model from explicit config, the latest logged routed model, then agent options. ### Auto-compaction runs on `agent/pre-step`, a dedicated surface-mutation seam diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index 435e14d875..c9264e2e99 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -13,7 +13,7 @@ This backend owns the compaction policy: - **Convergence** — retry head-checkpoint compaction up to `compactionRetries`; reject a summary that does not shrink its source, and throw if retries cannot return below threshold. - **Summarization** — a direct `llm/stream` call uses the configured model and cap without running the loop-only `agent/request` seam. The input transcript preserves non-text blocks as tagged placeholders; only returned text enters the checkpoint, excluding reasoning and tool calls that would leak private reasoning or create an orphaned call. - **Framing** — the replacement user message marks established checkpoint context with `` tags. The raw summary remains on the provenance event, and later automatic cycles merge the prior checkpoint. -- **Lifecycle** — `compactRegion()` records its start, summary, replacement, and end. The serial `agent/pre-step` listener checks pressure before every step, outside an open step, so a tool-heavy turn remains compactable and the loop derives history once after mutation. +- **Lifecycle** — `compactRegion()` requires its agent to own the exact target session and rejects mismatch before resolution or mutation; a valid call records its start, summary, replacement, and end. The serial `agent/pre-step` listener checks pressure before every step, outside an open step, so a tool-heavy turn remains compactable and the loop derives history once after mutation. - **Failure handling** — an unmatched `compact/start` is an inert crash marker because no replacement landed. Recoverable failure records an error end and leaves the surface unchanged. `summarize()` is the sole subclass hook. A template- or remote-summarizer subclass can override it while pressure, retention, provenance, shrink validation, and shadowed-token accounting stay on the conversation model's meter. The hook returns the summary blocks together with the call envelope it used (`{ summary, model, maxTokens? }`), which is logged on `compact/summary`. diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index f8a9060aa9..cd4ea5d1d5 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -159,11 +159,12 @@ export class BasicCompactService extends CompactService { /** * Compact one inclusive positional surface range using the effective - * conversation model for all retention and shrink pricing. - * @param session - session whose surface is mutated. + * conversation model for all retention and shrink pricing. Reject an agent + * that does not own the exact target before any resolution or mutation. + * @param session - session whose surface is mutated; must equal `agent.session`. * @param start - inclusive first surface-node seq. * @param end - inclusive last surface-node seq. - * @param agent - agent used by the summarizer and model resolver. + * @param agent - owner of the target session, used by the summarizer and model resolver. * @param signal - optional summarization cancellation signal. * @returns the successful durable compaction result. */ @@ -174,6 +175,9 @@ export class BasicCompactService extends CompactService { agent: Agent, signal?: AbortSignal, ): Promise { + if (session !== agent.session) { + throw new Error('compactRegion: agent.session must be the exact target session') + } const model = effectiveModel(agent) if (model === undefined || model.length === 0) { throw new Error('compactRegion: no routed or configured conversation model is available for token pricing') diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 4feb981237..98b4b2f15b 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -361,6 +361,26 @@ describe('pressure measurement and retention', () => { }) describe('compaction region transaction', () => { + it('rejects an agent that does not own the exact target session before mutation', async () => { + const compact = service() + const target = conversation(2) + const owner = conversation(1) + const targetEvents = [...target.events] + const ownerEvents = [...owner.events] + const nodes = target.surface.nodes + + await expect(compact.compactRegion( + target, + nodes[0]!.seq, + nodes[1]!.seq, + agent(owner), + )).rejects.toThrow('compactRegion: agent.session must be the exact target session') + + expect(target.events).toEqual(targetEvents) + expect(owner.events).toEqual(ownerEvents) + expect(compact.calls).toEqual([]) + }) + it('lands a framed, replayable checkpoint with exact pricing provenance', async () => { const compact = service() const session = conversation(3) diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index bbaeff0b17..89aacbb09b 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -19,9 +19,9 @@ Both methods are **abstract** — the backend owns trigger policy, retention, ev | Member | Semantics | |---|---| | `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` | Estimate the surface-derived history size; if over the backend's threshold, compact an older range via `compactRegion`, keeping recent context intact. Returns the `CompactionResult`, or `null` if nothing needed compacting. All parameters required — the loop's `agent/pre-step` checkpoint supplies the agent, assembled `fullSystemPrompt`, composed `sessionPrefix` (request-only messages every request carries but the derived history omits — the pressure estimate must count them), and turn `signal`. A backend's summarization request is a direct `ctx.llm.stream()` call (not a loop step), so per-call interception happens at `llm/stream`. | -| `compactRegion(session, start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. | +| `compactRegion(session, start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) into a single replacement node. The agent must own the exact target (`session === agent.session`); a backend rejects mismatch before model resolution, lock acquisition, summarization, or log mutation. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. | -`compactIfNeeded` takes a required `signal`; `compactRegion`'s is optional. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The session being compacted comes from the agent context; the turn that the `compact/*` events belong to is recoverable from the log (the currently-open turn), so the backend stamps it from the log rather than trusting a caller-supplied value. +`compactIfNeeded` takes a required `signal`; `compactRegion`'s is optional. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The turn that the `compact/*` events belong to is recoverable from the owned session's log (the currently-open turn), so the backend stamps it from the log rather than trusting a caller-supplied value. ## Tool-pairing boundaries diff --git a/packages/compact/compact/src/index.ts b/packages/compact/compact/src/index.ts index 6d32ad0159..7361d38ef3 100644 --- a/packages/compact/compact/src/index.ts +++ b/packages/compact/compact/src/index.ts @@ -67,17 +67,19 @@ export abstract class CompactService extends Service { * `start` and `end` name an inclusive span by surface position, not numeric seq * order; replacements can make visible seqs non-monotonic. Both edges must be * balanced so assistant tool calls remain paired with their results. A model- - * backed implementation forwards cancellation and rejects active, missing, - * reversed, or unbalanced ranges. + * backed implementation forwards cancellation. The agent must own the exact + * target session object; implementations reject an ownership mismatch before + * model resolution, lock acquisition, summarization, or log mutation, and + * reject active, missing, reversed, or unbalanced ranges. * Use {@link toolPairingBalancedBefore} and {@link toolPairingBalancedAfter} * for the edge checks. * - * @param session - session to mutate. + * @param session - session to mutate; must be identical to `agent.session`. * @param start - first surface seq, inclusive. * @param end - last surface seq, inclusive. - * @param agent - summarizer context. + * @param agent - owner of the target session and summarizer context. * @param signal - optional cancellation; model-backed implementations must forward it. - * @throws when compaction is active or the range is missing, reversed, or unbalanced. + * @throws when the agent does not own `session`, compaction is active, or the range is missing, reversed, or unbalanced. * @returns the replaced range and summary. */ abstract compactRegion( diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 99aef8b9cf..803a35fdc5 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -50,7 +50,7 @@ Configured agents start automatically. `cwd` applies only to fresh sessions; `re The driver owns one agent for its lifetime. It records turn, step, request, stream, and tool boundaries in the session log; live extension events coordinate policy around those durable facts. The [architecture turn flow](../../../docs/architecture.md#turn-flow) and generated [event catalog](../../../docs/cordis-catalog/events.md) are the authoritative sequence and signatures. -Every provider call that reaches a successful finish appends one `assistant/message` completion anchor after `agent/step-result`, including content-less calls and `max-tokens` finishes. The anchor records exact chunk provenance (`[]` for a stream with no chunks) and usage when available; empty content stays out of derived message history while those replay facts remain durable. +Every provider call that reaches a successful finish appends exactly one `assistant/message` completion anchor, including content-less calls and `max-tokens` finishes. A successful `agent/step-result` stores its transformed content; a rejected result records empty content before the original failure continues. The anchor retains exact chunk provenance (`[]` for a stream with no chunks) and usage when available, while empty content stays out of derived message history. Plugin failure ends the current turn, not the loop. Cancellation clears pending work and aborts the current step without leaking to the next prompt. Terminal continuation stops remain authoritative through turn close and durability flush. diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index af42d8ff6a..b925162a22 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -6,7 +6,7 @@ */ import type { Context } from 'cordis' -import type { FinishReason, GenerateOptions, LlmCallConfig, Message } from '@deepseek-ai/dsh-llm' +import type { FinishReason, GenerateOptions, LlmCallConfig, Message, TokenUsage } from '@deepseek-ai/dsh-llm' import { BlockAssembler, HarnessError, deepFreeze } from '@deepseek-ai/dsh-llm' import { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' import type { AgentEventDispatch, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' @@ -527,29 +527,26 @@ async function runStep( if (assembler.finish.kind === 'max-tokens') { let message: Message = withoutToolCalls(assembler.message()) - message = withoutToolCalls(await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message))) - // Every successful call records its completion anchor. Empty content is - // skipped by deriveMessages(), while exact chunk provenance lets replay - // distinguish a known empty provider stream from unrecorded provenance. - session.append( - 'assistant/message', - { turn, step, content: message.content, ...(assembler.usage ? { usage: assembler.usage } : {}) }, - { surfaceOp: 'append', sourceEventSeqs: chunkSeqs }, + message = withoutToolCalls(await processStepResult( + events, session, turn, step, message, assembler.usage, chunkSeqs, + )) + appendAssistantCompletion( + session, turn, step, message.content, assembler.usage, chunkSeqs, ) return { hadToolCalls: false, finish: assembler.finish } } // Record the post-waterfall message that tool dispatch uses. let message: Message = assembler.message() - message = await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message)) + message = await processStepResult( + events, session, turn, step, message, assembler.usage, chunkSeqs, + ) // Every successful call records its completion anchor. A present empty // source set means the provider stream was known to contain no chunks; // omission remains the conservative legacy/unrecorded representation. - session.append( - 'assistant/message', - { turn, step, content: message.content, ...(assembler.usage ? { usage: assembler.usage } : {}) }, - { surfaceOp: 'append', sourceEventSeqs: chunkSeqs }, + appendAssistantCompletion( + session, turn, step, message.content, assembler.usage, chunkSeqs, ) // Tool execution stays sequential; recheck abort around each normalized result. @@ -601,6 +598,42 @@ async function runStep( return { hadToolCalls: toolCalls.length > 0, finish: assembler.finish } } +/** Append the single durable completion anchor for one successful provider call. */ +function appendAssistantCompletion( + session: Session, + turn: number, + step: number, + content: Message['content'], + usage: TokenUsage | undefined, + sourceEventSeqs: number[], +): void { + session.append( + 'assistant/message', + { turn, step, content, ...(usage ? { usage } : {}) }, + { surfaceOp: 'append', sourceEventSeqs }, + ) +} + +/** Preserve successful-call accounting without retaining output that result processing rejected. */ +async function processStepResult( + events: AgentEventDispatch, + session: Session, + turn: number, + step: number, + message: Message, + usage: TokenUsage | undefined, + sourceEventSeqs: number[], +): Promise { + try { + return await events.waterfall( + 'agent/step-result', turn, step, message, () => Promise.resolve(message), + ) + } catch (error: unknown) { + appendAssistantCompletion(session, turn, step, [], usage, sourceEventSeqs) + throw error + } +} + function withoutToolCalls(message: Message): Message { return { ...message, content: message.content.filter(block => block.type !== 'tool-call') } } diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 4b2d9df1d3..dd5d2cdf4d 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -8,7 +8,7 @@ import AgentRegistry, { AgentId, type ContinuationDecision } from '@deepseek-ai/ import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { prepareReactLoopAgent } from '../src/agent.ts' import * as Invariants from '@deepseek-ai/dsh-invariants' -import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' +import { maxTokensResponse, MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' /** Regression tests for agent-loop boundary, identity, and lifecycle contracts. */ @@ -89,6 +89,72 @@ describe('session log records what agent/step-result actually produced', () => { }) }) +describe('successful provider completion survives agent/step-result failure', () => { + async function expectContentlessCompletionAnchor( + response: StreamChunk[], + id: string, + providerText: string, + ): Promise { + const adapter = new MockAdapter([response]) + const ctx = await harness(adapter) + await ctx.plugin(Invariants) + const agent = ctx.agentLoop.create(AgentId(id), { model: 'mock' }) + const failure = new Error(`${id} result processing failed`) + const reported: Error[] = [] + + ctx.on('agent/step-result', async () => { + throw failure + }) + ctx.on('agent/error', (subject, _turn, _step, error) => { + if (subject === agent) reported.push(error) + }) + + send(agent, 'go') + await waitForIdle(ctx, agent) + + const events = [...agent.session.events] + const chunks = events.filter(event => event.type === 'assistant/chunk') + const completions = events.filter(event => event.type === 'assistant/message') + expect(completions).toHaveLength(1) + expect(completions[0]?.type === 'assistant/message' && completions[0].data).toEqual({ + turn: 1, + step: 1, + content: [], + usage: { inputTokens: 10, outputTokens: providerText.length }, + }) + expect(completions[0]?.sourceEventSeqs).toEqual(chunks.map(event => event.seq)) + expect(agent.session.deriveMessages()).toEqual([ + { role: 'user', content: [{ type: 'text', text: 'go' }] }, + ]) + expect(reported).toHaveLength(1) + expect(reported[0]).toBe(failure) + const turnEnd = events.findLast(event => event.type === 'turn/end') + expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ + kind: 'error', + step: 1, + message: failure.message, + }) + } + + it('records one content-less anchor when ordinary stop result processing rejects', async () => { + const providerText = 'ordinary provider output' + await expectContentlessCompletionAnchor( + textResponse(providerText), + 'a-step-result-stop-failure', + providerText, + ) + }) + + it('records one content-less anchor when max-token result processing rejects', async () => { + const providerText = 'truncated provider output' + await expectContentlessCompletionAnchor( + maxTokensResponse(providerText), + 'a-step-result-max-token-failure', + providerText, + ) + }) +}) + describe('abort during tool execution ends the turn', () => { it('aborting the in-flight step inside a tool prevents both remaining tools and the next model step', async () => { const adapter = new MockAdapter([ From 634840d406237c88e19aa5170494e160f520b9bc Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Wed, 15 Jul 2026 15:26:03 +0800 Subject: [PATCH 141/359] fix(llm-pi-ai): validate replay provenance --- packages/llm/llm-pi-ai/README.md | 2 +- packages/llm/llm-pi-ai/src/replay.ts | 3 ++ packages/llm/llm-pi-ai/tests/convert.spec.ts | 30 +++++++++++++++++--- 3 files changed, 30 insertions(+), 5 deletions(-) diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index e5e9439713..bb63d82010 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -36,7 +36,7 @@ The selected pi-ai catalog descriptor supplies the protocol implementation. This Successful assistant responses store a versioned, lossless-JSON replay state beside their durable provider/model provenance. At request time, `LlmService` passes replay state only when the historical provider route and target provider route are currently owned by this same `PiAiAdapter` instance. The adapter validates the state and restores pi-ai response ids and provider signatures even when the target provider or model changes; pi-ai then decides which metadata its target API can reuse. History without replay state is translated as foreign provider-neutral content and never impersonates a native pi-ai response. -If a listener rewrites assembled assistant content, the loop drops replay state before logging the message because its provider metadata no longer describes the content. Invalid versions, malformed metadata, and content/block mismatches fail explicitly with `LlmError('INVALID_REPLAY_STATE')`. +If a listener rewrites assembled assistant content, the loop drops replay state before logging the message because its provider metadata no longer describes the content. Invalid versions, malformed metadata, provenance provider/model mismatches, and content/block mismatches fail explicitly with `LlmError('INVALID_REPLAY_STATE')`. ## Vocabulary differences diff --git a/packages/llm/llm-pi-ai/src/replay.ts b/packages/llm/llm-pi-ai/src/replay.ts index 665b236bfe..4e4fe679a5 100644 --- a/packages/llm/llm-pi-ai/src/replay.ts +++ b/packages/llm/llm-pi-ai/src/replay.ts @@ -156,6 +156,9 @@ function foreignAssistant(message: Message): AssistantMessage { /** Recombine durable Harness content with validated pi-ai replay metadata. */ function replayedAssistant(message: Message, rawState: unknown): AssistantMessage { const state = readReplayState(rawState) + const provenance = message.provenance + if (state.provider !== provenance?.provider) return invalidReplay('provider does not match assistant provenance') + if (state.model !== provenance.model) return invalidReplay('model does not match assistant provenance') if (state.blocks.length !== message.content.length) return invalidReplay('block count does not match assistant content') const content: AssistantMessage['content'] = message.content.map((block, index) => { const replay = state.blocks[index] diff --git a/packages/llm/llm-pi-ai/tests/convert.spec.ts b/packages/llm/llm-pi-ai/tests/convert.spec.ts index cf8e07de5c..50955f0607 100644 --- a/packages/llm/llm-pi-ai/tests/convert.spec.ts +++ b/packages/llm/llm-pi-ai/tests/convert.spec.ts @@ -255,7 +255,7 @@ describe('toPiContext', () => { { type: 'text', text: 'calling' }, { type: 'tool-call', id: CallId('c1'), name: 'f', arguments: '{"a":1}' }, ], - provenance: { provider: 'deepseek', model: 'old-model', replayState: state }, + provenance: { provider: 'deepseek', model: 'deepseek-v4-flash', replayState: state }, }], }) @@ -302,7 +302,7 @@ describe('toPiContext', () => { messages: [{ role: 'assistant', content: [{ type: 'reasoning', text: 'done' }], - provenance: { provider: 'deepseek', model: 'old', replayState: state }, + provenance: { provider: 'deepseek', model: 'deepseek-v4-flash', replayState: state }, }], })).toThrow(/block 0 does not match assistant content/) }) @@ -315,7 +315,7 @@ describe('toPiContext', () => { messages: [{ role: 'assistant', content: [{ type: 'text', text: 'done' }], - provenance: { provider: 'deepseek', model: 'old', replayState: state }, + provenance: { provider: 'deepseek', model: 'deepseek-v4-flash', replayState: state }, }], })).toThrow(/block count does not match assistant content/) }) @@ -330,6 +330,28 @@ describe('toPiContext', () => { blocks: [{ type: 'text' }], } + it.each([ + ['provider', { ...validReplay, provider: 'openai' }], + ['model', { ...validReplay, model: 'deepseek-v4-pro' }], + ])('rejects replay metadata whose %s differs from assistant provenance', (field, replayState) => { + try { + toPiContext({ + provider: 'deepseek', + model: 'next-model', + messages: [{ + role: 'assistant', + content: [{ type: 'text', text: 'done' }], + provenance: { provider: 'deepseek', model: 'deepseek-v4-flash', replayState }, + }], + }) + expect.fail('expected invalid replay state') + } catch (error: unknown) { + expect(error).toBeInstanceOf(LlmError) + expect((error as LlmError).code).toBe('INVALID_REPLAY_STATE') + expect((error as Error).message).toContain(`${field} does not match assistant provenance`) + } + }) + it.each([ ['number state', 1, 'expected an object'], ['null state', null, 'expected an object'], @@ -355,7 +377,7 @@ describe('toPiContext', () => { messages: [{ role: 'assistant', content: [{ type: 'text', text: 'done' }], - provenance: { provider: 'deepseek', model: 'old', replayState }, + provenance: { provider: 'deepseek', model: 'deepseek-v4-flash', replayState }, }], })).toThrow(message) }) From e8d066f7505afe83c08ba3cb0b8693a7126558fc Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 16:03:52 +0800 Subject: [PATCH 142/359] feat(core): add post-step request recovery (PR3 phase 1) --- docs/agent-lifecycle.md | 10 +- docs/architecture.md | 58 ++- docs/cordis-catalog/events.md | 52 ++- docs/cordis-catalog/services.md | 2 +- docs/core-data-structures/core.md | 14 + docs/core-data-structures/llm-streaming.md | 3 +- docs/event-producer-consumer.md | 30 +- .../cordis/tool-cordis/src/api-catalog.ts | 12 + packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/loop.ts | 179 +++++-- packages/core/agent-loop/tests/cancel.spec.ts | 57 ++- .../tests/contract-regressions.spec.ts | 10 + .../agent-loop/tests/request-recovery.spec.ts | 442 ++++++++++++++++++ packages/core/agent/README.md | 2 +- packages/core/agent/src/types.ts | 31 ++ packages/llm/llm-deepseek/README.md | 2 +- packages/llm/llm-deepseek/src/adapter.ts | 24 +- .../llm/llm-deepseek/tests/adapter.spec.ts | 28 +- packages/llm/llm-pi-ai/README.md | 2 +- packages/llm/llm-pi-ai/src/convert.ts | 3 +- packages/llm/llm-pi-ai/tests/convert.spec.ts | 14 +- packages/llm/llm/README.md | 5 +- packages/llm/llm/src/adapter-failure.ts | 34 ++ packages/llm/llm/src/error.ts | 41 ++ packages/llm/llm/src/index.ts | 58 ++- packages/llm/llm/tests/service.spec.ts | 198 +++++++- .../invariants/src/scoped-events.generated.ts | 2 + scripts/gen-doc-graphs.ts | 10 +- scripts/type-equiv.manifest.json | 2 + 29 files changed, 1207 insertions(+), 120 deletions(-) create mode 100644 packages/core/agent-loop/tests/request-recovery.spec.ts create mode 100644 packages/llm/llm/src/adapter-failure.ts diff --git a/docs/agent-lifecycle.md b/docs/agent-lifecycle.md index b9292aa80e..e4ed315e5b 100644 --- a/docs/agent-lifecycle.md +++ b/docs/agent-lifecycle.md @@ -32,14 +32,22 @@ sequenceDiagram LLM-->>Driver: StreamChunk* Driver->>Session: assistant/chunk* Session-->>SDK: session/event assistant/chunk* + alt final adapter or terminal in-band request failure + Driver->>Session: step/end + Driver->>Hooks: agent/request-error waterfall + Hooks-->>Driver: retry in a new step or preserve the original error + else model request succeeded Driver->>Hooks: agent/step-result waterfall Driver->>Session: assistant/message Driver->>Session: tool/call Driver->>Tools: execute through pre and post waterfalls Tools-->>Session: tool-owned events when applicable - Driver->>Session: tool/result and step/end + Driver->>Session: tool/result, post-tool context, and steering + Driver->>Hooks: agent/post-step serial checkpoint + Driver->>Session: step/end Driver->>Hooks: agent/turn-continuation waterfall Driver->>Hooks: agent/turn-stop serial terminal checkpoint + end Driver->>Session: turn/end Driver->>Persistence: session/flush parallel checkpoint Driver-->>SDK: agent/status idle diff --git a/docs/architecture.md b/docs/architecture.md index 1fa0ee377c..01988a43df 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -4,7 +4,7 @@ The **DeepSeek Harness SDK** builds agent harnesses on Cordis. The principle is ## Overview -A harness is one [Cordis](cordis-primer.md) context. Packages contribute service keys, typed events, and disposable registrations: services expose stable calls (`ctx.llm`, `ctx.tools`, `ctx.sessions`), events provide interception and notifications (`agent/request`, `tools/pre-execute`, `session/event`), and registrations install prompt sections, tools, providers, adapters, or listeners. +A harness is one [Cordis](cordis-primer.md) context. Packages add services (`ctx.llm`, `ctx.tools`, `ctx.sessions`), typed interception and notification events (`agent/request`, `tools/pre-execute`, `session/event`), and disposable registrations for prompts, tools, providers, adapters, and listeners. `packages/core/` groups the default agent flow; surrounding capabilities are equally first-class Cordis plugins. @@ -43,9 +43,9 @@ Events form the service extension API; see the exhaustive [events catalog](cordi ### Event Domains -- **Session events** are durable, replayable facts. Turn and step boundaries, user input, assistant output, tool calls, tool results, steering, compaction records, and tool-owned durable facts append to the session log and flow through `session/event`. -- **Agent events** carry the live `Agent` handle for status, diagnostics, prompt admission, call-config shaping, result validation, and continuation policy. -- **Capability events** belong to the seam that owns the action. `tools/*`, `llm/*`, `system-prompt/*`, `fs/*`, and `subagent/*` let policy and adapters attach without importing the loop. +- **Session events** are durable replay facts: boundaries, messages, tools, steering, compaction, and tool-owned state flow through `session/event`. +- **Agent events** carry the live `Agent` for status, diagnostics, prompt admission, request shaping, result validation, and continuation. +- **Capability events** belong to their action owner. `tools/*`, `llm/*`, `system-prompt/*`, `fs/*`, and `subagent/*` attach policy and adapters without importing the loop. ### Interception Semantics @@ -53,9 +53,9 @@ Waterfall events behave like around-middleware: a listener delegates by calling ## Default Loop Lifecycle -The shipped loop drains work, assembles requests, streams model answers, executes tools, applies continuation policy, and checkpoints state. Every pause is a service call or event available to plugins. +The shipped loop drains work, assembles requests, streams answers, executes tools, applies continuation policy, and checkpoints state through plugin-visible calls and events. -A **session** is one agent's append-only event log. A **turn** drains one queued batch and runs until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. +A **session** is an agent's append-only log; a **turn** drains one queued batch; a **step** is one model request and its tool executions. Quoted names below are durable events, and unquoted event names are extension points ([sequence companion](agent-lifecycle.md)). ### Turn Flow @@ -76,42 +76,50 @@ forever: assemble system prompt and tool schemas agent/session-prefix (first step) agent/pre-step - 'step/start' snapshot the derived messages (the reconstruction boundary) + 'step/start' agent/request (config only) -> log request/header -> llm/stream (frozen) + on final adapter failure or terminal in-band error/aborted finish: + 'step/end' + agent/request-error(original error, consecutive retry attempt, signal) + retry in the next numbered step or preserve the original error + otherwise: 'assistant/chunk' - agent/step-result - 'assistant/message' (transformed content, or an empty successful-call anchor if step-result rejects) - each tool call: - 'tool/call' - tools/pre-execute -> monotonic guards -> tools/execute -> tools/post-execute -> tools/result - 'tool/result' - append post-tool context and steering - 'step/end' - agent/turn-continuation - agent/turn-stop (terminal policy) - stop unless tools or continuation policy ask for another step + agent/step-result + 'assistant/message' (transformed content, or an empty successful-call anchor if step-result rejects) + each tool call: + 'tool/call' + tools/pre-execute -> monotonic guards -> tools/execute -> tools/post-execute -> tools/result + 'tool/result' + append post-tool context and steering + agent/post-step + 'step/end' + agent/turn-continuation + agent/turn-stop (terminal policy) + stop unless tools or continuation policy ask for another step 'turn/end' checkpoint persistence and notify idle/running status ``` -The loop renders one prompt assembly per step. Plugins contribute ordered sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn instead of shipping a hole. `dsh-system-prompt` owns the harness identity and default deployment persona; an agent-scoped persona may shadow the default. The loop supplies `model` and `cwd`. See the [prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md). +Each step renders one prompt assembly. Plugins contribute ordered sections, tool schemas, and `{{name}}` variables; missing values fail the turn. `dsh-system-prompt` owns harness identity and the default persona, which an agent-scoped persona may shadow. The loop supplies `model` and `cwd` ([prompt ownership](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)). -Post-tool context lands after all tool results so tool-call/result adjacency stays stable. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved. +Post-tool context follows all results, preserving call/result adjacency. Steering drains before `agent/post-step`, which observes durable output, results, context, and steering while the step signal remains open. Leftover steering becomes next-turn input. `agent/turn-stop` is terminal through close and flush: later steering is discarded, while ordinary queued prompts survive. ### Failure Boundaries -The turn is the containment boundary. A throwing listener, adapter error finish, or failed step ends the current turn with an error reason and reports live diagnostics through `agent/error`; it does not kill the driver loop. `cancel()` clears queued and steering work, aborts the active model/tool boundary when possible, and records the appropriate turn end. Disposal stops the loop, awaits quiescence, unregisters the agent, and lets service disposers drain. +The turn is the containment boundary. `LlmService` preserves and privately tags errors from final adapter selection, dispatch, and iteration. Those errors and terminal in-band error/aborted finishes close the failed step before `agent/request-error`; retry reconstructs the next numbered step from the log, while decline or failed recovery preserves the provider error. Attempts count consecutive failures and reset after success. -Every session event is turn-enclosed. Reloading a crashed session preserves the interrupted tail and closes it with a synthetic `interrupted` turn end. A failure after the durable turn has closed reports through `agent/error` only because no safe in-turn position remains. A turn ends with one `TurnEndReason` (`completed`, `aborted`, `error`, `disposed`, `max-tokens`, `rejected`, or `interrupted`); per-variant semantics are in [session.md § TurnEndReasonMap](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap). +Prompt, middleware, result, tool, post-step, and continuation failures remain ordinary `agent/error` failures. Cancellation and disposal beat recovery. Durable undispatched tool calls receive synthetic `ABORTED` results, preventing dangling replay. `cancel()` clears queues and aborts active work; disposal awaits quiescence before unregistering. + +Every session event is turn-enclosed. Reload preserves a crashed tail and closes it with synthetic `interrupted`; post-close failures report only through `agent/error`. A turn has one `TurnEndReason` (`completed`, `aborted`, `error`, `disposed`, `max-tokens`, `rejected`, or `interrupted`), detailed in [session.md](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap). ### Agent Handles -`ctx.agents` owns live agents and returns an `AgentHandle { agent, dispose() }`. `Agent` is the API other plugins drive: `send()` queues work, `steer()` injects mid-turn content, `inject()` appends context and opens a one-shot injection turn when idle, `cancel()` is the public stop primitive, and `whenIdle()` observes quiescence. The caller fiber and concrete factory provider structurally co-own programmatic lifecycles; a consumer handle is the only non-structural teardown capability, and every owner reaches the same awaited disposer. +`ctx.agents` owns live agents and returns `AgentHandle { agent, dispose() }`. Plugins use `send()`, `steer()`, `inject()`, `cancel()`, and `whenIdle()`. The caller fiber and factory provider structurally co-own programmatic lifecycles; the consumer handle is the sole non-structural teardown capability, and all owners share one awaited disposer. ### Agent Scope -Every live agent owns a scoped `agent.ctx`. Its registrations shadow same-named globals, receive only that agent's dispatches, and unwind with the agent. `CreateAgentOptions.setup(agentCtx)` composes the scope before publication. The [semantic-gates RFC](rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md) defines typed resolvers that derive carrier checks from merged `Events` signatures and `scopeTarget`, eliminating the handwritten event table. See the [agent-scope RFC](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md); subagent composition controls are documented [separately](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md). +Each agent owns `agent.ctx`; its registrations shadow globals, receive only that agent's dispatches, and unwind on disposal. `CreateAgentOptions.setup(agentCtx)` composes it before publication. Typed resolvers derive carrier checks from merged events and `scopeTarget` ([semantic gates](rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md), [agent scope](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md), [subagent controls](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md)). ## State @@ -152,7 +160,7 @@ New behavior should attach to a documented extension point; changing the shipped | Add command execution | implement and register a `ctx.bash` backend | | Add filesystem access or policy | implement a `ctx.fs` provider or listen on `fs/*` policy events | | Confine spawned processes | a `ctx.sandbox` backend; consumers wrap their argv before spawning | -| Intercept prompts, requests, tool use, or continuation | listen on the relevant `agent/*` or `tools/*` waterfall; use serial `agent/turn-stop` for a monotonic terminal stop | +| Intercept prompts, requests, model completion/failure, tool use, or continuation | listen on the relevant `agent/*` or `tools/*` event; use serial `agent/turn-stop` for a monotonic terminal stop | | Add a session-stable request prefix outside history | compose it on `agent/session-prefix`, once per loop instance; logged on the request header | | Add UI or editor integration | drive `ctx.agents` and render from `session/event` | | Add durable session state | add a `SessionEventMap` member and render/replay from the log | diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 5408a63720..7ce58b6140 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -23,7 +23,7 @@ A fully configured agent and live session were published. Setup is composition-o Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:139`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:145`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -35,7 +35,7 @@ An agent left the registry; AgentLoop emits this after driver quiescence but bef Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:148`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:154`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -47,7 +47,19 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:283`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:314`](../../packages/core/agent/src/types.ts) + +### `agent/post-step` — serial + +Awaited serial checkpoint after the response, tool results, injected context, and steering are durable but before `step/end`. + +```ts cordis-catalog +'agent/post-step'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void +``` + +Types: [Agent](../core-data-structures/core.md) + +Source: [`packages/core/agent/src/types.ts:267`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -59,7 +71,7 @@ Awaited serial checkpoint for session-surface mutation after prompt assembly and Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:202`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:208`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -71,7 +83,7 @@ Allow, rewrite, or block one drained prompt before it becomes a user message. Ca Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:212`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:218`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -83,7 +95,7 @@ Detached, frozen content entered the agent's inbox. Source defaults have already Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:167`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:173`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -95,7 +107,19 @@ Replace the frozen call configuration. Model-visible content must use logged cha Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:224`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:230`](../../packages/core/agent/src/types.ts) + +### `agent/request-error` — waterfall + +Recover a model-request failure after its failed step has closed. `retry` opens a new numbered step; `fail` preserves the original request error. Call `next()` to delegate to the next recovery listener or the default. + +```ts cordis-catalog +'agent/request-error'(this: Scoped, agent: Agent, turn: number, step: number, error: RequestError, retryAttempt: number, signal: AbortSignal, next: () => Promise): Promise +``` + +Types: [Agent](../core-data-structures/core.md) + +Source: [`packages/core/agent/src/types.ts:281`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -107,7 +131,7 @@ Compose request-only messages placed before derived history. The frozen result i Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:239`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:245`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -119,7 +143,7 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:180`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:186`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -131,7 +155,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does no Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:157`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:163`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -143,7 +167,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:250`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:256`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -155,7 +179,7 @@ Override whether the turn continues. The default continues after tool calls or s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:260`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:291`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -167,7 +191,7 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:270`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:301`](../../packages/core/agent/src/types.ts) ## `approval/*` @@ -233,7 +257,7 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:39`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:41`](../../packages/llm/llm/src/index.ts) ## `session/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 150cd35f7f..990a2bc1bc 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -127,7 +127,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:75`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:77`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 36d007eb38..1f8dca8abc 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -381,6 +381,20 @@ type ContinuationDecision = | { action: 'continue'; reason?: HookContext } ``` +`agent/request-error` receives the original `RequestError`, whose optional provider-neutral `code` supports stable routing without message parsing: + +```ts type-equiv +type RequestError = Error & { code?: string } +``` + +It returns a `RequestErrorDecision`; `retry` opens a new numbered step after the recovery listener's durable mutation, while `fail` preserves that error: + +```ts type-equiv +type RequestErrorDecision = { action: 'fail' } | { action: 'retry' } +``` + +`agent/post-step` is the awaited successful-step checkpoint after assistant output, tool results, buffered context, and steering are durable. Its signature is `(agent, turn, step, signal)`; replayable facts remain in the session log rather than a transient payload. + `agent/turn-stop` returns the stop-only `ContinuationStop` subset or `undefined`. The loop calls this serial checkpoint after folding the ordinary decision, its reason, and pending steering; a stop is terminal and discards pending steering. ```ts type-equiv diff --git a/docs/core-data-structures/llm-streaming.md b/docs/core-data-structures/llm-streaming.md index fff329310a..32174f0d03 100644 --- a/docs/core-data-structures/llm-streaming.md +++ b/docs/core-data-structures/llm-streaming.md @@ -26,6 +26,7 @@ Every adapter MUST obey these, and every consumer may rely on them: - **`usage` before `finish`, nothing after `finish`.** Defer both to the provider's end-of-stream marker so a trailing usage-only chunk can't violate the ordering. - **Tool-call `arguments` stay raw JSON strings end-to-end.** Partial fragments stream via `argumentsDelta`; a provider that hands back parsed objects re-stringifies at `block-end`. - **Two sanctioned error paths.** A failure may either THROW from `stream()` (transport/protocol errors) **or** end the stream with `finish {kind:'error'|'aborted'}` (provider in-band errors, for adapters that can't throw mid-stream). Consumers must handle *both*. The agent loop translates a finish-error/aborted into a turn error — it never logs a normal completed assistant message for a failed step. +- **Context overflow has one canonical code.** Both DeepSeek adapters classify explicit provider detail through `isContextWindowExceededError()` and surface `CONTEXT_WINDOW_EXCEEDED`, whether the failure arrives as a thrown HTTP `LlmError` or an in-band finish error. Consumers route on the code, never provider text. - **Every provider HTTP request carries the app-attribution header.** Adapters send `attributionHeaders()` (below) - the `User-Agent` baseline - and prove it with a wire-level test (mock server asserting the received header, or the library's header hook for a library-backed adapter). This contract is why two adapters exist as a deliberate pair: `dsh-llm-deepseek` (hand-rolled fetch/SSE) and `dsh-llm-pi-ai` (the same endpoint through `@earendil-works/pi-ai`). Two independent internals over one contract is what pinned the protocol down — the library-backed adapter can't throw mid-stream, so it exercises the finish-chunk error path the hand-rolled one might not. @@ -44,7 +45,7 @@ interface AppIdentity { ## `TokenUsage` -Per-call token accounting. Counts are **disjoint**: `inputTokens` is uncached input only; cached input is reported separately, and billed input is the sum of the three. Adapters whose providers fold cache hits into a single prompt total (DeepSeek's `prompt_tokens`) subtract them back out. +Per-call token accounting. Counts are **disjoint**: `inputTokens` is uncached input only; cached input is reported separately, and billed input is the sum of the three. Adapters whose providers fold cache hits into a single prompt total (DeepSeek's `prompt_tokens`) subtract them back out. `reasoningTokens`, when present, is informational detail already included in `outputTokens`; totals must not add it again. ```ts type-equiv interface TokenUsage { diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index e095aa4b7e..e6872669de 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,24 +7,26 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:139`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:148`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:283`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:202`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:212`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:167`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:224`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:239`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:180`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:157`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:250`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:260`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:270`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:145`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:154`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:314`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/post-step` | `serial` | [`packages/core/agent/src/types.ts:267`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:208`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:218`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:173`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:230`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:281`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:245`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:186`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:163`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:256`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:291`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:301`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:59`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:68`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:51`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | -| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | +| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:41`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | | `session/created` | `emit` | [`packages/core/session/src/index.ts:46`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:56`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | | `session/event` | `emit` | [`packages/core/session/src/index.ts:68`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio), [`token-meter`](../packages/llm/token-meter) | diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 5e4f5f0b69..7aafb3ce8a 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -280,6 +280,12 @@ export const EVENT_API: readonly EventApiEntry[] = [ signature: '\'agent/error\'(this: Scoped, agent: Agent, turn: number, step: number, error: Error): void', summary: 'A step or turn errored.', }, + { + name: 'agent/post-step', + mode: 'serial', + signature: '\'agent/post-step\'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void', + summary: 'Awaited serial checkpoint after the response, tool results, injected context, and steering are durable but before `step/end`.', + }, { name: 'agent/pre-step', mode: 'serial', @@ -304,6 +310,12 @@ export const EVENT_API: readonly EventApiEntry[] = [ signature: '\'agent/request\'(this: Scoped, agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise): Promise', summary: 'Replace the frozen call configuration.', }, + { + name: 'agent/request-error', + mode: 'waterfall', + signature: '\'agent/request-error\'(this: Scoped, agent: Agent, turn: number, step: number, error: RequestError, retryAttempt: number, signal: AbortSignal, next: () => Promise): Promise', + summary: 'Recover a model-request failure after its failed step has closed.', + }, { name: 'agent/session-prefix', mode: 'waterfall', diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 803a35fdc5..864ff95e8c 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -52,7 +52,7 @@ The driver owns one agent for its lifetime. It records turn, step, request, stre Every provider call that reaches a successful finish appends exactly one `assistant/message` completion anchor, including content-less calls and `max-tokens` finishes. A successful `agent/step-result` stores its transformed content; a rejected result records empty content before the original failure continues. The anchor retains exact chunk provenance (`[]` for a stream with no chunks) and usage when available, while empty content stays out of derived message history. -Plugin failure ends the current turn, not the loop. Cancellation clears pending work and aborts the current step without leaking to the next prompt. Terminal continuation stops remain authoritative through turn close and durability flush. +Plugin failure ends the current turn, not the loop. Only final adapter dispatch/iteration failures and terminal in-band error or aborted finishes enter `agent/request-error`; middleware, result processing, tools, and `agent/post-step` remain ordinary turn failures. Recovery observes a closed failed step, and a retry rebuilds the request from the durable log in a new numbered step. Cancellation clears pending work and aborts the current step without leaking to the next prompt; model-requested calls that were already durable receive synthetic aborted results when cancellation prevents dispatch. Terminal continuation stops remain authoritative through turn close and durability flush. ### What belongs to plugins diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 41c5d60646..e749018f55 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -7,37 +7,42 @@ import type { Context } from 'cordis' import type { FinishReason, GenerateOptions, LlmCallConfig, Message, TokenUsage } from '@deepseek-ai/dsh-llm' -import { BlockAssembler, HarnessError, deepFreeze } from '@deepseek-ai/dsh-llm' +import { BlockAssembler, HarnessError, deepFreeze, isLlmAdapterFailure } from '@deepseek-ai/dsh-llm' import { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' -import type { AgentEventDispatch, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' +import type { AgentEventDispatch, ContinuationDecision, HookContext, PromptDecision, RequestError, RequestErrorDecision } from '@deepseek-ai/dsh-agent' import { canonicalHeader } from '@deepseek-ai/dsh-session' import type { Session, TurnEndReason, TurnTrigger } from '@deepseek-ai/dsh-session' import { createTransmissionLog, recordRequestHeader } from './request-log.ts' import type { TransmissionLog } from './request-log.ts' import { renderPrompt } from '@deepseek-ai/dsh-system-prompt' import type { PromptAssembly } from '@deepseek-ai/dsh-system-prompt' -import type {} from '@deepseek-ai/dsh-tools' +import type { ToolExecutionResult } from '@deepseek-ai/dsh-tools' import type { ReactLoopAgent } from './agent.ts' import type { Inbox } from './inbox.ts' -/** An Error with an optional machine-readable code (e.g., from LlmError or a throwing plugin). */ -type CodedError = Error & { code?: string } - /** Normalize thrown values while preserving an existing error code. */ -function toError(error: unknown): CodedError { +function toError(error: unknown): RequestError { return error instanceof Error ? error : new HarnessError(String(error), 'UNKNOWN', { cause: error }) } +/** Distinguishes a terminal failure finish from failures in later step processing. */ +class TerminalModelRequestFailure extends Error { + constructor(readonly requestError: RequestError) { + super(requestError.message, { cause: requestError }) + this.name = 'TerminalModelRequestFailure' + } +} + /** Convert terminal failure finishes into step errors; unknown extensible finishes remain successful. */ -function finishError(finish: FinishReason): CodedError | undefined { +function finishError(finish: FinishReason): RequestError | undefined { switch (finish.kind) { case 'error': { - const error: CodedError = new Error(finish.message) + const error: RequestError = new Error(finish.message) if (finish.code !== undefined) error.code = finish.code return error } case 'aborted': { - const error: CodedError = new Error('model stream aborted') + const error: RequestError = new Error('model stream aborted') error.code = 'ABORTED' return error } @@ -51,10 +56,19 @@ function finishError(finish: FinishReason): CodedError | undefined { * Build the `{ message, code? }` part of an error payload, omitting the * `code` key entirely when absent (exactOptionalPropertyTypes-correct). */ -function errorData(err: CodedError): { message: string; code?: string } { +function errorData(err: RequestError): { message: string; code?: string } { return { message: err.message, ...typeof err.code === 'string' ? { code: err.code } : {} } } +/** Build the durable result for a model-requested call skipped after cancellation. */ +function skippedToolResult(): ToolExecutionResult { + return { + content: [{ type: 'text', text: 'Error: tool call skipped because the step was aborted before execution' }], + isError: true, + error: { name: 'AbortError', code: 'ABORTED' }, + } +} + /** Map a successful max-token finish onto the turn reason; other successful finishes add nothing. */ function stepFinishReason(finish: FinishReason): TurnEndReason | undefined { switch (finish.kind) { @@ -168,6 +182,7 @@ async function runTurn( let reason: TurnEndReason = { kind: 'completed' } let step = 0 + let requestRetryAttempt = 0 let stepOpen = false let errorReported = false let terminalStopped = false @@ -180,7 +195,7 @@ async function runTurn( } // Record the durable turn failure once and contain the live error notification. - const failTurn = (err: CodedError): void => { + const failTurn = (err: RequestError): void => { if (errorReported) return errorReported = true reason = { kind: 'error', step, ...errorData(err) } @@ -322,14 +337,65 @@ async function runTurn( break } - let stepOutcome: { hadToolCalls: boolean; finish: FinishReason } | { error: Error } + let stepOutcome: + | { hadToolCalls: boolean; finish: FinishReason } + | { requestError: RequestError } + | { error: RequestError } try { stepOutcome = await runStep( ctx, events, agent, turn, step, assembly, fullSystemPrompt, boundaryMessages, transmission, abort.signal) } catch (error: unknown) { - stepOutcome = { error: toError(error) } - } finally { + if (isLlmAdapterFailure(error)) { + stepOutcome = { requestError: error } + } else if (error instanceof TerminalModelRequestFailure) { + stepOutcome = { requestError: error.requestError } + } else { + stepOutcome = { error: toError(error) } + } + } + + if ('requestError' in stepOutcome) { + // Recovery observes a balanced failed step and the original provider + // error while the failed step's signal remains the active owner. + closeStep() + if (handle.isDisposed() || abort.signal.aborted) { + handle.setAbort(undefined) + reason = handle.isDisposed() + ? { kind: 'disposed' } + : { kind: 'aborted', reason: String(abort.signal.reason) } + break + } + + const defaultDecision: RequestErrorDecision = { action: 'fail' } + let recoveryDecision: RequestErrorDecision = defaultDecision + try { + recoveryDecision = await events.waterfall( + 'agent/request-error', turn, step, stepOutcome.requestError, + requestRetryAttempt, abort.signal, + () => Promise.resolve(defaultDecision), + ) + } catch (recoveryError: unknown) { + ctx.logger.warn( + `agent "${agent.id}": request recovery failed at turn ${turn}, step ${step}: ${toError(recoveryError).message}`, + ) + } handle.setAbort(undefined) + + // Cancellation and disposal always win over either a recovery decision + // or a recovery-listener failure. + // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition + if (handle.isDisposed() || abort.signal.aborted) { + reason = handle.isDisposed() + ? { kind: 'disposed' } + : { kind: 'aborted', reason: String(abort.signal.reason) } + break + } + if (recoveryDecision.action === 'retry') { + requestRetryAttempt += 1 + continue + } + failTurn(stepOutcome.requestError) + break } if ('error' in stepOutcome) { @@ -337,7 +403,9 @@ async function runTurn( // runLoop re-enqueues it as a queued message, so an abort-then-steer // starts a fresh turn instead of being silently consumed. closeStep() + handle.setAbort(undefined) const { error } = stepOutcome + /* v8 ignore next -- narrow race: disposal while non-request step work throws. */ if (handle.isDisposed()) { reason = { kind: 'disposed' } } else if (abort.signal.aborted) { @@ -349,6 +417,8 @@ async function runTurn( break } + requestRetryAttempt = 0 + // Preserve max-token completion unless a later disposal, abort, or error wins. const stepReason = stepFinishReason(stepOutcome.finish) if (stepReason) reason = stepReason @@ -356,7 +426,38 @@ async function runTurn( // Steering that arrived during streaming/tool execution. const steered = drainSteering(agent, handle.inbox, turn) + try { + await events.serial('agent/post-step', turn, step, abort.signal) + } catch (error: unknown) { + stepOutcome = { error: toError(error) } + } + + if ('error' in stepOutcome) { + closeStep() + handle.setAbort(undefined) + /* v8 ignore next -- narrow race: disposal while a post-step listener throws. */ + if (handle.isDisposed()) { + reason = { kind: 'disposed' } + } else if (abort.signal.aborted) { + /* v8 ignore next -- signal.reason always set by cancellation or disposal. */ + reason = { kind: 'aborted', reason: String(abort.signal.reason ?? 'aborted') } + } else { + failTurn(stepOutcome.error) + } + break + } + + if (handle.isDisposed() || abort.signal.aborted) { + reason = handle.isDisposed() + ? { kind: 'disposed' } + : { kind: 'aborted', reason: String(abort.signal.reason) } + closeStep() + handle.setAbort(undefined) + break + } + closeStep() + handle.setAbort(undefined) const defaultDecision: ContinuationDecision = { action: stepOutcome.hadToolCalls || steered ? 'continue' : 'stop' } let decision: ContinuationDecision @@ -523,7 +624,7 @@ async function runStep( // Normalize failure finish chunks into the same path as thrown stream errors. const stepError = finishError(assembler.finish) - if (stepError) throw stepError + if (stepError) throw new TerminalModelRequestFailure(stepError) if (assembler.finish.kind === 'max-tokens') { let message: Message = withoutToolCalls(assembler.message()) @@ -553,25 +654,30 @@ async function runStep( const toolCalls = message.content.filter(block => block.type === 'tool-call') // Buffer context until all results are appended to preserve call/result adjacency. const pendingContext: HookContext[] = [] + let aborted = signal.aborted for (const call of toolCalls) { - /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ - if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) const callEvent = session.append('tool/call', { turn, step, callId: call.id, name: call.name, arguments: call.arguments }) - let parsedArguments: unknown - try { - parsedArguments = call.arguments ? JSON.parse(call.arguments) : {} - } catch { - parsedArguments = call.arguments + let result: ToolExecutionResult + if (aborted || signal.aborted) { + aborted = true + result = skippedToolResult() + } else { + let parsedArguments: unknown + try { + parsedArguments = call.arguments ? JSON.parse(call.arguments) : {} + } catch { + parsedArguments = call.arguments + } + // TODO(pre-tool-input-rewrite): Keep logged history and live presentation aligned; + // see docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md. + result = await ctx.tools.execute({ + callId: call.id, + name: call.name, + arguments: parsedArguments, + agent, + signal, + }) } - // TODO(pre-tool-input-rewrite): Keep logged history and live presentation aligned; - // see docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md. - const result = await ctx.tools.execute({ - callId: call.id, - name: call.name, - arguments: parsedArguments, - agent, - signal, - }) session.append('tool/result', { turn, step, // Correlation comes from the immutable execution input; the result does @@ -584,13 +690,12 @@ async function runStep( ...result.meta !== undefined ? { meta: result.meta } : {}, }, { surfaceOp: 'append', sourceEventSeqs: [callEvent.seq] }) if (result.additionalContext) pendingContext.push(result.additionalContext) - // The signal may flip while the tool is awaited. - /* v8 ignore start -- signal.reason default unreachable: cancel()/disposal always set it */ - // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition - if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) - /* v8 ignore stop */ + if (signal.aborted) aborted = true } + /* v8 ignore next -- signal.reason always set by cancellation or disposal. */ + if (aborted) throw new Error(String(signal.reason ?? 'aborted')) + // Append buffered context after the complete result batch. for (const context of pendingContext) { agent.inject(context.content, { source: context.source }) diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index cad830e827..80284b64b5 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -12,10 +12,10 @@ import { Context } from 'cordis' import LlmService, { type Message } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry from '@deepseek-ai/dsh-tools' +import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' -import { MockAdapter, textResponse } from './mock-adapter.ts' +import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' async function harness(adapter: MockAdapter) { const ctx = new Context() @@ -139,6 +139,59 @@ describe('Agent.cancel()', () => { expect(reasons).toEqual([{ kind: 'aborted', reason: 'cancelled' }]) }) + it('cancel from an assistant/message observer skips execution but balances replay', async () => { + const adapter = new MockAdapter([ + toolCallResponse('c1', 'danger', {}), + textResponse('recovered after cancellation'), + ]) + const ctx = await harness(adapter) + let executions = 0 + ctx.tools.register(defineTool({ + name: 'danger', + description: 'must not run after cancellation', + parameters: {}, + async execute() { + executions += 1 + return [{ type: 'text', text: 'ran' }] + }, + })) + const agent = ctx.agentLoop.create(AgentId('cancel-after-assistant-message'), { model: 'mock' }) + const dispose = ctx.on('session/event', (session, event) => { + if (session === agent.session && event.type === 'assistant/message') { + agent.cancel('cancelled after assistant message') + } + }) + + const reasons: TurnEndReason[] = [] + ctx.on('session/event', (_session, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) + + send(agent, 'go') + await waitForIdle(ctx, agent) + dispose() + + expect(executions).toBe(0) + expect(reasons).toEqual([{ kind: 'aborted', reason: 'cancelled after assistant message' }]) + const call = agent.session.events.find(event => event.type === 'tool/call') + const result = agent.session.events.find(event => event.type === 'tool/result') + expect(call?.type === 'tool/call' ? call.data.callId : undefined).toBe('c1') + expect(result?.type === 'tool/result' ? result.data : undefined).toMatchObject({ + callId: 'c1', + isError: true, + error: { name: 'AbortError', code: 'ABORTED' }, + }) + + send(agent, 'continue safely') + await waitForIdle(ctx, agent) + const replayedResult = adapter.requests[1]!.messages + .flatMap(message => message.content) + .find(block => block.type === 'tool-result') + expect(replayedResult).toMatchObject({ toolCallId: 'c1', isError: true }) + expect(reasons).toEqual([ + { kind: 'aborted', reason: 'cancelled after assistant message' }, + { kind: 'completed' }, + ]) + }) + it('a prompt sent AFTER a cancelled turn settles runs normally (marker reset)', async () => { const adapter = new MockAdapter(['hang', textResponse('second reply')]) const ctx = await harness(adapter) diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 3907434395..6ca06fc096 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -204,6 +204,16 @@ describe('abort during tool execution ends the turn', () => { expect(executed).toEqual(['aborter']) // second tool never ran expect(adapter.requests).toHaveLength(1) // no follow-up model call expect(reasons).toEqual([{ kind: 'aborted', reason: 'user interrupt' }]) + const calls = agent.session.events.filter(event => event.type === 'tool/call') + const results = agent.session.events.filter(event => event.type === 'tool/result') + expect(calls.map(event => event.data.callId)).toEqual([CallId('c1'), CallId('c2')]) + expect(results).toHaveLength(2) + expect(results[0]!.data).toMatchObject({ callId: CallId('c1'), isError: false }) + expect(results[1]!.data).toMatchObject({ + callId: CallId('c2'), + isError: true, + error: { name: 'AbortError', code: 'ABORTED' }, + }) }) }) diff --git a/packages/core/agent-loop/tests/request-recovery.spec.ts b/packages/core/agent-loop/tests/request-recovery.spec.ts new file mode 100644 index 0000000000..003c678be0 --- /dev/null +++ b/packages/core/agent-loop/tests/request-recovery.spec.ts @@ -0,0 +1,442 @@ +/** + * Agent-loop coverage for the successful post-step checkpoint and model-request + * recovery. These tests keep the recovery boundary narrower than the whole + * step and pin retry reconstruction, numbering, cancellation, and identity. + */ + +import { describe, expect, it, vi } from 'vitest' +import { Context } from 'cordis' +import LlmService, { + CallId, + CONTEXT_WINDOW_EXCEEDED_CODE, + LlmAdapter, + LlmError, +} from '@deepseek-ai/dsh-llm' +import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' +import SessionStore from '@deepseek-ai/dsh-session' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' +import type { PostToolDecision } from '@deepseek-ai/dsh-tools' +import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts' + +class FailureScriptAdapter extends LlmAdapter { + requests: GenerateOptions[] = [] + + constructor(private readonly entries: (Error | StreamChunk[])[]) { + super() + } + + async * stream(options: GenerateOptions): AsyncIterable { + this.requests.push(options) + const entry = this.entries.shift() + if (entry === undefined) throw new Error('failure script exhausted') + if (entry instanceof Error) throw entry + yield* entry + } +} + +class IteratorConstructionFailureAdapter extends LlmAdapter { + stream(_options: GenerateOptions): AsyncIterable { + return { + [Symbol.asyncIterator](): AsyncIterator { + throw new LlmError('iterator construction failed', 'ITERATOR_CONSTRUCTION') + }, + } + } +} + +class SynchronousDispatchFailureAdapter extends LlmAdapter { + constructor(private readonly error: Error) { + super() + } + + stream(_options: GenerateOptions): AsyncIterable { + throw this.error + } +} + +class IteratorResultGetterFailureAdapter extends LlmAdapter { + constructor( + private readonly field: 'done' | 'value', + private readonly error: Error, + ) { + super() + } + + stream(_options: GenerateOptions): AsyncIterable { + const result = this.field === 'done' ? {} : { done: false } + Object.defineProperty(result, this.field, { get: () => { throw this.error } }) + return { + [Symbol.asyncIterator](): AsyncIterator { + return { next: () => Promise.resolve(result as unknown as IteratorResult) } + }, + } + } +} + +const streamListenerFailureCases: readonly [string, (ctx: Context) => void][] = [ + ['synchronous listener throw', (ctx) => { + ctx.on('llm/stream', () => { throw new Error('synchronous stream listener failed') }) + }], + ['invalid listener iterable', (ctx) => { + ctx.on('llm/stream', () => ({}) as AsyncIterable) + }], + ['listener wrapper iteration failure', (ctx) => { + ctx.on('llm/stream', (_options, next) => (async function * () { + for await (const chunk of next()) { + yield chunk + throw new Error('stream listener wrapper failed') + } + })()) + }], +] + +async function harness(adapter?: LlmAdapter): Promise { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentLoop, { agents: [] }) + if (adapter) ctx.llm.registerAdapter(['mock'], adapter) + return ctx +} + +function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { + return new Promise((resolve) => { + const dispose = ctx.on('agent/status', (subject, status) => { + if (subject === agent && status === 'idle') { + dispose() + resolve() + } + }) + }) +} + +function send(agent: ReactLoopAgent): void { + agent.send([{ type: 'text', text: 'go' }]) +} + +function contextError(message = 'context too large'): LlmError { + return new LlmError(message, CONTEXT_WINDOW_EXCEEDED_CODE, 400) +} + +describe('agent post-step and request-error lifecycle', () => { + it('fires post-step after results, buffered context, and steering but before step/end', async () => { + const twoCalls: StreamChunk[] = [ + { type: 'block-start', index: 0, blockType: 'tool-call' }, + { type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('call-1'), name: 'work', arguments: '{}' } }, + { type: 'block-start', index: 1, blockType: 'tool-call' }, + { type: 'block-end', index: 1, block: { type: 'tool-call', id: CallId('call-2'), name: 'work', arguments: '{}' } }, + { type: 'usage', usage: { inputTokens: 10, outputTokens: 5 } }, + { type: 'finish', reason: { kind: 'tool-calls' } }, + ] + const adapter = new FailureScriptAdapter([twoCalls, textResponse('done')]) + const ctx = await harness(adapter) + ctx.tools.register(defineTool({ + name: 'work', + description: 'do work', + parameters: {}, + async execute(_args, exec) { + if (exec.callId === CallId('call-2')) { + exec.agent?.steer([{ type: 'text', text: 'steered' }], { source: { kind: 'plugin', plugin: 'test' } }) + } + return [{ type: 'text', text: 'worked' }] + }, + })) + ctx.on('tools/post-execute', async (exec, _result): Promise => ({ + kind: 'accept', + additionalContext: { + content: [{ type: 'text', text: `context for ${exec.callId}` }], + source: { kind: 'plugin', plugin: 'test' }, + }, + })) + const agent = ctx.agentLoop.create(AgentId('post-step-order'), { model: 'mock' }) + const order: string[] = [] + ctx.on('session/event', (_session, event) => { + if ( + event.type === 'assistant/message' || event.type === 'tool/call' + || event.type === 'tool/result' || event.type === 'context/message' + || event.type === 'steering/message' || event.type === 'step/end' + ) { + if (!('step' in event.data) || event.data.step === 1) order.push(event.type) + } + }) + ctx.on('agent/post-step', (subject, turn, step, signal) => { + if (subject !== agent || step !== 1) return + expect({ turn, step, aborted: signal.aborted }).toEqual({ turn: 1, step: 1, aborted: false }) + subject.inject([{ type: 'text', text: 'listener mutation' }], { source: { kind: 'plugin', plugin: 'post-step' } }) + order.push('agent/post-step') + }) + + send(agent) + await waitForIdle(ctx, agent) + + expect(order).toEqual([ + 'assistant/message', + 'tool/call', + 'tool/result', + 'tool/call', + 'tool/result', + 'context/message', + 'context/message', + 'steering/message', + 'context/message', + 'agent/post-step', + 'step/end', + ]) + }) + + it('fires post-step for max-tokens and lets cancellation override that success', async () => { + const adapter = new FailureScriptAdapter([maxTokensResponse('partial')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('cancel-post-step-max-tokens'), { model: 'mock' }) + let entered!: () => void + const postStepEntered = new Promise((resolve) => { entered = resolve }) + ctx.on('agent/post-step', async (_agent, turn, step, signal) => { + expect({ turn, step }).toEqual({ turn: 1, step: 1 }) + entered() + await new Promise((resolve) => { + signal.addEventListener('abort', () => { resolve() }, { once: true }) + }) + }) + + send(agent) + const idle = waitForIdle(ctx, agent) + await postStepEntered + agent.cancel('cancelled during max-tokens post-step') + await idle + + expect(agent.session.events.find(event => event.type === 'assistant/message')).toMatchObject({ + data: { usage: { inputTokens: 10, outputTokens: 7 } }, + }) + expect(agent.session.events.at(-1)).toMatchObject({ + type: 'turn/end', + data: { reason: { kind: 'aborted', reason: 'cancelled during max-tokens post-step' } }, + }) + }) + + it.each([ + ['thrown', contextError()], + ['in-band', [{ type: 'finish', reason: { kind: 'error', message: 'too large', code: CONTEXT_WINDOW_EXCEEDED_CODE } }] satisfies StreamChunk[]], + ] as const)('recovers a %s request failure in a new reconstructable step', async (_style, failure) => { + const adapter = new FailureScriptAdapter([failure, textResponse('recovered')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId(`recover-${_style}`), { model: 'mock' }) + const attempts: number[] = [] + ctx.on('agent/request-error', async (subject, turn, step, error, attempt) => { + expect(subject).toBe(agent) + expect({ turn, step, code: error.code }).toEqual({ turn: 1, step: 1, code: CONTEXT_WINDOW_EXCEEDED_CODE }) + attempts.push(attempt) + subject.session.append('context/message', { + content: [{ type: 'text', text: 'RECOVERY SURFACE MUTATION' }], + source: { kind: 'plugin', plugin: 'test-recovery' }, + }, { surfaceOp: 'append' }) + return { action: 'retry' } + }) + + send(agent) + await waitForIdle(ctx, agent) + + expect(attempts).toEqual([0]) + expect(adapter.requests).toHaveLength(2) + expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('RECOVERY SURFACE MUTATION') + const starts = agent.session.events.filter(event => event.type === 'step/start') + const ends = agent.session.events.filter(event => event.type === 'step/end') + expect(starts.map(event => event.data.step)).toEqual([1, 2]) + expect(ends.map(event => event.data.step)).toEqual([1, 2]) + const recovery = agent.session.events.find(event => event.type === 'context/message')! + expect(ends[0]!.seq).toBeLessThan(recovery.seq) + expect(recovery.seq).toBeLessThan(starts[1]!.seq) + }) + + it.each(streamListenerFailureCases)('does not offer %s to request recovery', async (_name, install) => { + const ctx = await harness(new FailureScriptAdapter([textResponse('unused')])) + const agent = ctx.agentLoop.create(AgentId(`stream-plugin-${_name.replaceAll(' ', '-')}`), { model: 'mock' }) + let recoveries = 0 + install(ctx) + ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => { + recoveries += 1 + return next() + }) + + send(agent) + await waitForIdle(ctx, agent) + + expect(recoveries).toBe(0) + expect(agent.session.events.at(-1)).toMatchObject({ type: 'turn/end', data: { reason: { kind: 'error' } } }) + }) + + it.each(['prompt-submit', 'prompt-assembly', 'pre-step', 'request'] as const)( + 'does not offer %s middleware failures to request recovery', + async (boundary) => { + const adapter = new FailureScriptAdapter([textResponse('unused')]) + const ctx = await harness(adapter) + if (boundary === 'prompt-submit') { + ctx.on('agent/prompt-submit', () => { throw new Error('prompt submit failed') }) + } else if (boundary === 'prompt-assembly') { + ctx.on('system-prompt/assemble', () => { throw new Error('prompt assembly failed') }) + } else if (boundary === 'pre-step') { + ctx.on('agent/pre-step', () => { throw new Error('pre-step failed') }) + } else { + ctx.on('agent/request', () => { throw new Error('request middleware failed') }) + } + const agent = ctx.agentLoop.create(AgentId(`${boundary}-not-recoverable`), { model: 'mock' }) + let recoveries = 0 + ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => { + recoveries += 1 + return next() + }) + + send(agent) + await waitForIdle(ctx, agent) + + expect(recoveries).toBe(0) + expect(adapter.requests).toHaveLength(0) + expect(agent.session.events.at(-1)).toMatchObject({ type: 'turn/end', data: { reason: { kind: 'error' } } }) + }, + ) + + it('does not offer result, tool, or post-step plugin failures to request recovery', async () => { + for (const failure of ['result', 'tool', 'post-step'] as const) { + const adapter = new FailureScriptAdapter([ + failure === 'tool' ? toolCallResponse(`call-${failure}`, 'work', {}) : textResponse('done'), + ]) + const ctx = await harness(adapter) + if (failure === 'result') ctx.on('agent/step-result', () => { throw new Error('result failed') }) + if (failure === 'post-step') ctx.on('agent/post-step', () => { throw new Error('post-step failed') }) + if (failure === 'tool') { + vi.spyOn(ctx.tools, 'execute').mockRejectedValue(new Error('tool service failed')) + } + const agent = ctx.agentLoop.create(AgentId(`${failure}-not-recoverable`), { model: 'mock' }) + let recoveries = 0 + ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => { + recoveries += 1 + return next() + }) + send(agent) + await waitForIdle(ctx, agent) + expect(recoveries, failure).toBe(0) + } + }) + + it.each([ + ['synchronous dispatch', (error: Error) => new SynchronousDispatchFailureAdapter(error)], + ['done getter', (error: Error) => new IteratorResultGetterFailureAdapter('done', error)], + ['value getter', (error: Error) => new IteratorResultGetterFailureAdapter('value', error)], + ] as const)('preserves original Error identity for adapter %s', async (_name, makeAdapter) => { + const original = contextError(`${_name} overflow`) + const ctx = await harness(makeAdapter(original)) + const agent = ctx.agentLoop.create(AgentId(`identity-${_name.replaceAll(' ', '-')}`), { model: 'mock' }) + let seen: Error | undefined + ctx.on('agent/request-error', async (_agent, _turn, _step, error, _attempt, _signal, next) => { + seen = error + return next() + }) + + send(agent) + await waitForIdle(ctx, agent) + + expect(seen).toBe(original) + }) + + it('classifies iterator construction and explicit NO_ADAPTER as model-request failures', async () => { + for (const scenario of ['iterator', 'no-adapter'] as const) { + const ctx = scenario === 'iterator' ? await harness(new IteratorConstructionFailureAdapter()) : await harness() + const agent = ctx.agentLoop.create(AgentId(`request-boundary-${scenario}`), { model: 'mock' }) + let seen = '' + ctx.on('agent/request-error', async (_agent, _turn, _step, error, _attempt, _signal, next) => { + seen = error.code ?? '' + return next() + }) + send(agent) + await waitForIdle(ctx, agent) + expect(seen).toBe(scenario === 'iterator' ? 'ITERATOR_CONSTRUCTION' : 'NO_ADAPTER') + } + }) + + it('tracks consecutive retry attempts and resets after a successful request', async () => { + const capped = new FailureScriptAdapter([contextError('first overflow'), contextError('second overflow')]) + const cappedCtx = await harness(capped) + const cappedAgent = cappedCtx.agentLoop.create(AgentId('retry-cap'), { model: 'mock' }) + const cappedAttempts: number[] = [] + cappedCtx.on('agent/request-error', async (_agent, _turn, _step, _error, attempt, _signal, next) => { + cappedAttempts.push(attempt) + return attempt < 1 ? { action: 'retry' } : next() + }) + send(cappedAgent) + await waitForIdle(cappedCtx, cappedAgent) + expect(cappedAttempts).toEqual([0, 1]) + + const reset = new FailureScriptAdapter([ + contextError('first overflow'), + toolCallResponse('retry-reset-call', 'work', {}), + contextError('later overflow'), + ]) + const resetCtx = await harness(reset) + resetCtx.tools.register(defineTool({ + name: 'work', + description: 'continue', + parameters: {}, + async execute() { return [{ type: 'text', text: 'worked' }] }, + })) + const resetAgent = resetCtx.agentLoop.create(AgentId('retry-reset'), { model: 'mock' }) + const resetAttempts: { step: number; attempt: number }[] = [] + resetCtx.on('agent/request-error', async (_agent, _turn, step, _error, attempt, _signal, next) => { + resetAttempts.push({ step, attempt }) + return resetAttempts.length === 1 ? { action: 'retry' } : next() + }) + send(resetAgent) + await waitForIdle(resetCtx, resetAgent) + expect(resetAttempts).toEqual([{ step: 1, attempt: 0 }, { step: 3, attempt: 0 }]) + }) + + it('preserves the original provider error when recovery throws', async () => { + const adapter = new FailureScriptAdapter([contextError('original overflow')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('recovery-throws'), { model: 'mock' }) + ctx.on('agent/request-error', () => { throw new Error('recovery exploded') }) + + send(agent) + await waitForIdle(ctx, agent) + + expect(agent.session.events.at(-1)).toMatchObject({ + type: 'turn/end', + data: { reason: { kind: 'error', message: 'original overflow', code: CONTEXT_WINDOW_EXCEEDED_CODE } }, + }) + }) + + it.each(['cancel', 'dispose'] as const)('keeps %s live through request recovery', async (action) => { + const adapter = new FailureScriptAdapter([contextError()]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId(`${action}-recovery`), { model: 'mock' }) + let entered!: () => void + const recoveryEntered = new Promise((resolve) => { entered = resolve }) + ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, signal) => { + entered() + await new Promise((resolve) => { + signal.addEventListener('abort', () => { resolve() }, { once: true }) + }) + return { action: 'retry' } + }) + + send(agent) + const idle = waitForIdle(ctx, agent) + await recoveryEntered + if (action === 'cancel') { + agent.cancel('cancelled during recovery') + await idle + } else { + await ctx.fiber.dispose() + } + + expect(adapter.requests).toHaveLength(1) + expect(agent.session.events.at(-1)).toMatchObject({ + type: 'turn/end', + data: { reason: action === 'cancel' ? { kind: 'aborted', reason: 'cancelled during recovery' } : { kind: 'disposed' } }, + }) + }) +}) diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 5639f30daf..d37851a681 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -31,7 +31,7 @@ The loop plugin registers `AgentFactory`, keeping consumers independent of its c `agent/created` runs after setup and both registry entries; the following `agent/session-start` is the first supported startup injection point. `agent/disposed` means the exact entry left the registry. The loop quiesces its driver first; directly registered custom agents own any stronger ordering. -Most interception points are cooperative waterfalls returning seam-specific decisions. `agent/pre-step` is a serial surface-mutation checkpoint, while `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. The full rationale is in the [agent-scope runtime-design RFC](../../../docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way). +Most interception points are cooperative waterfalls returning seam-specific decisions. `agent/pre-step` and `agent/post-step` are serial checkpoints around a step's durable work, while `agent/request-error` is the failed-model-request recovery waterfall: a retry opens a new numbered step after the failed step closes. `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. The full rationale for scoped dispatch and terminal settlement is in the [agent-scope runtime-design RFC](../../../docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way). Turn and step boundaries and the model token stream are durable `session/event` facts rather than mirrored `agent/*` notifications. Consumers read `turn/*`, `step/*`, and `assistant/chunk` from the session feed; tool policy and outcome observation belong to the complete pipeline documented by [`dsh-tools`](../tools/README.md). diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index 3aad65a70e..1eda0df2d7 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -70,6 +70,12 @@ export type ContinuationDecision = | { action: 'stop' } | { action: 'continue'; reason?: HookContext } +/** Failed-request recovery decision; `retry` opens another numbered step while listeners delegate by calling `next()`. */ +export type RequestErrorDecision = { action: 'fail' } | { action: 'retry' } + +/** Model-request failure with an optional machine-routable provider code. */ +export type RequestError = Error & { code?: string } + /** * The terminal subset of {@link ContinuationDecision}. A listener on * `agent/turn-stop` returns this to make the already-composed continuation @@ -248,6 +254,31 @@ declare module 'cordis' { * @mode waterfall */ 'agent/step-result'(this: Scoped, agent: Agent, turn: number, step: number, message: Message, next: () => Promise): Promise + /** + * Awaited serial checkpoint after the response, tool results, injected + * context, and steering are durable but before `step/end`. + * @param agent - the agent that completed the step. + * @param turn - the open turn number. + * @param step - the completed step number. + * @param signal - the turn abort signal. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode serial + */ + 'agent/post-step'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void + /** + * Recover a model-request failure after its failed step has closed. `retry` + * opens a new numbered step; `fail` preserves the original request error. + * Call `next()` to delegate to the next recovery listener or the default. + * @param agent - the agent whose request failed. + * @param turn - the open turn number. + * @param step - the failed step number. + * @param error - the original model-request failure. + * @param retryAttempt - zero-based number of prior recovery retries. + * @param signal - the turn abort signal. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode waterfall + */ + 'agent/request-error'(this: Scoped, agent: Agent, turn: number, step: number, error: RequestError, retryAttempt: number, signal: AbortSignal, next: () => Promise): Promise /** * Override whether the turn continues. The default continues after tool * calls or steering and stops otherwise; a continue reason becomes steering. diff --git a/packages/llm/llm-deepseek/README.md b/packages/llm/llm-deepseek/README.md index 1270ad40a5..bd4228165b 100644 --- a/packages/llm/llm-deepseek/README.md +++ b/packages/llm/llm-deepseek/README.md @@ -36,7 +36,7 @@ Every request carries the shared attribution header from dsh-llm's `attributionH ## Errors -Non-2xx responses throw `LlmError` with stable codes: `AUTH` (401/403), `RATE_LIMIT` (429), `INVALID_REQUEST` (400), `SERVER` (5xx), `HTTP_` otherwise. Protocol violations throw `STREAM_CLOSED` (no `[DONE]`) or `MALFORMED_RESPONSE` (bad JSON payload). Unknown wire `finish_reason`s (e.g. `content_filter`, `insufficient_system_resource`) become `finish {kind: 'error', code: }` chunks. +Non-2xx responses throw `LlmError` with stable codes: `AUTH` (401/403), `RATE_LIMIT` (429), `CONTEXT_WINDOW_EXCEEDED` (a 400 whose provider code, type, or message identifies context overflow), `INVALID_REQUEST` (other 400s), `SERVER` (5xx), `HTTP_` otherwise. Protocol violations throw `STREAM_CLOSED` (no `[DONE]`) or `MALFORMED_RESPONSE` (bad JSON payload). Unknown wire `finish_reason`s (e.g. `content_filter`, `insufficient_system_resource`) become `finish {kind: 'error', code: }` chunks. ## Testing diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index 30760a8fbc..113cb6f25e 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -5,7 +5,7 @@ * @module dsh-llm-deepseek/adapter */ -import { attributionHeaders, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm' +import { attributionHeaders, CONTEXT_WINDOW_EXCEEDED_CODE, isContextWindowExceededError, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm' import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { serializeRequest } from './serialize.ts' import type { RequestDefaults } from './serialize.ts' @@ -26,12 +26,17 @@ export interface DeepSeekAdapterOptions { /** * Map an HTTP status to a stable LlmError code. * @param status - status of a non-2xx provider response. - * @returns `AUTH` (401/403), `RATE_LIMIT` (429), `INVALID_REQUEST` (400), `SERVER` (5xx), or `HTTP_` for anything else. + * @param error - parsed provider error body, when available. + * @returns the normalized harness error code. */ -export function httpErrorCode(status: number): string { +export function httpErrorCode(status: number, error?: WireError['error']): string { if (status === 401 || status === 403) return 'AUTH' if (status === 429) return 'RATE_LIMIT' - if (status === 400) return 'INVALID_REQUEST' + if (status === 400) { + const detail = [error?.code, error?.type, error?.message].filter(Boolean).join(' ') + if (isContextWindowExceededError(detail)) return CONTEXT_WINDOW_EXCEEDED_CODE + return 'INVALID_REQUEST' + } if (status >= 500) return 'SERVER' return `HTTP_${status}` } @@ -67,16 +72,17 @@ export class DeepSeekAdapter extends LlmAdapter { }) if (!response.ok) { - const code = httpErrorCode(response.status) let message = `DeepSeek API error (HTTP ${response.status})` + let providerError: WireError['error'] try { const parsed = await response.json() as WireError - if (parsed.error?.message) message = parsed.error.message + providerError = parsed.error + if (providerError?.message) message = providerError.message } catch { - // Only swallow error-body parsing: status and code are already captured, - // so malformed gateway JSON must not mask the actionable HTTP failure. + // Only swallow error-body parsing: the HTTP status still identifies the + // failure, so malformed gateway JSON must not mask it. } - throw new LlmError(message, code, response.status) + throw new LlmError(message, httpErrorCode(response.status, providerError), response.status) } if (!response.body) { throw new LlmError('DeepSeek API returned no response body', 'EMPTY_RESPONSE') diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 46f123a1c7..6cca0dde17 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -2,7 +2,7 @@ import { createServer } from 'node:http' import type { IncomingMessage, Server, ServerResponse } from 'node:http' import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import LlmService, { LlmError, userAgent } from '@deepseek-ai/dsh-llm' +import LlmService, { CONTEXT_WINDOW_EXCEEDED_CODE, LlmError, userAgent } from '@deepseek-ai/dsh-llm' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import { DeepSeekAdapter, httpErrorCode } from '@deepseek-ai/dsh-llm-deepseek' import { assemble } from './assemble.ts' @@ -173,6 +173,32 @@ describe('DeepSeekAdapter against a mock server', () => { ).resolves.toBe(status) }) + it('classifies a thrown HTTP context-window rejection with the canonical code', async () => { + const server = await mockServer([{ + kind: 'http-error', + status: 400, + body: JSON.stringify({ + error: { + message: 'This model maximum context length is 128000 tokens; your input exceeds that limit.', + type: 'invalid_request_error', + code: 'context_length_exceeded', + }, + }), + }]) + const ctx = await harness(server.url) + const code = await assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }) + .catch((error: unknown) => (error as LlmError).code) + expect(code).toBe(CONTEXT_WINDOW_EXCEEDED_CODE) + }) + + it('classifies only context-capacity HTTP 400 details as context overflow', () => { + expect(httpErrorCode(400, { message: 'request too large for model context' })) + .toBe(CONTEXT_WINDOW_EXCEEDED_CODE) + expect(httpErrorCode(400, { message: 'invalid input: temperature exceeds maximum allowed value' })) + .toBe('INVALID_REQUEST') + expect(httpErrorCode(413, { code: 'context_length_exceeded' })).toBe('HTTP_413') + }) + it('keeps the status-line message for JSON error bodies without a message', async () => { const server = await mockServer([{ kind: 'http-error', status: 500, body: '{"error":{"type":"x"}}' }]) const ctx = await harness(server.url) diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index dd1cb5b48c..6c8fc35104 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -7,7 +7,7 @@ DeepSeek adapter for the harness LLM seam backed by [`@earendil-works/pi-ai`](ht `@deepseek-ai/dsh-llm-deepseek` already talks to the same endpoint. This package is its **design-verification twin**: same models, same wire protocol, completely different internals — a unified LLM library with its own event vocabulary versus hand-rolled fetch/SSE. Anything the harness `StreamChunk` protocol cannot express for BOTH implementations is a core-vocabulary bug. The differences it exercised on purpose: - pi-ai hands tool-call `arguments` around as **parsed objects**; the harness keeps raw JSON strings. The adapter patches replay payloads back to the original raw strings before sending them, and re-stringifies parsed output tool calls at `block-end`. -- pi-ai reports failures as **in-stream error events** (it never throws mid-stream); these map to `finish {kind:'error'|'aborted'}` chunks — the protocol's other sanctioned error path besides throwing (which llm-deepseek uses). +- pi-ai reports failures as **in-stream error events** (it never throws mid-stream); these map to `finish {kind:'error'|'aborted'}` chunks — the protocol's other sanctioned error path besides throwing (which llm-deepseek uses). Context-overflow detail maps to the same canonical `CONTEXT_WINDOW_EXCEEDED` code as the hand-rolled adapter. - pi-ai folds reasoning tokens into `usage.output`; there is no separate reasoning count to map. - pi-ai's options omit some DeepSeek/OpenAI-compatible details; the adapter uses its `onPayload` hook to preserve the harness contract (`stop`, scrubbing pi-ai's own per-tool `strict` default — the hand-rolled twin sends no such field — omitted reasoning effort, raw replayed tool arguments). diff --git a/packages/llm/llm-pi-ai/src/convert.ts b/packages/llm/llm-pi-ai/src/convert.ts index 098b93edb3..88f134c8f2 100644 --- a/packages/llm/llm-pi-ai/src/convert.ts +++ b/packages/llm/llm-pi-ai/src/convert.ts @@ -8,7 +8,7 @@ * @module dsh-llm-pi-ai/convert */ -import { CallId, LlmError } from '@deepseek-ai/dsh-llm' +import { CallId, CONTEXT_WINDOW_EXCEEDED_CODE, isContextWindowExceededError, LlmError } from '@deepseek-ai/dsh-llm' import type { FinishReason, GenerateOptions, Message, StreamChunk, TokenUsage } from '@deepseek-ai/dsh-llm' import type { AssistantMessage, @@ -165,6 +165,7 @@ export function mapUsage(usage: PiUsage): TokenUsage { function classifyPiAiError(message: string): string { if (/\b(?:401|403)\b/.test(message)) return 'AUTH' if (/\b429\b|rate.?limit/i.test(message)) return 'RATE_LIMIT' + if (isContextWindowExceededError(message)) return CONTEXT_WINDOW_EXCEEDED_CODE if (/\b400\b|invalid.?request/i.test(message)) return 'INVALID_REQUEST' if (/\b5\d\d\b/.test(message)) return 'SERVER' return 'PI_AI_ERROR' diff --git a/packages/llm/llm-pi-ai/tests/convert.spec.ts b/packages/llm/llm-pi-ai/tests/convert.spec.ts index 078d2a4d3b..42576f7fed 100644 --- a/packages/llm/llm-pi-ai/tests/convert.spec.ts +++ b/packages/llm/llm-pi-ai/tests/convert.spec.ts @@ -1,5 +1,5 @@ import { describe, expect, it } from 'vitest' -import { CallId } from '@deepseek-ai/dsh-llm' +import { CallId, CONTEXT_WINDOW_EXCEEDED_CODE } from '@deepseek-ai/dsh-llm' import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm' import type { AssistantMessage, AssistantMessageEvent, Usage } from '@earendil-works/pi-ai' import { mapStopReason, mapUsage, toPiContext, toStreamChunks } from '@deepseek-ai/dsh-llm-pi-ai' @@ -300,6 +300,18 @@ describe('mapStopReason / mapUsage', () => { .toMatchObject({ kind: 'error', code: 'RATE_LIMIT' }) expect(mapStopReason(assistant({ stopReason: 'error', errorMessage: 'HTTP 500: backend down' }))) .toMatchObject({ kind: 'error', code: 'SERVER' }) + expect(mapStopReason(assistant({ + stopReason: 'error', + errorMessage: 'HTTP 400: input exceeds the model context window limit', + }))).toMatchObject({ kind: 'error', code: CONTEXT_WINDOW_EXCEEDED_CODE }) + expect(mapStopReason(assistant({ + stopReason: 'error', + errorMessage: 'HTTP 400: request too large for model context', + }))).toMatchObject({ kind: 'error', code: CONTEXT_WINDOW_EXCEEDED_CODE }) + expect(mapStopReason(assistant({ + stopReason: 'error', + errorMessage: 'HTTP 400: invalid input: temperature exceeds maximum allowed value', + }))).toMatchObject({ kind: 'error', code: 'INVALID_REQUEST' }) }) it('maps cache fields only when nonzero', () => { diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 296fd0c3d3..b7be205a97 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -12,6 +12,8 @@ An adapter registry plus a single streaming call surface, interceptable via a wa - `ctx.llm.models(): string[]` — model names with a registered adapter. - `ctx.llm.stream(options: GenerateOptions): AsyncIterable` Stream one model call as raw chunks (token-level deltas). Consumers assemble the chunks into blocks/messages with `BlockAssembler`. +`LlmService` preserves and privately tags errors from final adapter selection, synchronous dispatch, iterator construction, and iteration. `isLlmAdapterFailure(value)` exposes that provenance without classifying `llm/stream` middleware or downstream consumer failures as provider failures, and without replacing the adapter's original coded `Error`. + ### Events | Event | Mode | Purpose | @@ -43,6 +45,7 @@ Every product adapter sends application identity on provider HTTP requests. `att - `BlockAssembler` — incrementally assembles raw chunks into complete content blocks and an assistant message. The agent loop feeds it raw chunks (logging them for replay) while reading the assembled blocks/message for history. - `HarnessError` — base class for the harness error taxonomy: a stable `code` string (distinct from the human `message`) plus `cause` chaining. Lives here, in the leaf package every other imports, so a single base is shared without a new dependency edge. Per-package errors (`LlmError`, `ToolArgsError`, `InvariantError`, …) extend it. `isHarnessError(value)` narrows at seams. - `LlmError` — extends `HarnessError`; `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) plus an optional numeric `status` when the failure came from a non-2xx provider response. +- `CONTEXT_WINDOW_EXCEEDED_CODE` — the provider-neutral code both DeepSeek adapters use when a request exceeds the model context window, regardless of thrown-HTTP versus in-band finish delivery. `isContextWindowExceededError(detail)` is their shared conservative classifier for OpenAI-compatible provider detail. ### Real adapters @@ -54,7 +57,7 @@ None, as this adapter registry forwards an already assembled request without add ## Known Limitations and Deferred Work -- **No retry/caching/rate-limit layer ships** — `llm/stream` is the intended wrap seam and has no production listener, so provider 429/5xx failures surface immediately. +- **No default retry/caching/rate-limit policy ships in this service** — `llm/stream` remains the call-wrapper seam; the agent loop separately offers proven model-request failures to `agent/request-error`, whose default preserves the original failure. - **`GenerateOptions` sampling is `temperature`/`maxTokens`/`stop` only** — no `tool_choice`, `top_p`, or penalty fields; the vocabulary grows when a producer lands ([dropped inert knobs](../../../docs/rfc/implemented/simplification/2026-07-04-drop-inert-request-knobs.md)). - **Producer-gated variants stay out until produced** — `prefill`, per-tool `strict`, block `cache` hints, and the `agent` message-source variant were pruned as producerless ([RFC](../../../docs/rfc/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md)). - **`BlockAssembler` handles core block kinds only** — a plugin-added block type whose stream is never closed by `block-end` makes `blocks()` throw. diff --git a/packages/llm/llm/src/adapter-failure.ts b/packages/llm/llm/src/adapter-failure.ts new file mode 100644 index 0000000000..240f934c39 --- /dev/null +++ b/packages/llm/llm/src/adapter-failure.ts @@ -0,0 +1,34 @@ +/** + * Private provider-failure tagging shared by `LlmService` and its consumers. + * + * @module @deepseek-ai/dsh-llm/adapter-failure + */ + +import { HarnessError } from './error.ts' + +/** Errors proven to originate in final adapter dispatch or iteration. */ +const adapterFailures = new WeakSet() + +/** + * Preserve an adapter's Error identity while tagging its provider origin. + * @param value - arbitrary value thrown by adapter dispatch or iteration. + * @returns the original Error, or a coded Error wrapping a non-Error throw. + * @internal + */ +export function markLlmAdapterFailure(value: unknown): Error & { code?: string } { + const error = value instanceof Error + ? value as Error & { code?: string } + : new HarnessError(String(value), 'UNKNOWN', { cause: value }) + adapterFailures.add(error) + return error +} + +/** + * Whether a failure came from final adapter dispatch, iterator construction, + * or iteration rather than from an `llm/stream` waterfall listener. + * @param value - arbitrary failure caught by a model-call consumer. + * @returns true only for errors tagged at the final adapter boundary. + */ +export function isLlmAdapterFailure(value: unknown): value is Error & { code?: string } { + return value instanceof Error && adapterFailures.has(value) +} diff --git a/packages/llm/llm/src/error.ts b/packages/llm/llm/src/error.ts index c1fdbb9ffa..8c1c736492 100644 --- a/packages/llm/llm/src/error.ts +++ b/packages/llm/llm/src/error.ts @@ -21,6 +21,47 @@ export class HarnessError extends Error { } } +/** Canonical provider-neutral code for a model request rejected because its context window was exceeded. */ +export const CONTEXT_WINDOW_EXCEEDED_CODE = 'CONTEXT_WINDOW_EXCEEDED' + +/** Structured codes and plain phrases that explicitly name a context bound being exceeded. */ +const STRUCTURED_CONTEXT_OVERFLOW = new RegExp( + String.raw`(?:^|[^a-z0-9])context[\s_-](?:length|window)[\s_-]` + + String.raw`(?:exceed(?:ed|s)?|overflow(?:ed)?|limit[\s_-]exceeded)(?:$|[^a-z0-9])`, + 'i', +) + +/** Request-size wording that ties "too large" directly to model context capacity. */ +const TOO_LARGE_FOR_CONTEXT = new RegExp( + String.raw`\b(?:request|prompt|input|messages?)\s+(?:is\s+|are\s+)?` + + String.raw`too\s+(?:large|long)\s+for\s+(?:(?:this|the)\s+)?` + + String.raw`(?:model(?:'s)?\s+)?context(?:\s+window)?\b`, + 'i', +) + +/** "Exceeds" wording is safe only when its object is explicitly the model context. */ +const EXCEEDS_MODEL_CONTEXT = new RegExp( + String.raw`\b(?:input|prompt|request|messages?)\b.{0,40}` + + String.raw`\b(?:exceed(?:s|ed)?|overflows?|is\s+larger\s+than)\b.{0,40}` + + String.raw`\b(?:the\s+)?(?:model(?:'s)?\s+)?context(?:\s+(?:length|window))?\b`, + 'i', +) + +/** + * Recognize the context-overflow wording used by OpenAI-compatible providers + * and library adapters. Adapters pass all available provider code, type, and + * message text so both thrown and in-band delivery styles share one classifier. + * @param detail - provider error code/type/message text joined into one string. + * @returns true when the detail identifies a request exceeding the model context window. + */ +export function isContextWindowExceededError(detail: string): boolean { + return STRUCTURED_CONTEXT_OVERFLOW.test(detail) + || /\b(?:maximum|max)(?:\s+(?:allowed|supported))?\s+context\s+(?:length|window)\b/i.test(detail) + || TOO_LARGE_FOR_CONTEXT.test(detail) + || /\b(?:input|prompt|request)\s+(?:is\s+)?too\s+(?:long|large)\s+for\s+(?:this|the)\s+model\b/i.test(detail) + || EXCEEDS_MODEL_CONTEXT.test(detail) +} + /** * Narrow an arbitrary thrown value to a HarnessError (for `instanceof` at seams). * @param value - the caught value (`unknown` in catch clauses). diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 08f3f54c51..0b933d12a7 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -9,6 +9,7 @@ import { Context, Service } from 'cordis' import type { GenerateOptions, StreamChunk } from './types.ts' import { HarnessError } from './error.ts' +import { markLlmAdapterFailure } from './adapter-failure.ts' export * from './attribution.ts' export * from './brand.ts' @@ -18,6 +19,7 @@ export * from './types.ts' export { BlockAssembler } from './assembler.ts' export { callConfigEquals, deepFreeze } from './call-config.ts' export type { LlmCallConfig } from './call-config.ts' +export { isLlmAdapterFailure } from './adapter-failure.ts' declare module 'cordis' { interface Context { @@ -118,17 +120,65 @@ export class LlmService extends Service { return adapter } + /** + * Final adapter boundary. It tags only failures from adapter selection, + * synchronous dispatch, iterator construction, or iteration while preserving + * the original Error object. Middleware outside this generator remains + * distinguishable as plugin work. Adapter cleanup is best-effort after an + * earlier failure or downstream close and never masks the winning error. + */ + private async * adapterStream(options: GenerateOptions): AsyncGenerator { + let iterator: AsyncIterator + try { + const stream = this.adapter(options.model).stream(options) + iterator = stream[Symbol.asyncIterator]() + } catch (error: unknown) { + throw markLlmAdapterFailure(error) + } + + let completed = false + try { + while (true) { + let value: StreamChunk + try { + const item = await iterator.next() + if (item.done) { + completed = true + return + } + value = item.value + } catch (error: unknown) { + throw markLlmAdapterFailure(error) + } + // End the adapter-owned try before yielding: consumer/middleware + // failures resumed into this generator must remain untagged. + yield value + } + } finally { + if (!completed) { + try { + const close = iterator.return?.bind(iterator) + if (close) await close() + } catch { + // Lookup and invocation are both adapter-owned cleanup following an + // existing failure/downstream close; neither can replace it. + } + } + } + } + /** * Stream one model call as raw chunks (token-level deltas). Throws * `LlmError` with code `NO_ADAPTER` if no adapter is registered for - * `options.model`. Dispatches through the `llm/stream` waterfall. + * `options.model`. Dispatches through the `llm/stream` waterfall. Final + * adapter dispatch/iteration failures retain their original Error identity + * and are tagged so the agent loop can distinguish them from middleware + * failures without widening request recovery to plugin code. * @param options - the full request; `options.model` selects the adapter. * @returns the chunk stream, possibly wrapped by `llm/stream` listeners. */ stream(options: GenerateOptions): AsyncIterable { - return this.ctx.waterfall(this, 'llm/stream', options, () => { - return this.adapter(options.model).stream(options) - }) + return this.ctx.waterfall(this, 'llm/stream', options, () => this.adapterStream(options)) } } diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index f669069c44..8dc46529bd 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -1,6 +1,14 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import LlmService, { GenerateOptions, LlmAdapter, LlmError, StreamChunk } from '@deepseek-ai/dsh-llm' +import LlmService, { + GenerateOptions, + HarnessError, + isContextWindowExceededError, + isLlmAdapterFailure, + LlmAdapter, + LlmError, + StreamChunk, +} from '@deepseek-ai/dsh-llm' class ScriptedAdapter extends LlmAdapter { constructor(private script: StreamChunk[]) { @@ -19,6 +27,22 @@ const SCRIPT: StreamChunk[] = [ ] describe('LlmService', () => { + it('recognizes structured and model-capacity context-window overflow details', () => { + expect(isContextWindowExceededError('context_length_exceeded maximum context length')).toBe(true) + expect(isContextWindowExceededError('context-window-overflowed')).toBe(true) + expect(isContextWindowExceededError('This model maximum context length is 128000 tokens')).toBe(true) + expect(isContextWindowExceededError('input is too long for this model')).toBe(true) + expect(isContextWindowExceededError('request too large for model context')).toBe(true) + expect(isContextWindowExceededError('input exceeds the model context window limit')).toBe(true) + }) + + it('does not mistake unrelated input validation for context-window overflow', () => { + expect(isContextWindowExceededError('invalid request: malformed tool arguments')).toBe(false) + expect(isContextWindowExceededError('invalid input: temperature exceeds maximum allowed value')).toBe(false) + expect(isContextWindowExceededError('input exceeds maximum allowed value')).toBe(false) + expect(isContextWindowExceededError('context window size must be positive')).toBe(false) + }) + it('routes stream() to the registered adapter', async () => { const ctx = new Context() await ctx.plugin(LlmService) @@ -32,9 +56,177 @@ describe('LlmService', () => { it('throws NO_ADAPTER for unregistered models', async () => { const ctx = new Context() await ctx.plugin(LlmService) - await expect((async () => { + let caught: unknown + try { for await (const _ of ctx.llm.stream({ model: 'nope', messages: [] })) { /* drain */ } - })()).rejects.toThrow('no adapter registered') + } catch (error: unknown) { + caught = error + } + expect(caught).toBeInstanceOf(LlmError) + expect((caught as LlmError).code).toBe('NO_ADAPTER') + expect((caught as LlmError).message).toContain('no adapter registered') + expect(isLlmAdapterFailure(caught)).toBe(true) + }) + + it.each(['done', 'value'] as const)('tags a throwing IteratorResult.%s getter without replacing its Error', async (field) => { + const original = new LlmError(`${field} getter failed`, 'RESULT_GETTER_FAILED') + const result = field === 'done' ? {} : { done: false } + Object.defineProperty(result, field, { get: () => { throw original } }) + const adapter = new class extends LlmAdapter { + stream(_options: GenerateOptions): AsyncIterable { + return { + [Symbol.asyncIterator](): AsyncIterator { + return { next: () => Promise.resolve(result as unknown as IteratorResult) } + }, + } + } + }() + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['test-model'], adapter) + + let caught: unknown + try { + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } + } catch (error: unknown) { + caught = error + } + + expect(caught).toBe(original) + expect(isLlmAdapterFailure(caught)).toBe(true) + }) + + it.each(['dispatch', 'iterator'] as const)('tags synchronous adapter %s failures without replacing their Error', async (boundary) => { + const original = new LlmError(`${boundary} failed`, 'BOUNDARY_FAILED') + const adapter = new class extends LlmAdapter { + stream(_options: GenerateOptions): AsyncIterable { + if (boundary === 'dispatch') throw original + return { [Symbol.asyncIterator]: () => { throw original } } + } + }() + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['test-model'], adapter) + + let caught: unknown + try { + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } + } catch (error: unknown) { + caught = error + } + + expect(caught).toBe(original) + expect(isLlmAdapterFailure(caught)).toBe(true) + }) + + it('tags adapter iteration failures without replacing the original Error or cleanup outcome', async () => { + const original = new LlmError('provider failed', 'PROVIDER_FAILED') + let cleanupCalls = 0 + const adapter = new class extends LlmAdapter { + stream(_options: GenerateOptions): AsyncIterable { + return { + [Symbol.asyncIterator](): AsyncIterator { + return { + next: () => Promise.reject(original), + return: () => { + cleanupCalls += 1 + return Promise.reject(new Error('cleanup failed')) + }, + } + }, + } + } + }() + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['test-model'], adapter) + + let caught: unknown + try { + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } + } catch (error: unknown) { + caught = error + } + + expect(caught).toBe(original) + expect(isLlmAdapterFailure(caught)).toBe(true) + expect(cleanupCalls).toBe(1) + }) + + it('contains a throwing iterator.return getter after next fails without replacing the original Error', async () => { + const original = new LlmError('provider failed', 'PROVIDER_FAILED') + let cleanupLookups = 0 + const iterator: AsyncIterator = { next: () => Promise.reject(original) } + Object.defineProperty(iterator, 'return', { + get: () => { + cleanupLookups += 1 + throw new Error('return getter failed') + }, + }) + const adapter = new class extends LlmAdapter { + stream(_options: GenerateOptions): AsyncIterable { + return { [Symbol.asyncIterator]: () => iterator } + } + }() + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['test-model'], adapter) + + let caught: unknown + try { + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } + } catch (error: unknown) { + caught = error + } + + expect(caught).toBe(original) + expect(isLlmAdapterFailure(caught)).toBe(true) + expect(cleanupLookups).toBe(1) + }) + + it('normalizes and tags non-Error adapter failures once', async () => { + const adapter = new class extends LlmAdapter { + stream(_options: GenerateOptions): AsyncIterable { + return { + [Symbol.asyncIterator](): AsyncIterator { + // Third-party adapters can reject with arbitrary values; normalization is under test. + // eslint-disable-next-line @typescript-eslint/prefer-promise-reject-errors + return { next: () => Promise.reject('plain provider failure') } + }, + } + } + }() + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['test-model'], adapter) + + let caught: unknown + try { + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } + } catch (error: unknown) { + caught = error + } + + expect(caught).toBeInstanceOf(HarnessError) + expect(caught).toMatchObject({ code: 'UNKNOWN', cause: 'plain provider failure' }) + expect(isLlmAdapterFailure(caught)).toBe(true) + }) + + it('does not tag a failure thrown downstream while consuming adapter output', async () => { + const downstream = new Error('consumer failed') + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['test-model'], new ScriptedAdapter(SCRIPT)) + + let caught: unknown + try { + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) throw downstream + } catch (error: unknown) { + caught = error + } + + expect(caught).toBe(downstream) + expect(isLlmAdapterFailure(caught)).toBe(false) }) it('unregisters adapters when the owning fiber is disposed (HMR safety)', async () => { diff --git a/packages/support/invariants/src/scoped-events.generated.ts b/packages/support/invariants/src/scoped-events.generated.ts index 06cca6bf55..36d1721945 100644 --- a/packages/support/invariants/src/scoped-events.generated.ts +++ b/packages/support/invariants/src/scoped-events.generated.ts @@ -30,10 +30,12 @@ const scopedSubjectResolvers = Object.freeze({ 'agent/created': adapt<'agent/created'>(args => args[0]), 'agent/disposed': adapt<'agent/disposed'>(args => args[0]), 'agent/error': adapt<'agent/error'>(args => args[0]), + 'agent/post-step': adapt<'agent/post-step'>(args => args[0]), 'agent/pre-step': adapt<'agent/pre-step'>(args => args[0]), 'agent/prompt-submit': adapt<'agent/prompt-submit'>(args => args[0]), 'agent/queued': adapt<'agent/queued'>(args => args[0]), 'agent/request': adapt<'agent/request'>(args => args[0]), + 'agent/request-error': adapt<'agent/request-error'>(args => args[0]), 'agent/session-prefix': adapt<'agent/session-prefix'>(args => args[0]), 'agent/session-start': adapt<'agent/session-start'>(args => args[0]), 'agent/status': adapt<'agent/status'>(args => args[0]), diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 71fe28fbe0..11168ba000 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -818,14 +818,22 @@ function renderLifecycle(): string { ' LLM-->>Driver: StreamChunk*', ` Driver->>Session: ${mermaidCode('assistant/chunk')}*`, ` Session-->>SDK: ${mermaidCode('session/event')} ${mermaidCode('assistant/chunk')}*`, + ' alt final adapter or terminal in-band request failure', + ` Driver->>Session: ${mermaidCode('step/end')}`, + ` Driver->>Hooks: ${mermaidCode('agent/request-error')} waterfall`, + ' Hooks-->>Driver: retry in a new step or preserve the original error', + ' else model request succeeded', ` Driver->>Hooks: ${mermaidCode('agent/step-result')} waterfall`, ` Driver->>Session: ${mermaidCode('assistant/message')}`, ` Driver->>Session: ${mermaidCode('tool/call')}`, ' Driver->>Tools: execute through pre and post waterfalls', ' Tools-->>Session: tool-owned events when applicable', - ` Driver->>Session: ${mermaidCode('tool/result')} and ${mermaidCode('step/end')}`, + ` Driver->>Session: ${mermaidCode('tool/result')}, post-tool context, and steering`, + ` Driver->>Hooks: ${mermaidCode('agent/post-step')} serial checkpoint`, + ` Driver->>Session: ${mermaidCode('step/end')}`, ` Driver->>Hooks: ${mermaidCode('agent/turn-continuation')} waterfall`, ` Driver->>Hooks: ${mermaidCode('agent/turn-stop')} serial terminal checkpoint`, + ' end', ` Driver->>Session: ${mermaidCode('turn/end')}`, ` Driver->>Persistence: ${mermaidCode('session/flush')} parallel checkpoint`, ` Driver-->>SDK: ${mermaidCode('agent/status')} idle`, diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index 54fe328389..b0cea673ad 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -14,6 +14,8 @@ { "doc": "docs/core-data-structures/core.md", "symbol": "HookContext", "source": "packages/core/agent/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "PromptDecision", "source": "packages/core/agent/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "ContinuationDecision", "source": "packages/core/agent/src/types.ts" }, + { "doc": "docs/core-data-structures/core.md", "symbol": "RequestError", "source": "packages/core/agent/src/types.ts" }, + { "doc": "docs/core-data-structures/core.md", "symbol": "RequestErrorDecision", "source": "packages/core/agent/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "ContinuationStop", "source": "packages/core/agent/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "SessionStartSource", "source": "packages/core/agent/src/types.ts" }, From 12484104c89fd614a247b1a903f3c9c7821aac3d Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 16:50:44 +0800 Subject: [PATCH 143/359] feat(compact): recover context overflow (PR3 phase 2) --- docs/agent-lifecycle.md | 2 + docs/architecture.md | 2 + docs/capability-seams.md | 2 +- docs/config-catalog.md | 4 +- docs/cookbook/extension-cookbook.i18n.yaml | 4 +- docs/cookbook/extension-cookbook.md | 2 +- docs/cookbook/extension-cookbook.zh.md | 2 +- docs/cordis-catalog/events.md | 28 +- docs/cordis-catalog/services.md | 6 +- docs/core-data-structures/compaction.md | 10 +- docs/event-producer-consumer.md | 20 +- docs/rfc/INDEX.md | 1 + .../2026-06-11-microkernel-event-taxonomy.md | 4 +- ...t-variables-and-tool-guidance-ownership.md | 4 +- .../2026-07-05-reconstructable-requests.md | 4 +- ...n-pressure-and-overflow-recovery.i18n.yaml | 6 + ...mpaction-pressure-and-overflow-recovery.md | 63 +++ ...ction-pressure-and-overflow-recovery.zh.md | 63 +++ ...07-15-replay-token-meter-service.i18n.yaml | 4 +- .../2026-07-15-replay-token-meter-service.md | 8 +- ...026-07-15-replay-token-meter-service.zh.md | 8 +- .../2026-06-18-compaction-capability-seam.md | 42 +- .../feature/2026-07-07-session-prefix.md | 8 +- examples/coding-agent/cordis.yml | 4 +- packages/compact/compact-basic/README.md | 17 +- .../compact/compact-basic/src/automatic.ts | 58 ++- packages/compact/compact-basic/src/config.ts | 3 + packages/compact/compact-basic/src/index.ts | 64 ++-- .../compact/compact-basic/src/summarizer.ts | 2 +- packages/compact/compact-basic/src/types.ts | 5 +- .../compact-basic/tests/compact-basic.spec.ts | 360 ++++++++++++++++-- .../tests/compact-loop-repro.spec.ts | 176 ++++++++- packages/compact/compact/README.md | 7 +- packages/compact/compact/src/index.ts | 22 +- .../compact/compact/tests/compact.spec.ts | 10 +- .../cordis/tool-cordis/src/api-catalog.ts | 10 +- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/loop.ts | 12 +- .../agent-loop/tests/interception.spec.ts | 16 +- packages/core/agent-loop/tests/loop.spec.ts | 21 +- .../agent-loop/tests/request-recovery.spec.ts | 42 ++ packages/core/agent/src/types.ts | 18 +- .../invariants/tests/invariants.spec.ts | 2 +- .../ui/user-approval/tests/approval.spec.ts | 2 +- scripts/gen-doc-graphs.ts | 4 +- scripts/type-equiv.manifest.json | 1 + 46 files changed, 913 insertions(+), 242 deletions(-) create mode 100644 docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml create mode 100644 docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md create mode 100644 docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md diff --git a/docs/agent-lifecycle.md b/docs/agent-lifecycle.md index e4ed315e5b..c6010d4139 100644 --- a/docs/agent-lifecycle.md +++ b/docs/agent-lifecycle.md @@ -55,6 +55,8 @@ sequenceDiagram The `assistant/message` edge records every successful provider call, including content-less and `max-tokens` finishes. Empty content stays out of derived history while the durable anchor retains usage and exact chunk provenance, including an explicit empty source set. +`dsh-compact-basic` uses `agent/post-step` for pressure after those durable facts and `agent/request-error` only for canonical context overflow. Recovery compacts between the closed failed step and a fresh retry step, and returns retry only when the surface replacement generation advances; otherwise the original request error remains authoritative. + SDK users that need replayable transcript data should consume `session/event`; `agent/*` is the live coordination surface for queue/status, prompt interception, request shaping, steering, continuation, and errors. Maintenance mode: curated Mermaid sequence; exact event signatures live in the generated Cordis catalog. diff --git a/docs/architecture.md b/docs/architecture.md index 01988a43df..387327a526 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -105,6 +105,8 @@ Each step renders one prompt assembly. Plugins contribute ordered sections, tool Post-tool context follows all results, preserving call/result adjacency. Steering drains before `agent/post-step`, which observes durable output, results, context, and steering while the step signal remains open. Leftover steering becomes next-turn input. `agent/turn-stop` is terminal through close and flush: later steering is discarded, while ordinary queued prompts survive. +When loaded, `dsh-compact-basic` consumes that post-step checkpoint for `ctx.tokenMeter` pressure under the actual routed header. It also consumes canonical context overflow at `agent/request-error`, but authorizes retry only after a tool-balanced compaction advances `surface.replaceGeneration`. The same turn signal owns both summarization paths. + ### Failure Boundaries The turn is the containment boundary. `LlmService` preserves and privately tags errors from final adapter selection, dispatch, and iteration. Those errors and terminal in-band error/aborted finishes close the failed step before `agent/request-error`; retry reconstructs the next numbered step from the log, while decline or failed recovery preserves the provider error. Attempts count consecutive failures and reset after success. diff --git a/docs/capability-seams.md b/docs/capability-seams.md index fae89bfcfb..5f93bf0433 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -203,7 +203,7 @@ flowchart LR | `ctx.permission` | `core` | [`permission`](../packages/ui/permission) | - | [`acp`](../packages/ui/acp) | - | User-facing preset table (`workspace-write`/`danger-full-access`) bundling the sandbox-mode and approval-policy knobs; a switch writes one `permission/preset` event through to both knob events. | | `ctx.codeRuntime` | `seam` | [`code-runtime`](../packages/code-runtime/code-runtime) | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | [`tools`](../packages/core/tools) | - | Runs one model-written program against host-provided async bindings; backends differ by substrate and language (the tool registry consumes it for Code Mode). | | `ctx.fs` | `seam` | [`fs`](../packages/fs/fs) | [`fs-local`](../packages/fs/fs-local) | [`tool-fs`](../packages/fs/tool-fs) | [`fs-policy`](../packages/fs/fs-policy) | tool-fs executes read/write/edit through ctx.fs; fs-policy contributes observed-state checks through the fs/* event gate. | -| `ctx.compact` | `seam` | [`compact`](../packages/compact/compact) | [`compact-basic`](../packages/compact/compact-basic) | [`compact-basic`](../packages/compact/compact-basic) | - | The basic backend currently consumes the pre-step event directly; a model-facing compact tool remains deferred. | +| `ctx.compact` | `seam` | [`compact`](../packages/compact/compact) | [`compact-basic`](../packages/compact/compact-basic) | [`compact-basic`](../packages/compact/compact-basic) | - | The basic backend consumes post-step pressure and request-error recovery events; a model-facing compact tool remains deferred. | | `ctx.subagents` | `seam` | [`subagent`](../packages/subagent/subagent) | [`subagent-spawn`](../packages/subagent/subagent-spawn), [`subagent-fork`](../packages/subagent/subagent-fork), [`subagent-acp`](../packages/subagent/subagent-acp), [`subagent-mock`](../packages/support/subagent-mock) | [`tool-subagent`](../packages/subagent/tool-subagent) | - | Providers implement transports; tool-subagent exposes one configured provider as a model-facing tool name. | | `ctx.web` | `seam` | [`web`](../packages/web/web) | [`web-search-exa`](../packages/web/web-search-exa), [`web-search-perplexity`](../packages/web/web-search-perplexity), [`web-search-deepseek`](../packages/web/web-search-deepseek), [`web-fetch-local`](../packages/web/web-fetch-local) | [`tool-web`](../packages/web/tool-web) | - | Search and fetch providers register into one ctx.web seam; tool-web owns the stable model-facing names. | | `ctx.workflows` | `seam` | [`workflow`](../packages/workflow/workflow) | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | [`tool-workflow`](../packages/workflow/tool-workflow) | - | One engine per context (bash shape, no named-provider registry); the worker-thread engine fans agent() calls out through ctx.subagents. | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 22fc421f8a..886d7a63a1 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -220,7 +220,9 @@ export interface BasicCompactConfig { maxTokens?: number /** Extra attempts after the first compaction when pressure remains above threshold. Defaults to `1`. */ compactionRetries?: number - /** Enable the automatic `agent/pre-step` pressure listener. Defaults to `true`. */ + /** Maximum retries after canonical context overflow; `0` disables recovery. Defaults to `1`. */ + maxOverflowRetries?: number + /** Enable automatic post-step pressure and overflow-recovery listeners. Defaults to `true`. */ auto?: boolean } diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index ef1d8d606f..6408aaeea1 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -extension-cookbook.md: 40ee22b352c884d7f295c87726c54ab8e166c844 -extension-cookbook.zh.md: 4e5bc68c973649574bcb2404bea00096eb9ca41f +extension-cookbook.md: 712e4f2f1f98cabfeea1a899c111a39957d16e21 +extension-cookbook.zh.md: 494cb559cf17f13a494e6c695a661c559a0add12 diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index 40ee22b352..712e4f2f1f 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -102,7 +102,7 @@ Every product feature maps to a listener on a documented extension seam — the | `/loop` | on the `turn/end` session event, `send()` the next iteration; or force-continue | | Dynamic workflow | `ctx.workflows` + the worker-thread engine + the `workflow` tool; structured in-process children enforce output with scoped prompt/tool registrations, a monotonic tool guard, final `tools/result` commit (including enclosing `run_code`), and terminal `agent/turn-stop` | | Queued + steering messages | core `Agent.send()` / `Agent.steer()` | -| Context compaction (auto + manual) | the `ctx.compact` seam + a backend (`dsh-compact-basic`) on the serial `agent/pre-step` seam; auto = token-pressure check before each step; a manual trigger invokes the same `ctx.compact` routine ([compaction RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md) — the model-facing `/compact` consumer tool is deferred) | +| Context compaction (auto + manual) | the `ctx.compact` seam + `dsh-compact-basic`; automatic pressure runs on serial `agent/post-step`, canonical overflow recovery runs on `agent/request-error`, and manual callers use the same compact service ([compaction RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md) — the model-facing `/compact` consumer tool is deferred) | | System prompt configurability | `ctx.systemPrompt.section()` with ordering and scope-local shadowing | | AGENTS.md (root) | a section provider reading the file | | AGENTS.md (subdir, on-touch) + file-change notices | `agent.inject()` from a watcher / tool-result listener | diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index 4e5bc68c97..494cb559cf 100644 --- a/docs/cookbook/extension-cookbook.zh.md +++ b/docs/cookbook/extension-cookbook.zh.md @@ -102,7 +102,7 @@ export function apply(ctx: Context) { | `/loop` | 在 `turn/end` 会话事件上 `send()` 下一次迭代；或强制继续 | | 动态工作流 | `ctx.workflows` + worker-thread 引擎 + `workflow` 工具；结构化的进程内子任务通过作用域化的 prompt/工具注册、单调工具守卫、最终 `tools/result` 提交（包括外层 `run_code`）和终端 `agent/turn-stop` 来强制输出 | | 排队消息 + steering（中途引导） | 核心 `Agent.send()` / `Agent.steer()` | -| 上下文压缩（context compaction）（自动 + 手动） | `ctx.compact` seam + 串行 `agent/pre-step` seam 上的后端（`dsh-compact-basic`）；自动 = 每步之前的 token 压力检查；手动触发调用同一个 `ctx.compact` 例程（[压缩 RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)——面向模型的 `/compact` 消费方工具已推迟） | +| 上下文压缩（context compaction）（自动 + 手动） | `ctx.compact` seam + `dsh-compact-basic`；自动压力检查运行在串行 `agent/post-step`，规范化溢出恢复运行在 `agent/request-error`，手动调用方使用同一个压缩服务（[压缩 RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)——面向模型的 `/compact` 消费方工具已推迟） | | 系统提示词可配置性 | `ctx.systemPrompt.section()`，支持排序与作用域局部覆盖 | | AGENTS.md（根目录） | 一个读取该文件的 section provider | | AGENTS.md（子目录，按需触发）+ 文件变更通知 | 从 watcher / tool-result 监听器调用 `agent.inject()` | diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 7ce58b6140..131297b797 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:314`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:308`](../../packages/core/agent/src/types.ts) ### `agent/post-step` — serial @@ -59,19 +59,19 @@ Awaited serial checkpoint after the response, tool results, injected context, an Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:267`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:261`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial -Awaited serial checkpoint for session-surface mutation after prompt assembly and before `step/start`; appends land outside the pending step. The loop derives history once afterward, so compaction records and replacements are included without rewriting an assembled request. The prompt and prefix are the exact pressure inputs for that request, and `signal` cancels listener work. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. +Awaited serial checkpoint before `step/start`; appends land outside the pending step and are included when the loop derives request history. `signal` cancels listener work. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. ```ts cordis-catalog -'agent/pre-step'(this: Scoped, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void +'agent/pre-step'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void ``` -Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:208`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:202`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -83,7 +83,7 @@ Allow, rewrite, or block one drained prompt before it becomes a user message. Ca Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:218`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:212`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -107,7 +107,7 @@ Replace the frozen call configuration. Model-visible content must use logged cha Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:230`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:224`](../../packages/core/agent/src/types.ts) ### `agent/request-error` — waterfall @@ -119,11 +119,11 @@ Recover a model-request failure after its failed step has closed. `retry` opens Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:281`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:275`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall -Compose request-only messages placed before derived history. The frozen result is computed once per loop instance, logged on its anchoring request header, and reused so the provider prefix remains stable. Interrupted composition is discarded. Composition precedes the first `agent/pre-step` and request boundary, so listener appends join the current request and pressure accounting sees the composed prefix. Changing context belongs in history; contributors should prepend to `await next()` to preserve registration order. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. +Compose request-only messages placed before derived history. The frozen result is computed once per loop instance, logged on its anchoring request header, and reused so the provider prefix remains stable. Interrupted composition is discarded. Composition precedes the first `agent/pre-step` and request boundary, so listener appends join the current request. Changing context belongs in history; contributors should prepend to `await next()` to preserve registration order. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. ```ts cordis-catalog 'agent/session-prefix'(this: Scoped, agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise): Promise @@ -131,7 +131,7 @@ Compose request-only messages placed before derived history. The frozen result i Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:245`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:239`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -167,7 +167,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:256`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:250`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -179,7 +179,7 @@ Override whether the turn continues. The default continues after tool calls or s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:291`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:285`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -191,7 +191,7 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:301`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:295`](../../packages/core/agent/src/types.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 990a2bc1bc..02705dee99 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -89,13 +89,11 @@ Source: [`packages/code-runtime/code-runtime/src/index.ts:31`](../../packages/co Abstract compaction service. Implementations own trigger policy, retention, and summarization, and may consume a separate measurement service. A successful run replaces the selected surface span with one summary node and prevents concurrent compaction of the same session. Load one implementation per context as `ctx.compact`. ```ts cordis-catalog -abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise +abstract compactIfNeeded( agent: CompactAgentContext, trigger: CompactionTrigger, signal: AbortSignal, ): Promise abstract compactRegion( session: Session, start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise ``` -Types: [Message](../core-data-structures/core.md) - -Source: [`packages/compact/compact/src/index.ts:38`](../../packages/compact/compact/src/index.ts) +Source: [`packages/compact/compact/src/index.ts:40`](../../packages/compact/compact/src/index.ts) ## `ctx.fs` — `FileSystem` (abstract seam) diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 50a80208a9..f60d1e3e08 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -50,8 +50,14 @@ interface CompactionResult { ## The service -`CompactService` exposes `compactIfNeeded(...)` for pressure-triggered compaction, returning `null` when no compaction is needed, and `compactRegion(...)` for an explicit inclusive surface range. The pre-step caller supplies the agent, full prompt, session prefix, and abort signal; implementations must forward that signal to summarization. The seam owns no pricing API: `dsh-compact-basic` resolves the routed model through [`ctx.tokenMeter`](token-meter.md), whose model-bound handle owns estimation and replay, while the backend owns retention, event sequencing, and summarization. +Automatic callers state why policy is running; implementations may treat confirmed overflow more aggressively than ordinary pressure. -Auto-compaction runs at serial `agent/pre-step`, before the step and request derivation, so it can replace surface nodes while keeping trace events outside the step. Region boundaries preserve tool-call/result pairing but do not preserve whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns the retention and failure details. +```ts type-equiv +export type CompactionTrigger = 'pressure' | 'context-overflow' +``` + +`CompactService` exposes `compactIfNeeded(agent, trigger, signal)` for automatic `pressure` or `context-overflow` policy, returning `null` when no safe work exists, and `compactRegion(...)` for an explicit inclusive surface range. Implementations must forward the supplied signal to summarization. The seam owns no pricing API: `dsh-compact-basic` resolves the durable routed model through [`ctx.tokenMeter`](token-meter.md), whose model-bound handle owns estimation and replay, while the backend owns retention, event sequencing, and summarization. + +Pressure compaction runs at serial `agent/post-step`, after successful assistant output, tool results, buffered context, and steering are durable but before `step/end`. Failed-request recovery runs through `agent/request-error` after the failed step closes, and authorizes a fresh numbered-step retry only when the surface replacement generation advances. Region boundaries preserve tool-call/result pairing but do not preserve whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns thresholds, retained-tail policy, overflow caps, and failure handling. The seam exports `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)` for those edge checks. Both validate current surface membership, reject stale or missing seqs and orphan results, and ignore a caller-retained `node.next`; the [package contract](../../packages/compact/compact/README.md#tool-pairing-boundaries) owns their cache semantics. diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index e6872669de..1f280d74b1 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -9,19 +9,19 @@ This matrix shows which packages dispatch each harness-owned event and which pac | --- | --- | --- | --- | --- | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:145`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:154`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:314`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/post-step` | `serial` | [`packages/core/agent/src/types.ts:267`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:208`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:218`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:308`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/post-step` | `serial` | [`packages/core/agent/src/types.ts:261`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic) | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:202`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:212`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | | `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:173`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:230`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:281`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:245`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:224`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:275`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`compact-basic`](../packages/compact/compact-basic) | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:239`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | | `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:186`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | | `agent/status` | `emit` | [`packages/core/agent/src/types.ts:163`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:256`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:291`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:301`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:250`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:285`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:295`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:59`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:68`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index 4f41579a5b..0a80128a4e 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -142,6 +142,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [A shared timeout/deadline primitive, with hard-kill left to each capability](implemented/architecture/2026-07-06-timeout-deadline-library.md) | 2026-07-06 | | [Tool-call timeout policy as a plugin](implemented/architecture/2026-07-07-tool-call-timeout-policy.md) | 2026-07-07 | | [The agent is a registration scope](implemented/architecture/2026-07-08-agent-scope-contexts.md) | 2026-07-08 | +| [After-call compaction pressure and context-overflow recovery](implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md) | 2026-07-10 | | [Single-file executable SDK runtime distribution (single-exe)](implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) | 2026-07-10 | | [Agent-scope runtime design and correctness](implemented/architecture/2026-07-12-agent-scope-runtime-design.md) | 2026-07-12 | | [Replay token meter service](implemented/architecture/2026-07-15-replay-token-meter-service.md) | 2026-07-15 | diff --git a/docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md b/docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md index 8293924d37..1d10bfa479 100644 --- a/docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md +++ b/docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md @@ -10,8 +10,8 @@ The product principle is "everything is a plugin": hooks, /goal, /loop, dynamic Pure Cordis event taxonomy. The loop's extension seams are typed events with deliberate dispatch modes: -- **waterfall** (around-middleware) where plugins transform, veto, or wrap: `agent/prompt-submit`, `agent/request`, `agent/step-result`, `agent/turn-continuation`, `tools/pre-execute`, `tools/execute`, `tools/post-execute`, `llm/stream`, `system-prompt/assemble`. -- **serial** (awaited in listener order; a bail value stops later listeners) for ordered checkpoints: every `agent/pre-step` listener runs when all abstain, while the first stop returned from `agent/turn-stop` makes the terminal decision final. +- **waterfall** (around-middleware) where plugins transform, veto, recover, or wrap: `agent/prompt-submit`, `agent/request`, `agent/request-error`, `agent/step-result`, `agent/turn-continuation`, `tools/pre-execute`, `tools/execute`, `tools/post-execute`, `llm/stream`, `system-prompt/assemble`. +- **serial** (awaited in listener order; a bail value stops later listeners) for ordered checkpoints: every `agent/pre-step` and `agent/post-step` listener runs when all abstain, while the first stop returned from `agent/turn-stop` makes the terminal decision final. - **parallel** (awaited fan-out) where every listener must get an independent chance: the `session/flush` durability checkpoint. - **emit** (synchronous fire-and-forget) for notifications: turn/step boundaries, stream chunks, lifecycle, errors, and the contained immutable `tools/result` observation. diff --git a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md index 854807c109..e40759a182 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md +++ b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md @@ -30,7 +30,7 @@ Plugins register `{{name}}` values through `ctx.systemPrompt.variable(name, prov ### Persona as the order-0 section -`dsh-system-prompt` owns `harness:identity` at order `-100` and the configured `deployment:persona` at order 0, so both survive a replacement loop. Prompt rendering has one path, `renderPrompt(assembly)`, and `agent/pre-step` therefore measures the exact prompt used for compaction. An agent-scoped `deployment:persona` shadows the global default and lets subagent providers install a persona before publication. The conventional order bands are identity `-100`, persona `0`, and tool guidance `100–199`. +`dsh-system-prompt` owns `harness:identity` at order `-100` and the configured `deployment:persona` at order 0, so both survive a replacement loop. Prompt rendering has one path, `renderPrompt(assembly)`, and the routed request header therefore records the exact prompt later replayed by `ctx.tokenMeter` for compaction pressure. An agent-scoped `deployment:persona` shadows the global default and lets subagent providers install a persona before publication. The conventional order bands are identity `-100`, persona `0`, and tool guidance `100–199`. ### Tool guidance ownership @@ -43,7 +43,7 @@ Per-tool semantics and selection guidance live in tool descriptions. Prompt sect ## Alternatives considered - **The loop composes an identity line itself** — hardcodes model-facing prose in the one package that must stay thin ("plugins, not loop changes"), and outside the section pipeline it would be a second composition path. (The identity DOES ship as a code literal — but as an ordinary section registered by `dsh-system-prompt`, whose `system-prompt/assemble` waterfall remains the escape valve for a deployment that must drop it.) -- **Inject the model name via the `agent/request` waterfall** — prompt text composed in two places, and `agent/pre-step`'s `fullSystemPrompt` would omit it, so compaction would measure a prompt that is not what the model sees. +- **Inject the model name via the `agent/request` waterfall** — prompt text would be composed in two places and the earlier rendered persona could disagree with the final routed header. The request plugin that owns late routing must also own any earlier prompt claim about that model. - **Hand-write the model name in each persona** — duplicates the `model:` key one line above and silently lies after a config edit; the exact disease this RFC cures. - **Lenient interpolation (leave unknown refs verbatim, or substitute empty)** — a typo ships `{{modle}}` (or a hole) to the model and nobody notices until transcript review. - **Per-instance subagent wording in config** — returns model-facing prose to every deployment × instance, the P2 disease again. **Keying wording off the provider NAME** — `providerName` is itself config, so a renamed provider silently gets the wrong words. diff --git a/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md b/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md index d95a709ada..34bae2a2f5 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md +++ b/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md @@ -22,9 +22,9 @@ Prefix-cache stability is corollary #1, not the headline: an append-only log pro `EpochHeader` records the request's non-history state: call config, rendered system prompt, tool schemas, and session prefix, with empty values canonicalized to absence. `request/header` writes a full initial, resume, or fallback snapshot. `request/header-delta` encodes system changes by common-prefix/suffix line trim, tools by name-keyed additions/removals/changes, and config or prefix by full replacement. `foldRequestHeader`, `diffHeader`, and `applyHeaderDelta` are the pure codec. Each loop instance writes a snapshot on its first request to anchor process boundaries. Deltas are only an optimization: the writer verifies round-trip equality and falls back to a full snapshot for unrepresentable changes such as pure tool reordering. -Each step rebuilds prompt assembly. On the instance's first step, `agent/session-prefix` extends a frozen empty seed with request-only opener messages; the result is frozen and cached for that loop instance. `agent/pre-step` then receives the composed prefix before messages are snapshotted immediately ahead of `step/start`. The first call config starts from explicit `AgentOptions`, preserving fork overrides and resume reconfiguration; later calls start from the folded header. `agent/request` may replace only that frozen config seed, while model-visible content enters through logged channels. The loop records the owed header event—the prefix's only durable home—builds `GenerateOptions` from prefix, snapshot, and header, and deep-freezes it while leaving `AbortSignal` live. Per-instance state is only the cached prefix and whether its anchoring snapshot has been written. +Each step rebuilds prompt assembly. On the instance's first step, `agent/session-prefix` extends a frozen empty seed with request-only opener messages; the result is frozen and cached for that loop instance before the generic `agent/pre-step` checkpoint and boundary snapshot. The first call config starts from explicit `AgentOptions`, preserving fork overrides and resume reconfiguration; later calls start from the folded header. `agent/request` may replace only that frozen config seed, while model-visible content enters through logged channels. The loop records the owed header event—the prefix's only durable home—builds `GenerateOptions` from prefix, snapshot, and header, and deep-freezes it while leaving `AbortSignal` live. Per-instance state is only the cached prefix and whether its anchoring snapshot has been written. -**`step/start` is the reconstruction boundary.** A step derives messages from events before that sequence. Injection after the snapshot joins the next request, and reentrant appends are rejected during event publication. `agent/pre-step` is the seam for content needed by the current request. Header reconstruction folds through the step's own `request/header*` event, or carries the prior fold when no new header is written. +**`step/start` is the reconstruction boundary.** A step derives messages from events before that sequence. Injection after the snapshot joins the next request, and reentrant appends are rejected during event publication. `agent/pre-step(agent, turn, step, signal)` remains the generic seam for content needed by the current request. Header reconstruction folds through the step's own `request/header*` event, or carries the prior fold when no new header is written. **Enforcement.** In development, `dsh-invariants` independently rebuilds each loop request through a fresh `Session`, so the live cache cannot vouch for itself, then compares messages and folded header fields at `llm/stream`. Loop requests are identified by their frozen shape and session id; direct one-shots are excluded. Correctness depends on sequence-bounded reconstruction rather than listener order. A with-key e2e requires positive cache-read tokens after the first request; per-step usage is the production signal, and a header change or compaction appears as a cache-read drop on the next step. diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml new file mode 100644 index 0000000000..dbb9c76bbf --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: 92167dc7d444a3620abfbaab721260ed1c828db9 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: fe3b6617b25a58ef2c1c311df088f9c805fe9ef4 diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md new file mode 100644 index 0000000000..92167dc7d4 --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md @@ -0,0 +1,63 @@ +# RFC: After-call compaction pressure and context-overflow recovery + +Status: implemented + +English | [中文](2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md) + +## Problem + +Automatic compaction originally ran at `agent/pre-step` and received an assembled prompt and session prefix. That boundary was necessarily provisional: `agent/request` could still route another model or change call configuration, tool schemas were not frozen with the compaction inputs, and the next assistant output, tool results, buffered context, and steering did not exist yet. Expanding the pre-step signature could move the stale boundary but could not make it exact. + +Successful calls are not the only pressure signal. A provider can reject a request for exceeding its context window before it returns usage, and some successful calls omit usage. The system therefore needs replayable post-call pressure plus a narrow failure-recovery path that preserves the provider error whenever compaction cannot prove useful progress. + +## Decision + +### Successful pressure moves to a durable post-step checkpoint + +`agent/pre-step` is narrowed to `(agent, turn, step, signal)`. It remains a generic serial checkpoint before `step/start`, but it carries no compaction-only prompt or prefix fields. + +The loop fires awaited serial `agent/post-step(agent, turn, step, signal)` after assistant output, every dispatched or synthetic tool result, post-tool context, and steering are durable, but before `step/end`. This placement gives pressure policy the complete successful-call state without splitting an assistant tool call from its result. A listener failure is an ordinary turn failure; it never enters model-request recovery. + +`dsh-compact-basic` resolves the exact latest routed model from the durable request header and asks that model's `ctx.tokenMeter` handle to measure the canonical logged envelope and current surface. It does not fall back to `AgentOptions.model` for automatic pressure. A headerless session has no completed routed request to assess and produces no work. A durable unknown model throws `TOKEN_METER_MODEL_UNCONFIGURED` with its exact name and fails the otherwise-successful turn; operational selection or summarization failures warn and continue with full history. + +### Request recovery is limited to the final model boundary + +`RequestError`, `RequestErrorDecision`, and the `agent/request-error` waterfall represent failures after the final adapter has been selected. Private `WeakSet` tagging preserves the original thrown error identity across dispatch, iterator construction, and iteration. Terminal in-band `error` or `aborted` finishes enter the same path. Prompt assembly, request middleware, request logging, result processing, tools, post-step listeners, and cleanup remain ordinary failures. + +The failed step closes before recovery runs. A retry opens the next numbered step and rebuilds the request from the durable log; consecutive recovery attempts reset only after a successful provider request. Both DeepSeek adapters normalize recognized provider context-limit failures to `CONTEXT_WINDOW_EXCEEDED`. + +If cancellation lands after assistant tool calls are durable but before all calls dispatch, the loop records a synthetic aborted `tool/result` for every undispatched call before following the normal abort path. The surface therefore never retains orphaned durable tool calls merely because cancellation won the race. + +### CompactService exposes intent, not token accounting + +`CompactService.compactIfNeeded(agent, trigger, signal)` accepts `trigger: 'pressure' | 'context-overflow'`. The interface gains no estimation methods or token types; `ctx.tokenMeter` remains the reusable accounting owner. + +For `pressure`, compact-basic applies the selected meter profile's threshold and retained-tail policy, compares scalar and surface `logRevision`, and uses the same meter for range pricing, provenance, shadowed token counts, and non-shrinking-summary rejection. The common defaults remain threshold ratio `0.8`, retained history `floor(contextWindow × 0.16)`, summarization model `''`, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. + +For canonical overflow, compact-basic bypasses scalar pressure and the normal retained-token budget. It chooses the maximal tool-balanced head range while leaving the newest indivisible unit, then attempts exactly one shrinking compaction under the same signal. The automatic listener snapshots `session.surface.replaceGeneration` and returns `{ action: 'retry' }` only when compaction succeeds and the generation increases. A backend returning a result without replacement cannot authorize retry. + +`maxOverflowRetries` is optional and defaults to `1`; `0` disables overflow recovery without disabling pressure. `auto: false` registers neither automatic listener. Noncanonical errors, exhausted attempts, an already-aborted signal, missing or unknown routed models, no safe range, no generation change, and recovery throws all delegate to the next listener. With no later recovery, the loop reports the original provider error object and code. Cancellation or disposal remains authoritative even if recovery work completes concurrently. + +The default summarizer still resolves explicit configuration, then the latest logged route, then agent options. Because direct `llm/stream` middleware may reroute that auxiliary call, `compact/summary.model` records the final mutable `GenerateOptions.model` observed after dispatch rather than the pre-waterfall candidate. + +## Testing + +Lifecycle tests pin post-step ordering after durable tool/context/steering work, content-less and max-token successes, final-adapter dispatch/iterator/in-band boundaries, retry numbering, attempt reset, cancellation, disposal, synthetic tool results, and original error identity. + +Compact tests pin low-friction defaults, actual routed-model selection, exact unknown-model behavior, below-threshold forced overflow, newest tool-pair retention, non-shrinking rejection, generation proof, caps, disabled listeners, single downstream delegation, and auxiliary summary routing provenance. Real-loop composition covers both thrown and in-band overflow: the failed step closes, compaction lands between attempts, and the next numbered request is reconstructed from the replacement surface. + +## Alternatives considered + +- **Keep provisional pre-step pressure and add more arguments** — rejected because later routing and request mutation remain outside any earlier snapshot, while generic lifecycle becomes coupled to one plugin. +- **Retry the same numbered step** — rejected because recovery appends durable events after the failed boundary. A new step preserves balanced nesting and reconstructability. +- **Retry whenever `compactIfNeeded` returns a result** — rejected because a custom backend can report success without changing model-visible state. `replaceGeneration` is the authoritative proof. +- **Let compact-basic parse provider wording** — rejected because classification belongs at adapters and must cover both thrown and in-band delivery. +- **Use a universal model/window fallback during recovery** — rejected because destructive policy under the wrong context capacity can hide the original provider failure. Unknown durable routes delegate unchanged. + +## Consequences + +Pressure now describes the actual completed routed request, including durable tool results and request-only prefix fields, rather than a provisional next-call guess. Canonical overflow supplies the backstop when no successful usage anchor exists. Recovery is bounded, cancellation-owned, and monotonic: it retries only after a visible surface generation change. + +The cost is one additional serial checkpoint on successful steps and adapter-maintained overflow classification. Provider wording and heuristic character density remain maintenance risks. Surface compaction still cannot repair an envelope that alone exceeds the window or split one indivisible oversized message/tool unit. + +This RFC supersedes only the pre-step automatic-trigger portion of the [compaction capability-seam RFC](../feature/2026-06-18-compaction-capability-seam.md). The service split, standalone token meter, balanced range contract, log-recorded lock, summary replacement, and sole `summarize()` subclass hook remain unchanged. diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md new file mode 100644 index 0000000000..fe3b6617b2 --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md @@ -0,0 +1,63 @@ +# RFC：调用后压缩压力与上下文溢出恢复 + +Status: implemented + +[English](2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md) | 中文 + +## 问题 + +自动压缩最初运行在 `agent/pre-step`，并接收已装配提示词与会话前缀。这个边界必然只是临时状态：`agent/request` 仍可能路由到另一个模型或改变调用配置，工具 schema 没有与压缩输入在同一位置冻结，而下一次 assistant 输出、工具结果、缓冲上下文与 steering 此时还不存在。继续扩充 pre-step 签名只能移动陈旧边界，无法让它变得精确。 + +成功调用也不是唯一的压力信号。提供方可能在返回 usage 之前就因上下文窗口超限拒绝请求，一些成功调用也不提供 usage。因此，系统需要可重放的调用后压力，以及一条狭窄的失败恢复路径；当压缩无法证明取得有效进展时，必须保留原始提供方错误。 + +## 决策 + +### 成功压力移动到持久 post-step 检查点 + +`agent/pre-step` 收窄为 `(agent, turn, step, signal)`。它仍是 `step/start` 之前的通用串行检查点，但不再携带压缩专用的提示词或前缀字段。 + +循环在 assistant 输出、所有已分发或合成的工具结果、工具后上下文与 steering 都持久化之后、`step/end` 之前，触发等待式串行 `agent/post-step(agent, turn, step, signal)`。该位置让压力策略看到完整的成功调用状态，同时不会拆开 assistant 工具调用与其结果。监听器失败属于普通 turn 失败，绝不会进入模型请求恢复。 + +`dsh-compact-basic` 从持久请求头解析精确的最新实际路由模型，并让该模型的 `ctx.tokenMeter` handle 计量规范日志信封与当前表层。自动压力不会回退到 `AgentOptions.model`。没有请求头的会话尚无已完成路由请求可供判断，因此不执行工作。持久记录的未知模型会携带精确名称抛出 `TOKEN_METER_MODEL_UNCONFIGURED`，使原本成功的 turn 失败；操作性的选择或摘要失败则警告并继续使用完整历史。 + +### 请求恢复只覆盖最终模型边界 + +`RequestError`、`RequestErrorDecision` 与 `agent/request-error` waterfall 表示最终适配器已经选定之后的失败。私有 `WeakSet` 标记在分发、异步迭代器构造与迭代过程中保留原始抛出错误的身份。终止性的带内 `error` 或 `aborted` finish 进入同一路径。提示词装配、请求中间件、请求日志、结果处理、工具、post-step 监听器与清理仍属于普通失败。 + +恢复运行前，失败 step 已经关闭。重试会打开下一个编号 step，并从持久日志重建请求；连续恢复尝试计数只在提供方请求成功后重置。两个 DeepSeek 适配器都把识别出的提供方上下文限制错误规范化为 `CONTEXT_WINDOW_EXCEEDED`。 + +如果取消发生在 assistant 工具调用已经持久化之后、所有调用完成分发之前，循环会为每个尚未分发的调用记录合成的 aborted `tool/result`，随后进入正常中止路径。因此，表层不会仅因取消赢得竞态而留下孤立的持久工具调用。 + +### CompactService 暴露意图，而不拥有 token 核算 + +`CompactService.compactIfNeeded(agent, trigger, signal)` 接收 `trigger: 'pressure' | 'context-overflow'`。接口不增加估算方法或 token 类型；`ctx.tokenMeter` 继续作为可复用的核算所有者。 + +对于 `pressure`，compact-basic 应用所选 meter profile 的阈值与保留尾部策略，比较标量和表层的 `logRevision`，并用同一个 meter 完成范围定价、来源、被遮蔽 token 数与非缩小摘要拒绝。通用默认值保持为阈值比例 `0.8`、保留历史 `floor(contextWindow × 0.16)`、摘要模型 `''`、`maxTokens: 8192`、`compactionRetries: 1` 与 `auto: true`。 + +对于规范化溢出，compact-basic 绕过标量压力与普通保留 token 预算。它在保留最新不可分割单元的同时，选择最大的工具配对平衡头部范围，并在同一 signal 下只尝试一次缩小压缩。自动监听器先记录 `session.surface.replaceGeneration`，只有压缩成功且 generation 增加时才返回 `{ action: 'retry' }`。后端若只返回结果但没有替换表层，不能授权重试。 + +`maxOverflowRetries` 可选且默认为 `1`；`0` 只禁用溢出恢复，不会禁用压力检查。`auto: false` 不注册任何自动监听器。非规范化错误、尝试耗尽、已经中止的 signal、缺失或未知路由模型、没有安全范围、generation 未变化，以及恢复抛错都会委托给下一个监听器。若没有后续恢复，循环报告原始提供方错误对象与代码。即使恢复工作并发完成，取消或销毁仍具有最终优先级。 + +默认摘要器仍依次解析显式配置、最近记录的路由与 agent options。因为直接 `llm/stream` 中间件可以重新路由该辅助调用，`compact/summary.model` 记录分发后最终可变的 `GenerateOptions.model`，而不是 waterfall 之前的候选值。 + +## 测试 + +生命周期测试固定 post-step 位于持久工具、上下文与 steering 工作之后，覆盖无内容与达到 token 上限的成功、最终适配器分发/迭代器/带内边界、重试编号、尝试重置、取消、销毁、合成工具结果与原始错误身份。 + +压缩测试固定低摩擦默认值、实际路由模型选择、精确未知模型行为、低于阈值的强制溢出、最新工具配对保留、非缩小拒绝、generation 证明、上限、禁用监听器、单次下游委托与辅助摘要路由来源。真实循环组合同时覆盖抛出式和带内溢出：失败 step 关闭，压缩落在两次尝试之间，下一个编号请求从替换表层重建。 + +## 考虑过的替代方案 + +- **保留临时 pre-step 压力并增加更多参数**——不予采纳，因为后续路由与请求变换仍在更早快照之外，同时通用生命周期会耦合到单个插件。 +- **重试相同编号的 step**——不予采纳，因为恢复会在失败边界之后追加持久事件。新 step 保持边界配对与可重建性。 +- **只要 `compactIfNeeded` 返回结果就重试**——不予采纳，因为自定义后端可能报告成功却没有改变模型可见状态。`replaceGeneration` 才是权威证明。 +- **让 compact-basic 解析提供方措辞**——不予采纳，因为分类属于适配器，而且必须同时覆盖抛出式与带内交付。 +- **恢复时使用通用模型/窗口回退**——不予采纳，因为基于错误上下文容量执行破坏性策略可能掩盖原始提供方失败。未知持久路由会原样委托。 + +## 后果 + +压力现在描述实际完成的路由请求，包括持久工具结果与仅请求前缀字段，而不是对下一次调用的临时猜测。当成功 usage 锚点不存在时，规范化溢出提供兜底路径。恢复有上限、受取消所有，并保持单调：只有模型可见的表层 generation 变化后才重试。 + +代价是成功 step 增加一个串行检查点，并需要适配器持续维护溢出分类。提供方措辞与启发式字符密度仍是维护风险。表层压缩依然无法修复仅信封本身就超出窗口的情况，也不能拆分单个不可分割的超大消息或工具单元。 + +本 RFC 只取代[压缩能力接缝 RFC](../feature/2026-06-18-compaction-capability-seam.md) 中的 pre-step 自动触发部分。服务拆分、独立 token meter、平衡范围契约、日志记录锁、摘要替换与唯一 `summarize()` 子类 hook 均保持不变。 diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml index 99c6301f25..dbb2a582f0 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-replay-token-meter-service.md: 4452c151e122c4a4ad72e3f0bc2616cd2fa28b9d -2026-07-15-replay-token-meter-service.zh.md: 23edc11ffd19b9cfaeb794f3608e9ced4e7dbb7b +2026-07-15-replay-token-meter-service.md: 079eb58f38a69a40b3f47a23e72d159f7025d285 +2026-07-15-replay-token-meter-service.zh.md: 7c3c9ce47ad81029b03747ddb17b87dc55def8e7 diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md index 4452c151e1..079eb58f38 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md @@ -32,13 +32,13 @@ Usage sums the disjoint input, cache-read, cache-write, and output buckets. Reas `dsh-compact-basic` requires `ctx.tokenMeter`; `CompactService` gains no token methods or types. The backend is factored into configuration, automatic triggering, region transaction, and summarizer modules, while `summarize()` remains its sole subclass hook. The conversation model's meter consistently prices pressure, retention, shadowed content, provenance, and non-shrinking-summary rejection. -Every metered model receives a compact policy with defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, summarization model `''`, maximum summary output `8192`, one extra compaction attempt, and automatic triggering enabled. Per-model compact overrides merge `thresholdRatio` and `retainTokens`; retention must remain below the resulting threshold. Empty summarization model resolves the latest logged routed model, then `AgentOptions.model`. +Every metered model receives a compact policy with defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, summarization model `''`, maximum summary output `8192`, one extra pressure-compaction attempt, one context-overflow retry, and automatic triggering enabled. Per-model compact overrides merge `thresholdRatio` and `retainTokens`; retention must remain below the resulting threshold. Empty summarization model resolves the latest logged routed model, then `AgentOptions.model`. -The pre-step trigger measures a provisional envelope: the current prompt and prefix override logged values, while the latest logged header supplies model, tools, and other call config. A model-less router-only agent skips that provisional check because `agent/request` can route later; naming an unknown model remains an error. +Automatic pressure runs at `agent/post-step` and measures the canonical durable envelope under the model actually selected by `agent/request`. A headerless session has no completed routed request to assess and produces no work; a durable unknown routed model remains an exact typed error. Canonical overflow recovery uses the same meter for forced range selection, and retries only after a proven surface replacement. ## Testing -Unit coverage pins profiles, field-wise overrides, custom and unknown models, envelope invalidation, model switching, usage and missing-usage paths, seeded append/replace replay, signed deltas, provenance modes, malformed boundaries, immutable snapshots, listener ordering, reload, compact defaults, routing fallback, retention, convergence, and transaction rollback. A real Loader/Include YAML fixture loads the exact zero-config token-meter and compact-basic package names in dependency order. +Unit coverage pins profiles, field-wise overrides, custom and unknown models, envelope invalidation, model switching, usage and missing-usage paths, seeded append/replace replay, signed deltas, provenance modes, malformed boundaries, immutable snapshots, listener ordering, reload, compact defaults, actual routing, retention, convergence, forced overflow, and transaction rollback. A real Loader/Include YAML fixture loads the exact zero-config token-meter and compact-basic package names in dependency order. ## Alternatives considered @@ -54,4 +54,4 @@ Unit coverage pins profiles, field-wise overrides, custom and unknown models, en - Defaults make the bundled DeepSeek composition usable with two zero-config plugin entries, while custom models must state the one fact that cannot be guessed safely: context capacity. - Heuristic density and provider usage remain estimates of provider behavior. Maintainers must update built-in profiles and overflow wording as models evolve. - Measurements fail loudly on malformed durable boundaries. This turns corrupted replay into a named integration failure instead of silently drifting pressure. -- The pre-step compact integration can skip a router-only first check and can miss tool or routing changes applied later in request middleware. +- Post-step pressure reads the exact logged routing/tools/prefix boundary; provider overflow classification remains the adapter-maintained backstop for requests rejected before a successful usage anchor. diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md index 23edc11ffd..7c3c9ce47a 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md @@ -32,13 +32,13 @@ Usage 会对互不重叠的输入、缓存读取、缓存写入与输出 bucket `dsh-compact-basic` 要求 `ctx.tokenMeter`；`CompactService` 不增加 token 方法或类型。后端拆分为配置、自动触发、区域事务与摘要器模块，而 `summarize()` 仍是唯一的子类 hook。会话模型的 meter 一致用于压力、保留、被遮蔽内容、来源以及非缩小摘要拒绝。 -每个已计量模型都会获得默认压缩策略：阈值比例 `0.8`、保留尾部 `floor(contextWindow × 0.16)`、摘要模型 `''`、摘要最大输出 `8192`、一次额外压缩尝试，以及启用自动触发。逐模型压缩覆盖按字段合并 `thresholdRatio` 与 `retainTokens`；保留值必须小于最终阈值。空摘要模型先解析最近记录的实际路由模型，再使用 `AgentOptions.model`。 +每个已计量模型都会获得默认压缩策略：阈值比例 `0.8`、保留尾部 `floor(contextWindow × 0.16)`、摘要模型 `''`、摘要最大输出 `8192`、一次额外压力压缩尝试、一次上下文溢出重试，以及启用自动触发。逐模型压缩覆盖按字段合并 `thresholdRatio` 与 `retainTokens`；保留值必须小于最终阈值。空摘要模型先解析最近记录的实际路由模型，再使用 `AgentOptions.model`。 -pre-step 触发器计量临时请求信封：当前提示词与前缀覆盖日志值，最近记录的请求头提供模型、工具及其他调用配置。没有模型的纯路由 agent 会跳过该临时检查，因为 `agent/request` 仍可稍后路由；显式命名未知模型仍然报错。 +自动压力检查运行在 `agent/post-step`，并使用 `agent/request` 实际选择的模型计量规范持久信封。没有请求头的会话尚无已完成的路由请求可供判断，因此不执行工作；持久记录的未知路由模型仍抛出带精确名称的类型化错误。规范化溢出恢复使用同一 meter 强制选择范围，并且只有在表层替换得到证明后才重试。 ## 测试 -单元覆盖固定 profile、按字段覆盖、自定义与未知模型、信封失效、模型切换、有无 usage 的路径、种子追加/替换重放、有符号增量、来源模式、畸形边界、不可变快照、监听器顺序、重载、压缩默认值、路由回退、保留、收敛与事务回滚。真实 Loader/Include YAML fixture 按依赖顺序加载精确的零配置 token-meter 与 compact-basic package 名称。 +单元覆盖固定 profile、按字段覆盖、自定义与未知模型、信封失效、模型切换、有无 usage 的路径、种子追加/替换重放、有符号增量、来源模式、畸形边界、不可变快照、监听器顺序、重载、压缩默认值、实际路由、保留、收敛、强制溢出与事务回滚。真实 Loader/Include YAML fixture 按依赖顺序加载精确的零配置 token-meter 与 compact-basic package 名称。 ## 考虑过的替代方案 @@ -54,4 +54,4 @@ pre-step 触发器计量临时请求信封：当前提示词与前缀覆盖日 - 默认值让内置 DeepSeek 组合只需两个零配置插件条目即可使用，而自定义模型必须声明唯一不能安全猜测的事实：上下文容量。 - 启发式密度与提供方 usage 仍然只是提供方行为的估计。随着模型演进，维护者必须更新内置 profile 与溢出措辞。 - 遇到畸形持久边界时，计量会明确失败。这会把损坏的重放转化为具名集成错误，而不是让压力静默漂移。 -- pre-step 压缩集成可能跳过纯路由的首次检查，也可能错过请求中间件稍后应用的工具或路由变化。 +- post-step 压力检查读取精确记录的路由、工具与前缀边界；对于在成功 usage 锚点出现前就被拒绝的请求，提供方溢出分类仍是由适配器维护的兜底路径。 diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index 42b93f1225..7714db14b7 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -17,7 +17,7 @@ Two forces shape the design. First, compaction policy and reusable token measure Per the [capability-seams RFC](../../implemented/architecture/2026-06-13-capability-seams.md), compaction ships as separate packages so the contract, the algorithm, and (later) the consumer surface evolve independently: 1. **Interface** — `@deepseek-ai/dsh-compact`: an abstract `CompactService` owning the `ctx.compact` key, the `CompactionResult` vocabulary, and the `compact/*` session events. It declares `compactIfNeeded()` and `compactRegion()` as **abstract** — the contract states *what* compaction does, not *how*. -2. **Implementation** — `@deepseek-ai/dsh-compact-basic`: a concrete `BasicCompactService` that consumes `ctx.tokenMeter` and owns the tail→head retention walk, summarization via `ctx.llm.stream()`, the surface replacement, the lock, and the `agent/pre-step` auto-compaction listener. `summarize()` is its sole subclass hook; pricing and replay stay with the meter. +2. **Implementation** — `@deepseek-ai/dsh-compact-basic`: a concrete `BasicCompactService` that consumes `ctx.tokenMeter` and owns the tail→head retention walk, summarization via `ctx.llm.stream()`, the surface replacement, the lock, post-step pressure, and canonical context-overflow recovery. `summarize()` is its sole subclass hook; pricing and replay stay with the meter. 3. **Consumer** — deferred. A `/compact` tool and slash command will `inject: ['compact']` and call the contract; they are intentionally out of scope here so the seam settles first. ### The contract depends on `dsh-session` and `dsh-llm` — a deliberate deviation @@ -30,27 +30,27 @@ This is not a coupling smell — it is the contract's domain. The "only cordis" An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the standalone service lets multiple consumers share one model/session replay fold. -`compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` takes required pressure inputs and cancellation. The session comes from the agent. `compactRegion(session, start, end, agent, signal?)` keeps an optional signal for manual callers and requires `session === agent.session`; implementations reject mismatch before model resolution, lock acquisition, summarization, or log mutation. The pre-step integration resolves a provisional model from the latest logged request header, then `AgentOptions.model`; a model-less router-only first step skips pressure because `agent/request` can route later. The default summarizer resolves its model from explicit config, the latest logged routed model, then agent options. +`compactIfNeeded(agent, trigger, signal)` takes an explicit `'pressure' | 'context-overflow'` trigger and cancellation. It resolves only the latest durable routed request model; no header means no work, while a named unconfigured model produces the token meter's exact typed error. `compactRegion(session, start, end, agent, signal?)` keeps an optional signal for manual callers and requires `session === agent.session`; implementations reject mismatch before model resolution, lock acquisition, summarization, or log mutation. The default summarizer resolves its model from explicit config, the latest logged routed model, then agent options, and records the model after any `llm/stream` routing. -### Auto-compaction runs on `agent/pre-step`, a dedicated surface-mutation seam +### Automatic pressure runs after successful durable step work -Compaction mutates the session surface, so it runs before the step opens and before messages are derived. `agent/request` remains a call-config transform and never needs to rebuild history after a surface change. +The original pre-step placement used a provisional envelope and could not see final `agent/request` routing, tools, provider output, tool results, buffered context, or steering. The corrected lifecycle fires serial `agent/post-step(agent, turn, step, signal)` after those successful facts are durable and before `step/end`. `dsh-compact-basic` measures the canonical logged request through `ctx.tokenMeter`, so the next request sees any replacement without a speculative envelope override. -The fix is a dedicated loop seam, **`agent/pre-step`** (`@mode serial`), fired by the loop *after* system assembly and *before* the step opens (`step/start`): +Canonical provider context overflow takes a separate path. The failed step closes, `agent/request-error` receives the original request error and consecutive retry count, and compact-basic forces one useful balanced reduction. It returns retry only if `session.surface.replaceGeneration` increases; the loop then opens a new numbered step and reconstructs its request from the durable log. No range, no replacement, recovery failure, cancellation, an exhausted cap, or an unrelated error preserves the original provider failure. The complete lifecycle decision is in the [after-call recovery RFC](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md). ``` -assembly = ctx.systemPrompt.assemble() -await ctx.serial('agent/pre-step', agent, turn, step, system, prefix, signal) ⟵ compaction mutates the surface here -session('step/start') ⟵ the step opens AFTER the seam -messages = session.deriveMessages() ⟵ single derive, reflects the compaction -request = waterfall agent/request ⟵ pure request transform (hooks, model switch) -``` +assistant/message → tool/result/context/steering +await serial agent/post-step ⟵ pressure compaction inside the successful step +step/end -The loop derives messages once after `agent/pre-step`. Running before `step/start` keeps compaction records outside any half-open step, simplifying crash repair. The seam is awaited and serial so surface mutations cannot interleave; listeners return `void` and do not use Cordis bail values as vetoes. +provider overflow → step/end +await waterfall agent/request-error ⟵ forced compaction between attempts +retry → next numbered step/start ⟵ derives from the replacement surface +``` ### Retention is turn-agnostic; tool-pairing balance is the only structural guard -Auto-compaction fires before **every** step, not once per turn. This is **load-bearing for runaway-turn survival**: a tool-heavy ReAct turn appends an `assistant/message` + a `tool/result` per step, so the surface grows *within* a turn. A single turn can grow past the window on its own (a "runaway turn") — and the only moment to rescue it before the next model call overflows is the next step's `pre-step` checkpoint. Gating compaction to a turn's first step (or, worse, retaining the whole in-flight turn verbatim) re-opens exactly the hole compaction exists to close: the harness would die when compaction is most needed. +Auto-compaction checks after **every successful** step, not once per turn. This is load-bearing for runaway-turn survival: a tool-heavy ReAct turn appends an `assistant/message` + a `tool/result` per step, so the surface grows within a turn. The post-step check can compact early closed tool pairs before continuation opens the next step, and provider-confirmed overflow remains the backstop when a request crosses the limit first. `compactIfNeeded` retains the smallest tail of whole surface units whose estimated size reaches `retainTokens` and compacts older nodes. A unit is a complete closed step or one no-step message. If the token cutoff lands inside a step, retention expands until the cut is tool-pairing balanced. Balance is checked on surface order, not log sequence, because replacement summaries have new sequence numbers at old surface positions. `dsh-compact` exports the before/after edge helpers; their per-session cache folds only appended surface-tail nodes while `replaceGeneration` is unchanged, does no event reads for log-only growth, and rebuilds current membership, positional successors, and balances after replacement. `compactRegion` rejects boundaries that split a tool call from its result. The in-flight turn receives no special retention. @@ -64,7 +64,7 @@ Auto-compaction always starts at the surface head, merging the prior checkpoint ### Approximate convergence invariant -`resolveConfig` supplies usable common defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, empty summarization-model override, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. Optional per-model threshold/retention fields merge over those defaults and must name a configured meter profile; retained tokens must be below the resulting threshold. Convergence remains dynamic because provider output caps can be spent on hidden or surfaced reasoning tokens and summary size is unpredictable. If the compacted surface remains over threshold, `compactIfNeeded()` re-compacts the head checkpoint up to the configured retry count, but each committed summary must be smaller than what it shadows. +`resolveConfig` supplies usable common defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, empty summarization-model override, `maxTokens: 8192`, `compactionRetries: 1`, `maxOverflowRetries: 1`, and `auto: true`. Optional per-model threshold/retention fields merge over those defaults and must name a configured meter profile; retained tokens must be below the resulting threshold. Convergence remains dynamic because provider output caps can be spent on hidden or surfaced reasoning tokens and summary size is unpredictable. If pressure remains over threshold, `compactIfNeeded()` re-compacts the head checkpoint up to the configured retry count, but each committed summary must be smaller than what it shadows. Overflow bypasses threshold and retained-tail policy for one maximal balanced head reduction, leaving the newest indivisible unit. ### Surface replacement: `compact/*` events are log-only; one `user/message` carries the summary @@ -90,12 +90,12 @@ The basic backend wraps the summary as established checkpoint context and tags i The `compact/start … compact/end` bracket is justified, in order of what now does the work: 1. **Crash-detectable orphan + provenance** (primary). Summarization is a slow model call persisted *after* `compact/start`. A crash mid-summarization leaves a `compact/start` with no matching `compact/end` — a detectable orphan. Releasing the lock last (rather than first) converts the crash window from *silent corruption* into that detectable orphan. -2. **Prevents concurrent compaction.** `compactRegion` refuses to start if the current turn holds an unmatched `compact/start`. (The loop is single-threaded across the awaited `pre-step`, so this is also a re-entry tripwire — a thrown "already in progress" signals a real bug.) +2. **Prevents concurrent compaction.** `compactRegion` refuses to start if the current turn holds an unmatched `compact/start`. (The loop is single-threaded across either awaited automatic seam, so this is also a re-entry tripwire — a thrown "already in progress" signals a real bug.) Two failure paths, both documented: -- **Crash** (the loop dies mid-summarization): a dangling `compact/start`, no closer. Because `compact/*` are **log-only**, the orphan is **inert** — the surface replacement never landed, so the full, uncompacted history derives correctly. Generic turn-repair (`interruptedTurnClosers`) closes the turn with a synthetic `turn/end`; the orphan sits *before* that `turn/end`, so the turn-scoped in-progress check never sees it and a crash can't wedge future compaction. Compaction simply re-attempts at the next `pre-step`. -- **Recoverable** (summarization throws but the loop survives): the backend appends `compact/end` with its **`error`** field set, leaving the surface untouched, and the model call proceeds with full history. +- **Crash** (the loop dies mid-summarization): a dangling `compact/start`, no closer. Because `compact/*` are **log-only**, the orphan is **inert** — the surface replacement never landed, so the full, uncompacted history derives correctly. Generic turn-repair (`interruptedTurnClosers`) closes the turn with a synthetic `turn/end`; the orphan sits *before* that `turn/end`, so the turn-scoped in-progress check never sees it and a crash cannot wedge future compaction. +- **Recoverable** (summarization throws but the loop survives): the backend appends `compact/end` with its **`error`** field set and leaves the surface untouched. Post-step pressure warns and continues; overflow recovery delegates so the original provider error remains authoritative. `compact/end` keeps its `error?` field (mirroring `tool/result`'s self-contained error — one event tells success from failure without correlating a sibling). There is no separate `compact/error` event. @@ -104,14 +104,14 @@ Two failure paths, both documented: ## Alternatives considered - **The full algorithm as concrete interface methods** — rejected because it recouples the contract to one retention strategy. Both core methods are abstract; reusable measurement is a separate LLM-family service and `summarize()` is basic's sole hook. -- **Compaction on the `agent/request` waterfall** — the earlier cut; rejected for the double-derive it forced and for handing the listener context it structurally cannot compact. The dedicated `agent/pre-step` seam makes the layering correct by construction. +- **Compaction on `agent/request` or provisional `agent/pre-step` inputs** — rejected because neither proves the final durable request and both couple generic lifecycle to compaction-specific envelope data. Post-step replay plus canonical overflow recovery covers both successful and rejected calls. - **A separate `compact/error` event** — rejected: `compact/end` keeps an `error?` field, mirroring `tool/result`'s self-contained error — one event tells success from failure without correlating a sibling. - **Teaching core turn-repair about `compact/*`** — rejected: the log-only orphan is inert, and a core module patched for every future `xxx/start … xxx/end` plugin pair is exactly the coupling the capability-seam architecture exists to avoid. ## Consequences - **Packages**: `packages/compact/compact` supplies the interface and `compact-basic` supplies the backend. `packages/llm/token-meter` owns replay-aware measurement independently. The consumer tier is deferred. -- **New loop seam**: `agent/pre-step` (`@mode serial`) declared in `dsh-agent` and emitted by `dsh-agent-loop` after system assembly and before `step/start`. This is a documented change to the loop — `docs/architecture.md` records it and the generated cordis catalog carries its signature. +- **Automatic seams**: `agent/post-step` (`@mode serial`) handles successful-call pressure and `agent/request-error` (`@mode waterfall`) handles final request failures after the failed step closes. Generic `agent/pre-step` remains a four-argument checkpoint with no compaction-only prompt/prefix payload. - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry. - **`dsh-compact`** owns `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)`, the cached surface-edge checks that `compactRegion` and `compactIfNeeded` use to avoid splitting a tool-call/result pair. The cache validates current membership by seq and resolves after-edges from its positional successor map instead of trusting a caller-retained `node.next`; stale or missing seqs and orphan results reject. `dsh-session` continues to own the surface `replace` operation, positional nodes, and rewrite generation. - **`dsh-invariants`** drops its `surface replace: start must be <= end` assertion: a head-anchored compaction lands a high-seq replacement node at an older range's *position*, so `start > end` numerically is normal and valid (the range is positional, validated by the surface's `indexOf` checks that remain). The turn-enclosure invariant is reused unchanged. @@ -119,7 +119,7 @@ Two failure paths, both documented: ## Testing -- **Unit:** Real Loader and invariant plugins cover whole-unit retention, convergence failure, both `compact/end` outcomes, head anchoring, open-tail refusal, inert crash orphans, and compacting closed steps inside one oversized open turn. -- **Loop:** Tests pin one awaited `agent/pre-step` per step between `turn/start` and `step/start`; a surface mutation there lands outside the step and appears in the single derived request. +- **Unit:** Real Loader and invariant plugins cover whole-unit retention, convergence failure, both `compact/end` outcomes, head anchoring, open-tail refusal, inert crash orphans, forced below-threshold overflow, generation proof, caps, and original-error preservation. +- **Loop:** Tests pin post-step after durable tool results and before `step/end`, actual `agent/request` routing, closed failed steps, fresh retry numbering, and complete thrown/in-band overflow → compaction → reconstructed retry composition. - **With-key e2e:** A real model and bash session with lowered limits triggers compaction, records a complete `compact/start…end` pair, shrinks the surface, and finishes the task. - **Snapshot gap:** Runaway-turn compaction cannot yet replay because the summarization call records no `assistant/chunk` events or `sessionId`; interleaved summarization-call replay remains follow-up work. diff --git a/docs/rfc/implemented/feature/2026-07-07-session-prefix.md b/docs/rfc/implemented/feature/2026-07-07-session-prefix.md index f0d458368a..e6ecf69a74 100644 --- a/docs/rfc/implemented/feature/2026-07-07-session-prefix.md +++ b/docs/rfc/implemented/feature/2026-07-07-session-prefix.md @@ -16,13 +16,13 @@ Three properties carry the design: - **Request-only, header-logged.** `deriveMessages()` never returns the prefix; its one durable record is `EpochHeader.messagePrefix` on the instance's anchoring `request/header` snapshot — the channel the reconstructable-requests RFC already owns for the request's non-history half, so no new session event exists. The dev invariant ([dsh-invariants](../../../../packages/support/invariants/src/index.ts)) recomputes `messagePrefix + boundary derivation` against every loop-built request; an unlogged prefix cannot reach the wire. - **Frozen per instance.** Reuse is structural, not disciplined: the cached product cannot change mid-session, so the provider's prompt cache holds by construction and the prefix extends the cacheable region at zero marginal cost per step. A process restart or `ctx.agents.resume()` is a new instance: it recomposes, and any drift lands attributably on the `'resume'` header snapshot. This is the routing rule the seam creates: session-frozen openers ride the prefix; content that changes mid-session rides the append-only history channels (`agent.inject()`, a `tools/post-execute` decision's `additionalContext`, prompt-submit `additionalContext` — [the interception-seams RFC](2026-06-30-interception-seams.md)), each a durable `context/message` paid once and prefix-cached thereafter. -- **Composed before the pressure gate.** Composition precedes the instance's first `agent/pre-step`, and the seam hands the composed value through: `agent/pre-step` carries a `sessionPrefix` parameter and `CompactService.compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` counts it in its token-pressure estimate — a gate reading the previous instance's folded prefix instead would under-gate a resumed or forked instance whose contributor grew, skipping compaction and shipping an over-window first request. A composition interrupted by a cancel/dispose landing inside the waterfall is discarded, never cached: an abort-aware listener's degraded fallback cannot leak into later requests, and the next turn recomposes under a live signal. +- **Exact in the durable request envelope.** Composition precedes the instance's first `agent/pre-step` and request boundary. The first routed request logs the current prefix on its header, so post-step token pressure reads the exact prefix together with the actual prompt, tools, and routed model; no compaction-only parameter is carried through the generic pre-step seam. A composition interrupted by cancel/dispose is discarded, never cached: an abort-aware listener's degraded fallback cannot leak into later requests, and the next turn recomposes under a live signal. Because composition runs before the boundary snapshot, a composing listener's session append joins the CURRENT request's derived history. Compaction structurally cannot touch the prefix (or the system prompt): it rewrites surface nodes, and header state never enters the surface. ## Testing -[Interception tests](../../../../packages/core/agent-loop/tests/interception.spec.ts) pin compose-once reuse with no header deltas, prepend order, empty-prefix omission, immutability, and composition before pre-step; [cancellation tests](../../../../packages/core/agent-loop/tests/cancel.spec.ts) pin discard and recomposition. Session codec, invariant, and compaction tests cover header round trips, request reconstruction, and prefix-aware pressure accounting. Snapshot normalization preserves prefix counts, while the [pinned-header scenario](../testing/2026-07-06-pin-request-header-content-in-one-scenario.md) owns content and the default example remains prefix-free. No prefix-specific e2e is needed because the seam is deterministic and provider-independent; the with-key [request-cache e2e](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts) covers its cache economics. +[Interception tests](../../../../packages/core/agent-loop/tests/interception.spec.ts) pin compose-once reuse with no header deltas, prepend order, empty-prefix omission, immutability, composition before pre-step, and the prefix on the routed header; [cancellation tests](../../../../packages/core/agent-loop/tests/cancel.spec.ts) pin discard and recomposition. Session codec, invariant, token-meter, and compaction tests cover header round trips, request reconstruction, and durable prefix-aware pressure accounting. Snapshot normalization preserves prefix counts, while the [pinned-header scenario](../testing/2026-07-06-pin-request-header-content-in-one-scenario.md) owns content and the default example remains prefix-free. No prefix-specific e2e is needed because the seam is deterministic and provider-independent; the with-key [request-cache e2e](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts) covers its cache economics. ## Alternatives considered @@ -30,12 +30,12 @@ Because composition runs before the boundary snapshot, a composing listener's se - **A system-prompt section** (`system-prompt/assemble`) — rejected for this content: the assembly renders to the single `system` string, so message-shaped openers do not fit, and the system prompt is deliberately re-assembled per step (with header deltas when it changes) while the opener wants instance-frozen semantics. - **A durable history opener** (`inject()` at session start) — rejected: permanent history is the failure mode in the problem statement — replayed everywhere, compactable, stale across resumes. - **Compose per turn instead of per instance** — rejected: a turn-boundary recompose either desyncs silently from the log or forces a header delta per change, and it busts the provider cache exactly as often as it fires; the legitimate refresh point is the instance boundary, where the `'resume'` snapshot already records drift attributably. -- **Compose lazily at the first request and let compaction read the folded header** (the shape as first merged) — superseded in review: the fold matches the live prefix only from the instance's second request on, so on a resumed/forked instance's first step the pressure gate read the PREVIOUS instance's prefix and could under-gate. Composing before the first pre-step and handing the live value through the seam makes the estimate exact at every step. +- **Carry prompt/prefix through `agent/pre-step` for provisional pressure** — superseded by post-step replay. It coupled a generic lifecycle seam to one consumer and still missed later request routing/tools; the routed header is the exact durable home for all request-envelope fields. - **A dedicated session event carrying the prefix** — rejected: the header events are the request's non-history record by design; a second event would be a second home for the same fact and another codec to keep total. ## Consequences -- `agent/pre-step` and `CompactService.compactIfNeeded` carry a `sessionPrefix` parameter: every pre-step listener and compaction backend sees the real per-instance value (all in-repo implementations updated in the same change, per the pre-release stance). +- `agent/pre-step` stays a generic `(agent, turn, step, signal)` checkpoint. Compaction receives no prefix parameter; `ctx.tokenMeter` folds the prefix from the canonical routed header at post-step. - A contributor whose content changes mid-session is not re-read until the next instance — by design. A deployment needing mid-session catalog updates routes the change notice through the append-only history channels and pays one durable `context/message`. - The dropped `after` slot leaves no request-only channel near the request tail; nothing in the repo needs one, and adding it back would re-open the every-step re-pay cost the design exists to avoid. - The `request/header-delta` `messagePrefix` arm (whole-array replacement, empty array encoding transition to absence) exists for codec totality; the loop never exercises it, because the cached prefix cannot change within an instance. diff --git a/examples/coding-agent/cordis.yml b/examples/coding-agent/cordis.yml index 1208480388..281ae3e9d1 100644 --- a/examples/coding-agent/cordis.yml +++ b/examples/coding-agent/cordis.yml @@ -49,8 +49,8 @@ - id: token-meter name: '@deepseek-ai/dsh-token-meter' -# Summarize an older range when measured history approaches the context window. -# Built-in model policies provide the ordinary threshold and retained-tail defaults. +# Summarize an older range after measured pressure or a canonical provider overflow. +# Built-in policies provide pressure, retention, and one overflow-retry default. - id: compact-basic name: '@deepseek-ai/dsh-compact-basic' diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index c9264e2e99..b3b910cfb7 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -8,13 +8,14 @@ This is the implementation tier of the compaction capability — see the [interf This backend owns the compaction policy: -- **Measurement** — the effective conversation model's `ModelTokenMeter` prices the provisional request envelope and current surface at one consumed-log revision. The current prompt and prefix override their logged values; the pre-step boundary reuses logged tools and call config. +- **Measurement** — the latest durable routed request model's `ModelTokenMeter` prices the canonical logged envelope and current surface at one consumed-log revision. Post-step pressure therefore includes the actual system prompt, tools, prefix, routing, assistant completion, tool results, buffered context, and steering. - **Retention** — compact the oldest whole surface units while preserving a recent tail and balanced tool-call/result cuts through the [`dsh-compact` boundary helpers](../compact/README.md#tool-pairing-boundaries). Turn boundaries do not protect old steps inside a runaway turn. An open indivisible tail declines until it closes; a single unit larger than the budget remains out of scope. - **Convergence** — retry head-checkpoint compaction up to `compactionRetries`; reject a summary that does not shrink its source, and throw if retries cannot return below threshold. - **Summarization** — a direct `llm/stream` call uses the configured model and cap without running the loop-only `agent/request` seam. The input transcript preserves non-text blocks as tagged placeholders; only returned text enters the checkpoint, excluding reasoning and tool calls that would leak private reasoning or create an orphaned call. - **Framing** — the replacement user message marks established checkpoint context with `` tags. The raw summary remains on the provenance event, and later automatic cycles merge the prior checkpoint. -- **Lifecycle** — `compactRegion()` requires its agent to own the exact target session and rejects mismatch before resolution or mutation; a valid call records its start, summary, replacement, and end. The serial `agent/pre-step` listener checks pressure before every step, outside an open step, so a tool-heavy turn remains compactable and the loop derives history once after mutation. -- **Failure handling** — an unmatched `compact/start` is an inert crash marker because no replacement landed. Recoverable failure records an error end and leaves the surface unchanged. +- **Lifecycle** — `compactRegion()` requires its agent to own the exact target session and rejects mismatch before resolution or mutation; a valid call records its start, summary, replacement, and end. The serial `agent/post-step` listener checks pressure after successful output and tool work are durable but before `step/end`. Canonical provider overflow is handled through `agent/request-error` after the failed step closes. +- **Overflow recovery** — below-threshold overflow bypasses normal retention and attempts one maximal balanced head reduction while leaving the newest indivisible unit. Retry is authorized only when `surface.replaceGeneration` advances; no range, no replacement, recovery failure, an exhausted cap, cancellation, or an unknown/noncanonical error preserves the original provider failure. +- **Failure handling** — an unmatched `compact/start` is an inert crash marker because no replacement landed. Operational post-step failures warn and continue, while an actually routed model without a meter profile fails the otherwise-successful turn with the typed meter error. `summarize()` is the sole subclass hook. A template- or remote-summarizer subclass can override it while pressure, retention, provenance, shrink validation, and shadowed-token accounting stay on the conversation model's meter. The hook returns the summary blocks together with the call envelope it used (`{ summary, model, maxTokens? }`), which is logged on `compact/summary`. @@ -29,7 +30,8 @@ Every common setting is optional. Every model known to `ctx.tokenMeter` receives | `summarizationModel` | no (default `''`) | Empty resolves the latest logged routed model, then `AgentOptions.model`. | | `maxTokens` | no (default `8192`) | Provider generation cap for the summarization call; may include reasoning tokens. | | `compactionRetries` | no (default `1`) | Extra attempts after the first when pressure remains above threshold. | -| `auto` | no (default `true`) | Register the `agent/pre-step` automatic listener. Set `false` for manual-only. | +| `maxOverflowRetries` | no (default `1`) | Maximum retries after canonical context-window overflow; `0` disables recovery only. | +| `auto` | no (default `true`) | Register post-step pressure and overflow-recovery listeners. Set `false` for manual-only. | ## Usage @@ -39,7 +41,7 @@ import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' import TokenMeterService from '@deepseek-ai/dsh-token-meter' export const name = 'compact-basic' -export const inject = ['llm'] +export const inject = ['llm', 'tokenMeter'] export function apply(ctx: Context): void { ctx.plugin(TokenMeterService) @@ -53,7 +55,7 @@ Loading the plugin registers `ctx.compact`. With `auto: true` (the default) it c ### Conversation history -**What the model sees**: Before a step whose estimated envelope and history exceed the threshold, the conversation model receives the checkpoint preamble below, a blank line, ``, the data-dependent summary, and ``. This one checkpoint replaces the selected older range and is followed by the retained recent units. +**What the model sees**: After a successful step crosses the threshold, the next request receives the checkpoint preamble below, a blank line, ``, the data-dependent summary, and ``. Overflow recovery rebuilds the immediate retry from that replacement. This one checkpoint replaces the selected older range and is followed by the retained recent units. **Token effect**: The replacement reduces future input history rather than appending a second copy. The summary remains until a later compaction replaces it; one oversized indivisible unit can still exceed the budget. @@ -115,8 +117,9 @@ Rules: ## Known Limitations and Deferred Work -- **Pre-step sees a provisional request envelope** — the current prompt and prefix are exact, but routing and tool changes made later in `agent/request` are not logged yet. A router-only agent with no provisional model skips that check. - **Meter accuracy follows the selected profile** — missing provider usage falls back to the token meter's configured character density and structural overhead. +- **Overflow classification is adapter-maintained** — provider wording can change; both DeepSeek adapters normalize currently recognized context-limit failures to `CONTEXT_WINDOW_EXCEEDED`. +- **Single-unit and envelope-only overflow remain outside surface compaction** — recovery cannot split one indivisible message/tool unit or shrink system/tools/prefix. - **`compactRegion` requires an open turn** — a manual call on a fully-closed session throws ("no open turn") rather than compacting. - **Summarization failure fails closed with full, over-budget history** — including truncation at the summarization `maxTokens`, which hidden reasoning tokens can consume; the auto path logs a warning and proceeds. - **The summarization call has no transcript-snapshot coverage** — `dsh-llm-replay` derives calls from `assistant/chunk` events, so this chunk-less direct `ctx.llm.stream()` call cannot replay (named deferred replay infrastructure in [the seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)). diff --git a/packages/compact/compact-basic/src/automatic.ts b/packages/compact/compact-basic/src/automatic.ts index 504b0d8a9f..16e71c081a 100644 --- a/packages/compact/compact-basic/src/automatic.ts +++ b/packages/compact/compact-basic/src/automatic.ts @@ -1,12 +1,12 @@ /** - * Automatic pre-step pressure listener for compact-basic. + * Automatic post-step pressure and context-overflow recovery listeners. * * @module @deepseek-ai/dsh-compact-basic/automatic */ import type { Context } from 'cordis' -import type { CompactionResult } from '@deepseek-ai/dsh-compact' -import type { Message } from '@deepseek-ai/dsh-llm' +import type { CompactionResult, CompactionTrigger } from '@deepseek-ai/dsh-compact' +import { CONTEXT_WINDOW_EXCEEDED_CODE } from '@deepseek-ai/dsh-llm' import { TOKEN_METER_MODEL_UNCONFIGURED, TokenMeterError, @@ -14,10 +14,10 @@ import { import type { Agent } from '@deepseek-ai/dsh-agent' interface AutomaticCompactor { + readonly config: { readonly maxOverflowRetries: number } compactIfNeeded( agent: Agent, - fullSystemPrompt: string, - sessionPrefix: readonly Message[], + trigger: CompactionTrigger, signal: AbortSignal, ): Promise } @@ -31,30 +31,54 @@ export function registerAutomaticCompaction( ctx: Context, service: AutomaticCompactor, ): void { - ctx.on('agent/pre-step', async ( + const logResult = (result: CompactionResult, trigger: string): void => { + ctx.logger.info( + `compaction (${trigger}): shadowed ${result.shadowedSeqs.length} surface nodes ` + + `(seqs ${result.shadowedRange.start}-${result.shadowedRange.end}, ` + + `~${result.shadowedTokenCount} tokens)`, + ) + } + + ctx.on('agent/post-step', async ( agent: Agent, _turn: number, _step: number, - fullSystemPrompt: string, - sessionPrefix: readonly Message[], signal: AbortSignal, ) => { try { - const result = await service.compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal) - if (result !== null) { - ctx.logger.info( - `compaction: shadowed ${result.shadowedSeqs.length} surface nodes ` - + `(seqs ${result.shadowedRange.start}-${result.shadowedRange.end}, ` - + `~${result.shadowedTokenCount} tokens)`, - ) - } + const result = await service.compactIfNeeded(agent, 'pressure', signal) + if (result !== null) logResult(result, 'post-step pressure') } catch (error: unknown) { // A named routed model without a meter profile is configuration failure, // not an optional operational compaction miss. if (error instanceof TokenMeterError && error.code === TOKEN_METER_MODEL_UNCONFIGURED) throw error const message = error instanceof Error ? error.message : String(error) - ctx.logger.warn(`compaction failed: ${message}; proceeding with full history`) + ctx.logger.warn(`post-step compaction failed: ${message}; continuing the turn`) } }) + + ctx.on('agent/request-error', async (agent, _turn, _step, error, retryAttempt, signal, next) => { + if (error.code !== CONTEXT_WINDOW_EXCEEDED_CODE + || retryAttempt >= service.config.maxOverflowRetries + || signal.aborted) return next() + + let generation: number + let result: CompactionResult | null + try { + generation = agent.session.surface.replaceGeneration + result = await service.compactIfNeeded(agent, 'context-overflow', signal) + } catch (recoveryError: unknown) { + const message = recoveryError instanceof Error ? recoveryError.message : String(recoveryError) + ctx.logger.warn( + `context-overflow compaction failed: ${message}; preserving the original request error`, + ) + return next() + } + // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while compaction is awaited. + if (signal.aborted || result === null + || agent.session.surface.replaceGeneration <= generation) return next() + logResult(result, 'context overflow recovery') + return { action: 'retry' } + }) } diff --git a/packages/compact/compact-basic/src/config.ts b/packages/compact/compact-basic/src/config.ts index 3169d7f5aa..e4d567da3b 100644 --- a/packages/compact/compact-basic/src/config.ts +++ b/packages/compact/compact-basic/src/config.ts @@ -47,6 +47,7 @@ export function resolveConfig( summarizationModel: '', maxTokens: 8192, compactionRetries: 1, + maxOverflowRetries: 1, auto: true, }, meter) } @@ -56,10 +57,12 @@ export function resolveConfig( summarizationModel: config.summarizationModel ?? '', maxTokens: config.maxTokens ?? 8192, compactionRetries: config.compactionRetries ?? 1, + maxOverflowRetries: config.maxOverflowRetries ?? 1, auto: config.auto ?? true, } assertPositiveInteger('maxTokens', resolved.maxTokens) assertNonNegativeInteger('compactionRetries', resolved.compactionRetries) + assertNonNegativeInteger('maxOverflowRetries', resolved.maxOverflowRetries) if (typeof resolved.summarizationModel !== 'string') { throw new Error('BasicCompactConfig: summarizationModel must be a string') } diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index cd4ea5d1d5..d420851166 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -7,10 +7,9 @@ import { Context } from 'cordis' import z from 'schemastery' import { CompactService } from '@deepseek-ai/dsh-compact' -import type { CompactionResult } from '@deepseek-ai/dsh-compact' -import { canonicalHeader } from '@deepseek-ai/dsh-session' -import type { EpochHeader, Session } from '@deepseek-ai/dsh-session' -import type { ContentBlock, Message } from '@deepseek-ai/dsh-llm' +import type { CompactionResult, CompactionTrigger } from '@deepseek-ai/dsh-compact' +import type { Session } from '@deepseek-ai/dsh-session' +import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { ModelTokenMeter } from '@deepseek-ai/dsh-token-meter' import type { Agent } from '@deepseek-ai/dsh-agent' import { registerAutomaticCompaction } from './automatic.ts' @@ -36,24 +35,10 @@ function effectiveModel(agent: Agent): string | undefined { return agent.session.requestHeader()?.config.model ?? agent.options.model } -/** - * Build the provisional pre-step request envelope. Prompt and prefix are exact; - * tools and non-model call config come from the latest logged request because - * later request middleware has not run yet. - */ -function provisionalHeader( - model: string, - session: Session, - fullSystemPrompt: string, - sessionPrefix: readonly Message[], -): EpochHeader { - const latest = session.requestHeader() - return canonicalHeader({ - config: latest === undefined ? { model } : { ...latest.config, model }, - ...fullSystemPrompt.length === 0 ? {} : { system: fullSystemPrompt }, - ...latest?.tools === undefined ? {} : { tools: latest.tools }, - ...sessionPrefix.length === 0 ? {} : { messagePrefix: [...sessionPrefix] }, - }) +/** Resolve the exact model durably routed for the latest provider request. */ +function routedModel(session: Session): string | undefined { + const model = session.requestHeader()?.config.model + return model === undefined || model.length === 0 ? undefined : model } /** @@ -75,6 +60,7 @@ export class BasicCompactService extends CompactService { summarizationModel: z.string().default(''), maxTokens: z.number().step(1).min(1).default(8192), compactionRetries: z.number().step(1).min(0).default(1), + maxOverflowRetries: z.number().step(1).min(0).default(1), auto: z.boolean().default(true), }) @@ -106,29 +92,33 @@ export class BasicCompactService extends CompactService { } /** - * Check replayed pressure for the provisional pre-step envelope and compact - * a tool-balanced head until it falls below the effective model threshold. - * A genuinely model-less router-first step skips this provisional check; - * naming an unconfigured model throws the token meter's typed error. - * @param agent - agent whose session and provisional model are measured. - * @param fullSystemPrompt - current assembled system prompt override. - * @param sessionPrefix - current request-only prefix override. - * @param signal - live step cancellation signal forwarded to summarization. + * Compact for replayed post-step pressure or one provider-confirmed context + * overflow. Both triggers price the latest durable routed request model; + * overflow bypasses the normal threshold and retained-tail policy so it can + * force one useful balanced reduction. + * @param agent - agent whose latest durable routed request is measured. + * @param trigger - normal post-step pressure or context-overflow recovery. + * @param signal - live turn cancellation signal forwarded to summarization. * @returns the latest compaction result, or `null` when no check/work applies. */ override async compactIfNeeded( agent: Agent, - fullSystemPrompt: string, - sessionPrefix: readonly Message[], + trigger: CompactionTrigger, signal: AbortSignal, ): Promise { - const model = effectiveModel(agent) - if (model === undefined || model.length === 0) return null + const model = routedModel(agent.session) + if (model === undefined) return null const meter = this.ctx.tokenMeter.resolve(model) const policy = this._modelConfig(meter) - const requestHeader = provisionalHeader(model, agent.session, fullSystemPrompt, sessionPrefix) + if (trigger === 'context-overflow') { + const surface = meter.measureSurface(agent.session) + const range = selectCompactableRange(agent.session, surface, 0) + if (range === null) return null + return this.compactRegion(agent.session, range.start, range.end, agent, signal) + } + const threshold = Math.floor(policy.contextWindow * policy.thresholdRatio) - let measurement = meter.measure(agent.session, requestHeader) + let measurement = meter.measure(agent.session) if (measurement.totalTokens < threshold) return null let result: CompactionResult | null = null @@ -147,7 +137,7 @@ export class BasicCompactService extends CompactService { break } result = await this.compactRegion(agent.session, range.start, range.end, agent, signal) - measurement = meter.measure(agent.session, requestHeader) + measurement = meter.measure(agent.session) if (measurement.totalTokens < threshold) return result } diff --git a/packages/compact/compact-basic/src/summarizer.ts b/packages/compact/compact-basic/src/summarizer.ts index 359421f0f5..78730cc1a6 100644 --- a/packages/compact/compact-basic/src/summarizer.ts +++ b/packages/compact/compact-basic/src/summarizer.ts @@ -106,7 +106,7 @@ export async function summarizeWithLlm( if (!summary.some(block => block.text.trim().length > 0)) { throw new Error('summarization produced no text summary content') } - return { summary, model, maxTokens: config.maxTokens } + return { summary, model: options.model, maxTokens: config.maxTokens } } /** diff --git a/packages/compact/compact-basic/src/types.ts b/packages/compact/compact-basic/src/types.ts index 44ff06435d..4a3f372e08 100644 --- a/packages/compact/compact-basic/src/types.ts +++ b/packages/compact/compact-basic/src/types.ts @@ -22,7 +22,9 @@ export interface BasicCompactConfig { maxTokens?: number /** Extra attempts after the first compaction when pressure remains above threshold. Defaults to `1`. */ compactionRetries?: number - /** Enable the automatic `agent/pre-step` pressure listener. Defaults to `true`. */ + /** Maximum retries after canonical context overflow; `0` disables recovery. Defaults to `1`. */ + maxOverflowRetries?: number + /** Enable automatic post-step pressure and overflow-recovery listeners. Defaults to `true`. */ auto?: boolean } @@ -32,6 +34,7 @@ export interface ResolvedConfig { readonly summarizationModel: string readonly maxTokens: number readonly compactionRetries: number + readonly maxOverflowRetries: number readonly auto: boolean } diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 98b4b2f15b..163c2b6b45 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -6,9 +6,10 @@ import BasicCompactService, { } from '@deepseek-ai/dsh-compact-basic' import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic' import { selectCompactableRange } from '@deepseek-ai/dsh-compact-basic/src/region.ts' +import { toolPairingBalancedAfter, toolPairingBalancedBefore } from '@deepseek-ai/dsh-compact' import type { CompactionResult } from '@deepseek-ai/dsh-compact' -import LlmService, { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' -import type { ContentBlock, GenerateOptions, Message, StreamChunk } from '@deepseek-ai/dsh-llm' +import LlmService, { CallId, CONTEXT_WINDOW_EXCEEDED_CODE, LlmAdapter } from '@deepseek-ai/dsh-llm' +import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { Session, SessionId } from '@deepseek-ai/dsh-session' import TokenMeterService, { TOKEN_METER_MODEL_UNCONFIGURED, @@ -43,6 +44,12 @@ function conversation(turns = 4, text = 'fixture'): Session { source: { kind: 'user' }, }, { surfaceOp: 'append' }) session.append('step/start', { turn, step: 1 }) + if (turn === 1) { + session.append('request/header', { + header: { config: { model: MODEL } }, + reason: 'initial', + }) + } session.append('assistant/message', { turn, step: 1, @@ -68,6 +75,12 @@ function toolConversation(): Session { source: { kind: 'user' }, }, { surfaceOp: 'append' }) session.append('step/start', { turn, step: 1 }) + if (turn === 1) { + session.append('request/header', { + header: { config: { model: MODEL } }, + reason: 'initial', + }) + } session.append('assistant/message', { turn, step: 1, @@ -120,11 +133,10 @@ function service( async function compactIfNeeded( compact: BasicCompactService, session: Session, + trigger: 'pressure' | 'context-overflow' = 'pressure', model: string | undefined = MODEL, - system = '', - prefix: readonly Message[] = [], ): Promise { - return compact.compactIfNeeded(agent(session, model), system, prefix, SIGNAL) + return compact.compactIfNeeded(agent(session, model), trigger, SIGNAL) } describe('compact configuration and defaults', () => { @@ -140,6 +152,7 @@ describe('compact configuration and defaults', () => { summarizationModel: '', maxTokens: 8192, compactionRetries: 1, + maxOverflowRetries: 1, auto: true, }) expect(resolveModelConfig(resolved, ctx.tokenMeter.resolve(MODEL))).toEqual({ @@ -176,6 +189,7 @@ describe('compact configuration and defaults', () => { const bad = [ [{ maxTokens: 0 }, /maxTokens/], [{ compactionRetries: -1 }, /compactionRetries/], + [{ maxOverflowRetries: -1 }, /maxOverflowRetries/], [{ auto: 'yes' }, /auto must be a boolean/], [{ summarizationModel: 1 }, /summarizationModel must be a string/], [{ models: null }, /models must be an object/], @@ -207,19 +221,57 @@ describe('pressure measurement and retention', () => { models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, } - it('skips the provisional check only when no routed or fallback model exists', async () => { + it('skips when no durable routed model exists instead of using AgentOptions fallback', async () => { const compact = service(compactConfig) - const session = conversation() - expect(await compact.compactIfNeeded(agent(session), '', [], SIGNAL)).toBeNull() + const session = new Session(SessionId('headerless')) + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + await expect(compact.compactIfNeeded(agent(session, MODEL), 'pressure', SIGNAL)) + .resolves.toBeNull() expect(compact.calls).toHaveLength(0) }) it('throws for a named unconfigured model instead of swallowing it', async () => { const compact = service(compactConfig) - await expect(compactIfNeeded(compact, conversation(), 'missing')) + const session = conversation() + session.append('request/header', { + header: { config: { model: 'missing' } }, + reason: 'resume', + }) + await expect(compactIfNeeded(compact, session)) .rejects.toMatchObject({ code: TOKEN_METER_MODEL_UNCONFIGURED, model: 'missing' }) }) + it('declines forced overflow when the whole surface is one indivisible tool pair', async () => { + const compact = service(compactConfig) + const session = new Session(SessionId('single-tool-pair')) + const callId = CallId('single-call') + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + session.append('step/start', { turn: 1, step: 1 }) + session.append('request/header', { + header: { config: { model: MODEL } }, + reason: 'initial', + }) + session.append('assistant/message', { + turn: 1, + step: 1, + content: [{ type: 'tool-call', id: callId, name: 'read', arguments: '{}' }], + }, { surfaceOp: 'append' }) + session.append('tool/call', { turn: 1, step: 1, callId, name: 'read', arguments: '{}' }) + session.append('tool/result', { + turn: 1, + step: 1, + callId, + content: [{ type: 'text', text: 'result' }], + isError: false, + }, { surfaceOp: 'append' }) + session.append('step/end', { turn: 1, step: 1 }) + const generation = session.surface.replaceGeneration + + await expect(compactIfNeeded(compact, session, 'context-overflow')).resolves.toBeNull() + expect(session.surface.replaceGeneration).toBe(generation) + expect(session.events.some(event => event.type === 'compact/start')).toBe(false) + }) + it('does nothing below threshold and compacts a priced head above threshold', async () => { const compact = service(compactConfig) expect(await compactIfNeeded(compact, conversation(2))).toBeNull() @@ -231,7 +283,7 @@ describe('pressure measurement and retention', () => { expect(session.surface.nodes.length).toBeLessThan(8) }) - it('counts the current prompt and request prefix without putting either on the surface', async () => { + it('counts the durable routed request envelope without putting its prefix on the surface', async () => { const compact = service({ auto: false, models: { [MODEL]: { thresholdRatio: 0.7, retainTokens: 9 } }, @@ -239,11 +291,16 @@ describe('pressure measurement and retention', () => { const session = conversation(2, 'x'.repeat(2_000)) expect(await compactIfNeeded(compact, session)).toBeNull() - const prefix: Message[] = [{ - role: 'user', - content: [{ type: 'text', text: 'p'.repeat(10_000) }], - }] - const result = await compactIfNeeded(compact, session, MODEL, 's'.repeat(5_000), prefix) + const prefix = [{ role: 'user' as const, content: [{ type: 'text' as const, text: 'p'.repeat(10_000) }] }] + session.append('request/header', { + header: { + config: { model: MODEL }, + system: 's'.repeat(5_000), + messagePrefix: prefix, + }, + reason: 'resume', + }) + const result = await compactIfNeeded(compact, session) expect(result).not.toBeNull() expect(prefix).toHaveLength(1) expect(session.events.some(event => event.type === 'context/message')).toBe(false) @@ -264,17 +321,26 @@ describe('pressure measurement and retention', () => { reason: 'initial', }) - const result = await compactIfNeeded(compact, session, 'fallback') + const result = await compactIfNeeded(compact, session, 'pressure', 'fallback') expect(result).not.toBeNull() }) it('declines when envelope pressure is high but the surface has no compactable range', async () => { const compact = service(compactConfig) const empty = new Session(SessionId('empty')) - expect(await compactIfNeeded(compact, empty, MODEL, 'x'.repeat(100_000))).toBeNull() + empty.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + empty.append('request/header', { + header: { config: { model: MODEL }, system: 'x'.repeat(100_000) }, + reason: 'initial', + }) + expect(await compactIfNeeded(compact, empty)).toBeNull() const retained = conversation(1) - expect(await compactIfNeeded(compact, retained, MODEL, 'x'.repeat(100_000))).toBeNull() + retained.append('request/header', { + header: { config: { model: MODEL }, system: 'x'.repeat(100_000) }, + reason: 'resume', + }) + expect(await compactIfNeeded(compact, retained)).toBeNull() }) it('detects scalar/surface revision disagreement', async () => { @@ -587,7 +653,19 @@ describe('compaction region transaction', () => { it('requires a conversation model for pricing', async () => { const compact = service() - const session = conversation(1) + const session = new Session(SessionId('model-less-region')) + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + session.append('user/message', { + content: [{ type: 'text', text: 'history' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + session.append('step/start', { turn: 1, step: 1 }) + session.append('assistant/message', { + turn: 1, + step: 1, + content: [{ type: 'text', text: 'answer' }], + }, { surfaceOp: 'append' }) + session.append('step/end', { turn: 1, step: 1 }) const nodes = session.surface.nodes await expect(compact.compactRegion( session, @@ -679,6 +757,25 @@ describe('default one-shot summarizer', () => { expect(adapter.lastOptions?.model).toBe('routed') }) + it('records the model actually dispatched after one-shot stream routing', async () => { + const { ctx, compact } = await summarizerHarness([{ type: 'text', text: 'unused' }]) + const routedAdapter = new ScriptedAdapter([{ type: 'text', text: 'routed summary' }]) + ctx.llm.registerAdapter(['routed-summary-model'], routedAdapter) + ctx.on('llm/stream', (options, next) => { + options.model = 'routed-summary-model' + return next() + }) + + const session = conversation(3, 'large history '.repeat(500)) + const nodes = session.surface.nodes + await compact.compactRegion(session, nodes[0]!.seq, nodes[3]!.seq, agent(session, MODEL), SIGNAL) + expect(session.events.findLast(event => event.type === 'compact/summary')?.data).toMatchObject({ + summary: [{ type: 'text', text: 'routed summary' }], + model: 'routed-summary-model', + }) + expect(routedAdapter.lastOptions?.model).toBe('routed-summary-model') + }) + it('fails clearly when no summarization model can be resolved', async () => { const ctx = new Context() await ctx.plugin(LlmService) @@ -717,21 +814,36 @@ describe('default one-shot summarizer', () => { }) describe('automatic listener and loader composition', () => { - function preStep(ctx: Context, owner: Agent): Promise { - return ctx.serial('agent/pre-step', owner, 1, 1, '', [], SIGNAL) + function postStep(ctx: Context, owner: Agent, signal = SIGNAL): Promise { + return ctx.serial('agent/post-step', owner, 1, 1, signal) } - it('compacts above threshold and remains idle below it', async () => { + function recover( + ctx: Context, + owner: Agent, + error: Error & { code?: string }, + retryAttempt = 0, + signal = SIGNAL, + next: () => Promise<{ action: 'fail' | 'retry' }> = () => Promise.resolve({ action: 'fail' }), + ): Promise<{ action: 'fail' | 'retry' }> { + return ctx.waterfall('agent/request-error', owner, 1, 1, error, retryAttempt, signal, next) + } + + function overflow(message = 'provider overflow'): Error & { code: string } { + return Object.assign(new Error(message), { code: CONTEXT_WINDOW_EXCEEDED_CODE }) + } + + it('compacts post-step above threshold using the durable routed model and remains idle below it', async () => { const ctx = createContext() const compact = new TestCompactService(ctx, { models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, }) const pressured = conversation(4) - await preStep(ctx, agent(pressured, MODEL)) + await postStep(ctx, agent(pressured, 'unconfigured-agent-fallback')) expect(pressured.events.some(event => event.type === 'compact/summary')).toBe(true) const small = conversation(1) - await preStep(ctx, agent(small, MODEL)) + await postStep(ctx, agent(small, MODEL)) expect(small.events.some(event => event.type === 'compact/start')).toBe(false) expect(compact.calls).toHaveLength(1) }) @@ -746,7 +858,7 @@ describe('automatic listener and loader composition', () => { compact.error = 'temporary failure' const session = conversation(4) - await expect(preStep(ctx, agent(session, MODEL))).resolves.toBeUndefined() + await expect(postStep(ctx, agent(session, MODEL))).resolves.toBeUndefined() expect(warnings).toContainEqual(expect.stringContaining('temporary failure')) expect(session.events.some(event => event.type === 'compact/summary')).toBe(false) }) @@ -754,21 +866,210 @@ describe('automatic listener and loader composition', () => { it('propagates a named unknown-model configuration failure', async () => { const ctx = createContext() void new TestCompactService(ctx) - await expect(preStep(ctx, agent(conversation(4), 'missing'))).rejects.toMatchObject({ + const session = conversation(4) + session.append('request/header', { + header: { config: { model: 'missing' } }, + reason: 'resume', + }) + await expect(postStep(ctx, agent(session, MODEL))).rejects.toMatchObject({ code: TOKEN_METER_MODEL_UNCONFIGURED, model: 'missing', }) }) - it('auto:false installs no listener', async () => { + it('force-compacts below normal pressure for canonical overflow and retries only after replacement', async () => { + const ctx = createContext() + void new TestCompactService(ctx, { + models: { [MODEL]: { thresholdRatio: 1, retainTokens: 90 } }, + }) + const session = conversation(3) + const beforeGeneration = session.surface.replaceGeneration + const retainedSeq = session.surface.nodes.at(-1)!.seq + const threshold = 100 + expect(ctx.tokenMeter.resolve(MODEL).measure(session).totalTokens).toBeLessThan(threshold) + const decision = await recover(ctx, agent(session, 'unconfigured-agent-fallback'), overflow()) + + expect(decision).toEqual({ action: 'retry' }) + expect(session.surface.replaceGeneration).toBe(beforeGeneration + 1) + expect(session.events.some(event => event.type === 'compact/summary')).toBe(true) + expect(session.surface.nodes.some(node => node.seq === retainedSeq)).toBe(true) + }) + + it('preserves the newest whole tool-call/result pair during forced overflow compaction', async () => { + const ctx = createContext() + void new TestCompactService(ctx, { + models: { [MODEL]: { thresholdRatio: 1, retainTokens: 90 } }, + }) + const session = toolConversation() + const newestAssistant = session.surface.nodes.at(-2)! + const newestResult = session.surface.nodes.at(-1)! + + expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' }) + const currentAssistant = session.surface.nodes.find(node => node.seq === newestAssistant.seq) + const currentResult = session.surface.nodes.find(node => node.seq === newestResult.seq) + expect(currentAssistant).toBeDefined() + expect(currentResult).toBeDefined() + expect(toolPairingBalancedBefore(session, currentAssistant!)).toBe(true) + expect(toolPairingBalancedAfter(session, currentResult!)).toBe(true) + }) + + it('does not retry when a backend reports success without replacing the surface', async () => { + const ctx = createContext() + const compact = new TestCompactService(ctx) + const session = conversation(2) + const fakeResult: CompactionResult = { + startSeq: 1, + summarySeq: 2, + endSeq: 3, + summary: [{ type: 'text', text: 'fake' }], + shadowedRange: { start: 1, end: 2 }, + shadowedSeqs: [1, 2], + shadowedTokenCount: 10, + } + vi.spyOn(compact, 'compactIfNeeded').mockResolvedValue(fakeResult) + + expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'fail' }) + expect(session.surface.replaceGeneration).toBe(0) + }) + + it('delegates downstream exactly once when no replacement is available', async () => { + const ctx = createContext() + const compact = new TestCompactService(ctx) + vi.spyOn(compact, 'compactIfNeeded').mockResolvedValue(null) + const downstream = new Error('downstream recovery failed') + let calls = 0 + + await expect(recover( + ctx, + agent(conversation(2), MODEL), + overflow(), + 0, + SIGNAL, + () => { + calls += 1 + return Promise.reject(downstream) + }, + )).rejects.toBe(downstream) + expect(calls).toBe(1) + }) + + it('preserves the original provider error when recovery throws', async () => { + const ctx = createContext() + const warnings: string[] = [] + ctx.logger.warn = ((message: string) => void warnings.push(message)) as typeof ctx.logger.warn + const compact = new TestCompactService(ctx) + compact.error = new Error('summary unavailable') + const original = overflow('original provider overflow') + + expect(await recover(ctx, agent(conversation(3), MODEL), original)).toEqual({ action: 'fail' }) + expect(original).toMatchObject({ + message: 'original provider overflow', + code: CONTEXT_WINDOW_EXCEEDED_CODE, + }) + expect(warnings).toContainEqual(expect.stringContaining('preserving the original request error')) + }) + + it('delegates once when overflow recovery throws a non-Error value', async () => { + const ctx = createContext() + const warnings: string[] = [] + ctx.logger.warn = ((message: string) => void warnings.push(message)) as typeof ctx.logger.warn + const compact = new TestCompactService(ctx) + compact.error = 'non-error recovery failure' + const session = conversation(3) + const generation = session.surface.replaceGeneration + const original = overflow('original provider failure') + let delegations = 0 + + const decision = await recover(ctx, agent(session, MODEL), original, 0, SIGNAL, () => { + delegations += 1 + return Promise.resolve({ action: 'fail' }) + }) + + expect(decision).toEqual({ action: 'fail' }) + expect(delegations).toBe(1) + expect(session.surface.replaceGeneration).toBe(generation) + expect(original).toMatchObject({ + message: 'original provider failure', + code: CONTEXT_WINDOW_EXCEEDED_CODE, + }) + expect(warnings).toContainEqual(expect.stringContaining('non-error recovery failure')) + }) + + it('delegates once and preserves the original overflow for an unknown routed meter model', async () => { + const ctx = createContext() + void new TestCompactService(ctx) + const session = conversation(2) + session.append('request/header', { + header: { config: { model: 'unknown-routed-model' } }, + reason: 'resume', + }) + const original = overflow('original unknown-model overflow') + let delegations = 0 + + const decision = await recover(ctx, agent(session, MODEL), original, 0, SIGNAL, () => { + delegations += 1 + return Promise.resolve({ action: 'fail' }) + }) + expect(decision).toEqual({ action: 'fail' }) + expect(delegations).toBe(1) + expect(original).toMatchObject({ + message: 'original unknown-model overflow', + code: CONTEXT_WINDOW_EXCEEDED_CODE, + }) + }) + + it('honors retry caps, non-context failures, and cancellation', async () => { + const ctx = createContext() + const compact = new TestCompactService(ctx, { maxOverflowRetries: 1 }) + const compactSpy = vi.spyOn(compact, 'compactIfNeeded') + const owner = agent(conversation(3), MODEL) + expect(await recover(ctx, owner, Object.assign(new Error('rate limit'), { code: 'RATE_LIMIT' }))) + .toEqual({ action: 'fail' }) + expect(await recover(ctx, owner, overflow(), 1)).toEqual({ action: 'fail' }) + + const controller = new AbortController() + controller.abort('cancelled') + expect(await recover(ctx, owner, overflow(), 0, controller.signal)).toEqual({ action: 'fail' }) + expect(compactSpy).not.toHaveBeenCalled() + }) + + it('does not retry when cancellation lands during an awaited compaction', async () => { + const ctx = createContext() + const compact = new TestCompactService(ctx) + const controller = new AbortController() + compact.mutateDuringSummary = () => { controller.abort('cancelled during summary') } + const session = conversation(3) + const generation = session.surface.replaceGeneration + + expect(await recover(ctx, agent(session, MODEL), overflow(), 0, controller.signal)) + .toEqual({ action: 'fail' }) + expect(session.surface.replaceGeneration).toBe(generation + 1) + }) + + it('maxOverflowRetries:0 disables recovery without disabling post-step pressure', async () => { + const ctx = createContext() + void new TestCompactService(ctx, { + maxOverflowRetries: 0, + models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + }) + const session = conversation(4) + await postStep(ctx, agent(session, MODEL)) + const summaries = session.events.filter(event => event.type === 'compact/summary').length + expect(summaries).toBe(1) + expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'fail' }) + expect(session.events.filter(event => event.type === 'compact/summary')).toHaveLength(summaries) + }) + + it('auto:false installs neither automatic listener', async () => { const ctx = createContext() void new TestCompactService(ctx, { auto: false, models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, }) const session = conversation(4) - await preStep(ctx, agent(session, MODEL)) + await postStep(ctx, agent(session, MODEL)) expect(session.events.some(event => event.type === 'compact/start')).toBe(false) + expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'fail' }) }) it('loads and disposes the real zero-config service stack', async () => { @@ -797,8 +1098,9 @@ describe('automatic listener and loader composition', () => { await fiber.dispose() const session = conversation(4) - await preStep(ctx, agent(session, MODEL)) + await postStep(ctx, agent(session, MODEL)) expect(session.events.some(event => event.type === 'compact/start')).toBe(false) + expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'fail' }) }) }) diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index cc1111c5f1..2fe9725d77 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -1,7 +1,7 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import { toolPairingBalancedAfter, toolPairingBalancedBefore } from '@deepseek-ai/dsh-compact' -import LlmService from '@deepseek-ai/dsh-llm' +import LlmService, { CONTEXT_WINDOW_EXCEEDED_CODE, LlmError } from '@deepseek-ai/dsh-llm' import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' import SessionStore from '@deepseek-ai/dsh-session' @@ -53,6 +53,45 @@ class StepwiseToolAdapter extends LlmAdapter { } } +/** First conversation request overflows, then the rebuilt retry succeeds. */ +class OverflowRecoveryAdapter extends LlmAdapter { + readonly conversationRequests: GenerateOptions[] = [] + readonly summaryRequests: GenerateOptions[] = [] + + constructor(private readonly delivery: 'thrown' | 'in-band') { + super() + } + + override async * stream(options: GenerateOptions): AsyncIterable { + if (options.system?.includes('You are a compaction engine')) { + this.summaryRequests.push(options) + yield { type: 'block-start', index: 0, blockType: 'text' } + yield { type: 'block-end', index: 0, block: { type: 'text', text: 'RECOVERY CHECKPOINT' } } + yield { type: 'finish', reason: { kind: 'stop' } } + return + } + + this.conversationRequests.push(options) + if (this.conversationRequests.length === 1) { + if (this.delivery === 'thrown') { + throw new LlmError('request too large for model context', CONTEXT_WINDOW_EXCEEDED_CODE, 400) + } + yield { + type: 'finish', + reason: { + kind: 'error', + message: 'request too large for model context', + code: CONTEXT_WINDOW_EXCEEDED_CODE, + }, + } + return + } + yield { type: 'block-start', index: 0, blockType: 'text' } + yield { type: 'block-end', index: 0, block: { type: 'text', text: 'recovered' } } + yield { type: 'finish', reason: { kind: 'stop' } } + } +} + async function harness(toolSteps: number): Promise<{ ctx: Context; compact: ReproCompactService }> { const ctx = new Context() await ctx.plugin(LlmService) @@ -98,6 +137,53 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { } describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () => { + it('uses the model actually routed by agent/request for post-step pressure', async () => { + const { ctx } = await harness(8) + ctx.on('agent/request', async (_agent, _turn, _step, config) => ({ ...config, model: 'mock' })) + try { + const agent = ctx.agentLoop.create(AgentId('routed-pressure'), { + model: 'unconfigured-agent-fallback', + }) + agent.send([{ type: 'text', text: 'do a routed multi-step task' }]) + await waitForIdle(ctx, agent) + + expect(agent.session.requestHeader()?.config.model).toBe('mock') + expect(agent.session.events.some(event => event.type === 'compact/summary')).toBe(true) + expect(agent.session.events.at(-1)).toMatchObject({ + type: 'turn/end', + data: { reason: { kind: 'completed' } }, + }) + } finally { + await ctx.fiber.dispose() + } + }) + + it('runs automatic pressure after the current tool result and before step/end', async () => { + const { ctx } = await harness(4) + try { + const agent = ctx.agentLoop.create(AgentId('post-step-order'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'do tool work' }]) + await waitForIdle(ctx, agent) + + const events = [...agent.session.events] + const compactStart = events.find(event => event.type === 'compact/start') + expect(compactStart).toBeDefined() + const precedingResult = events.findLast(event => + event.type === 'tool/result' && event.seq < compactStart!.seq, + ) + if (precedingResult?.type !== 'tool/result') throw new Error('expected a durable tool result before compaction') + const stepEnd = events.find(event => + event.type === 'step/end' + && event.data.step === precedingResult.data.step + && event.seq > compactStart!.seq, + ) + expect(precedingResult.seq).toBeLessThan(compactStart!.seq) + expect(compactStart!.seq).toBeLessThan(stepEnd!.seq) + } finally { + await ctx.fiber.dispose() + } + }) + it('the head checkpoint the loop lands is a balanced cut on both sides', async () => { const { ctx } = await harness(8) try { @@ -130,3 +216,91 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () } }) }) + +describe('context-overflow recovery across the real loop and compact-basic', () => { + it.each(['thrown', 'in-band'] as const)( + 'force-compacts a %s overflow between failed and retry steps', + async (delivery) => { + const ctx = new Context() + const adapter = new OverflowRecoveryAdapter(delivery) + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(Invariants) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentLoop, { agents: [] }) + await ctx.plugin(TokenMeterService, { + models: { mock: { contextWindow: 128, charsPerToken: 4 } }, + }) + ctx.llm.registerAdapter(['mock'], adapter) + ctx.on('agent/request', async (_agent, _turn, _step, config) => ({ ...config, model: 'mock' })) + await ctx.plugin(BasicCompactService, { + models: { mock: { thresholdRatio: 1, retainTokens: 100 } }, + maxTokens: 64, + compactionRetries: 0, + maxOverflowRetries: 1, + }) + + try { + const agent = ctx.agentLoop.create(AgentId(`overflow-${delivery}`), { + model: 'unconfigured-agent-fallback', + }) + for (let turn = 1; turn <= 2; turn += 1) { + const sentinel = turn === 1 ? 'OLD HISTORY SENTINEL' : 'RECENT HISTORY' + agent.session.append('turn/start', { + turn, + trigger: { kind: 'message', source: { kind: 'user' } }, + }) + agent.session.append('user/message', { + content: [{ type: 'text', text: `${sentinel} ${'old context '.repeat(200)}` }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + agent.session.append('step/start', { turn, step: 1 }) + agent.session.append('assistant/message', { + turn, + step: 1, + content: [{ type: 'text', text: `historical response ${turn} ${'detail '.repeat(200)}` }], + }, { surfaceOp: 'append' }) + agent.session.append('step/end', { turn, step: 1 }) + agent.session.append('turn/end', { turn, reason: { kind: 'completed' } }) + } + + agent.send([{ type: 'text', text: 'continue from history' }]) + await agent.whenIdle() + + expect(adapter.conversationRequests).toHaveLength(2) + expect(adapter.summaryRequests).toHaveLength(1) + expect(JSON.stringify(adapter.conversationRequests[0]!.messages)).toContain('OLD HISTORY SENTINEL') + const retry = JSON.stringify(adapter.conversationRequests[1]!.messages) + expect(retry).toContain('RECOVERY CHECKPOINT') + expect(retry).not.toContain('OLD HISTORY SENTINEL') + + const events = [...agent.session.events] + const failedEnd = events.find(event => + event.type === 'step/end' && event.data.turn === 3 && event.data.step === 1, + )! + const retryStart = events.find(event => + event.type === 'step/start' && event.data.turn === 3 && event.data.step === 2, + )! + const compaction = events.filter(event => + event.type === 'compact/start' + || event.type === 'compact/summary' + || event.type === 'compact/end', + ) + expect(compaction.map(event => event.type)).toEqual([ + 'compact/start', + 'compact/summary', + 'compact/end', + ]) + expect(compaction.every(event => event.seq > failedEnd.seq && event.seq < retryStart.seq)).toBe(true) + expect(events.at(-1)).toMatchObject({ + type: 'turn/end', + data: { reason: { kind: 'completed' } }, + }) + } finally { + await ctx.fiber.dispose() + } + }, + ) +}) diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index 89aacbb09b..a4c94f6c3a 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -18,7 +18,7 @@ Both methods are **abstract** — the backend owns trigger policy, retention, ev | Member | Semantics | |---|---| -| `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` | Estimate the surface-derived history size; if over the backend's threshold, compact an older range via `compactRegion`, keeping recent context intact. Returns the `CompactionResult`, or `null` if nothing needed compacting. All parameters required — the loop's `agent/pre-step` checkpoint supplies the agent, assembled `fullSystemPrompt`, composed `sessionPrefix` (request-only messages every request carries but the derived history omits — the pressure estimate must count them), and turn `signal`. A backend's summarization request is a direct `ctx.llm.stream()` call (not a loop step), so per-call interception happens at `llm/stream`. | +| `compactIfNeeded(agent, trigger, signal)` | Consider automatic compaction for `trigger: 'pressure' \| 'context-overflow'`. A pressure trigger may apply the backend's threshold and retained-tail policy; a confirmed overflow may force a useful balanced reduction. Returns the `CompactionResult`, or `null` when no safe range exists. A backend's summarization request is a direct `ctx.llm.stream()` call (not a loop step), so per-call interception happens at `llm/stream`. | | `compactRegion(session, start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) into a single replacement node. The agent must own the exact target (`session === agent.session`); a backend rejects mismatch before model resolution, lock acquisition, summarization, or log mutation. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. | `compactIfNeeded` takes a required `signal`; `compactRegion`'s is optional. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The turn that the `compact/*` events belong to is recoverable from the owned session's log (the currently-open turn), so the backend stamps it from the log rather than trusting a caller-supplied value. @@ -72,6 +72,5 @@ Subclass `CompactService`, implement `compactIfNeeded` and `compactRegion`, and ## Known Limitations and Deferred Work - **No model-facing consumer tier yet** — `@deepseek-ai/dsh-tool-compact` (the `/compact` tool) is deferred; compaction is reachable only via direct `ctx.compact` calls or a backend's auto listener. -- **Single-unit overflow is out of contract** — one retained unit (a closed step or a large pasted `user/message`) alone exceeding the budget cannot be compacted; the call may go out over-budget. -- **A session prefix that alone approaches the window is a configuration error no backend fixes** — compaction shrinks derived history, never the prefix. -- **Request context injected by downstream `agent/request` listeners sits outside pressure accounting** — `compactIfNeeded` counts prefix, derived history, and system prompt only. +- **Single-unit overflow is out of contract** — one indivisible unit (a closed tool pair or a large pasted `user/message`) alone exceeding the budget cannot be compacted. +- **An envelope that alone approaches the window is not surface-compaction work** — compaction shrinks derived history, never the system prompt, tools, or session prefix. diff --git a/packages/compact/compact/src/index.ts b/packages/compact/compact/src/index.ts index 7361d38ef3..80058f6145 100644 --- a/packages/compact/compact/src/index.ts +++ b/packages/compact/compact/src/index.ts @@ -8,7 +8,6 @@ */ import { Context, Service } from 'cordis' -import type { Message } from '@deepseek-ai/dsh-llm' import type { Session } from '@deepseek-ai/dsh-session' import type { CompactionResult } from './types.ts' @@ -16,6 +15,9 @@ export type { CompactionResult } from './types.ts' export { renderContentBlocks, renderTranscript } from './render.ts' export { toolPairingBalancedAfter, toolPairingBalancedBefore } from './tool-pairing.ts' +/** Why automatic policy is asking a backend to consider compaction. */ +export type CompactionTrigger = 'pressure' | 'context-overflow' + /** Minimal agent context compaction needs without depending on the agent package. */ export interface CompactAgentContext { session: Session @@ -41,24 +43,20 @@ export abstract class CompactService extends Service { } /** - * Check token pressure and compact if the conversation is too large. - * Estimate the next request, including its session prefix, derived history, - * and system prompt. Above threshold, compact a head-anchored range ending at - * a balanced tool boundary and reconsolidate any prior automatic checkpoint. - * Return `null` when no compaction is needed or an open tail leaves no safe - * cutoff. A single oversized retained unit or prefix cannot be repaired here. + * Consider automatic compaction for one explicit trigger. Pressure policy + * uses the latest durable routed request, while context-overflow policy may + * force a useful balanced reduction even below the normal threshold. Return + * `null` when no safe range can be compacted. A single oversized retained + * unit or request envelope cannot be repaired through surface compaction. * * @param agent - agent context owning the session surface and model options. - * @param fullSystemPrompt - assembled system prompt, counted toward the estimate. - * @param sessionPrefix - the instance's composed session prefix, counted toward the - * estimate. + * @param trigger - normal pressure or provider-confirmed context overflow. * @param signal - cancellation signal; model-backed implementations must forward it. * @returns the compaction result, or `null` if no compaction was needed. */ abstract compactIfNeeded( agent: CompactAgentContext, - fullSystemPrompt: string, - sessionPrefix: readonly Message[], + trigger: CompactionTrigger, signal: AbortSignal, ): Promise diff --git a/packages/compact/compact/tests/compact.spec.ts b/packages/compact/compact/tests/compact.spec.ts index c4daa8cc5a..946b2e8b83 100644 --- a/packages/compact/compact/tests/compact.spec.ts +++ b/packages/compact/compact/tests/compact.spec.ts @@ -1,8 +1,7 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import { CompactService } from '@deepseek-ai/dsh-compact' -import type { CompactionResult } from '@deepseek-ai/dsh-compact' -import type { Message } from '@deepseek-ai/dsh-llm' +import type { CompactionResult, CompactionTrigger } from '@deepseek-ai/dsh-compact' import { Session, SessionId } from '@deepseek-ai/dsh-session' import type { CompactAgentContext } from '@deepseek-ai/dsh-compact' @@ -18,8 +17,7 @@ class StubCompactService extends CompactService { override async compactIfNeeded( _agent: CompactAgentContext, - _fullSystemPrompt: string, - _sessionPrefix: readonly Message[], + _trigger: CompactionTrigger, signal: AbortSignal, ): Promise { this.lastSignal = signal @@ -80,7 +78,7 @@ describe('CompactService seam', () => { const ctx = new Context() const svc = new StubCompactService(ctx) const session = new Session(SessionId('s')) - expect(await svc.compactIfNeeded(stubAgent(session), '', [], new AbortController().signal)).toBeNull() + expect(await svc.compactIfNeeded(stubAgent(session), 'pressure', new AbortController().signal)).toBeNull() }) it('compact/* events merge into SessionEventMap and are log-only', async () => { @@ -109,7 +107,7 @@ describe('CompactService seam', () => { await svc.compactRegion(session, 0, 0, stubAgent(session, 'm'), controller.signal) expect(svc.lastSignal).toBe(controller.signal) - await svc.compactIfNeeded(stubAgent(session), '', [], controller.signal) + await svc.compactIfNeeded(stubAgent(session), 'context-overflow', controller.signal) expect(svc.lastSignal).toBe(controller.signal) }) }) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 7aafb3ce8a..fad2094fa9 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -108,7 +108,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ key: 'compact', summary: 'Abstract compaction service.', methods: [ - 'abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise', + 'abstract compactIfNeeded( agent: CompactAgentContext, trigger: CompactionTrigger, signal: AbortSignal, ): Promise', 'abstract compactRegion( session: Session, start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise', ], }, @@ -289,8 +289,8 @@ export const EVENT_API: readonly EventApiEntry[] = [ { name: 'agent/pre-step', mode: 'serial', - signature: '\'agent/pre-step\'(this: Scoped, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void', - summary: 'Awaited serial checkpoint for session-surface mutation after prompt assembly and before `step/start`; appends land outside the pending step.', + signature: '\'agent/pre-step\'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void', + summary: 'Awaited serial checkpoint before `step/start`; appends land outside the pending step and are included when the loop derives request history.', }, { name: 'agent/prompt-submit', @@ -656,6 +656,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'CompactionResult', declaration: 'export interface CompactionResult {\n startSeq: number;\n summarySeq: number;\n endSeq: number;\n summary: ContentBlock[];\n shadowedRange: {\n start: number;\n end: number;\n };\n shadowedSeqs: number[];\n shadowedTokenCount: number;\n}', }, + { + name: 'CompactionTrigger', + declaration: 'export type CompactionTrigger = \'pressure\' | \'context-overflow\';', + }, { name: 'ConfinedArgv', declaration: 'export interface ConfinedArgv {\n argv: string[];\n enforcement: SandboxEnforcement;\n denialSignatures: readonly string[];\n runnerFailureSignatures: readonly string[];\n}', diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 864ff95e8c..70d7c16cf0 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -58,7 +58,7 @@ Plugin failure ends the current turn, not the loop. Only final adapter dispatch/ Everything that goes beyond "call the model, run the tools, repeat" belongs to plugins listening on the event taxonomy: - Hooks and policy: the relevant `agent/*` checkpoints plus the guarded `tools/pre-execute` → `tools/execute` → `tools/post-execute` → `tools/result` pipeline; exact signatures and modes live in the [generated event catalog](../../../docs/cordis-catalog/events.md) -- Compaction: `agent/pre-step` +- Compaction: pressure on `agent/post-step`; canonical context overflow on `agent/request-error` - Sandbox, permission, plan mode: `tools/pre-execute` for extensible deny/ask, `tools.guard()` for monotonic owner policy, `tools/post-execute` for result decisions, and `tools/result` for final observation - Sub-agents: implemented outside the loop as `ctx.subagents` providers; in-process providers use `ctx.agents.create()` and owned `AgentHandle` teardown, while child streaming/progress and background/poll collection remain deferred. - Persistence: `session/event` + `session/flush` diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index e749018f55..620cdd9fbc 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -276,7 +276,7 @@ async function runTurn( const abort = new AbortController() handle.setAbort(abort) - // Assemble once before pre-step so pressure checks and the request share the same prompt. + // Assemble once before pre-step so listener work and the request share one prompt value. const assembly = await ctx.systemPrompt.assemble(assembleContextFor(agent)) const fullSystemPrompt = renderPrompt(assembly) @@ -287,9 +287,9 @@ async function runTurn( break } - // Compose the request-only prefix once per loop instance before pressure - // checks. It precedes all derived history and is recorded only in the - // request header, not as session history. + // Compose the request-only prefix once per loop instance before the first + // request boundary. It precedes all derived history and is recorded only + // in the request header, not as session history. if (transmission.sessionPrefix === undefined) { const emptyPrefix: Message[] = deepFreeze([]) const composed = await events.waterfall( @@ -306,8 +306,8 @@ async function runTurn( transmission.sessionPrefix = deepFreeze(structuredClone(composed)) } - // Await surface mutations outside the step; pressure checks receive the pending prefix. - await events.serial('agent/pre-step', turn, step, fullSystemPrompt, transmission.sessionPrefix, abort.signal) + // Await surface mutations outside the step before snapshotting history. + await events.serial('agent/pre-step', turn, step, abort.signal) // Interruption landing during the pre-step seam: do not open an empty step. if (handle.isCancelled() || handle.isDisposed()) { diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index 4b37210993..d89e5b0b0e 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -118,7 +118,7 @@ describe('agent/prompt-submit', () => { it('a prompt-submit rewrite + additionalContext is VISIBLE to the agent/pre-step seam (merged ordering)', async () => { // Prompt rewrites and injected context land before `agent/pre-step`, so a - // compaction listener measures the current surface before the single derive. + // surface listener sees the current state before the single derive. const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) @@ -130,8 +130,7 @@ describe('agent/prompt-submit', () => { additionalContext: { content: [{ type: 'text', text: 'injected ctx' }], source: { kind: 'plugin', plugin: 'test' } }, })) - // The pre-step seam (where compaction lives) derives the surface it would act - // on. Capture what it sees on the first step. + // Capture the surface visible at the generic pre-step seam on the first step. let preStepDerived: string | undefined ctx.on('agent/pre-step', (subject, _turn, step) => { if (subject === agent && step === 1) preStepDerived = JSON.stringify(subject.session.deriveMessages()) @@ -375,7 +374,7 @@ describe('agent/session-prefix', () => { expect(agent.session.deriveMessages()[0]).toEqual({ role: 'user', content: [{ type: 'text', text: 'go' }] }) }) - it('composes before the first pre-step and hands the prefix to the seam (pressure gates see the real value)', async () => { + it('composes before the first pre-step and records the prefix on the request header', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) @@ -386,20 +385,15 @@ describe('agent/session-prefix', () => { order.push('compose') return [reminder, ...await next()] }) - const seen: (readonly Message[])[] = [] - ctx.on('agent/pre-step', (_agent, _turn, _step, _system, sessionPrefix) => { + ctx.on('agent/pre-step', () => { order.push('pre-step') - seen.push(sessionPrefix) }) send(agent, 'hi') await waitForIdle(ctx, agent) - // Composition precedes the pre-step seam, and the seam receives THIS - // instance's composed prefix — a token-pressure gate (compaction) counts - // what the request will actually carry, never a stale logged prefix. expect(order).toEqual(['compose', 'pre-step']) - expect(seen[0]).toEqual([reminder]) + expect(agent.session.requestHeader()?.messagePrefix).toEqual([reminder]) }) it('the canonical prepend pattern composes contributions in registration order', async () => { diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index f282301a2b..89d8cc306c 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -486,9 +486,8 @@ describe('agent loop', () => { it('agent/pre-step fires once per step before the step is opened', async () => { // Two steps (a tool call, then a final text turn) → two model calls → two - // pre-step fires, each carrying the assembled full system prompt, BEFORE - // the step is opened and its request is derived (the request the adapter - // sees reflects any surface state at fire time). + // pre-step fires BEFORE the step is opened and its request is derived (the + // request the adapter sees reflects any surface state at fire time). const adapter = new MockAdapter([ toolCallResponse('c1', 'echo', {}, 'calling echo'), textResponse('done'), @@ -500,21 +499,19 @@ describe('agent loop', () => { })) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - const fires: { turn: number; step: number; fullSystemPrompt: string }[] = [] - ctx.on('agent/pre-step', (subject, turn, step, fullSystemPrompt) => { - if (subject === agent) fires.push({ turn, step, fullSystemPrompt }) + const fires: { turn: number; step: number; signal: AbortSignal }[] = [] + ctx.on('agent/pre-step', (subject, turn, step, signal) => { + if (subject === agent) fires.push({ turn, step, signal }) }) send(agent, 'go') await waitForIdle(ctx, agent) - // One fire per step, in order, each with the assembled system prompt - // (here just the loop's own harness-identity section — no persona set). - const HARNESS = 'You are an AI agent powered by the DeepSeek Harness SDK.' - expect(fires).toEqual([ - { turn: 1, step: 1, fullSystemPrompt: HARNESS }, - { turn: 1, step: 2, fullSystemPrompt: HARNESS }, + expect(fires.map(({ turn, step }) => ({ turn, step }))).toEqual([ + { turn: 1, step: 1 }, + { turn: 1, step: 2 }, ]) + expect(fires.every(({ signal }) => signal instanceof AbortSignal)).toBe(true) }) it('agent/pre-step fires BEFORE the step it precedes opens (events land outside the step)', async () => { diff --git a/packages/core/agent-loop/tests/request-recovery.spec.ts b/packages/core/agent-loop/tests/request-recovery.spec.ts index 003c678be0..416ede21b3 100644 --- a/packages/core/agent-loop/tests/request-recovery.spec.ts +++ b/packages/core/agent-loop/tests/request-recovery.spec.ts @@ -219,6 +219,48 @@ describe('agent post-step and request-error lifecycle', () => { }) }) + it('closes the successful step as disposed when disposal lands during post-step', async () => { + const adapter = new FailureScriptAdapter([ + toolCallResponse('dispose-call', 'work', {}), + textResponse('must not continue'), + ]) + const ctx = await harness(adapter) + ctx.tools.register(defineTool({ + name: 'work', + description: 'do work', + parameters: {}, + async execute() { return [{ type: 'text', text: 'worked' }] }, + })) + const agent = ctx.agentLoop.create(AgentId('dispose-post-step'), { model: 'mock' }) + let entered!: () => void + const postStepEntered = new Promise((resolve) => { entered = resolve }) + ctx.on('agent/post-step', async (_agent, turn, step, signal) => { + expect({ turn, step }).toEqual({ turn: 1, step: 1 }) + entered() + await new Promise((resolve) => { + signal.addEventListener('abort', () => { resolve() }, { once: true }) + }) + }) + + send(agent) + await postStepEntered + await ctx.fiber.dispose() + + expect(adapter.requests).toHaveLength(1) + const boundaries = agent.session.events.filter(event => + event.type === 'step/start' || event.type === 'step/end', + ) + expect(boundaries.map(event => event.type)).toEqual(['step/start', 'step/end']) + expect(boundaries.map(event => event.data)).toEqual([ + { turn: 1, step: 1 }, + { turn: 1, step: 1 }, + ]) + expect(agent.session.events.at(-1)).toMatchObject({ + type: 'turn/end', + data: { reason: { kind: 'disposed' } }, + }) + }) + it.each([ ['thrown', contextError()], ['in-band', [{ type: 'finish', reason: { kind: 'error', message: 'too large', code: CONTEXT_WINDOW_EXCEEDED_CODE } }] satisfies StreamChunk[]], diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index 1eda0df2d7..05f473e07c 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -189,23 +189,17 @@ declare module 'cordis' { // ---- step/request extension seams (serial + waterfall) ---- /** - * Awaited serial checkpoint for session-surface mutation after prompt - * assembly and before `step/start`; appends land outside the pending step. - * The loop derives history once afterward, so compaction records and - * replacements are included without rewriting an assembled request. The - * prompt and prefix are the exact pressure inputs for that request, and + * Awaited serial checkpoint before `step/start`; appends land outside the + * pending step and are included when the loop derives request history. * `signal` cancels listener work. * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @param agent - the agent opening the step. * @param turn - the open turn number. * @param step - the pending step number. - * @param fullSystemPrompt - the assembled prompt. - * @param sessionPrefix - the frozen request prefix. * @param signal - the turn abort signal. * @mode serial */ - // TODO: Move prompt-pressure inputs behind a compaction-specific seam if no second consumer appears. - 'agent/pre-step'(this: Scoped, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void + 'agent/pre-step'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void /** * Allow, rewrite, or block one drained prompt before it becomes a user * message. Call `next()` for the unchanged default. @@ -233,9 +227,9 @@ declare module 'cordis' { * result is computed once per loop instance, logged on its anchoring request * header, and reused so the provider prefix remains stable. Interrupted * composition is discarded. Composition precedes the first `agent/pre-step` - * and request boundary, so listener appends join the current request and - * pressure accounting sees the composed prefix. Changing context belongs in - * history; contributors should prepend to `await next()` to preserve registration order. + * and request boundary, so listener appends join the current request. + * Changing context belongs in history; contributors should prepend to + * `await next()` to preserve registration order. * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @param agent - the agent whose session prefix is being composed. * @param prefix - the frozen seed; return an extended replacement. diff --git a/packages/support/invariants/tests/invariants.spec.ts b/packages/support/invariants/tests/invariants.spec.ts index 7af8d97848..af84c569b9 100644 --- a/packages/support/invariants/tests/invariants.spec.ts +++ b/packages/support/invariants/tests/invariants.spec.ts @@ -849,7 +849,7 @@ describe('scoped-dispatch invariants', () => { ['agent/status', [agent, 'idle']], ['agent/queued', [agent, [], { source: { kind: 'user' }, steering: false }]], ['agent/session-start', [agent, 'startup']], - ['agent/pre-step', [agent, 1, 1, '', new AbortController().signal]], + ['agent/pre-step', [agent, 1, 1, new AbortController().signal]], ['agent/prompt-submit', [agent, [], { kind: 'user' }, () => Promise.resolve({ kind: 'allow' })]], ['agent/request', [agent, 1, 1, { model: 'm' }, () => Promise.resolve({ model: 'm' })]], ['agent/session-prefix', [agent, [], new AbortController().signal, () => Promise.resolve([])]], diff --git a/packages/ui/user-approval/tests/approval.spec.ts b/packages/ui/user-approval/tests/approval.spec.ts index f248e5c468..0a2874499a 100644 --- a/packages/ui/user-approval/tests/approval.spec.ts +++ b/packages/ui/user-approval/tests/approval.spec.ts @@ -371,7 +371,7 @@ describe('approval policy (the approval/policy fold)', () => { } const preStep = (ctx: Context, agent: Agent): Promise => - ctx.serial('agent/pre-step', agent, 1, 1, '', [], new AbortController().signal) + ctx.serial('agent/pre-step', agent, 1, 1, new AbortController().signal) /** Append a `request/header` snapshot whose system text is exactly `system`. */ function appendHeader(session: Session, system: string): void { diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 11168ba000..05547c9b5b 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -228,7 +228,7 @@ const SERVICE_ROLES: ServiceRole[] = [ mode: 'seam', implementations: ['compact-basic'], consumers: ['compact-basic'], - note: 'The basic backend currently consumes the pre-step event directly; a model-facing compact tool remains deferred.', + note: 'The basic backend consumes post-step pressure and request-error recovery events; a model-facing compact tool remains deferred.', }, { key: 'subagents', @@ -841,6 +841,8 @@ function renderLifecycle(): string { '', 'The `assistant/message` edge records every successful provider call, including content-less and `max-tokens` finishes. Empty content stays out of derived history while the durable anchor retains usage and exact chunk provenance, including an explicit empty source set.', '', + '`dsh-compact-basic` uses `agent/post-step` for pressure after those durable facts and `agent/request-error` only for canonical context overflow. Recovery compacts between the closed failed step and a fresh retry step, and returns retry only when the surface replacement generation advances; otherwise the original request error remains authoritative.', + '', 'SDK users that need replayable transcript data should consume `session/event`; `agent/*` is the live coordination surface for queue/status, prompt interception, request shaping, steering, continuation, and errors.', '', ...maintenanceFooter(maintenance), diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index b0cea673ad..17bbb787dc 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -134,6 +134,7 @@ { "doc": "docs/core-data-structures/skills.md", "symbol": "Config", "source": "packages/skill/skill/src/index.ts" }, { "doc": "docs/core-data-structures/compaction.md", "symbol": "CompactionResult", "source": "packages/compact/compact/src/types.ts" }, + { "doc": "docs/core-data-structures/compaction.md", "symbol": "CompactionTrigger", "source": "packages/compact/compact/src/index.ts" }, { "doc": "docs/core-data-structures/subagent.md", "symbol": "SubagentCapabilities", "source": "packages/subagent/subagent/src/types.ts" }, { "doc": "docs/core-data-structures/subagent.md", "symbol": "SubagentStartRequest", "source": "packages/subagent/subagent/src/types.ts" }, From 8e7cf8cc10c3559ded0ee7f93f62d14ff5f18ad4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:09:18 +0800 Subject: [PATCH 144/359] Update ACP launcher example path --- packages/support/acp-snapshot/src/launcher.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index c0dc21dc06..95292df38a 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -27,7 +27,7 @@ const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) /** The unbuilt agent entry, leaf config, and workspace tsconfig an ACP test boots. */ export interface AgentUnderTest { - /** The agent bin entry (for example `packages/ui/acp-agent/src/bin.ts`). */ + /** The agent bin entry (for example `packages/examples/acp-demo/src/bin.ts`). */ binScript: string /** The leaf `cordis.yml` loaded by the bin. */ configPath: string From f6350ac553dc9f34b7c397eb62991e2566f1ca6b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:10:46 +0800 Subject: [PATCH 145/359] Keep root instructions within budget --- AGENTS.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/AGENTS.md b/AGENTS.md index 0c5272b105..4209b0f95c 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -59,7 +59,7 @@ pnpm run demo:cordis # self-referential demo: the agent modifies its own runt pnpm run demo:acp # ACP server agent (needs DEEPSEEK_API_KEY) ``` -### Run the CI gates locally before marking a PR ready +### Run CI gates locally before marking a PR ready Run narrow checks during implementation and this CI-equivalent sequence before marking a PR ready. Fresh worktrees need `pnpm run build` before publint and NodeNext inspect `lib/`: From d25a56b431d98a6df3ff242df6386975acce05d4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:23:39 +0800 Subject: [PATCH 146/359] Restore CompactionResult diagnostics --- packages/compact/compact-basic/src/index.ts | 6 +++++- .../compact-basic/tests/compact-basic.spec.ts | 4 +++- packages/compact/compact/src/index.ts | 2 +- packages/compact/compact/src/types.ts | 8 ++++++++ packages/compact/compact/tests/compact.spec.ts | 16 ++++++++++++---- 5 files changed, 29 insertions(+), 7 deletions(-) diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index 9449fc84f9..8bc21ddf5b 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -426,9 +426,13 @@ export class BasicCompactService extends CompactService { // compact/start and here leaves a detectable orphaned lock (a compact/start // with no matching compact/end) rather than a compact/end that falsely // claims compaction finished before the surface replacement landed. - session.append('compact/end', { turn: openTurn }) + const endEvent = session.append('compact/end', { turn: openTurn }) return { + startSeq: startEvent.seq, + summarySeq: summaryEvent.seq, + endSeq: endEvent.seq, + summary, shadowedRange: { start, end }, shadowedSeqs, shadowedTokenCount, diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 7cb872f274..4b06b321b7 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -346,6 +346,7 @@ describe('BasicCompactService.compactRegion', () => { expect(result.shadowedSeqs).toEqual([firstSeq, secondSeq]) expect(result.shadowedRange.start).toBe(firstSeq) expect(result.shadowedRange.end).toBe(secondSeq) + expect(result.summary).toEqual(svc.mockSummary) expect(result.shadowedTokenCount).toBe(20) const events = session.events @@ -1057,7 +1058,8 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { const session = multiTurnSession(2, 1) const nodes = session.surface.nodes - await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') + const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') + expect(result.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) const summaryEvent = session.events.findLast(e => e.type === 'compact/summary')! expect(summaryEvent.data.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) // The raw summary is wrapped in the checkpoint framing on the surface. diff --git a/packages/compact/compact/src/index.ts b/packages/compact/compact/src/index.ts index e4baec6551..680f684ac6 100644 --- a/packages/compact/compact/src/index.ts +++ b/packages/compact/compact/src/index.ts @@ -73,7 +73,7 @@ export abstract class CompactService extends Service { * @param agent - context whose session is mutated and whose routing options guide summarization. * @param signal - optional cancellation; model-backed implementations must forward it. * @throws when compaction is active or the range is missing, reversed, or unbalanced. - * @returns the replaced range and token accounting; the durable event owns the summary. + * @returns the appended event seqs, summary, replaced range, and token accounting. */ abstract compactRegion( start: number, diff --git a/packages/compact/compact/src/types.ts b/packages/compact/compact/src/types.ts index 0d3d35ace8..10a5eabfcc 100644 --- a/packages/compact/compact/src/types.ts +++ b/packages/compact/compact/src/types.ts @@ -41,6 +41,14 @@ declare module '@deepseek-ai/dsh-session' { /** Result of a successful compaction operation. */ export interface CompactionResult { + /** The seq of the appended `compact/start` event. */ + startSeq: number + /** The seq of the appended `compact/summary` event. */ + summarySeq: number + /** The seq of the appended `compact/end` event. */ + endSeq: number + /** The summary content blocks produced by the backend. */ + summary: ContentBlock[] /** * The surface-boundary pair that was shadowed: the seqs of the first * (`start`) and last (`end`) surface nodes of the replaced range. A diff --git a/packages/compact/compact/tests/compact.spec.ts b/packages/compact/compact/tests/compact.spec.ts index e34c8420d9..3d95c12249 100644 --- a/packages/compact/compact/tests/compact.spec.ts +++ b/packages/compact/compact/tests/compact.spec.ts @@ -34,17 +34,22 @@ class StubCompactService extends CompactService { ): Promise { this.lastSignal = signal const session = agent.session + const summary = [{ type: 'text' as const, text: 'stub' }] // Minimal stub honoring the lock + log-only event contract. - session.append('compact/start', { turn: 0 }) - session.append('compact/summary', { - summary: [{ type: 'text', text: 'stub' }], + const startEvent = session.append('compact/start', { turn: 0 }) + const summaryEvent = session.append('compact/summary', { + summary, shadowedRange: { start, end }, shadowedSeqs: [], shadowedTokenCount: 0, model: 'stub', }) - session.append('compact/end', { turn: 0 }) + const endEvent = session.append('compact/end', { turn: 0 }) return { + startSeq: startEvent.seq, + summarySeq: summaryEvent.seq, + endSeq: endEvent.seq, + summary, shadowedRange: { start, end }, shadowedSeqs: [], shadowedTokenCount: 0, @@ -92,6 +97,9 @@ describe('CompactService seam', () => { // verify the runtime value is absent. const raw = startEvent as unknown as { surfaceOp?: unknown } expect(raw.surfaceOp).toBeUndefined() + expect(result.summary).toEqual([{ type: 'text', text: 'stub' }]) + expect(result.summarySeq).toBeGreaterThan(result.startSeq) + expect(result.endSeq).toBeGreaterThan(result.summarySeq) expect(result.shadowedRange).toEqual({ start: 0, end: 0 }) expect(session.events.filter(e => e.type.startsWith('compact/')).map(e => e.type)) .toEqual(['compact/start', 'compact/summary', 'compact/end']) From 8eccd5416e58d1ea63f6dfb411a247ff6c272ced Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:25:39 +0800 Subject: [PATCH 147/359] Document restored compaction result fields --- docs/core-data-structures/compaction.md | 10 +++++++++- packages/cordis/tool-cordis/src/api-catalog.ts | 2 +- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index d253166fcf..1075f3c985 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -20,10 +20,18 @@ These variants are merged inside a `declare module '@deepseek-ai/dsh-session'` b ## `CompactionResult` -What a successful compaction returns to its caller: the shadowed range and seqs plus the estimated token count. The durable `compact/summary` event owns the raw summary and bookkeeping-event identity. +What a successful compaction returns to its caller: the bookkeeping-event seqs, raw summary, shadowed range and seqs, and estimated token count. ```ts type-equiv interface CompactionResult { + /** The seq of the appended `compact/start` event. */ + startSeq: number + /** The seq of the appended `compact/summary` event. */ + summarySeq: number + /** The seq of the appended `compact/end` event. */ + endSeq: number + /** The summary content blocks produced by the backend. */ + summary: ContentBlock[] /** * The surface-boundary pair that was shadowed: the seqs of the first * (`start`) and last (`end`) surface nodes of the replaced range. A diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 8e6477258e..bfa494f829 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -631,7 +631,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'CompactionResult', - declaration: 'export interface CompactionResult {\n shadowedRange: {\n start: number;\n end: number;\n };\n shadowedSeqs: number[];\n shadowedTokenCount: number;\n}', + declaration: 'export interface CompactionResult {\n startSeq: number;\n summarySeq: number;\n endSeq: number;\n summary: ContentBlock[];\n shadowedRange: {\n start: number;\n end: number;\n };\n shadowedSeqs: number[];\n shadowedTokenCount: number;\n}', }, { name: 'ConfinedArgv', From cdeec6fc1d984adfdbd645d1a481dd0a2a9fdba8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:36:51 +0800 Subject: [PATCH 148/359] Update built JSON-RPC probe path --- packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts index bc6642263e..ed4dfbb9db 100644 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -33,7 +33,7 @@ const [ { SessionId }, ] = await Promise.all([ load("vendor/cordis/lib/index.js"), - load("packages/core/agent-core/lib/index.js"), + load("packages/examples/agent-spine-demo/lib/index.js"), load("packages/subagent/subagent/lib/index.js"), load("packages/session-persistence/session-persistence-jsonl/lib/index.js"), load("packages/ui/jsonrpc/lib/index.js"), From d66c926d7a63d5416f766f2de90b16760ffb5176 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 17:43:33 +0800 Subject: [PATCH 149/359] fix(agent): preserve lifecycle recovery boundaries (PR3 round 2) --- .../compact/compact-basic/src/automatic.ts | 1 + .../compact-basic/tests/compact-basic.spec.ts | 15 +++ packages/core/agent-loop/src/loop.ts | 6 +- .../tests/contract-regressions.spec.ts | 57 ++++++++++- packages/llm/llm/src/index.ts | 19 ++-- packages/llm/llm/tests/service.spec.ts | 95 ++++++++++++++----- 6 files changed, 151 insertions(+), 42 deletions(-) diff --git a/packages/compact/compact-basic/src/automatic.ts b/packages/compact/compact-basic/src/automatic.ts index 16e71c081a..e837e076cc 100644 --- a/packages/compact/compact-basic/src/automatic.ts +++ b/packages/compact/compact-basic/src/automatic.ts @@ -45,6 +45,7 @@ export function registerAutomaticCompaction( _step: number, signal: AbortSignal, ) => { + if (signal.aborted) return try { const result = await service.compactIfNeeded(agent, 'pressure', signal) if (result !== null) logResult(result, 'post-step pressure') diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 163c2b6b45..d5e3246777 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -848,6 +848,21 @@ describe('automatic listener and loader composition', () => { expect(compact.calls).toHaveLength(1) }) + it('skips post-step pressure when the step signal is already aborted', async () => { + const ctx = createContext() + const compact = new TestCompactService(ctx, { + models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + }) + const pressured = conversation(4) + const compactIfNeeded = vi.spyOn(compact, 'compactIfNeeded') + + await expect(postStep(ctx, agent(pressured, MODEL), AbortSignal.abort('step aborted'))) + .resolves.toBeUndefined() + + expect(compactIfNeeded).not.toHaveBeenCalled() + expect(pressured.events.some(event => event.type === 'compact/start')).toBe(false) + }) + it('warns and continues after operational failures, including non-Errors', async () => { const ctx = createContext() const warnings: string[] = [] diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 620cdd9fbc..59b0d26088 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -650,7 +650,8 @@ async function runStep( session, turn, step, message.content, assembler.usage, chunkSeqs, ) - // Tool execution stays sequential; recheck abort around each normalized result. + // Tool execution stays sequential; cancellation latches synthetic results for + // every remaining call while preserving one complete result batch. const toolCalls = message.content.filter(block => block.type === 'tool-call') // Buffer context until all results are appended to preserve call/result adjacency. const pendingContext: HookContext[] = [] @@ -693,9 +694,6 @@ async function runStep( if (signal.aborted) aborted = true } - /* v8 ignore next -- signal.reason always set by cancellation or disposal. */ - if (aborted) throw new Error(String(signal.reason ?? 'aborted')) - // Append buffered context after the complete result batch. for (const context of pendingContext) { agent.inject(context.content, { source: context.source }) diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 6ca06fc096..75afb08b0c 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -156,7 +156,7 @@ describe('successful provider completion survives agent/step-result failure', () }) describe('abort during tool execution ends the turn', () => { - it('aborting the in-flight step inside a tool prevents both remaining tools and the next model step', async () => { + it('balances an aborted tool batch through context, steering, and post-step before closing', async () => { const adapter = new MockAdapter([ // model asks for two tool calls in one step [ @@ -175,8 +175,12 @@ describe('abort during tool execution ends the turn', () => { name: 'aborter', description: '', parameters: {}, - async execute() { + async execute(_args, exec) { executed.push('aborter') + exec.agent?.steer( + [{ type: 'text', text: 'steering before abort' }], + { source: { kind: 'plugin', plugin: 'abort-test' } }, + ) // Fire the in-flight step's AbortController directly (the loop registers // it on the agent). This is the bare step-abort path — distinct from // cancel(), which would also clear the inbox; here the subject is the @@ -185,6 +189,13 @@ describe('abort during tool execution ends the turn', () => { return [{ type: 'text', text: 'done' }] }, })) + ctx.on('tools/post-execute', async exec => ({ + kind: 'accept', + additionalContext: { + content: [{ type: 'text', text: `context for ${exec.callId}` }], + source: { kind: 'plugin', plugin: 'abort-test' }, + }, + })) ctx.tools.register(defineTool({ name: 'second', description: '', @@ -196,13 +207,53 @@ describe('abort during tool execution ends the turn', () => { })) const reasons: TurnEndReason[] = [] - ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) + const order: string[] = [] + ctx.on('session/event', (session, event) => { + if (session !== agent.session) return + switch (event.type) { + case 'assistant/message': order.push('assistant/message'); break + case 'tool/call': order.push(`tool/call:${event.data.callId}`); break + case 'tool/result': { + const outcome = event.data.error?.code === 'ABORTED' ? 'synthetic-aborted' : 'real' + order.push(`tool/result:${event.data.callId}:${outcome}`) + break + } + case 'context/message': order.push('context/message'); break + case 'steering/message': order.push('steering/message'); break + case 'step/end': order.push('step/end'); break + case 'turn/end': { + reasons.push(event.data.reason) + order.push(`turn/end:${event.data.reason.kind}`) + break + } + } + }) + let postSteps = 0 + ctx.on('agent/post-step', (subject, turn, step, signal) => { + if (subject !== agent) return + postSteps += 1 + expect({ turn, step, aborted: signal.aborted }).toEqual({ turn: 1, step: 1, aborted: true }) + order.push('agent/post-step') + }) send(agent, 'go') await waitForIdle(ctx, agent) expect(executed).toEqual(['aborter']) // second tool never ran expect(adapter.requests).toHaveLength(1) // no follow-up model call + expect(postSteps).toBe(1) + expect(order).toEqual([ + 'assistant/message', + 'tool/call:c1', + 'tool/result:c1:real', + 'tool/call:c2', + 'tool/result:c2:synthetic-aborted', + 'context/message', + 'steering/message', + 'agent/post-step', + 'step/end', + 'turn/end:aborted', + ]) expect(reasons).toEqual([{ kind: 'aborted', reason: 'user interrupt' }]) const calls = agent.session.events.filter(event => event.type === 'tool/call') const results = agent.session.events.filter(event => event.type === 'tool/result') diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 0b933d12a7..1be716cbfb 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -124,8 +124,9 @@ export class LlmService extends Service { * Final adapter boundary. It tags only failures from adapter selection, * synchronous dispatch, iterator construction, or iteration while preserving * the original Error object. Middleware outside this generator remains - * distinguishable as plugin work. Adapter cleanup is best-effort after an - * earlier failure or downstream close and never masks the winning error. + * distinguishable as plugin work. An iteration failure skips adapter cleanup + * so it cannot suppress the primary provider error. A downstream close awaits + * adapter cleanup, whose failures remain ordinary untagged work. */ private async * adapterStream(options: GenerateOptions): AsyncGenerator { let iterator: AsyncIterator @@ -137,6 +138,7 @@ export class LlmService extends Service { } let completed = false + let iterationFailed = false try { while (true) { let value: StreamChunk @@ -148,6 +150,7 @@ export class LlmService extends Service { } value = item.value } catch (error: unknown) { + iterationFailed = true throw markLlmAdapterFailure(error) } // End the adapter-owned try before yielding: consumer/middleware @@ -155,14 +158,10 @@ export class LlmService extends Service { yield value } } finally { - if (!completed) { - try { - const close = iterator.return?.bind(iterator) - if (close) await close() - } catch { - // Lookup and invocation are both adapter-owned cleanup following an - // existing failure/downstream close; neither can replace it. - } + // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- the iteration catch sets its latch before entering finally. + if (!completed && !iterationFailed) { + const close = iterator.return?.bind(iterator) + if (close) await close() } } } diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index 8dc46529bd..b488002666 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -72,11 +72,21 @@ describe('LlmService', () => { const original = new LlmError(`${field} getter failed`, 'RESULT_GETTER_FAILED') const result = field === 'done' ? {} : { done: false } Object.defineProperty(result, field, { get: () => { throw original } }) + let cleanupLookups = 0 + const iterator: AsyncIterator = { + next: () => Promise.resolve(result as unknown as IteratorResult), + } + Object.defineProperty(iterator, 'return', { + get: () => { + cleanupLookups += 1 + throw new Error('return getter must not run after iteration fails') + }, + }) const adapter = new class extends LlmAdapter { stream(_options: GenerateOptions): AsyncIterable { return { [Symbol.asyncIterator](): AsyncIterator { - return { next: () => Promise.resolve(result as unknown as IteratorResult) } + return iterator }, } } @@ -94,6 +104,7 @@ describe('LlmService', () => { expect(caught).toBe(original) expect(isLlmAdapterFailure(caught)).toBe(true) + expect(cleanupLookups).toBe(0) }) it.each(['dispatch', 'iterator'] as const)('tags synchronous adapter %s failures without replacing their Error', async (boundary) => { @@ -119,7 +130,7 @@ describe('LlmService', () => { expect(isLlmAdapterFailure(caught)).toBe(true) }) - it('tags adapter iteration failures without replacing the original Error or cleanup outcome', async () => { + it('propagates a rejected next promptly without awaiting a non-settling return', async () => { const original = new LlmError('provider failed', 'PROVIDER_FAILED') let cleanupCalls = 0 const adapter = new class extends LlmAdapter { @@ -130,7 +141,49 @@ describe('LlmService', () => { next: () => Promise.reject(original), return: () => { cleanupCalls += 1 - return Promise.reject(new Error('cleanup failed')) + return new Promise>(() => {}) + }, + } + }, + } + } + }() + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['test-model'], adapter) + + const failure = (async (): Promise => { + try { + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } + } catch (error: unknown) { + return error + } + return new Error('expected adapter iteration to fail') + })() + let timer: ReturnType | undefined + const timeout = new Promise((resolve) => { + timer = setTimeout(() => { resolve(new Error('adapter failure did not settle promptly')) }, 100) + }) + const caught = await Promise.race([failure, timeout]) + if (timer !== undefined) clearTimeout(timer) + + expect(caught).toBe(original) + expect(isLlmAdapterFailure(caught)).toBe(true) + expect(cleanupCalls).toBe(0) + }) + + it('awaits one adapter return on downstream close and leaves its rejection unclassified', async () => { + const cleanup = new Error('cleanup failed') + let cleanupCalls = 0 + const adapter = new class extends LlmAdapter { + stream(_options: GenerateOptions): AsyncIterable { + return { + [Symbol.asyncIterator](): AsyncIterator { + return { + next: () => Promise.resolve({ done: false, value: SCRIPT[0]! }), + return: () => { + cleanupCalls += 1 + return Promise.reject(cleanup) }, } }, @@ -143,45 +196,37 @@ describe('LlmService', () => { let caught: unknown try { - for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) break } catch (error: unknown) { caught = error } - expect(caught).toBe(original) - expect(isLlmAdapterFailure(caught)).toBe(true) + expect(caught).toBe(cleanup) + expect(isLlmAdapterFailure(caught)).toBe(false) expect(cleanupCalls).toBe(1) }) - it('contains a throwing iterator.return getter after next fails without replacing the original Error', async () => { - const original = new LlmError('provider failed', 'PROVIDER_FAILED') - let cleanupLookups = 0 - const iterator: AsyncIterator = { next: () => Promise.reject(original) } - Object.defineProperty(iterator, 'return', { - get: () => { - cleanupLookups += 1 - throw new Error('return getter failed') - }, - }) + it('allows downstream close when the adapter iterator has no return method', async () => { const adapter = new class extends LlmAdapter { stream(_options: GenerateOptions): AsyncIterable { - return { [Symbol.asyncIterator]: () => iterator } + return { + [Symbol.asyncIterator](): AsyncIterator { + return { next: () => Promise.resolve({ done: false, value: SCRIPT[0]! }) } + }, + } } }() const ctx = new Context() await ctx.plugin(LlmService) ctx.llm.registerAdapter(['test-model'], adapter) - let caught: unknown - try { - for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } - } catch (error: unknown) { - caught = error + let chunks = 0 + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { + chunks += 1 + break } - expect(caught).toBe(original) - expect(isLlmAdapterFailure(caught)).toBe(true) - expect(cleanupLookups).toBe(1) + expect(chunks).toBe(1) }) it('normalizes and tags non-Error adapter failures once', async () => { From 25a5dc35ba4498a3dbb75264aa74b3937c9782d2 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:53:51 +0800 Subject: [PATCH 150/359] Refresh Cordis event API summaries --- .../cordis/tool-cordis/src/api-catalog.ts | 20 +++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 9102e928db..5d16b5d496 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -259,13 +259,13 @@ export const EVENT_API: readonly EventApiEntry[] = [ name: 'agent/created', mode: 'emit', signature: '\'agent/created\'(this: Scoped, agent: Agent): void', - summary: 'An agent\'s fully composed scoped world was published in the AgentRegistry.', + summary: 'A fully configured agent and live session were published.', }, { name: 'agent/disposed', mode: 'emit', signature: '\'agent/disposed\'(this: Scoped, agent: Agent): void', - summary: 'An agent was removed from the registry.', + summary: 'An agent left the registry; AgentLoop emits this after driver quiescence but before session detachment and scoped-registration unwind.', }, { name: 'agent/error', @@ -277,37 +277,37 @@ export const EVENT_API: readonly EventApiEntry[] = [ name: 'agent/pre-step', mode: 'serial', signature: '\'agent/pre-step\'(this: Scoped, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void', - summary: 'Awaited pre-step surface-mutation checkpoint, fired once per step AFTER `turn/start` (and after the prior step closed) but BEFORE this step\'s `step/start` — so anything a listener appends lands OUTSIDE the step, between `turn/start`/`step/end` and the upcoming `step/start`.', + summary: 'Awaited serial checkpoint for session-surface mutation after prompt assembly and before `step/start`; appends land outside the pending step.', }, { name: 'agent/prompt-submit', mode: 'waterfall', signature: '\'agent/prompt-submit\'(this: Scoped, agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise): Promise', - summary: 'Waterfall: decide what happens to ONE drained queued message before it becomes a `user/message` — allow (optionally rewriting the prompt bytes or attaching `additionalContext`) or block it.', + summary: 'Allow, rewrite, or block one drained prompt before it becomes a user message.', }, { name: 'agent/queued', mode: 'emit', signature: '\'agent/queued\'(this: Scoped, agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void', - summary: 'A message entered the agent\'s inbox (queued or steering).', + summary: 'Detached, frozen content entered the agent\'s inbox.', }, { name: 'agent/request', mode: 'waterfall', signature: '\'agent/request\'(this: Scoped, agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise): Promise', - summary: 'Waterfall: shape the step\'s call configuration — model switching, sampling overrides — by returning a replacement LlmCallConfig (the frozen seed is the config the loop would otherwise use).', + summary: 'Replace the frozen call configuration.', }, { name: 'agent/session-prefix', mode: 'waterfall', signature: '\'agent/session-prefix\'(this: Scoped, agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise): Promise', - summary: 'Waterfall: compose the SESSION PREFIX — request-only messages placed in front of the ENTIRE derived history (directly after the provider\'s system slot) on every request this loop instance sends.', + summary: 'Compose request-only messages placed before derived history.', }, { name: 'agent/session-start', mode: 'emit', signature: '\'agent/session-start\'(this: Scoped, agent: Agent, source: SessionStartSource): void', - summary: 'The agent\'s session lifecycle began, fired once before its first turn.', + summary: 'The session lifecycle began, once before the first turn.', }, { name: 'agent/status', @@ -325,13 +325,13 @@ export const EVENT_API: readonly EventApiEntry[] = [ name: 'agent/turn-continuation', mode: 'waterfall', signature: '\'agent/turn-continuation\'(this: Scoped, agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise): Promise', - summary: 'Waterfall: override the turn-continuation decision via a typed ContinuationDecision.', + summary: 'Override whether the turn continues.', }, { name: 'agent/turn-stop', mode: 'serial', signature: '\'agent/turn-stop\'(this: Scoped, agent: Agent, turn: number): ContinuationStop | undefined', - summary: 'Serial terminal-stop checkpoint after the ordinary `agent/turn-continuation` waterfall, any `continue.reason`, and the pending-steering continuation override have been folded.', + summary: 'Monotonic terminal-stop checkpoint after continuation and steering are folded; a stop remains authoritative through turn close and flush: steering queued in that window is discarded, while ordinary sends survive.', }, { name: 'approval/request', From 87c900dfb2a8b73f153828a01c9fbd90cd962311 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:55:48 +0800 Subject: [PATCH 151/359] Document compaction result diagnostics --- packages/compact/compact/README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index 51ba50382f..0e0b63d765 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -21,6 +21,8 @@ Both methods are **abstract** — the backend owns the entire strategy (token es | `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` | Estimate the surface-derived history size; if over the backend's threshold, compact an older range via `compactRegion`, keeping recent context intact. Returns the `CompactionResult`, or `null` if nothing needed compacting. All parameters required — the loop's `agent/pre-step` checkpoint supplies the agent, assembled `fullSystemPrompt`, composed `sessionPrefix` (request-only messages every request carries but the derived history omits — the pressure estimate must count them), and turn `signal`. A backend's summarization request is a direct `ctx.llm.stream()` call (not a loop step), so per-call interception happens at `llm/stream`. | | `compactRegion(start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) from `agent.session` into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. | +`CompactionResult` keeps the raw summary and bookkeeping-event seqs available to callers alongside the shadowed range and token accounting; its drift-checked shape lives in the [compaction data-structure reference](../../../docs/core-data-structures/compaction.md#compactionresult). + `compactIfNeeded` takes a required `signal`; `compactRegion`'s is optional. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The session being compacted comes from the agent context; the turn that the `compact/*` events belong to is recoverable from the log (the currently-open turn), so the backend stamps it from the log rather than trusting a caller-supplied value. ## Surface contract From 54fb96ef04df12bf59c69b14de24bcba8ada98d4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 04:46:35 +0800 Subject: [PATCH 152/359] refactor: name front door defaults --- packages/examples/acp-demo/src/index.ts | 7 +++---- packages/examples/stdio-demo/src/index.ts | 12 ++++++------ 2 files changed, 9 insertions(+), 10 deletions(-) diff --git a/packages/examples/acp-demo/src/index.ts b/packages/examples/acp-demo/src/index.ts index 0439363301..a26220dbf7 100644 --- a/packages/examples/acp-demo/src/index.ts +++ b/packages/examples/acp-demo/src/index.ts @@ -18,6 +18,7 @@ import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import UserInteractionService from '@deepseek-ai/dsh-user-interaction' export const name = 'acp-demo' +const DEFAULT_PERSISTENCE_ROOT = './.sessions' /** * App config: the swappable per-deployment values. `model` configures the @@ -54,9 +55,7 @@ export const Config: z = z.object({ // schemastery's native [] default would read as an invalid configured list. toolOrder: z.array(z.string()).default(undefined as unknown as string[]), tools: ToolRegistry.Config, - // TODO(single-default-literal): share this schema default and the defensive - // apply() fallback through one named constant while retaining both boundaries. - persistenceRoot: z.string().default('./.sessions'), + persistenceRoot: z.string().default(DEFAULT_PERSISTENCE_ROOT), skills: agentCore.SkillConfigSchema, }) /* jscpd:ignore-end */ @@ -76,6 +75,6 @@ export function apply(ctx: Context, config: Config): void { ...config.skills !== undefined ? { skills: config.skills } : {}, }) ctx.plugin(UserInteractionService) - ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) + ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? DEFAULT_PERSISTENCE_ROOT }) ctx.plugin(acp, { model: config.model }) } diff --git a/packages/examples/stdio-demo/src/index.ts b/packages/examples/stdio-demo/src/index.ts index 742371ecd5..c54f9499c6 100644 --- a/packages/examples/stdio-demo/src/index.ts +++ b/packages/examples/stdio-demo/src/index.ts @@ -23,6 +23,8 @@ import * as toolAskUser from '@deepseek-ai/dsh-tool-ask-user' import * as uiStdio from '@deepseek-ai/dsh-stdio' export const name = 'stdio-demo' +const DEFAULT_PERSISTENCE_ROOT = './.sessions' +const DEFAULT_WELCOME = 'ready.' /** * App config: the swappable per-demo values, each routed to where the app wires @@ -65,10 +67,8 @@ export const Config: z = z.object({ // schemastery's native [] default would read as an invalid configured list. toolOrder: z.array(z.string()).default(undefined as unknown as string[]), tools: ToolRegistry.Config, - // TODO(single-default-literal): share these schema defaults and defensive - // apply() fallbacks through named constants while retaining both boundaries. - persistenceRoot: z.string().default('./.sessions'), - welcome: z.string().default('ready.'), + persistenceRoot: z.string().default(DEFAULT_PERSISTENCE_ROOT), + welcome: z.string().default(DEFAULT_WELCOME), skills: agentCore.SkillConfigSchema, resumeSessionId: z.string(), }) @@ -85,10 +85,10 @@ export function apply(ctx: Context, config: Config): void { const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId const sessionId = SessionId(resumeSessionId ?? `main-session-${randomUUID()}`) ctx.plugin(ConsoleExporter) - ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) + ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? DEFAULT_PERSISTENCE_ROOT }) ctx.plugin(UserInteractionService) ctx.plugin(uiStdio, { - welcome: config.welcome ?? 'ready.', + welcome: config.welcome ?? DEFAULT_WELCOME, sessionId, }) ctx.plugin(agentCore, { From 732735b27fb23fe90ee7f6c9853c7953b8879fdc Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:32:15 +0800 Subject: [PATCH 153/359] docs: align default fallback test comments --- packages/examples/acp-demo/tests/acp-agent.spec.ts | 2 +- packages/examples/stdio-demo/tests/stdio-agent.spec.ts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/examples/acp-demo/tests/acp-agent.spec.ts b/packages/examples/acp-demo/tests/acp-agent.spec.ts index f3495c827c..ab36aa56c8 100644 --- a/packages/examples/acp-demo/tests/acp-agent.spec.ts +++ b/packages/examples/acp-demo/tests/acp-agent.spec.ts @@ -82,7 +82,7 @@ describe('dsh-acp-demo composition', () => { }) it('defaults the persistence root when omitted', async () => { - // Exercises the `?? './.sessions'` fallback for a direct-apply caller that + // Exercises the `DEFAULT_PERSISTENCE_ROOT` fallback for a direct-apply caller that // bypasses the schema's `.default(...)`: call `apply` directly (not via // `ctx.plugin`, which validates+defaults the config first) with no // persistenceRoot, so the runtime fallback is the one that fires. diff --git a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts index 79681fd954..b2398fea7c 100644 --- a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts +++ b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts @@ -100,7 +100,7 @@ describe('dsh-stdio-demo app', () => { it('defaults persistenceRoot and welcome when omitted', async () => { // Direct apply (NOT via ctx.plugin, which validates+defaults the config - // first) so the runtime `?? './.sessions'` / `?? 'ready.'` fallbacks on + // first) so the runtime `DEFAULT_PERSISTENCE_ROOT` / `DEFAULT_WELCOME` fallbacks on // apply()'s last two lines are the ones that fire — covering a // schema-bypassing direct-mount caller. const ctx = new Context() From 29d545eb212e88f9589134be420eff3ed8673b81 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 19:52:45 +0800 Subject: [PATCH 154/359] Refresh front-door config catalog --- docs/config-catalog.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 29be66bbbe..5bbdbe5fd3 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -63,7 +63,7 @@ export interface Config { Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/examples/acp-demo/src/index.ts:31`](../packages/examples/acp-demo/src/index.ts) +Source: [`packages/examples/acp-demo/src/index.ts:32`](../packages/examples/acp-demo/src/index.ts) ## `@deepseek-ai/dsh-agent-loop` @@ -722,7 +722,7 @@ export interface Config { Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/examples/stdio-demo/src/index.ts:37`](../packages/examples/stdio-demo/src/index.ts) +Source: [`packages/examples/stdio-demo/src/index.ts:39`](../packages/examples/stdio-demo/src/index.ts) ## `@deepseek-ai/dsh-subagent-acp` From b78cdbcd51d5c397f181a71ff5b0e61063e6f791 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 21:21:24 +0800 Subject: [PATCH 155/359] feat(examples): add one-shot CLI demo --- .agents/skills/dsh-pre-push-checks/SKILL.md | 2 +- AGENTS.md | 13 +- docs/architecture.md | 2 +- docs/capability-seams.md | 7 +- docs/config-catalog.md | 24 ++ docs/event-producer-consumer.md | 2 +- docs/module-graph.md | 9 + examples/README.md | 4 +- examples/coding-agent/README.md | 22 +- examples/coding-agent/cli.cordis.yml | 24 ++ .../tests/cli-keyless-smoke.e2e.ts | 43 ++ examples/coding-agent/tests/cli.e2e.ts | 33 ++ .../tests/fixtures/cli-mock-llm.ts | 37 ++ .../tests/fixtures/cli.cordis.yml | 24 ++ knip.json | 5 + package.json | 1 + packages/README.md | 2 +- packages/examples/README.md | 3 +- packages/examples/cli-demo/README.md | 62 +++ packages/examples/cli-demo/package.json | 59 +++ packages/examples/cli-demo/src/bin.ts | 34 ++ packages/examples/cli-demo/src/cli.ts | 380 ++++++++++++++++++ packages/examples/cli-demo/src/index.ts | 63 +++ .../examples/cli-demo/tests/built-bin.e2e.ts | 172 ++++++++ .../examples/cli-demo/tests/cli-demo.spec.ts | 105 +++++ packages/examples/cli-demo/tests/cli.spec.ts | 362 +++++++++++++++++ packages/examples/cli-demo/tsconfig.json | 22 + packages/examples/cli-demo/tsdown.config.ts | 13 + packages/support/loader-smoke/README.md | 2 +- packages/support/loader-smoke/src/index.ts | 19 +- .../loader-smoke/tests/fixtures/success.ts | 1 + .../loader-smoke/tests/loader-smoke.spec.ts | 27 ++ pnpm-lock.yaml | 39 ++ scripts/gen-doc-graphs.ts | 8 +- scripts/run-gates.ts | 1 + tsconfig.build.json | 1 + tsconfig.json | 1 + 37 files changed, 1600 insertions(+), 28 deletions(-) create mode 100644 examples/coding-agent/cli.cordis.yml create mode 100644 examples/coding-agent/tests/cli-keyless-smoke.e2e.ts create mode 100644 examples/coding-agent/tests/cli.e2e.ts create mode 100644 examples/coding-agent/tests/fixtures/cli-mock-llm.ts create mode 100644 examples/coding-agent/tests/fixtures/cli.cordis.yml create mode 100644 packages/examples/cli-demo/README.md create mode 100644 packages/examples/cli-demo/package.json create mode 100644 packages/examples/cli-demo/src/bin.ts create mode 100644 packages/examples/cli-demo/src/cli.ts create mode 100644 packages/examples/cli-demo/src/index.ts create mode 100644 packages/examples/cli-demo/tests/built-bin.e2e.ts create mode 100644 packages/examples/cli-demo/tests/cli-demo.spec.ts create mode 100644 packages/examples/cli-demo/tests/cli.spec.ts create mode 100644 packages/examples/cli-demo/tsconfig.json create mode 100644 packages/examples/cli-demo/tsdown.config.ts diff --git a/.agents/skills/dsh-pre-push-checks/SKILL.md b/.agents/skills/dsh-pre-push-checks/SKILL.md index 4ce005ee79..433aa38942 100644 --- a/.agents/skills/dsh-pre-push-checks/SKILL.md +++ b/.agents/skills/dsh-pre-push-checks/SKILL.md @@ -54,7 +54,7 @@ pnpm run test:snapshot Run built-bin smoke tests after `pnpm run build` when app packages, app boot, package runtime imports, bin entries, loader behavior, or published artifact paths change. ```sh -pnpm exec vitest run --config vitest.e2e.config.ts packages/examples/stdio-demo/tests/built-bin.e2e.ts packages/examples/acp-demo/tests/built-bin.e2e.ts +pnpm exec vitest run --config vitest.e2e.config.ts packages/examples/stdio-demo/tests/built-bin.e2e.ts packages/examples/cli-demo/tests/built-bin.e2e.ts packages/examples/acp-demo/tests/built-bin.e2e.ts ``` Run real e2e when behavior depends on a real model/API, tool-use loop, ACP integration, prompt injection, or end-to-end agent UX. If `.env` is available, use it; do not print secrets. diff --git a/AGENTS.md b/AGENTS.md index 23d7c0263b..b9731f2c80 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -43,8 +43,8 @@ Package groups: [packages/README.md](packages/README.md). ```sh pnpm install # pnpm workspaces, node ^22.19 || >=24 pnpm run test # vitest unit tests -pnpm run test:coverage # THE gating test run: per-file 100% coverage on packages/*/*/src -pnpm run test:e2e # real-API tests; self-skip without DEEPSEEK_API_KEY +pnpm run test:coverage # gate: per-file 100% on packages/*/*/src +pnpm run test:e2e # real API; skips without key pnpm run test:snapshot # keyless ACP replay vs goldens; filter: -t pnpm run test:snapshot:record # re-record goldens (needs key) pnpm run typecheck @@ -54,9 +54,10 @@ pnpm run build # tsc emits lib/types, tsdown bundles runtime pnpm run hygiene # knip + publint + workspace constraints + NodeNext consumer check pnpm run doc-sync # all documentation gates; see the doc-sync script in package.json pnpm run demo:echo # mock-model REPL, no key needed -pnpm run demo:repl # real REPL coding agent (needs DEEPSEEK_API_KEY) -pnpm run demo:cordis # self-referential demo: the agent modifies its own runtime (needs key) -pnpm run demo:acp # ACP server agent (needs DEEPSEEK_API_KEY) +pnpm run demo:repl # real coding REPL (needs key) +pnpm run demo:cli -- "task" # one-shot agent (needs key) +pnpm run demo:cordis # self-modifying runtime demo (needs key) +pnpm run demo:acp # ACP server (needs key) ``` ### Run the CI gates locally before marking a PR ready @@ -79,7 +80,7 @@ printf '%s\n' "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})' printf '%s\n' "$out" | grep -q '\[tool result\] ECHO: CI SMOKE' test -n "$(find .sessions -path '.sessions/cwd-*/main-session-*.jsonl' -type f -print -quit)" rm -rf .sessions -pnpm exec vitest run --config vitest.e2e.config.ts packages/examples/stdio-demo/tests/built-bin.e2e.ts packages/examples/acp-demo/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts +pnpm exec vitest run --config vitest.e2e.config.ts packages/examples/stdio-demo/tests/built-bin.e2e.ts packages/examples/cli-demo/tests/built-bin.e2e.ts packages/examples/acp-demo/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts ``` `test:coverage`, not `test`, is the gate ([why](docs/testing.md)); report only commands actually run. diff --git a/docs/architecture.md b/docs/architecture.md index 4049049e25..c46e7b1619 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -138,7 +138,7 @@ Some seams bend the template deliberately. LLM keeps interface and consumer voca ### Bundles And Apps -`dsh-agent-spine-demo` is the default composition bundle: one plugin loading the shared spine ([README](../packages/examples/agent-spine-demo/README.md)). App packages compose it with a front door and boot `bin`: `dsh-stdio-demo` for terminal REPL, and `dsh-acp-demo` for ACP over JSON-RPC stdio with no stdout logger ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` instead boots an external `cordis.yml`; the Python SDK injects the package default only when no explicit config channel is set and drives `dsh-jsonrpc` over line-delimited stdio JSON-RPC ([Python SDK](../python/README.md)). A deployment is a thin `cordis.yml` leaf: swappable backends, one app entry, and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)). +`dsh-agent-spine-demo` is the default composition bundle: one plugin loading the shared spine ([README](../packages/examples/agent-spine-demo/README.md)). App packages compose it with a front door and boot `bin`: `dsh-stdio-demo` for terminal REPL, `dsh-cli-demo` for one headless persisted turn with format-pure stdout, and `dsh-acp-demo` for ACP over JSON-RPC stdio with no stdout logger ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` instead boots an external `cordis.yml`; the Python SDK injects the package default only when no explicit config channel is set and drives `dsh-jsonrpc` over line-delimited stdio JSON-RPC ([Python SDK](../python/README.md)). A deployment is a thin `cordis.yml` leaf: swappable backends, one app entry, and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)). ### Where New Behavior Goes diff --git a/docs/capability-seams.md b/docs/capability-seams.md index af22ba4c15..ff22465148 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -17,6 +17,7 @@ flowchart LR pkg_session["session"] svc_sessions["ctx.sessions
In-memory session store"] pkg_agent["agent"] + pkg_cli_demo["cli-demo"] pkg_session_persistence["session-persistence"] pkg_session_query["session-query"] pkg_subagent_inprocess["subagent-inprocess"] @@ -132,6 +133,7 @@ flowchart LR svc_agentLoop --> pkg_agent_spine_demo svc_agents --> pkg_acp svc_agents --> pkg_agent_loop + svc_agents --> pkg_cli_demo svc_agents --> pkg_invariants svc_agents --> pkg_stdio_demo svc_agents --> pkg_subagent_inprocess @@ -152,6 +154,7 @@ flowchart LR svc_sessionPersistence --> pkg_session_query svc_sessions --> pkg_agent svc_sessions --> pkg_agent_loop + svc_sessions --> pkg_cli_demo svc_sessions --> pkg_invariants svc_sessions --> pkg_session_persistence svc_sessions --> pkg_session_query @@ -183,14 +186,14 @@ flowchart LR | ctx key | Role | Owner | Implementations | Direct consumers | Companion plugins | Note | | --- | --- | --- | --- | --- | --- | --- | | `ctx.llm` | `seam` | [`llm`](../packages/llm/llm) | [`llm-deepseek`](../packages/llm/llm-deepseek), [`llm-pi-ai`](../packages/llm/llm-pi-ai), [`llm-replay`](../packages/support/llm-replay) | [`agent-loop`](../packages/core/agent-loop), [`compact-basic`](../packages/compact/compact-basic) | - | Adapters register provider implementations; the loop and compaction call the provider-neutral stream service. | -| `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. | +| `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`cli-demo`](../packages/examples/cli-demo), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. | | `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`session-query`](../packages/session-query/session-query) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. | | `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | - | - | - | Resolves live and optional persisted logs into one logical corpus for exact reads. | | `ctx.systemPrompt` | `core` | [`system-prompt`](../packages/core/system-prompt) | - | [`agent-loop`](../packages/core/agent-loop), [`tools`](../packages/core/tools), [`tool-fs`](../packages/fs/tool-fs), [`tool-web`](../packages/web/tool-web) | - | Collects prompt sections and model-facing tool schemas for each step. | | `ctx.tools` | `core` | [`tools`](../packages/core/tools) | - | [`agent-loop`](../packages/core/agent-loop), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tool-bash`](../packages/bash/tool-bash), [`tool-cordis`](../packages/cordis/tool-cordis), [`tool-fs`](../packages/fs/tool-fs), [`tool-skill`](../packages/skill/tool-skill), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-todo`](../packages/todo/tool-todo), [`tool-web`](../packages/web/tool-web), [`acp`](../packages/ui/acp) | - | Registers capabilities, owns Code Mode transport, and routes calls through pre-policy, monotonic guards, around dispatch, post-policy, and final-result observation. | | `ctx.userInteraction` | `seam` | [`user-interaction`](../packages/ui/user-interaction) | [`stdio-demo`](../packages/examples/stdio-demo), [`acp`](../packages/ui/acp) | [`tool-ask-user`](../packages/ui/tool-ask-user), [`stdio-demo`](../packages/examples/stdio-demo), [`acp`](../packages/ui/acp) | - | UI front doors provide the active human-answer provider; tool-ask-user pauses a tool call on the provider-neutral ask() promise. | | `ctx.skills` | `seam` | [`skill`](../packages/skill/skill) | [`skill-local`](../packages/skill/skill-local) | [`tool-skill`](../packages/skill/tool-skill) | - | Merges provider skill catalogs; tool-skill renders the session-prefix catalog and loads complete skill bodies. | -| `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`stdio-demo`](../packages/examples/stdio-demo), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles and the create/resume factory seam. | +| `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`cli-demo`](../packages/examples/cli-demo), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`stdio-demo`](../packages/examples/stdio-demo), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles and the create/resume factory seam. | | `ctx.agentLoop` | `bundle` | [`agent-loop`](../packages/core/agent-loop) | - | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | - | The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package. | | `ctx.bash` | `seam` | [`bash`](../packages/bash/bash) | [`bash-local`](../packages/bash/bash-local), [`bash-sandbox`](../packages/bash/bash-sandbox) | [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors replace bash-local without touching them. | | `ctx.sandbox` | `seam` | [`sandbox`](../packages/sandbox/sandbox) | [`sandbox-local`](../packages/sandbox/sandbox-local) | [`bash-sandbox`](../packages/bash/bash-sandbox) | - | Consumers hand over the exact argv they are about to spawn; same-world backends wrap it under a per-call policy and report enforcement. | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index af8ef0832c..54438b0738 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -169,6 +169,30 @@ Depends on: [`LocalConfig`](#deepseek-aidsh-bash-local) · [`SandboxMode`](core- Source: [`packages/bash/bash-sandbox/src/index.ts:26`](../packages/bash/bash-sandbox/src/index.ts) +## `@deepseek-ai/dsh-cli-demo` + +```ts config-catalog +/** App config forwarded to the spine, pre-created agent, and JSONL backend. */ +export interface Config { + /** Model name for the `main` agent; a matching adapter must be registered. */ + model: string + /** Deployment persona forwarded to the system-prompt plugin. */ + persona?: string + /** Explicit model-facing tool order forwarded to the system-prompt plugin. */ + toolOrder?: string[] + /** Tool-registry presentation config forwarded through agent-spine-demo. */ + tools?: ToolsConfig + /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */ + persistenceRoot?: string + /** Skill registry, local-provider, and model-facing consumer config. */ + skills?: agentCore.SkillConfig +} +``` + +Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) + +Source: [`packages/examples/cli-demo/src/index.ts:21`](../packages/examples/cli-demo/src/index.ts) + ## `@deepseek-ai/dsh-code-runtime-worker` ```ts config-catalog diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index ec2da1408d..794466b60b 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -27,7 +27,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | | `session/created` | `emit` | [`packages/core/session/src/index.ts:47`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:57`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | -| `session/event` | `emit` | [`packages/core/session/src/index.ts:69`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio) | +| `session/event` | `emit` | [`packages/core/session/src/index.ts:69`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`cli-demo`](../packages/examples/cli-demo), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio) | | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:79`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:92`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:66`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | diff --git a/docs/module-graph.md b/docs/module-graph.md index 5d5ef1addf..6400ba89c9 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -111,6 +111,7 @@ flowchart TD subgraph group_examples["packages/examples"] pkg_acp_demo["acp-demo"] pkg_agent_spine_demo["agent-spine-demo"] + pkg_cli_demo["cli-demo"] pkg_jsonrpc_demo["jsonrpc-demo"] pkg_stdio_demo["stdio-demo"] end @@ -340,6 +341,13 @@ flowchart TD pkg_acp_demo --> pkg_session_persistence_jsonl pkg_acp_demo --> pkg_tools pkg_acp_demo --> pkg_user_interaction + pkg_cli_demo --> pkg_agent + pkg_cli_demo --> pkg_agent_spine_demo + pkg_cli_demo --> pkg_app_boot + pkg_cli_demo --> pkg_llm + pkg_cli_demo --> pkg_session + pkg_cli_demo --> pkg_session_persistence_jsonl + pkg_cli_demo --> pkg_tools pkg_stdio_demo --> pkg_agent pkg_stdio_demo --> pkg_agent_spine_demo pkg_stdio_demo --> pkg_app_boot @@ -427,4 +435,5 @@ flowchart TD | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | +| [`cli-demo`](../packages/examples/cli-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools) | | [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | diff --git a/examples/README.md b/examples/README.md index 5db1e18372..d9e3e544db 100644 --- a/examples/README.md +++ b/examples/README.md @@ -1,6 +1,6 @@ # Examples -Runnable demos (not workspaces) that showcase how the harness is wired. Each example is a **thin leaf**: a `cordis.yml` that picks the swappable backends (an LLM adapter, a bash executor), loads one app package, and may add optional product tools or demo-only mocks. The composition — the spine, the front-door cluster, and the boot glue — lives in the app packages ([`@deepseek-ai/dsh-stdio-demo`](../packages/examples/stdio-demo), [`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo)) and the [`@deepseek-ai/dsh-agent-spine-demo`](../packages/examples/agent-spine-demo) bundle they share. There is no `start.ts`; the `demo:*` scripts invoke each app package's `bin`. +Runnable demos (not workspaces) that showcase how the harness is wired. Each example is a **thin leaf**: a `cordis.yml` that picks the swappable backends (an LLM adapter, a bash executor), loads one app package, and may add optional product tools or demo-only mocks. The composition — the spine, the front-door cluster, and the boot glue — lives in the app packages ([`@deepseek-ai/dsh-stdio-demo`](../packages/examples/stdio-demo), [`@deepseek-ai/dsh-cli-demo`](../packages/examples/cli-demo), [`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo)) and the [`@deepseek-ai/dsh-agent-spine-demo`](../packages/examples/agent-spine-demo) bundle they share. There is no `start.ts`; the `demo:*` scripts invoke each app package's `bin`. ## echo-agent @@ -17,7 +17,7 @@ Run with: `pnpm run demo:echo`. When prompted, type "echo " to trigge A REPL agent demo: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite, `subagent` delegation, and the `todo_write` task tracker on the same `@deepseek-ai/dsh-stdio-demo` app. The UI is a terminal readline REPL. -Run with: `pnpm run demo:repl` (needs `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. +Run interactively with `pnpm run demo:repl`, or run one headless task with `pnpm run demo:cli -- "task"` (both need `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. Run the Code Mode overlay with `pnpm run demo:code-mode`, or pass `acp` for the ACP example. See the [Code Mode example](coding-agent/README.md#code-mode) for its composition and a sample task. diff --git a/examples/coding-agent/README.md b/examples/coding-agent/README.md index 380ab8134f..c9f606766d 100644 --- a/examples/coding-agent/README.md +++ b/examples/coding-agent/README.md @@ -1,6 +1,6 @@ # coding-agent -The REPL agent demo wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + `todo_write` + stdio chat + JSONL persistence, loaded from `cordis.yml`. The UI is a terminal readline REPL. +Coding-agent demo wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + workflows + `todo_write` + JSONL persistence. `cordis.yml` runs the terminal readline REPL; `cli.cordis.yml` keeps the same coding capabilities behind a headless one-shot CLI. ## Run it @@ -17,10 +17,24 @@ Type a coding task. The agent works through the `read`/`write`/`edit` filesystem > fix the failing test in /path/to/project [main turn 1] (reasoning…) [tool call] bash({"command": "node --test", "workdir": "/path/to/project"}) - [tool result] … [exit code: 1] +[tool result] … [exit code: 1] … ``` +### One-shot CLI + +Run one task through all model and tool steps, flush its fresh session, print the final result, and exit: + +```sh +pnpm run demo:cli -- "fix the failing test in this workspace" +pnpm run demo:cli --output-format json -- "summarize the current implementation" +pnpm run demo:cli --output-format stream-json -- "run the focused tests" +``` + +The root command supplies `cli.cordis.yml`, which disables HMR and the REPL app and inserts [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo). Exactly one quoted positional task is required; there is no `-p` flag. `text` prints the last text-bearing assistant message, `json` prints one DSH-native result record, and `stream-json` emits the parent `main` session's canonical task-turn events before that record. Non-completed turns retain partial output but exit nonzero; argument and boot failures leave stdout empty. + +This is non-interactive automation with the same local bash, filesystem, skill, subagent, workflow, and todo capabilities as the REPL. It can mutate the launch workspace and spend provider tokens. No prompt, approval, resume, further turn, or stdin context is available in v1; see the [CLI package contract](../../packages/examples/cli-demo/README.md). + ### Resuming a prior session Each run starts a fresh session by default (its event log lands under `./.sessions/`). To **continue** a previous conversation, set `RESUME_SESSION_ID` to that session's id — the `main` agent then rehydrates the persisted log instead of starting fresh, so the model sees the earlier turns as history: @@ -55,7 +69,7 @@ This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads | `hmr` (`@cordisjs/plugin-hmr`) | the dev/demo edit-reload loop — a **leaf** entry (not baked into the app) because it is Loader-only and needs `node --expose-internals`, which `demo:repl` passes | | `llm-deepseek` | real `LlmAdapter` via config (`!!js process.env.…` secrets); swap one line to `@deepseek-ai/dsh-llm-pi-ai` for the library-backed twin | | `bash` (`dsh-bash-local`) | the executor implementation — the swappable half of the bash seam. The model-facing `bash`/`bash_output`/`bash_kill` tool schemas (`tool-bash`) come from `agent-core`, so only the executor is a leaf choice | -| `stdio-agent` (`@deepseek-ai/dsh-stdio-demo`) | the app bundle: the agent-core spine + console logger + JSONL persistence + readline UI + a pre-created `main` agent. Its config carries the model, system prompt, `persistenceRoot` (`./.sessions`), and `resumeSessionId` — so persistence and the agent are configured here, not wired as separate leaf plugins | +| `stdio-agent` (`@deepseek-ai/dsh-stdio-demo`) | the REPL app bundle: the agent-core spine + console logger + JSONL persistence + readline UI + a pre-created `main` agent. Its config carries the model, system prompt, `persistenceRoot` (`./.sessions`), and `resumeSessionId` — so persistence and the agent are configured here, not wired as separate leaf plugins | | `subagent`, `subagent-spawn`, `subagent-fork` | the subagent provider registry plus the two in-process backends: a fresh child and a child seeded with the parent's completed-turn prefix | | `tool-subagent`, `tool-subagent-fork` | two model-facing `dsh-tool-subagent` loads, each bound to a different provider and exposed under a distinct tool name (`subagent`, `subagent_fork`) | | `tool-todo` | the model-facing `todo_write` tool; writes the whole task list to the session log and renders as a checklist in stdio | @@ -69,4 +83,4 @@ This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads - `tests/compaction.e2e.ts` — the compaction smoke: a real multi-step bash task runs with a deliberately tiny context window so the auto-compaction listener fires MID-SESSION. Verifies the WORLD — a `compact/start…end` pair landed in the real log, the surface shrank (a replace node shadowed older nodes), and the agent still produced a correct final answer after compaction. - `tests/todo-write.e2e.ts` — a real model drives the real `todo_write` tool and the test verifies the resulting `todo/write` session event. -These self-skip without `DEEPSEEK_API_KEY`. `tests/code-mode.e2e.ts` is the with-key Code Mode proof — a real model, a two-tool task, asserting the wire tool list was exactly `[run_code]`, the `tool/code-dispatch` events landed under the parent call, and the curated answer came back. The keyless boot smokes run in the default e2e gate: `tests/keyless-smoke.e2e.ts` (the full real tree, dummy key, no prompt → no model call) and `tests/code-mode-keyless-smoke.e2e.ts` (the same guard for the Code Mode overlay). +These self-skip without `DEEPSEEK_API_KEY`. `tests/code-mode.e2e.ts` is the with-key Code Mode proof — a real model, a two-tool task, asserting the wire tool list was exactly `[run_code]`, the `tool/code-dispatch` events landed under the parent call, and the curated answer came back. `tests/cli.e2e.ts` runs the one-shot bin with a real model and verifies its temporary file externally. The keyless Loader smokes run in the default e2e gate: `tests/keyless-smoke.e2e.ts`, `tests/code-mode-keyless-smoke.e2e.ts`, and `tests/cli-keyless-smoke.e2e.ts`; the CLI smoke mocks only the LLM boundary and asserts a real bash round trip plus persisted stream output. diff --git a/examples/coding-agent/cli.cordis.yml b/examples/coding-agent/cli.cordis.yml new file mode 100644 index 0000000000..5a58dfd889 --- /dev/null +++ b/examples/coding-agent/cli.cordis.yml @@ -0,0 +1,24 @@ +# One-shot headless overlay: keep the coding capabilities from `cordis.yml`, +# replace its REPL app with the stdout-pure CLI app, and disable dev-only HMR. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./cordis.yml + patches: + - id: hmr + name: '@cordisjs/plugin-hmr' + disabled: true + - id: stdio-agent + name: '@deepseek-ai/dsh-stdio-demo' + disabled: true + - insert: + - id: cli-agent + name: '@deepseek-ai/dsh-cli-demo' + config: + model: deepseek-v4-flash + persistenceRoot: './.sessions' + persona: | + You are coding-agent, a coding assistant powered by the {{model}} model. + + Verify your work by running the code or tests. Keep answers brief and + factual. diff --git a/examples/coding-agent/tests/cli-keyless-smoke.e2e.ts b/examples/coding-agent/tests/cli-keyless-smoke.e2e.ts new file mode 100644 index 0000000000..c2d0f3f946 --- /dev/null +++ b/examples/coding-agent/tests/cli-keyless-smoke.e2e.ts @@ -0,0 +1,43 @@ +import { readdir } from 'node:fs/promises' +import { fileURLToPath } from 'node:url' +import { describe, expect, it } from 'vitest' +import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke' +import type { SessionEvent } from '@deepseek-ai/dsh-session' + +const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url)) +const configPath = fileURLToPath(new URL('./fixtures/cli.cordis.yml', import.meta.url)) +const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) + +describe('coding-agent one-shot CLI keyless smoke', () => { + it('boots the real Loader tree, runs a real bash tool round trip, and persists the turn', async () => { + let persisted = false + const { stdout, stderr } = await runLoaderSmoke({ + label: 'coding-agent CLI', + tempDirPrefix: 'coding-cli-smoke-', + binScript, + configPath, + binArgs: ['--config', configPath, '--output-format', 'stream-json', 'prove the tool path'], + tsconfigPath, + inspect: async (cwd) => { + const files = await readdir(cwd, { recursive: true }) + persisted = files.some(file => file.endsWith('.jsonl')) + }, + }) + const lines = stdout.trimEnd().split('\n').map(line => JSON.parse(line) as Record) + const events = lines.slice(0, -1).map(line => line['event'] as SessionEvent) + const result = lines.at(-1) + expect(stderr).toBe('') + expect(events.some(event => event.type === 'tool/call' && event.data.name === 'bash')).toBe(true) + const toolResult = events.find(event => event.type === 'tool/result') + expect(JSON.stringify(toolResult)).toContain('CLI_TOOL_ROUND_TRIP') + expect(result).toMatchObject({ + type: 'result', + success: true, + turn: 1, + reason: { kind: 'completed' }, + usage: { inputTokens: 18, outputTokens: 8, cacheReadTokens: 2, reasoningTokens: 1 }, + }) + expect(String(result?.['result'])).toContain('CLI_TOOL_ROUND_TRIP') + expect(persisted).toBe(true) + }, LOADER_SMOKE_TEST_TIMEOUT_MS) +}) diff --git a/examples/coding-agent/tests/cli.e2e.ts b/examples/coding-agent/tests/cli.e2e.ts new file mode 100644 index 0000000000..a05e19fc06 --- /dev/null +++ b/examples/coding-agent/tests/cli.e2e.ts @@ -0,0 +1,33 @@ +import { readFile, writeFile } from 'node:fs/promises' +import { join } from 'node:path' +import { fileURLToPath } from 'node:url' +import { describe, expect, it } from 'vitest' +import { runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke' + +const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url)) +const configPath = fileURLToPath(new URL('../cli.cordis.yml', import.meta.url)) +const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) +const hasKey = Boolean(process.env.DEEPSEEK_API_KEY) + +describe.skipIf(!hasKey)('coding-agent one-shot CLI with real model', () => { + it('modifies a temporary workspace and verifies the file outside the agent', async () => { + let verified = '' + const { stdout } = await runLoaderSmoke({ + label: 'coding-agent CLI real model', + tempDirPrefix: 'coding-cli-real-', + binScript, + configPath, + binArgs: [ + '--config', + configPath, + 'Read task.txt, replace its complete contents with exactly "value=after" followed by a newline, read it again, and report briefly.', + ], + tsconfigPath, + processTimeoutMs: 120_000, + prepare: cwd => writeFile(join(cwd, 'task.txt'), 'value=before\n'), + inspect: async (cwd) => { verified = await readFile(join(cwd, 'task.txt'), 'utf8') }, + }) + expect(verified).toBe('value=after\n') + expect(stdout.trim().length).toBeGreaterThan(0) + }, 135_000) +}) diff --git a/examples/coding-agent/tests/fixtures/cli-mock-llm.ts b/examples/coding-agent/tests/fixtures/cli-mock-llm.ts new file mode 100644 index 0000000000..6447ba1e18 --- /dev/null +++ b/examples/coding-agent/tests/fixtures/cli-mock-llm.ts @@ -0,0 +1,37 @@ +import type { Context } from 'cordis' +import { CallId, LlmAdapter, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm' + +/** Keyless coding smoke adapter: one real bash call followed by a final answer. */ +class CliMockAdapter extends LlmAdapter { + async * stream(options: GenerateOptions): AsyncIterable { + const toolResult = options.messages.at(-1)?.content.find(block => block.type === 'tool-result') + if (toolResult === undefined) { + const args = JSON.stringify({ command: 'printf CLI_TOOL_ROUND_TRIP', description: 'Prove the CLI tool round trip.' }) + yield { type: 'block-start', index: 0, blockType: 'tool-call' } + yield { type: 'tool-call-delta', index: 0, id: CallId('cli-smoke-call'), name: 'bash', argumentsDelta: args } + yield { type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('cli-smoke-call'), name: 'bash', arguments: args } } + yield { type: 'usage', usage: { inputTokens: 11, outputTokens: 3, cacheReadTokens: 2 } } + yield { type: 'finish', reason: { kind: 'tool-calls' } } + return + } + + const toolText = toolResult.content + .filter(block => block.type === 'text') + .map(block => block.text) + .join('') + const reply = `CLI tool round trip complete: ${toolText.trim()}` + yield { type: 'block-start', index: 0, blockType: 'text' } + yield { type: 'text-delta', index: 0, text: reply } + yield { type: 'block-end', index: 0, block: { type: 'text', text: reply } } + yield { type: 'usage', usage: { inputTokens: 7, outputTokens: 5, reasoningTokens: 1 } } + yield { type: 'finish', reason: { kind: 'stop' } } + } +} + +export const name = 'cli-mock-llm' +export const inject = ['llm'] + +/** Register the keyless `cli-mock` adapter. */ +export function apply(ctx: Context): void { + ctx.llm.registerAdapter(['cli-mock'], new CliMockAdapter()) +} diff --git a/examples/coding-agent/tests/fixtures/cli.cordis.yml b/examples/coding-agent/tests/fixtures/cli.cordis.yml new file mode 100644 index 0000000000..bdec0154c4 --- /dev/null +++ b/examples/coding-agent/tests/fixtures/cli.cordis.yml @@ -0,0 +1,24 @@ +- id: cli-mock-llm + name: './cli-mock-llm.ts' + +- id: base + name: '@cordisjs/plugin-include' + config: + path: ../../cordis.yml + patches: + - id: hmr + name: '@cordisjs/plugin-hmr' + disabled: true + - id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + disabled: true + - id: stdio-agent + name: '@deepseek-ai/dsh-stdio-demo' + disabled: true + - insert: + - id: cli-agent + name: '@deepseek-ai/dsh-cli-demo' + config: + model: cli-mock + persistenceRoot: './.sessions' + persona: 'Keyless CLI smoke.' diff --git a/knip.json b/knip.json index 71c9d1e01d..754aace023 100644 --- a/knip.json +++ b/knip.json @@ -9,6 +9,7 @@ "examples/echo-agent/src/*.ts", "examples/echo-agent/tests/**/*.e2e.ts", "examples/coding-agent/tests/**/*.e2e.ts", + "examples/coding-agent/tests/fixtures/*.ts", "examples/cordis-agent/tests/**/*.e2e.ts", "examples/acp-agent/tests/**/*.e2e.ts", "examples/*/tests/**/*.snapshot.ts" @@ -90,6 +91,10 @@ "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] }, + "packages/examples/cli-demo": { + "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], + "project": ["src/**/*.ts", "tests/**/*.ts"] + }, "packages/ui/stdio": { "entry": ["tests/**/*.spec.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] diff --git a/package.json b/package.json index aaec1e62c4..d6f64f210b 100644 --- a/package.json +++ b/package.json @@ -74,6 +74,7 @@ "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-cordis-config && pnpm run verify-node-next-types && pnpm run verify-runtime-closure", "demo:echo": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/echo-agent/cordis.yml", "demo:repl": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/coding-agent/cordis.yml", + "demo:cli": "node --expose-internals --import tsx packages/examples/cli-demo/src/bin.ts --config examples/coding-agent/cli.cordis.yml", "demo:code-mode": "node scripts/demo-code-mode.mjs", "demo:cordis": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/cordis-agent/cordis.yml", "demo:acp": "node --import tsx packages/examples/acp-demo/src/bin.ts --config examples/acp-agent/cordis.yml", diff --git a/packages/README.md b/packages/README.md index db364421b1..fcd29c3666 100644 --- a/packages/README.md +++ b/packages/README.md @@ -28,7 +28,7 @@ Packages are grouped by modular role at `packages///`. The group dir | [`session-persistence/`](session-persistence/README.md) | Persistence capability family: the seam + JSONL/SQLite backends | Product — stable surface | | [`session-query/`](session-query/README.md) | Session retrieval family: logical corpus, surface records, and bounded exact reads | Product — stable surface | | [`ui/`](ui/README.md) | Editor/client integration surfaces: ACP bridge, JSON-RPC SDK server, user-approval/user-interaction seams, ask-user tool | Product — stable surface | -| [`examples/`](examples/README.md) | Demo bundles (agent-spine + stdio/ACP/JSON-RPC bins) the leaves load | Support — example infra | +| [`examples/`](examples/README.md) | Demo bundles (agent-spine + stdio/one-shot CLI/ACP/JSON-RPC bins) the leaves load | Support — example infra | | [`support/`](support/README.md) | Support infrastructure (invariants, replay, Loader smokes) | Support — lower compatibility expectations | | [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (the `Branded` primitive) | Support — small, stable, harness-dep-free | diff --git a/packages/examples/README.md b/packages/examples/README.md index 5ee0206d0f..d961e38aeb 100644 --- a/packages/examples/README.md +++ b/packages/examples/README.md @@ -6,10 +6,11 @@ Pre-composed plugin bundles a thin leaf `cordis.yml` loads instead of assembling |---|---|---| | `agent-spine-demo/` | `@deepseek-ai/dsh-agent-spine-demo` | The executor-less/UI-less agent spine as one bundle plugin (`timer` + `llm` + sessions + system-prompt + tools + skills + agents + invariants + `tool-bash` + `tool-skill` + `agent-loop`) | | `stdio-demo/` | `@deepseek-ai/dsh-stdio-demo` | Terminal stdio chat app: the spine + console logger + readline UI + a pre-created `main` agent, with a boot `bin` | +| `cli-demo/` | `@deepseek-ai/dsh-cli-demo` | Headless one-shot app: the spine + JSONL persistence + a pre-created `main` agent, with text and DSH-native JSON output | | `acp-demo/` | `@deepseek-ai/dsh-acp-demo` | ACP server app: the spine + JSONL persistence + the [`acp`](../ui/acp/README.md) bridge (no stdout logger), with a boot `bin` | | `jsonrpc-demo/` | `@deepseek-ai/dsh-jsonrpc-demo` | Bin-only runtime that boots an external `cordis.yml` for the stdio JSON-RPC SDK client | -`agent-spine-demo` is the shared bundle; `stdio-demo` and `acp-demo` compose it with opposite front-door clusters (console logger + readline UI vs the stdout-owning ACP bridge) and own their boot bins. `jsonrpc-demo` mounts no composition of its own — it boots whatever tree the deployment's `cordis.yml` names, and is what the Python SDK runtime launches. +`agent-spine-demo` is the shared bundle; `stdio-demo`, `cli-demo`, and `acp-demo` compose it with terminal, headless one-shot, and ACP front doors and own their boot bins. `jsonrpc-demo` mounts no composition of its own — it boots whatever tree the deployment's `cordis.yml` names, and is what the Python SDK runtime launches. These are **not** product API. The spine pieces they bundle live in [`core/`](../core/README.md), the bridges/channels/boot-glue in [`ui/`](../ui/README.md), and the swappable backends (LLM adapter, bash executor) in their capability groups; a demo bundle just picks one concrete composition of them. Swap or fork one freely. diff --git a/packages/examples/cli-demo/README.md b/packages/examples/cli-demo/README.md new file mode 100644 index 0000000000..558c5eeff3 --- /dev/null +++ b/packages/examples/cli-demo/README.md @@ -0,0 +1,62 @@ +# @deepseek-ai/dsh-cli-demo + +Headless one-shot app and bin for running one coding-agent task without a readline or editor client. The app composes [`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md), JSONL persistence, and one fresh `main` agent; the bin submits one task, waits through all model and tool steps, emits the selected result, disposes to quiescence, and exits. + +The package mounts no console logger, readline UI, user-interaction service, or `ask_user_question` tool. Stdout is reserved for the selected output format; diagnostics use stderr. + +## Config + +| Key | Default | Routed to | +|---|---|---| +| `model` | required | the pre-created `main` agent's model | +| `persona` | — | the deployment persona in `dsh-system-prompt` | +| `toolOrder` | lexicographic | explicit model-facing tool order in `dsh-system-prompt` | +| `tools` | `{ mode: 'native' }` | tool-registry presentation config through `dsh-agent-spine-demo` | +| `skills` | owner defaults | skill registry, local provider, and model-facing skill tool | +| `persistenceRoot` | `./.sessions` | JSONL session root | + +Each process creates a new session whose workspace cwd is the launch directory. The app has no resume setting. + +## CLI contract + +```sh +dsh-cli-demo [--config path] [--output-format text|json|stream-json] +``` + +`--config` defaults to `./cordis.yml`; `--output-format` defaults to `text`. Exactly one nonblank positional task is required, so quote tasks containing spaces. `--help` prints usage without booting. There is no `-p` or `--print` flag. + +The root coding demo supplies its overlay: + +```sh +pnpm run demo:cli -- "inspect the failing test and fix it" +``` + +Loader configs with bare package specifiers require `node --expose-internals` or the Loader's optional native fallback. The root command supplies the Node flag. + +### Output formats + +- `text` writes the last assistant message containing text, followed by one newline. +- `json` writes one DSH-native result record: `{ type: "result", success, sessionId, turn, result, reason, usage? }`. `usage` sums every model step in the task turn. +- `stream-json` writes each canonical event from the `main` session's task turn as `{ type: "session_event", sessionId, event }`, then the same result record. Child-agent activity appears only through the parent tool events and results. + +Only `reason.kind === "completed"` exits successfully. Other durable turn endings still emit partial text or a result record, add a stderr diagnostic, and exit nonzero. Argument and boot failures leave stdout empty. SIGINT and SIGTERM cancel active work, await disposal, and exit 130 and 143 respectively. + +The task turn is explicitly flushed before final output. Session logs remain under `persistenceRoot` after the process exits. + +## Operational safety + +The coding overlay retains local bash, filesystem, skill, subagent, workflow, and todo capabilities. A task can therefore mutate the launch workspace, run commands, spawn child agents, and consume provider tokens. Run the CLI from the intended project directory, review the leaf's capability and sandbox configuration, and do not treat non-interactive execution as an approval boundary. + +## Model Experience + +### One-shot task turn + +**What the model sees**: The positional task becomes one user message. Through `dsh-agent-spine-demo`, the `main` agent also receives the configured persona, skill catalog, visible tool schemas, and retained tool results needed for later steps in the same turn. + +**Token effect**: The task, prompt sections, tool schemas, assistant output, and tool results consume tokens on each model step. JSON event streaming and final rendering add no model tokens; delegated child work has its own model usage and is not included in the parent result's `usage` total. + +## Known Limitations and Deferred Work + +- **One fresh main session per process** — there is no resume, second prompt, stdin context, or concurrent top-level session in this app. +- **No interactive question or approval provider** — tools that require a human answer cannot complete unless a different leaf composes a non-interactive provider with explicit policy. +- **Streaming is main-session-only** — child sessions are not flattened into the stream, and aggregate usage covers only model steps recorded on the parent task turn. diff --git a/packages/examples/cli-demo/package.json b/packages/examples/cli-demo/package.json new file mode 100644 index 0000000000..3268f9733f --- /dev/null +++ b/packages/examples/cli-demo/package.json @@ -0,0 +1,59 @@ +{ + "name": "@deepseek-ai/dsh-cli-demo", + "description": "Headless one-shot coding-agent app with text and DSH-native JSON output", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "bin": { + "dsh-cli-demo": "lib/bin.js" + }, + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./bin": { + "types": "./lib/types/bin.d.ts", + "default": "./lib/bin.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/bin.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@cordisjs/plugin-include": "^1.0.4", + "@cordisjs/plugin-loader": "^1.0.0-rc.5", + "@deepseek-ai/dsh-agent": "^0.0.1", + "@deepseek-ai/dsh-agent-spine-demo": "^0.0.1", + "@deepseek-ai/dsh-app-boot": "^0.0.1", + "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", + "@deepseek-ai/dsh-session-persistence-jsonl": "^0.0.1", + "@deepseek-ai/dsh-tools": "^0.0.1", + "cordis": "^4.0.0-rc.7", + "schemastery": "^3.17.0" + }, + "devDependencies": { + "@cordisjs/plugin-include": "workspace:^", + "@cordisjs/plugin-loader": "workspace:^", + "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-spine-demo": "workspace:^", + "@deepseek-ai/dsh-app-boot": "workspace:^", + "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", + "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", + "@deepseek-ai/dsh-system-prompt": "workspace:^", + "@deepseek-ai/dsh-tools": "workspace:^", + "cordis": "^4.0.0-rc.7", + "schemastery": "^3.17.0" + } +} diff --git a/packages/examples/cli-demo/src/bin.ts b/packages/examples/cli-demo/src/bin.ts new file mode 100644 index 0000000000..5b6638ef72 --- /dev/null +++ b/packages/examples/cli-demo/src/bin.ts @@ -0,0 +1,34 @@ +#!/usr/bin/env node +/** + * Process wrapper for `dsh-cli-demo`; covered parsing and task execution live in + * `cli.ts` while this entry owns Unix signal-to-exit-code mapping. + * @module @deepseek-ai/dsh-cli-demo/bin + */ + +import { installFailLoud } from '@deepseek-ai/dsh-app-boot' +import { executeCli } from './cli.ts' + +const NAME = 'dsh-cli-demo' + +/* v8 ignore start -- thin self-executing process glue; built-bin tests exercise + real argv, signals, Loader boot, output, and exit codes */ +const abort = new AbortController() +let signalExitCode: number | undefined +const interrupt = (signal: 'SIGINT' | 'SIGTERM', code: number): void => { + signalExitCode ??= code + if (!abort.signal.aborted) abort.abort(`received ${signal}`) +} +const onSigint = (): void => { interrupt('SIGINT', 130) } +const onSigterm = (): void => { interrupt('SIGTERM', 143) } +const uninstallFailLoud = installFailLoud(NAME) +process.on('SIGINT', onSigint) +process.on('SIGTERM', onSigterm) +try { + const code = await executeCli(process.argv.slice(2), { signal: abort.signal }) + process.exitCode = signalExitCode ?? code +} finally { + process.off('SIGINT', onSigint) + process.off('SIGTERM', onSigterm) + uninstallFailLoud() +} +/* v8 ignore stop */ diff --git a/packages/examples/cli-demo/src/cli.ts b/packages/examples/cli-demo/src/cli.ts new file mode 100644 index 0000000000..6e42220939 --- /dev/null +++ b/packages/examples/cli-demo/src/cli.ts @@ -0,0 +1,380 @@ +/** + * Covered command parser and one-turn driver for `dsh-cli-demo`. The executable + * entry only installs process signal handlers and delegates here. + * @module @deepseek-ai/dsh-cli-demo/cli + */ + +import { parseArgs } from 'node:util' +import type { Context } from 'cordis' +import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import type { TokenUsage } from '@deepseek-ai/dsh-llm' +import type { SessionEvent, TurnEndReason } from '@deepseek-ai/dsh-session' +import { boot, loadEnv, resolveConfigPath } from '@deepseek-ai/dsh-app-boot' + +const CLI_NAME = 'dsh-cli-demo' +const DEFAULT_CONFIG_PATH = './cordis.yml' +const OUTPUT_FORMATS = ['text', 'json', 'stream-json'] as const +const USAGE = `Usage: ${CLI_NAME} [--config path] [--output-format text|json|stream-json] \n` + +/** Supported CLI output encodings. */ +export type OutputFormat = typeof OUTPUT_FORMATS[number] + +/** Parsed command: help exits before boot; run carries one validated task. */ +export type CliCommand = + | { readonly kind: 'help' } + | { + readonly kind: 'run' + readonly configPath: string + readonly outputFormat: OutputFormat + readonly task: string + } + +/** DSH-native final record emitted by JSON modes. */ +export interface CliResult { + readonly type: 'result' + readonly success: boolean + readonly sessionId: string + readonly turn: number + readonly result: string + readonly reason: TurnEndReason + readonly usage?: TokenUsage +} + +/** Options for one turn against the pre-created `main` agent. */ +export interface OneShotOptions { + /** Exactly one nonblank user task. */ + readonly task: string + /** Optional cancellation signal owned by the process wrapper. */ + readonly signal?: AbortSignal + /** Synchronous observer for each canonical event in the selected task turn. */ + readonly onEvent?: (sessionId: string, event: SessionEvent) => void +} + +/** Injectable process boundaries used by {@link executeCli}. */ +export interface CliRuntime { + /** Process cwd for config resolution and `.env` loading. */ + readonly cwd?: string + /** Cancellation signal, normally aborted by SIGINT or SIGTERM. */ + readonly signal?: AbortSignal + /** Loader boot boundary. */ + readonly boot?: (name: string, absoluteConfigPath: string) => Promise + /** Optional `.env` loader boundary. */ + readonly loadEnv?: (name: string, dir: string, warn: (line: string) => void) => void + /** Stdout sink; throws are treated as output failures. */ + readonly writeStdout?: (chunk: string) => unknown + /** Stderr diagnostic sink. */ + readonly writeStderr?: (chunk: string) => unknown + /** Context disposal boundary. */ + readonly dispose?: (ctx: Context) => Promise +} + +interface ParsedArguments { + readonly values: { + readonly config?: string + readonly 'output-format'?: string + readonly help?: boolean + } + readonly positionals: string[] +} + +class CliArgumentError extends Error { + constructor(message: string) { + super(message) + this.name = 'CliArgumentError' + } +} + +class CliInterruptedError extends Error { + constructor(reason: string) { + super(reason) + this.name = 'CliInterruptedError' + } +} + +/** Convert an unknown thrown value to an Error without losing its text. */ +function toError(error: unknown): Error { + return error instanceof Error ? error : new Error(String(error)) +} + +/** Render the reason carried by an AbortSignal. */ +function interruptionReason(signal: AbortSignal): string { + return signal.reason === undefined ? 'interrupted' : String(signal.reason) +} + +/** + * Parse the bin arguments and enforce the one-positional-task contract. + * @param args - arguments after the executable name. + * @returns a help or run command. + * @throws {@link CliArgumentError} for unknown flags, invalid formats, or task cardinality. + */ +export function parseCliArgs(args: readonly string[]): CliCommand { + let parsed: ParsedArguments + try { + parsed = parseArgs({ + args: [...args], + options: { + config: { type: 'string' }, + 'output-format': { type: 'string' }, + help: { type: 'boolean' }, + }, + allowPositionals: true, + strict: true, + }) + } catch (error: unknown) { + throw new CliArgumentError(toError(error).message) + } + + if (parsed.values.help === true) return { kind: 'help' } + if (parsed.positionals.length !== 1) { + throw new CliArgumentError(`expected exactly one positional task, received ${parsed.positionals.length}`) + } + // Cardinality was checked above, so index zero exists. + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + const task = parsed.positionals[0]! + if (task.trim().length === 0) throw new CliArgumentError('task must not be blank') + + const requestedFormat = parsed.values['output-format'] ?? 'text' + if (!OUTPUT_FORMATS.some(format => format === requestedFormat)) { + throw new CliArgumentError(`unsupported output format ${JSON.stringify(requestedFormat)}`) + } + return { + kind: 'run', + configPath: parsed.values.config ?? DEFAULT_CONFIG_PATH, + outputFormat: requestedFormat as OutputFormat, + task, + } +} + +/** Add one model step's usage into a detached turn total. */ +function addUsage(total: TokenUsage | undefined, step: TokenUsage): TokenUsage { + const next: TokenUsage = { + inputTokens: (total?.inputTokens ?? 0) + step.inputTokens, + outputTokens: (total?.outputTokens ?? 0) + step.outputTokens, + } + for (const key of ['cacheReadTokens', 'cacheWriteTokens', 'reasoningTokens'] as const) { + if (total?.[key] !== undefined || step[key] !== undefined) next[key] = (total?.[key] ?? 0) + (step[key] ?? 0) + } + return next +} + +/** Select the text blocks from an assistant message, or undefined when it has none. */ +function assistantText(event: Extract): string | undefined { + const blocks = event.data.content.filter(block => block.type === 'text') + return blocks.length === 0 ? undefined : blocks.map(block => block.text).join('') +} + +/** Wait for startup quiescence while making pre-run cancellation terminal. */ +async function waitForStartupIdle(agent: Agent, signal?: AbortSignal): Promise { + if (signal === undefined) { + await agent.whenIdle() + return + } + if (signal.aborted) { + agent.cancel(interruptionReason(signal)) + throw new CliInterruptedError(interruptionReason(signal)) + } + await new Promise((resolve, reject) => { + const onAbort = (): void => { + agent.cancel(interruptionReason(signal)) + reject(new CliInterruptedError(interruptionReason(signal))) + } + signal.addEventListener('abort', onAbort, { once: true }) + void agent.whenIdle().then(resolve, reject).finally(() => { + signal.removeEventListener('abort', onAbort) + }) + }) +} + +/** + * Run one message-triggered turn on the pre-created `main` agent, aggregate its + * final text and model usage, wait for idle plus an explicit persistence flush, + * and return its durable ending. Only the exact main-session task turn reaches + * `onEvent`; startup injections and unrelated sessions are ignored. + * @param ctx - settled Loader root containing `ctx.agents` and `ctx.sessions`. + * @param options - task, optional cancellation, and optional stream observer. + * @returns the DSH-native result envelope after durable quiescence. + */ +export async function runOneShot(ctx: Context, options: OneShotOptions): Promise { + const agent = ctx.get('agents')?.get(AgentId('main')) + if (agent === undefined) throw new Error('config did not create the required "main" agent') + await waitForStartupIdle(agent, options.signal) + + let targetTurn: number | undefined + let reason: TurnEndReason | undefined + let result = '' + let usage: TokenUsage | undefined + let outputError: Error | undefined + let resolveTurn!: () => void + let rejectTurn!: (error: Error) => void + let settled = false + const turnEnded = new Promise((resolve, reject) => { + resolveTurn = resolve + rejectTurn = reject + }) + + const settleResolved = (): void => { + settled = true + resolveTurn() + } + const settleRejected = (error: Error): void => { + settled = true + rejectTurn(error) + } + const observe = (sessionId: string, event: SessionEvent): void => { + if (outputError !== undefined || options.onEvent === undefined) return + try { + options.onEvent(sessionId, event) + } catch (error: unknown) { + outputError = toError(error) + agent.cancel('stream output failed') + } + } + + const disposeListener = ctx.on('session/event', (session, event) => { + if (session !== agent.session || settled) return + if (targetTurn === undefined) { + if (event.type !== 'turn/start' || event.data.trigger.kind !== 'message') return + targetTurn = event.data.turn + } + observe(session.id, event) + if (event.type === 'assistant/message' && event.data.turn === targetTurn) { + result = assistantText(event) ?? result + if (event.data.usage !== undefined) usage = addUsage(usage, event.data.usage) + } + if (event.type === 'turn/end' && event.data.turn === targetTurn) { + reason = event.data.reason + settleResolved() + } + }) + + const signal = options.signal + let onAbort: (() => void) | undefined + if (signal !== undefined) { + onAbort = (): void => { + agent.cancel(interruptionReason(signal)) + if (targetTurn === undefined) settleRejected(new CliInterruptedError(interruptionReason(signal))) + } + signal.addEventListener('abort', onAbort, { once: true }) + /* v8 ignore next -- closes the race between startup-idle completion and listener registration */ + if (signal.aborted) onAbort() + } + + try { + /* v8 ignore next -- skips send only when cancellation wins the listener-registration race above */ + if (!settled) { // eslint-disable-line @typescript-eslint/no-unnecessary-condition + agent.send([{ type: 'text', text: options.task }]) + } + await turnEnded + } finally { + if (onAbort !== undefined) signal?.removeEventListener('abort', onAbort) + disposeListener() + await agent.whenIdle() + } + + /* v8 ignore next 3 -- turnEnded resolves only from the matching branch that assigns both values */ + if (targetTurn === undefined || reason === undefined) { + throw new Error('task ended without a correlated turn/end event') + } + await ctx.sessions.flush(agent.session) + if (outputError !== undefined) throw outputError + return { + type: 'result', + success: reason.kind === 'completed', + sessionId: agent.session.id, + turn: targetTurn, + result, + reason, + ...usage === undefined ? {} : { usage }, + } +} + +/** Render one final result in the selected output encoding. */ +function renderResult(outputFormat: OutputFormat, result: CliResult): string { + return outputFormat === 'text' ? `${result.result}\n` : `${JSON.stringify(result)}\n` +} + +/** + * Render a non-completed turn reason for stderr. + * @param reason - durable turn ending to describe. + * @returns a concise diagnostic fragment. + */ +export function formatTurnFailure(reason: TurnEndReason): string { + switch (reason.kind) { + case 'completed': return 'completed' + case 'aborted': return reason.reason === undefined ? 'was aborted' : `was aborted: ${reason.reason}` + case 'error': return `failed at step ${reason.step}: ${reason.message}` + case 'disposed': return 'was disposed' + case 'max-tokens': return 'reached the model output-token limit' + case 'rejected': return `was rejected: ${reason.reason}` + case 'interrupted': return 'was interrupted during persistence recovery' + default: return `ended with ${JSON.stringify(reason)}` + } +} + +/** + * Parse, boot, run, render, diagnose, and dispose one CLI invocation. Argument + * and boot failures never write stdout; all booted contexts are disposed before + * this promise resolves. + * @param args - arguments after the executable name. + * @param runtime - optional injected process boundaries for tests and embedding. + * @returns the ordinary process exit code; the thin bin overrides it for Unix signals. + */ +export async function executeCli(args: readonly string[], runtime: CliRuntime = {}): Promise { + /* v8 ignore next -- default process sinks are exercised by the built-bin smoke */ + const writeStdout = runtime.writeStdout ?? (chunk => process.stdout.write(chunk)) + /* v8 ignore next -- default process sinks are exercised by the built-bin smoke */ + const writeStderr = runtime.writeStderr ?? (chunk => process.stderr.write(chunk)) + let command: CliCommand + try { + command = parseCliArgs(args) + } catch (error: unknown) { + writeStderr(`${CLI_NAME}: ${toError(error).message}\n${USAGE}`) + return 1 + } + if (command.kind === 'help') { + writeStdout(USAGE) + return 0 + } + + /* v8 ignore next -- default process cwd is exercised by the built-bin smoke */ + const cwd = runtime.cwd ?? process.cwd() + /* v8 ignore next -- default env/boot boundaries are exercised by the Loader and built-bin smokes */ + const loadEnvironment = runtime.loadEnv ?? loadEnv + /* v8 ignore next -- default env/boot boundaries are exercised by the Loader and built-bin smokes */ + const bootContext = runtime.boot ?? boot + /* v8 ignore next -- default disposal is exercised by the built-bin smoke */ + const disposeContext = runtime.dispose ?? (target => target.fiber.dispose()) + let ctx: Context | undefined + let exitCode = 1 + let diagnostic: string | undefined + try { + loadEnvironment(CLI_NAME, cwd, line => writeStderr(line)) + ctx = await bootContext(CLI_NAME, resolveConfigPath(command.configPath, undefined, cwd)) + if (runtime.signal?.aborted === true) throw new CliInterruptedError(interruptionReason(runtime.signal)) + const result = await runOneShot(ctx, { + task: command.task, + ...runtime.signal === undefined ? {} : { signal: runtime.signal }, + ...command.outputFormat === 'stream-json' + ? { onEvent: (sessionId: string, event: SessionEvent) => { + writeStdout(`${JSON.stringify({ type: 'session_event', sessionId, event })}\n`) + } } + : {}, + }) + writeStdout(renderResult(command.outputFormat, result)) + exitCode = result.success ? 0 : 1 + if (!result.success) diagnostic = `${CLI_NAME}: turn ${result.turn} ${formatTurnFailure(result.reason)}\n` + } catch (error: unknown) { + diagnostic = `${CLI_NAME}: ${toError(error).message}\n` + } finally { + if (ctx !== undefined) { + try { + await disposeContext(ctx) + } catch (error: unknown) { + diagnostic ??= `${CLI_NAME}: dispose failed: ${toError(error).message}\n` + exitCode = 1 + } + } + } + if (diagnostic !== undefined) writeStderr(diagnostic) + return exitCode +} diff --git a/packages/examples/cli-demo/src/index.ts b/packages/examples/cli-demo/src/index.ts new file mode 100644 index 0000000000..a2a2271b03 --- /dev/null +++ b/packages/examples/cli-demo/src/index.ts @@ -0,0 +1,63 @@ +/** + * Headless one-shot app composition: the default agent spine, JSONL session + * persistence, and one pre-created `main` agent. The CLI driver owns task + * submission and output; the app deliberately mounts no interactive or logging + * front door so stdout remains protocol-pure. + * @module @deepseek-ai/dsh-cli-demo + */ + +import type { Context } from 'cordis' +import z from 'schemastery' +import { AgentId } from '@deepseek-ai/dsh-agent' +import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools' +import * as agentCore from '@deepseek-ai/dsh-agent-spine-demo' +import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' + +const DEFAULT_PERSISTENCE_ROOT = './.sessions' + +export const name = 'cli-demo' + +/** App config forwarded to the spine, pre-created agent, and JSONL backend. */ +export interface Config { + /** Model name for the `main` agent; a matching adapter must be registered. */ + model: string + /** Deployment persona forwarded to the system-prompt plugin. */ + persona?: string + /** Explicit model-facing tool order forwarded to the system-prompt plugin. */ + toolOrder?: string[] + /** Tool-registry presentation config forwarded through agent-spine-demo. */ + tools?: ToolsConfig + /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */ + persistenceRoot?: string + /** Skill registry, local-provider, and model-facing consumer config. */ + skills?: agentCore.SkillConfig +} + +export const Config: z = z.object({ + model: z.string().required(), + persistenceRoot: z.string().default(DEFAULT_PERSISTENCE_ROOT), + persona: z.string(), + skills: agentCore.SkillConfigSchema, + // Absent means lexicographic order; schemastery's native array default is []. + toolOrder: z.array(z.string()).default(undefined as unknown as string[]), + tools: ToolRegistry.Config, +}) + +/** + * Compose the UI-less spine, a fresh `main` agent rooted at the process cwd, + * and JSONL persistence. Swappable adapters, executors, and product tools stay + * in the leaf `cordis.yml`. + * @param ctx - app context that owns the composed child plugins. + * @param config - validated app configuration. + */ +export function apply(ctx: Context, config: Config): void { + const spineConfig: agentCore.Config = { + agents: [{ id: AgentId('main'), model: config.model, cwd: process.cwd() }], + } + if (config.persona !== undefined) spineConfig.persona = config.persona + if (config.toolOrder !== undefined) spineConfig.toolOrder = config.toolOrder + if (config.tools !== undefined) spineConfig.tools = config.tools + if (config.skills !== undefined) spineConfig.skills = config.skills + ctx.plugin(agentCore, spineConfig) + ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? DEFAULT_PERSISTENCE_ROOT }) +} diff --git a/packages/examples/cli-demo/tests/built-bin.e2e.ts b/packages/examples/cli-demo/tests/built-bin.e2e.ts new file mode 100644 index 0000000000..aed7f1f2d4 --- /dev/null +++ b/packages/examples/cli-demo/tests/built-bin.e2e.ts @@ -0,0 +1,172 @@ +import { spawn } from 'node:child_process' +import { existsSync } from 'node:fs' +import { mkdtemp, mkdir, readFile, readdir, rm, symlink, writeFile } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { dirname, join } from 'node:path' +import { fileURLToPath } from 'node:url' +import { afterEach, describe, expect, it } from 'vitest' + +const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url)) +const cliBin = join(repoRoot, 'packages/examples/cli-demo/lib/bin.js') +const dshPackages = [ + 'examples/agent-spine-demo', 'examples/cli-demo', 'core/agent', 'core/session', + 'core/system-prompt', 'core/tools', 'core/agent-loop', 'llm/llm', 'bash/bash', + 'bash/bash-local', 'bash/tool-bash', 'support/invariants', 'ui/app-boot', + 'session-persistence/session-persistence', 'session-persistence/session-persistence-jsonl', +] +const vendorPackages = ['cordis', 'loader', 'include', 'timer', 'schemastery', 'cosmokit'] + +async function packageName(dir: string): Promise { + return (JSON.parse(await readFile(join(dir, 'package.json'), 'utf8')) as { name: string }).name +} + +async function linkPackage(dir: string, nodeModules: string): Promise { + const target = join(nodeModules, await packageName(dir)) + await mkdir(dirname(target), { recursive: true }) + await symlink(dir, target) +} + +async function makeConsumer(): Promise { + const dir = await mkdtemp(join(tmpdir(), 'cli-built-bin-')) + const nodeModules = join(dir, 'node_modules') + for (const rel of dshPackages) await linkPackage(join(repoRoot, 'packages', rel), nodeModules) + for (const rel of vendorPackages) await linkPackage(join(repoRoot, 'vendor', rel), nodeModules) + await writeFile(join(dir, 'mock-llm.mjs'), [ + "import { LlmAdapter } from '@deepseek-ai/dsh-llm'", + 'class Mock extends LlmAdapter {', + ' async * stream(options) {', + " const text = options.messages.flatMap(message => message.content).filter(block => block.type === 'text').at(-1)?.text ?? ''", + " yield { type: 'block-start', index: 0, blockType: 'text' }", + " if (text === 'hang') {", + " yield { type: 'text-delta', index: 0, text: 'partial' }", + ' await new Promise((resolve, reject) => {', + " const timer = setTimeout(() => reject(new Error('hang timeout')), 30000)", + " const onAbort = () => { clearTimeout(timer); reject(new Error('aborted')) }", + ' if (options.signal.aborted) onAbort()', + " else options.signal.addEventListener('abort', onAbort, { once: true })", + ' })', + ' return', + ' }', + ' const reply = `BUILT: ${text}`', + " yield { type: 'text-delta', index: 0, text: reply }", + " yield { type: 'block-end', index: 0, block: { type: 'text', text: reply } }", + " yield { type: 'usage', usage: { inputTokens: 4, outputTokens: 2 } }", + " yield { type: 'finish', reason: { kind: 'stop' } }", + ' }', + '}', + "export const name = 'built-cli-mock'", + "export const inject = ['llm']", + "export function apply(ctx) { ctx.llm.registerAdapter(['built-cli-mock'], new Mock()) }", + '', + ].join('\n')) + await writeFile(join(dir, 'cordis.yml'), [ + '- id: mock-llm', + " name: './mock-llm.mjs'", + '- id: bash', + " name: '@deepseek-ai/dsh-bash-local'", + '- id: cli-agent', + " name: '@deepseek-ai/dsh-cli-demo'", + ' config:', + ' model: built-cli-mock', + " persona: 'built CLI test'", + " persistenceRoot: './.sessions'", + '', + ].join('\n')) + return dir +} + +interface BinResult { + readonly code: number + readonly signal: NodeJS.Signals | null + readonly stdout: string + readonly stderr: string +} + +function runBuiltBin(cwd: string, args: readonly string[], interrupt?: NodeJS.Signals): Promise { + return new Promise((resolveResult, reject) => { + const child = spawn(process.execPath, ['--expose-internals', cliBin, ...args], { + cwd, + env: { ...process.env, DSH_HOME: join(cwd, '.dsh'), DSH_AGENTS_HOME: join(cwd, '.agents') }, + stdio: ['ignore', 'pipe', 'pipe'], + }) + let stdout = '' + let stderr = '' + let interrupted = false + child.stdout.setEncoding('utf8') + child.stdout.on('data', (chunk: string) => { + stdout += chunk + if (interrupt !== undefined && !interrupted && stdout.includes('assistant/chunk')) { + interrupted = true + child.kill(interrupt) + } + }) + child.stderr.setEncoding('utf8') + child.stderr.on('data', (chunk: string) => { stderr += chunk }) + const timer = setTimeout(() => { + child.kill('SIGKILL') + reject(new Error(`built CLI did not exit. stdout:\n${stdout}\nstderr:\n${stderr}`)) + }, 25_000) + child.once('error', (error) => { clearTimeout(timer); reject(error) }) + child.once('exit', (code, signal) => { + clearTimeout(timer) + resolveResult({ code: code ?? -1, signal, stdout, stderr }) + }) + }) +} + +let consumer: string | undefined + +afterEach(async () => { + if (consumer !== undefined) await rm(consumer, { recursive: true, force: true, maxRetries: 10, retryDelay: 100 }) + consumer = undefined +}) + +describe.skipIf(!existsSync(cliBin))('dsh-cli-demo BUILT bin', () => { + it('runs text, json, and stream-json under plain Node and persists fresh sessions', async () => { + consumer = await makeConsumer() + const text = await runBuiltBin(consumer, ['--config', './cordis.yml', 'hello']) + expect(text).toMatchObject({ code: 0, signal: null, stdout: 'BUILT: hello\n', stderr: '' }) + + const json = await runBuiltBin(consumer, ['--config', './cordis.yml', '--output-format', 'json', 'json task']) + expect(JSON.parse(json.stdout)).toMatchObject({ + type: 'result', success: true, result: 'BUILT: json task', reason: { kind: 'completed' }, + usage: { inputTokens: 4, outputTokens: 2 }, + }) + + const stream = await runBuiltBin(consumer, ['--config', './cordis.yml', '--output-format', 'stream-json', 'stream task']) + const lines = stream.stdout.trimEnd().split('\n').map(line => JSON.parse(line) as Record) + expect(lines[0]).toMatchObject({ type: 'session_event', event: { type: 'turn/start' } }) + expect(lines.at(-1)).toMatchObject({ type: 'result', success: true, result: 'BUILT: stream task' }) + const files = await readdir(join(consumer, '.sessions'), { recursive: true }) + expect(files.filter(file => file.endsWith('.jsonl'))).toHaveLength(3) + }, 30_000) + + it('keeps stdout empty for invalid argv and missing config', async () => { + consumer = await makeConsumer() + for (const args of [ + ['--config', './cordis.yml'], + ['--config', './cordis.yml', 'one', 'two'], + ['--config', './missing.yml', 'task'], + ]) { + const result = await runBuiltBin(consumer, args) + expect(result.code).not.toBe(0) + expect(result.stdout).toBe('') + expect(result.stderr.length).toBeGreaterThan(0) + } + }, 30_000) + + it.each([ + ['SIGINT', 130], + ['SIGTERM', 143], + ] as const)('cancels and disposes on %s with exit %i', async (signal, code) => { + consumer = await makeConsumer() + const result = await runBuiltBin( + consumer, + ['--config', './cordis.yml', '--output-format', 'stream-json', 'hang'], + signal, + ) + expect(result, JSON.stringify(result)).toMatchObject({ code, signal: null }) + expect(result.stdout).toContain('"kind":"aborted"') + expect(result.stderr).toContain(`received ${signal}`) + }, 30_000) +}) diff --git a/packages/examples/cli-demo/tests/cli-demo.spec.ts b/packages/examples/cli-demo/tests/cli-demo.spec.ts new file mode 100644 index 0000000000..4cb7a243a5 --- /dev/null +++ b/packages/examples/cli-demo/tests/cli-demo.spec.ts @@ -0,0 +1,105 @@ +import { mkdtemp } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { Context } from 'cordis' +import Loader from '@cordisjs/plugin-loader' +import { AgentId, agentEvents, type Agent } from '@deepseek-ai/dsh-agent' +import type { Message } from '@deepseek-ai/dsh-llm' +import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' +import { afterEach, describe, expect, it } from 'vitest' +import * as cliDemo from '../src/index.ts' + +const contexts: Context[] = [] + +async function skillConfig(catalogDescriptionMaxLength?: number): Promise> { + const home = await mkdtemp(join(tmpdir(), 'dsh-cli-demo-skills-')) + return { + local: { dshHome: join(home, '.dsh'), agentsHome: join(home, '.agents') }, + ...catalogDescriptionMaxLength === undefined ? {} : { tool: { catalogDescriptionMaxLength } }, + } +} + +async function mount(config: cliDemo.Config): Promise { + const ctx = new Context() + contexts.push(ctx) + await ctx.plugin(cliDemo, config) + await new Promise(resolve => setTimeout(resolve, 80)) + return ctx +} + +async function composePrefix(ctx: Context): Promise { + const agent = { session: { header: { cwd: '/tmp' } } } as unknown as Agent + const empty: Message[] = [] + return await agentEvents(ctx, agent).waterfall( + 'agent/session-prefix', empty, new AbortController().signal, + () => Promise.resolve(empty), + ) +} + +afterEach(async () => { + await Promise.all(contexts.splice(0).map(ctx => ctx.fiber.dispose())) +}) + +describe('dsh-cli-demo app composition', () => { + it('composes the UI-less spine, JSONL persistence, and a main agent', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cli-demo-compose-')) + const ctx = await mount({ + model: 'mock', + persona: 'Headless.', + tools: { mode: 'native' }, + persistenceRoot: root, + skills: await skillConfig(), + }) + const agent = ctx.get('agents')?.get(AgentId('main')) + expect(ctx.get('agentLoop')).toBeDefined() + expect(ctx.get('sessionPersistence')).toBeDefined() + expect(agent?.session.header.cwd).toBe(process.cwd()) + expect(ctx.get('userInteraction')).toBeUndefined() + expect(ctx.get('tools')?.get('ask_user_question')).toBeUndefined() + }) + + it('covers direct-apply defaults and forwards skill and tool-order config', async () => { + const oldDshHome = process.env.DSH_HOME + const oldAgentsHome = process.env.DSH_AGENTS_HOME + const home = await mkdtemp(join(tmpdir(), 'dsh-cli-demo-defaults-')) + process.env.DSH_HOME = join(home, '.dsh') + process.env.DSH_AGENTS_HOME = join(home, '.agents') + try { + const ctx = new Context() + contexts.push(ctx) + cliDemo.apply(ctx, { model: 'mock' }) + await new Promise(resolve => setTimeout(resolve, 80)) + expect(ctx.get('sessionPersistence')).toBeDefined() + expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() + expect(await ctx.skills.list()).toEqual([]) + } finally { + if (oldDshHome === undefined) delete process.env.DSH_HOME + else process.env.DSH_HOME = oldDshHome + if (oldAgentsHome === undefined) delete process.env.DSH_AGENTS_HOME + else process.env.DSH_AGENTS_HOME = oldAgentsHome + } + + const ctx = await mount({ + model: 'mock', + toolOrder: ['zulu', TOOL_ORDER_REST], + skills: await skillConfig(6), + }) + ctx.skills.register({ name: 'cli-skill', description: 'CLI skill', source: 'runtime', content: 'body' }) + for (const name of ['alpha', 'zulu']) { + ctx.tools.register({ name, description: name, parameters: {}, execute: async () => [] }) + } + expect(JSON.stringify(await composePrefix(ctx))).toContain('- `cli-skill`: CLI...') + expect((await ctx.systemPrompt.assemble()).tools.map(tool => tool.name)).toEqual(['zulu', 'alpha', 'skill']) + }) + + it('exposes the Loader-safe namespace plugin shape and schema', () => { + expect(cliDemo.name).toBe('cli-demo') + expect(cliDemo.Config).toBeDefined() + expect('default' in cliDemo).toBe(false) + const loader = Object.create(Loader.prototype) as Loader + const unwrapped = loader.unwrapExports(cliDemo) as Record + expect(unwrapped).toBe(cliDemo) + expect(unwrapped.name).toBe('cli-demo') + expect(typeof unwrapped.apply).toBe('function') + }) +}) diff --git a/packages/examples/cli-demo/tests/cli.spec.ts b/packages/examples/cli-demo/tests/cli.spec.ts new file mode 100644 index 0000000000..c4d46ea3da --- /dev/null +++ b/packages/examples/cli-demo/tests/cli.spec.ts @@ -0,0 +1,362 @@ +import { readdir, mkdtemp } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join, resolve } from 'node:path' +import { Context } from 'cordis' +import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { CallId, LlmAdapter, type GenerateOptions, type StreamChunk, type TokenUsage } from '@deepseek-ai/dsh-llm' +import { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' +import { afterEach, describe, expect, it } from 'vitest' +import * as cliDemo from '../src/index.ts' +import { + executeCli, + formatTurnFailure, + parseCliArgs, + runOneShot, + type CliResult, +} from '../src/cli.ts' + +type ScriptEntry = readonly StreamChunk[] | 'hang' + +class ScriptedAdapter extends LlmAdapter { + readonly requests: GenerateOptions[] = [] + private cursor = 0 + + constructor(private readonly script: readonly ScriptEntry[]) { + super() + } + + async * stream(options: GenerateOptions): AsyncIterable { + this.requests.push(options) + const entry = this.script[this.cursor++] + if (entry === undefined) throw new Error('script exhausted') + if (entry === 'hang') { + yield { type: 'block-start', index: 0, blockType: 'text' } + yield { type: 'text-delta', index: 0, text: 'partial' } + await new Promise((_resolve, reject) => { + if (options.signal?.aborted === true) { + reject(new Error('aborted')) + return + } + options.signal?.addEventListener('abort', () => { reject(new Error('aborted')) }, { once: true }) + }) + return + } + for (const chunk of entry) yield chunk + } +} + +function textResponse(text: string, usage?: TokenUsage, finish: 'stop' | 'max-tokens' = 'stop'): StreamChunk[] { + return [ + { type: 'block-start', index: 0, blockType: 'text' }, + { type: 'text-delta', index: 0, text }, + { type: 'block-end', index: 0, block: { type: 'text', text } }, + ...usage === undefined ? [] : [{ type: 'usage', usage } as const], + { type: 'finish', reason: { kind: finish } }, + ] +} + +function toolResponse(usage: TokenUsage): StreamChunk[] { + const id = CallId('cli-call') + const args = JSON.stringify({ text: 'round trip' }) + return [ + { type: 'block-start', index: 0, blockType: 'text' }, + { type: 'text-delta', index: 0, text: 'working' }, + { type: 'block-end', index: 0, block: { type: 'text', text: 'working' } }, + { type: 'block-start', index: 1, blockType: 'tool-call' }, + { type: 'tool-call-delta', index: 1, id, name: 'echo', argumentsDelta: args }, + { type: 'block-end', index: 1, block: { type: 'tool-call', id, name: 'echo', arguments: args } }, + { type: 'usage', usage }, + { type: 'finish', reason: { kind: 'tool-calls' } }, + ] +} + +function reasoningResponse(text: string): StreamChunk[] { + return [ + { type: 'block-start', index: 0, blockType: 'reasoning' }, + { type: 'reasoning-delta', index: 0, text }, + { type: 'block-end', index: 0, block: { type: 'reasoning', text } }, + { type: 'finish', reason: { kind: 'stop' } }, + ] +} + +interface Harness { + readonly ctx: Context + readonly agent: Agent + readonly persistenceRoot: string +} + +const liveContexts: Context[] = [] + +async function harness(script: readonly ScriptEntry[]): Promise { + const root = await mkdtemp(join(tmpdir(), 'dsh-cli-runner-')) + const skillHome = await mkdtemp(join(tmpdir(), 'dsh-cli-runner-skills-')) + const ctx = new Context() + liveContexts.push(ctx) + await ctx.plugin(cliDemo, { + model: 'mock', + persistenceRoot: root, + skills: { local: { dshHome: join(skillHome, '.dsh'), agentsHome: join(skillHome, '.agents') } }, + }) + await new Promise(resolve => setTimeout(resolve, 80)) + ctx.llm.registerAdapter(['mock'], new ScriptedAdapter(script)) + ctx.tools.register({ + name: 'echo', + description: 'Echo text.', + parameters: { text: { type: 'string', required: true } }, + execute: async args => [{ type: 'text', text: `ECHO: ${(args as { text: string }).text}` }], + }) + const agent = ctx.agents.get(AgentId('main')) + if (agent === undefined) throw new Error('test main agent missing') + return { ctx, agent, persistenceRoot: root } +} + +async function invoke( + ctx: Context, + args: readonly string[], + options: { signal?: AbortSignal; failStdout?: boolean; failDispose?: boolean } = {}, +): Promise<{ code: number; stdout: string; stderr: string }> { + let stdout = '' + let stderr = '' + const code = await executeCli(args, { + cwd: '/tmp/cli-cwd', + ...options.signal === undefined ? {} : { signal: options.signal }, + boot: async () => ctx, + loadEnv: () => {}, + writeStdout: (chunk) => { + if (options.failStdout === true) throw new Error('stdout closed') + stdout += chunk + }, + writeStderr: (chunk) => { stderr += chunk }, + ...options.failDispose === true + ? { dispose: async (target: Context) => { + await target.fiber.dispose() + throw new Error('dispose exploded') + } } + : {}, + }) + return { code, stdout, stderr } +} + +afterEach(async () => { + await Promise.all(liveContexts.splice(0).map(ctx => ctx.fiber.dispose())) +}) + +describe('parseCliArgs', () => { + it('parses defaults, explicit options, spaces, and an option-like task after --', () => { + expect(parseCliArgs(['task with spaces'])).toEqual({ + kind: 'run', configPath: './cordis.yml', outputFormat: 'text', task: 'task with spaces', + }) + expect(parseCliArgs(['--config', 'custom.yml', '--output-format', 'stream-json', 'do it'])).toEqual({ + kind: 'run', configPath: 'custom.yml', outputFormat: 'stream-json', task: 'do it', + }) + expect(parseCliArgs(['--', '-task'])).toMatchObject({ task: '-task' }) + expect(parseCliArgs(['--help', 'ignored'])).toEqual({ kind: 'help' }) + }) + + it('rejects missing, blank, extra, invalid-format, and unsupported flags', () => { + expect(() => parseCliArgs([])).toThrow('received 0') + expect(() => parseCliArgs([' '])).toThrow('must not be blank') + expect(() => parseCliArgs(['one', 'two'])).toThrow('received 2') + expect(() => parseCliArgs(['--output-format', 'xml', 'task'])).toThrow('unsupported output format') + expect(() => parseCliArgs(['-p', 'task'])).toThrow('Unknown option') + }) +}) + +describe('runOneShot and executeCli', () => { + it('prints help and argument diagnostics without booting or contaminating stdout', async () => { + let booted = false + let stdout = '' + let stderr = '' + const runtime = { + boot: async (): Promise => { booted = true; throw new Error('unexpected') }, + writeStdout: (chunk: string): void => { stdout += chunk }, + writeStderr: (chunk: string): void => { stderr += chunk }, + } + expect(await executeCli(['--help'], runtime)).toBe(0) + expect(stdout).toContain('Usage: dsh-cli-demo') + stdout = '' + expect(await executeCli([], runtime)).toBe(1) + expect(stdout).toBe('') + expect(stderr).toContain('received 0') + expect(booted).toBe(false) + }) + + it('leaves stdout empty for environment and boot failures and resolves the default config', async () => { + let bootPath = '' + let stderr = '' + const code = await executeCli(['task'], { + cwd: '/tmp/cli-work', + loadEnv: (_name, _dir, warn) => { warn('env warning\n') }, + boot: async (_name, path) => { bootPath = path; throw 'boot exploded' }, + writeStdout: () => { throw new Error('stdout must stay empty') }, + writeStderr: (chunk) => { stderr += chunk }, + }) + expect(code).toBe(1) + expect(bootPath).toBe(resolve('/tmp/cli-work/cordis.yml')) + expect(stderr).toContain('env warning') + expect(stderr).toContain('boot exploded') + }) + + it('renders text, flushes a persisted fresh session, and disposes the context', async () => { + const { ctx, agent, persistenceRoot } = await harness([textResponse('final answer')]) + const output = await invoke(ctx, ['task']) + expect(output).toEqual({ code: 0, stdout: 'final answer\n', stderr: '' }) + expect(agent.status).toBe('disposed') + const files = await readdir(persistenceRoot, { recursive: true }) + expect(files.some(file => file.endsWith('.jsonl'))).toBe(true) + }) + + it('sums usage across tool steps and selects the last text-bearing assistant message', async () => { + const first = { inputTokens: 10, outputTokens: 3, cacheReadTokens: 2, cacheWriteTokens: 1 } + const second = { inputTokens: 7, outputTokens: 5, cacheReadTokens: 4, reasoningTokens: 6 } + const { ctx } = await harness([toolResponse(first), textResponse('done', second)]) + const output = await invoke(ctx, ['--output-format', 'json', 'task']) + const result = JSON.parse(output.stdout) as CliResult + expect(output.code).toBe(0) + expect(result).toMatchObject({ type: 'result', success: true, turn: 1, result: 'done', reason: { kind: 'completed' } }) + expect(result.usage).toEqual({ + inputTokens: 17, + outputTokens: 8, + cacheReadTokens: 6, + cacheWriteTokens: 1, + reasoningTokens: 6, + }) + }) + + it('keeps the prior text when a later assistant message has no text blocks', async () => { + const { ctx } = await harness([ + toolResponse({ inputTokens: 1, outputTokens: 1 }), + reasoningResponse('reasoning only'), + ]) + const result = await runOneShot(ctx, { task: 'task' }) + expect(result.result).toBe('working') + }) + + it('streams only the correlated main message turn and then the result envelope', async () => { + const { ctx, agent } = await harness([textResponse('streamed')]) + const other = ctx.sessions.create(SessionId('unrelated')) + let injected = false + ctx.on('agent/queued', (subject) => { + if (subject !== agent || injected) return + injected = true + agent.inject([{ type: 'text', text: 'startup injection' }], { source: { kind: 'plugin', plugin: 'test' } }) + other.append('turn/start', { turn: 1, trigger: { kind: 'injection', source: { kind: 'plugin', plugin: 'test' } } }) + other.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + }) + const output = await invoke(ctx, ['--output-format', 'stream-json', 'task']) + const lines = output.stdout.trimEnd().split('\n').map(line => JSON.parse(line) as Record) + const events = lines.slice(0, -1).map(line => line['event'] as SessionEvent) + expect(lines.at(-1)).toMatchObject({ type: 'result', success: true, turn: 2, result: 'streamed' }) + expect(events[0]).toMatchObject({ type: 'turn/start', data: { turn: 2, trigger: { kind: 'message' } } }) + expect(events.at(-1)).toMatchObject({ type: 'turn/end', data: { turn: 2 } }) + expect(lines.slice(0, -1).every(line => line['sessionId'] === agent.session.id)).toBe(true) + expect(events.some(event => event.type === 'context/message')).toBe(false) + }) + + it('emits partial data and a diagnostic for non-completed turns', async () => { + const { ctx } = await harness([textResponse('partial', { inputTokens: 2, outputTokens: 3 }, 'max-tokens')]) + const output = await invoke(ctx, ['--output-format', 'json', 'task']) + expect(JSON.parse(output.stdout)).toMatchObject({ success: false, result: 'partial', reason: { kind: 'max-tokens' } }) + expect(output.code).toBe(1) + expect(output.stderr).toContain('output-token limit') + }) + + it('cancels an active turn, emits its durable aborted result, and disposes', async () => { + const { ctx, agent } = await harness(['hang']) + const abort = new AbortController() + let started!: () => void + const running = new Promise((resolveStarted) => { started = resolveStarted }) + ctx.on('session/event', (session, event) => { + if (session === agent.session && event.type === 'assistant/chunk') started() + }) + const outcome = invoke(ctx, ['--output-format', 'json', 'task'], { signal: abort.signal }) + await running + abort.abort('received SIGINT') + const output = await outcome + expect(JSON.parse(output.stdout)).toMatchObject({ success: false, reason: { kind: 'aborted', reason: 'received SIGINT' } }) + expect(output.code).toBe(1) + expect(output.stderr).toContain('was aborted: received SIGINT') + expect(agent.status).toBe('disposed') + }) + + it('contains stream-writer failures, cancels, flushes, and returns the output error', async () => { + const { ctx, agent } = await harness(['hang']) + await expect(runOneShot(ctx, { + task: 'task', + onEvent: () => { throw new Error('stream sink failed') }, + })).rejects.toThrow('stream sink failed') + expect(agent.status).toBe('idle') + }) + + it('handles cancellation before submission, a missing main agent, and final-output failure', async () => { + const early = await harness([textResponse('unused')]) + const fakeSignal = { + aborted: true, + reason: undefined, + } as unknown as AbortSignal + await expect(runOneShot(early.ctx, { task: 'task', signal: fakeSignal })).rejects.toThrow('interrupted') + + const preBootAbort = new AbortController() + preBootAbort.abort('before boot completed') + const preBoot = await invoke(early.ctx, ['task'], { signal: preBootAbort.signal }) + expect(preBoot).toMatchObject({ code: 1, stdout: '' }) + expect(preBoot.stderr).toContain('before boot completed') + + const empty = new Context() + liveContexts.push(empty) + await expect(runOneShot(empty, { task: 'task' })).rejects.toThrow('required "main" agent') + + const final = await harness([textResponse('answer')]) + const output = await invoke(final.ctx, ['task'], { failStdout: true }) + expect(output.code).toBe(1) + expect(output.stdout).toBe('') + expect(output.stderr).toContain('stdout closed') + expect(final.agent.status).toBe('disposed') + + const disposal = await harness([textResponse('answer')]) + const disposalOutput = await invoke(disposal.ctx, ['task'], { failDispose: true }) + expect(disposalOutput).toMatchObject({ code: 1, stdout: 'answer\n' }) + expect(disposalOutput.stderr).toContain('dispose exploded') + }) + + it('cancels startup work and queued work before the correlated turn begins', async () => { + const startup = await harness(['hang']) + let started!: () => void + const running = new Promise((resolveStarted) => { started = resolveStarted }) + startup.ctx.on('session/event', (session, event) => { + if (session === startup.agent.session && event.type === 'assistant/chunk') started() + }) + startup.agent.send([{ type: 'text', text: 'first' }]) + await running + const startupAbort = new AbortController() + const waiting = runOneShot(startup.ctx, { task: 'second', signal: startupAbort.signal }) + startupAbort.abort('cancel startup') + await expect(waiting).rejects.toThrow('cancel startup') + await startup.agent.whenIdle() + + const queued = await harness([textResponse('unused')]) + const queuedAbort = new AbortController() + queued.ctx.on('agent/queued', (agent) => { + if (agent === queued.agent) queuedAbort.abort('cancel queued') + }) + await expect(runOneShot(queued.ctx, { task: 'task', signal: queuedAbort.signal })).rejects.toThrow('cancel queued') + await queued.agent.whenIdle() + }) +}) + +describe('formatTurnFailure', () => { + it('diagnoses every durable reason and preserves merge-extensible unknowns', () => { + const cases: [TurnEndReason, string][] = [ + [{ kind: 'completed' }, 'completed'], + [{ kind: 'aborted' }, 'was aborted'], + [{ kind: 'aborted', reason: 'stop' }, 'was aborted: stop'], + [{ kind: 'error', step: 2, message: 'bad' }, 'failed at step 2: bad'], + [{ kind: 'disposed' }, 'was disposed'], + [{ kind: 'max-tokens' }, 'output-token limit'], + [{ kind: 'rejected', reason: 'policy' }, 'was rejected: policy'], + [{ kind: 'interrupted' }, 'persistence recovery'], + ] + for (const [reason, expected] of cases) expect(formatTurnFailure(reason)).toContain(expected) + expect(formatTurnFailure({ kind: 'extension' } as unknown as TurnEndReason)).toContain('extension') + }) +}) diff --git a/packages/examples/cli-demo/tsconfig.json b/packages/examples/cli-demo/tsconfig.json new file mode 100644 index 0000000000..f25b1592ca --- /dev/null +++ b/packages/examples/cli-demo/tsconfig.json @@ -0,0 +1,22 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "composite": true, + "rootDir": "src", + "outDir": "lib/types", + "tsBuildInfoFile": "../../../.typecheck/cli-demo.tsbuildinfo" + }, + "include": ["src/**/*.ts"], + "references": [ + { "path": "../../../vendor/schemastery" }, + { "path": "../../../vendor/cordis" }, + { "path": "../../llm/llm" }, + { "path": "../../core/session" }, + { "path": "../../core/agent" }, + { "path": "../../core/system-prompt" }, + { "path": "../../core/tools" }, + { "path": "../agent-spine-demo" }, + { "path": "../../session-persistence/session-persistence-jsonl" }, + { "path": "../../ui/app-boot" } + ] +} diff --git a/packages/examples/cli-demo/tsdown.config.ts b/packages/examples/cli-demo/tsdown.config.ts new file mode 100644 index 0000000000..e5b164d46f --- /dev/null +++ b/packages/examples/cli-demo/tsdown.config.ts @@ -0,0 +1,13 @@ +import { defineConfig } from 'tsdown' + +/** Builds the plugin and executable entries from declarations emitted by `tsc -b`. */ +export default defineConfig({ + entry: ['lib/types/index.js', 'lib/types/bin.js'], + outDir: 'lib', + format: ['esm'], + platform: 'node', + target: 'es2024', + fixedExtension: false, + dts: false, + clean: false, +}) diff --git a/packages/support/loader-smoke/README.md b/packages/support/loader-smoke/README.md index ea197b25d0..4527be6430 100644 --- a/packages/support/loader-smoke/README.md +++ b/packages/support/loader-smoke/README.md @@ -1,6 +1,6 @@ # `@deepseek-ai/dsh-loader-smoke` -Shared subprocess harness for keyless example smokes that boot the real stdio-agent bin and a real `cordis.yml` through the Cordis Loader. A test supplies absolute bin/config/tsconfig paths, optional environment overrides, and stdin lines; `runLoaderSmoke` owns the isolated cwd, DSH homes, tsx path resolution, 30-second process deadline, captured diagnostics, forced kill, EOF, and cleanup. +Shared subprocess harness for keyless example smokes that boot a real app bin and `cordis.yml` through the Cordis Loader. A test supplies absolute bin/config/tsconfig paths, optional complete bin arguments, environment overrides, stdin lines, pre-run world setup, and a pre-cleanup world assertion; `runLoaderSmoke` owns the isolated cwd, DSH homes, tsx path resolution, 30-second process deadline, captured diagnostics, forced kill, EOF, and cleanup. Successful runs return stdout and stderr only after a zero exit. Non-zero exits and deadlines reject with both captured streams. `LOADER_SMOKE_TEST_TIMEOUT_MS` leaves Vitest enough room for the process-owned diagnostic timeout to fire first. diff --git a/packages/support/loader-smoke/src/index.ts b/packages/support/loader-smoke/src/index.ts index 72839c6a05..c49fe1f4cc 100644 --- a/packages/support/loader-smoke/src/index.ts +++ b/packages/support/loader-smoke/src/index.ts @@ -1,6 +1,6 @@ /** * Shared subprocess harness for keyless example smokes that boot a real - * `cordis.yml` through the stdio-agent bin and Cordis Loader. + * `cordis.yml` through an app bin and Cordis Loader. * * @module @deepseek-ai/dsh-loader-smoke */ @@ -23,10 +23,12 @@ export interface LoaderSmokeOptions { readonly label: string /** Prefix for the isolated temporary process cwd. */ readonly tempDirPrefix: string - /** Absolute stdio-agent bin path. */ + /** Absolute app-bin path. */ readonly binScript: string - /** Absolute real Loader config path. */ + /** Absolute real Loader config path, passed as the sole bin argument by default. */ readonly configPath: string + /** Complete argv after the bin path; overrides the default `[configPath]`. */ + readonly binArgs?: readonly string[] /** Absolute repo tsconfig path used for unbuilt workspace-package resolution. */ readonly tsconfigPath: string /** Environment overrides layered over the parent and isolated DSH homes. */ @@ -35,6 +37,10 @@ export interface LoaderSmokeOptions { readonly stdinLines?: readonly string[] /** Process deadline override for harness tests. */ readonly processTimeoutMs?: number + /** Optional world-state setup run in the isolated cwd before process start. */ + readonly prepare?: (cwd: string) => Promise | void + /** Optional world-state assertion run in the isolated cwd before cleanup. */ + readonly inspect?: (cwd: string) => Promise | void } /** Captured output from a Loader smoke that exited successfully. */ @@ -56,10 +62,11 @@ export async function runLoaderSmoke(options: LoaderSmokeOptions): Promise { + await options.prepare?.(cwd) + const result = await new Promise((resolve, reject) => { const child = spawn( process.execPath, - ['--expose-internals', '--import', TSX_LOADER, options.binScript, options.configPath], + ['--expose-internals', '--import', TSX_LOADER, options.binScript, ...(options.binArgs ?? [options.configPath])], { cwd, env: { @@ -111,6 +118,8 @@ export async function runLoaderSmoke(options: LoaderSmokeOptions): Promise `${line}\n`).join('')) }) + await options.inspect?.(cwd) + return result } finally { await rm(cwd, { recursive: true, force: true }) } diff --git a/packages/support/loader-smoke/tests/fixtures/success.ts b/packages/support/loader-smoke/tests/fixtures/success.ts index fed57162e2..82a63cdfd3 100644 --- a/packages/support/loader-smoke/tests/fixtures/success.ts +++ b/packages/support/loader-smoke/tests/fixtures/success.ts @@ -6,6 +6,7 @@ process.stdin.on('data', (chunk: string) => { input += chunk }) process.stdin.on('end', () => { console.log(JSON.stringify({ configPath: process.argv[2], + args: process.argv.slice(2), cwd: process.cwd(), dshHome: process.env.DSH_HOME, agentsHome: process.env.DSH_AGENTS_HOME, diff --git a/packages/support/loader-smoke/tests/loader-smoke.spec.ts b/packages/support/loader-smoke/tests/loader-smoke.spec.ts index 4cc9f878f9..e4e899d67d 100644 --- a/packages/support/loader-smoke/tests/loader-smoke.spec.ts +++ b/packages/support/loader-smoke/tests/loader-smoke.spec.ts @@ -1,4 +1,6 @@ import { existsSync } from 'node:fs' +import { readFile, writeFile } from 'node:fs/promises' +import { join } from 'node:path' import { fileURLToPath } from 'node:url' import { describe, expect, it } from 'vitest' import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke' @@ -21,6 +23,7 @@ describe('runLoaderSmoke', () => { }) const output = JSON.parse(result.stdout) as { configPath: string + args: string[] cwd: string dshHome: string agentsHome: string @@ -29,6 +32,7 @@ describe('runLoaderSmoke', () => { } expect(output).toMatchObject({ configPath, + args: [configPath], marker: 'present', input: 'one\ntwo\n', }) @@ -38,6 +42,29 @@ describe('runLoaderSmoke', () => { expect(existsSync(output.cwd)).toBe(false) }, LOADER_SMOKE_TEST_TIMEOUT_MS) + it('passes an arbitrary bin argv and inspects world state before cleanup', async () => { + let inspected = '' + let marker = '' + const result = await runLoaderSmoke({ + label: 'argv fixture', + tempDirPrefix: 'loader-smoke-argv-', + binScript: fixture('success'), + configPath, + binArgs: ['--config', configPath, '--output-format', 'json', 'task with spaces'], + tsconfigPath, + prepare: cwd => writeFile(join(cwd, 'marker.txt'), 'prepared'), + inspect: async (cwd) => { + inspected = cwd + marker = await readFile(join(cwd, 'marker.txt'), 'utf8') + }, + }) + const output = JSON.parse(result.stdout) as { args: string[]; cwd: string } + expect(output.args).toEqual(['--config', configPath, '--output-format', 'json', 'task with spaces']) + expect(canonicalTempPath(inspected)).toBe(canonicalTempPath(output.cwd)) + expect(marker).toBe('prepared') + expect(existsSync(inspected)).toBe(false) + }, LOADER_SMOKE_TEST_TIMEOUT_MS) + it('rejects a non-zero exit with captured diagnostics', async () => { await expect(runLoaderSmoke({ label: 'failure fixture', diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index ea9494fe81..5be597e52e 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -525,6 +525,45 @@ importers: specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) + packages/examples/cli-demo: + devDependencies: + '@cordisjs/plugin-include': + specifier: workspace:^ + version: link:../../../vendor/include + '@cordisjs/plugin-loader': + specifier: workspace:^ + version: link:../../../vendor/loader + '@deepseek-ai/dsh-agent': + specifier: workspace:^ + version: link:../../core/agent + '@deepseek-ai/dsh-agent-spine-demo': + specifier: workspace:^ + version: link:../agent-spine-demo + '@deepseek-ai/dsh-app-boot': + specifier: workspace:^ + version: link:../../ui/app-boot + '@deepseek-ai/dsh-llm': + specifier: workspace:^ + version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + '@deepseek-ai/dsh-session-persistence-jsonl': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence-jsonl + '@deepseek-ai/dsh-system-prompt': + specifier: workspace:^ + version: link:../../core/system-prompt + '@deepseek-ai/dsh-tools': + specifier: workspace:^ + version: link:../../core/tools + cordis: + specifier: ^4.0.0-rc.7 + version: 4.0.0-rc.7(@cordisjs/plugin-include@vendor+include)(@cordisjs/plugin-loader@vendor+loader) + schemastery: + specifier: ^3.17.0 + version: 3.18.0 + packages/examples/jsonrpc-demo: dependencies: '@deepseek-ai/dsh-app-boot': diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 0e1774c2e0..2c24396e12 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -89,7 +89,7 @@ const SERVICE_ROLES: ServiceRole[] = [ pkg: 'session', title: 'In-memory session store', mode: 'core', - consumers: ['agent-loop', 'agent', 'session-persistence', 'session-query', 'subagent-inprocess', 'invariants'], + consumers: ['agent-loop', 'agent', 'cli-demo', 'session-persistence', 'session-query', 'subagent-inprocess', 'invariants'], note: 'Owns append-only Session instances and emits the durable session event feed.', }, { @@ -147,7 +147,7 @@ const SERVICE_ROLES: ServiceRole[] = [ pkg: 'agent', title: 'Agent registry', mode: 'core', - consumers: ['agent-loop', 'acp', 'subagent-inprocess', 'stdio-demo', 'invariants'], + consumers: ['agent-loop', 'acp', 'cli-demo', 'subagent-inprocess', 'stdio-demo', 'invariants'], note: 'Owns live Agent handles and the create/resume factory seam.', }, { @@ -426,6 +426,8 @@ function renderAppExpansion(lines: string[], appNode: string, pluginName: string lines.push(` ${appNode} --> ${jsonl}["@deepseek-ai/dsh-session-persistence-jsonl"]`) if (pluginName === '@deepseek-ai/dsh-stdio-demo') { lines.push(` ${appNode} --> ${nodeId('frontdoor', 'stdio')}["readline UI
console logger
pre-created main agent"]`) + } else if (pluginName === '@deepseek-ai/dsh-cli-demo') { + lines.push(` ${appNode} --> ${nodeId('frontdoor', 'cli')}["one-shot driver
format-pure stdout
pre-created main agent"]`) } else if (pluginName === '@deepseek-ai/dsh-acp-demo') { lines.push(` ${appNode} --> ${nodeId('frontdoor', 'acp')}["@deepseek-ai/dsh-acp
JSON-RPC stdio bridge
sessions created by client"]`) } @@ -452,7 +454,7 @@ function renderAppComposition(example: AppExample): string { const pluginNode = nodeId(`plugin_${example.id}`, plugin.id) lines.push(` ${pluginNode}["${escLabel(plugin.id)}
${escLabel(plugin.name)}"]`) lines.push(` cfg --> ${pluginNode}`) - if (plugin.name === '@deepseek-ai/dsh-stdio-demo' || plugin.name === '@deepseek-ai/dsh-acp-demo') { + if (plugin.name === '@deepseek-ai/dsh-stdio-demo' || plugin.name === '@deepseek-ai/dsh-cli-demo' || plugin.name === '@deepseek-ai/dsh-acp-demo') { renderAppExpansion(lines, pluginNode, plugin.name) } } diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index d103f11461..b01cb8a579 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -344,6 +344,7 @@ function builtBinSmokeGate(): Gate { '--config', 'vitest.e2e.config.ts', 'packages/examples/stdio-demo/tests/built-bin.e2e.ts', + 'packages/examples/cli-demo/tests/built-bin.e2e.ts', 'packages/examples/acp-demo/tests/built-bin.e2e.ts', // The worker-entry packages' built bundles: the only automated proof // that lib/index.js resolves its sibling lib/worker.cjs under plain node diff --git a/tsconfig.build.json b/tsconfig.build.json index 05725fe0ae..05f27b0849 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -32,6 +32,7 @@ { "path": "./packages/ui/tool-ask-user" }, { "path": "./packages/core/agent-loop" }, { "path": "./packages/examples/agent-spine-demo" }, + { "path": "./packages/examples/cli-demo" }, { "path": "./packages/bash/bash" }, { "path": "./packages/code-runtime/code-runtime" }, { "path": "./packages/code-runtime/code-runtime-worker" }, diff --git a/tsconfig.json b/tsconfig.json index af6e900f0f..6f39963be3 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -43,6 +43,7 @@ { "path": "./packages/ui/tool-ask-user" }, { "path": "./packages/core/agent-loop" }, { "path": "./packages/examples/agent-spine-demo" }, + { "path": "./packages/examples/cli-demo" }, { "path": "./packages/bash/bash" }, { "path": "./packages/code-runtime/code-runtime" }, { "path": "./packages/code-runtime/code-runtime-worker" }, From 7278fc21d8bfad12124fe876a61f5a6cc0ba5bc4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 21:36:42 +0800 Subject: [PATCH 156/359] fix(session-persistence): handle Windows directory fsync --- .../examples/cli-demo/tests/built-bin.e2e.ts | 30 +++++++------- .../session-persistence-jsonl/README.md | 3 +- .../session-persistence-jsonl/src/index.ts | 14 ++++++- .../tests/jsonl.spec.ts | 41 ++++++++++++++++++- 4 files changed, 70 insertions(+), 18 deletions(-) diff --git a/packages/examples/cli-demo/tests/built-bin.e2e.ts b/packages/examples/cli-demo/tests/built-bin.e2e.ts index aed7f1f2d4..7fa9bf977a 100644 --- a/packages/examples/cli-demo/tests/built-bin.e2e.ts +++ b/packages/examples/cli-demo/tests/built-bin.e2e.ts @@ -155,18 +155,20 @@ describe.skipIf(!existsSync(cliBin))('dsh-cli-demo BUILT bin', () => { } }, 30_000) - it.each([ - ['SIGINT', 130], - ['SIGTERM', 143], - ] as const)('cancels and disposes on %s with exit %i', async (signal, code) => { - consumer = await makeConsumer() - const result = await runBuiltBin( - consumer, - ['--config', './cordis.yml', '--output-format', 'stream-json', 'hang'], - signal, - ) - expect(result, JSON.stringify(result)).toMatchObject({ code, signal: null }) - expect(result.stdout).toContain('"kind":"aborted"') - expect(result.stderr).toContain(`received ${signal}`) - }, 30_000) + describe.skipIf(process.platform === 'win32')('POSIX signal delivery', () => { + it.each([ + ['SIGINT', 130], + ['SIGTERM', 143], + ] as const)('cancels and disposes on %s with exit %i', async (signal, code) => { + consumer = await makeConsumer() + const result = await runBuiltBin( + consumer, + ['--config', './cordis.yml', '--output-format', 'stream-json', 'hang'], + signal, + ) + expect(result, JSON.stringify(result)).toMatchObject({ code, signal: null }) + expect(result.stdout).toContain('"kind":"aborted"') + expect(result.stderr).toContain(`received ${signal}`) + }, 30_000) + }) }) diff --git a/packages/session-persistence/session-persistence-jsonl/README.md b/packages/session-persistence/session-persistence-jsonl/README.md index 343fb4a70a..1d00f28301 100644 --- a/packages/session-persistence/session-persistence-jsonl/README.md +++ b/packages/session-persistence/session-persistence-jsonl/README.md @@ -21,7 +21,7 @@ The JSONL durable session-persistence backend — a concrete `SessionPersistence ## Durability and crash semantics -- **Lazy materialization.** `create(meta)` writes nothing; on the first `append`, the backend writes and `fsync`s a temporary file, publishes it without overwrite via a hard link, then `fsync`s the directory. A created-but-never-appended session leaves nothing on disk and is absent from `list`. +- **Lazy materialization.** `create(meta)` writes nothing; on the first `append`, the backend writes and `fsync`s a temporary file, publishes it without overwrite via a hard link, then `fsync`s the directory when the host supports it. A created-but-never-appended session leaves nothing on disk and is absent from `list`. - **Append-only.** Committed events (at or below a flushed `turn/end`) are never rewritten. Subsequent appends are line appends at EOF + `fsync`. - **Crash recovery — preserve valid tail work.** `load` keeps the contiguous valid prefix of an interrupted final turn. It truncates from the first unparsable or sequence-gapped uncommitted record, then appends the synthetic tool, step, and turn closers required by the shared [persistence contract](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md); the same defect at or before the last committed `turn/end` rejects. - **Contiguous-seq.** `append` rejects a batch whose first `seq` does not continue the stored log, and rejects non-JSON-serializable `event.data` naming the offending event type. @@ -44,3 +44,4 @@ The plugin buffers frozen session events and drains them on flush or disposal. A - **Nothing deletes session files** — logs accumulate under `root` until removed externally (the seam has no deletion surface). - **Single-process assumption** — per-session serialization and the write cursor live in this process; two processes appending to the same `root` are not coordinated. - **Initial materialization requires hard-link support** — first append uses `link()` so same-id races fail instead of overwriting a committed log; a filesystem that cannot create hard links cannot host this backend. +- **Windows cannot `fsync` directory handles through Node** — the backend tolerates only Windows `EPERM` from directory `fsync`; file-content `fsync` remains mandatory, but a crash can lose a newly published directory entry on a host without an equivalent directory-sync primitive. diff --git a/packages/session-persistence/session-persistence-jsonl/src/index.ts b/packages/session-persistence/session-persistence-jsonl/src/index.ts index 1d13ff424e..95b8b1078c 100644 --- a/packages/session-persistence/session-persistence-jsonl/src/index.ts +++ b/packages/session-persistence/session-persistence-jsonl/src/index.ts @@ -56,6 +56,9 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi private root: string private coordinator: PersistenceCoordinator + /** Runtime-only host-platform seam for directory-sync compatibility tests. */ + readonly internals: { platform: NodeJS.Platform } = { platform: process.platform } + constructor(ctx: Context, public config: Config) { super(ctx) // Resolve once so later process.cwd() changes cannot split one backend across roots. @@ -202,11 +205,18 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi } } - /** fsync a directory so a just-created or published entry inside it is crash-durable. */ + /** fsync a directory when the host exposes that durability primitive. */ private async syncDir(dir: string): Promise { const handle = await open(dir, 'r') try { - await handle.sync() + try { + await handle.sync() + } catch (error: unknown) { + const code = (error as NodeJS.ErrnoException | null)?.code + // Node opens directories on Windows but its fsync binding rejects them. + // File-content fsync remains mandatory; only this unsupported primitive is skipped. + if (this.internals.platform !== 'win32' || code !== 'EPERM') throw error + } } finally { await handle.close() } diff --git a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts index 75fcb48732..c85278f0c4 100644 --- a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts +++ b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts @@ -1,6 +1,7 @@ import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { appendFile, mkdtemp, mkdir, rm, readFile, writeFile, readdir, stat } from 'node:fs/promises' +import { appendFile, mkdtemp, mkdir, open, rm, readFile, writeFile, readdir, stat } from 'node:fs/promises' +import type { FileHandle } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' @@ -40,9 +41,25 @@ async function freshRoot(): Promise { } afterEach(async () => { + vi.restoreAllMocks() for (const d of dirs.splice(0)) await rm(d, { recursive: true, force: true }) }) +async function rejectDirectorySync(code: string): Promise { + const handle = await open(root, 'r') + const proto = Object.getPrototypeOf(handle) as { sync: () => Promise } + await handle.close() + const realSync = proto.sync + vi.spyOn(proto, 'sync').mockImplementation(async function (this: FileHandle) { + if ((await this.stat()).isDirectory()) { + const error = new Error(`simulated directory fsync ${code}`) as NodeJS.ErrnoException + error.code = code + throw error + } + return realSync.call(this) + }) +} + function appendClosedTurn(session: Session): void { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('user/message', { @@ -264,6 +281,28 @@ describe('SessionPersistenceJsonl: durability and crash semantics', () => { expect(loaded.events.map(e => e.seq)).toEqual([0, 1, 2, 3, 4, 5, 6, 7]) }) + it('keeps file fsync mandatory while tolerating unsupported Windows directory fsync', async () => { + await rejectDirectorySync('EPERM') + const backend = ctx.sessionPersistence as SessionPersistenceJsonl + backend.internals.platform = 'win32' + const m = meta('windows-directory-sync') + await ctx.sessionPersistence.create(m) + await expect(ctx.sessionPersistence.append(m.id, oneTurnLog())).resolves.toBeUndefined() + expect((await ctx.sessionPersistence.load(m.id)).events).toEqual(oneTurnLog()) + }) + + it.each([ + ['linux', 'EPERM'], + ['win32', 'EIO'], + ] as const)('surfaces directory fsync errors on %s with %s', async (platform, code) => { + await rejectDirectorySync(code) + const backend = ctx.sessionPersistence as SessionPersistenceJsonl + backend.internals.platform = platform + const m = meta(`directory-sync-${platform}-${code}`) + await ctx.sessionPersistence.create(m) + await expect(ctx.sessionPersistence.append(m.id, oneTurnLog())).rejects.toMatchObject({ code }) + }) + it('load returns a meta copy: mutating it does not corrupt backend pathing', async () => { const m = meta('meta-copy', '/proj') await ctx.sessionPersistence.create(m) From 5e3da065db2cf3d2442e274dea95311d5c4cd257 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 22:43:03 +0800 Subject: [PATCH 157/359] test(examples): snapshot headless one-shot stream --- AGENTS.md | 4 +- README.i18n.yaml | 4 +- README.md | 1 + README.zh.md | 1 + docs/testing.md | 4 +- examples/README.md | 2 +- examples/acp-agent/README.md | 2 +- .../advanced-headless.cordis.snapshot.yml | 32 ++++ examples/acp-agent/tests/headless.snapshot.ts | 140 ++++++++++++++++++ .../stream-json.golden.jsonl | 64 ++++++++ examples/coding-agent/README.md | 6 +- package.json | 2 +- packages/examples/cli-demo/README.md | 2 +- 13 files changed, 251 insertions(+), 13 deletions(-) create mode 100644 examples/acp-agent/advanced-headless.cordis.snapshot.yml create mode 100644 examples/acp-agent/tests/headless.snapshot.ts create mode 100644 examples/acp-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl diff --git a/AGENTS.md b/AGENTS.md index b9731f2c80..cf6d1c3e89 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -45,7 +45,7 @@ pnpm install # pnpm workspaces, node ^22.19 || >=24 pnpm run test # vitest unit tests pnpm run test:coverage # gate: per-file 100% on packages/*/*/src pnpm run test:e2e # real API; skips without key -pnpm run test:snapshot # keyless ACP replay vs goldens; filter: -t +pnpm run test:snapshot # keyless ACP/headless replay vs goldens; filter: -t pnpm run test:snapshot:record # re-record goldens (needs key) pnpm run typecheck pnpm run lint @@ -55,7 +55,7 @@ pnpm run hygiene # knip + publint + workspace constraints + NodeNext cons pnpm run doc-sync # all documentation gates; see the doc-sync script in package.json pnpm run demo:echo # mock-model REPL, no key needed pnpm run demo:repl # real coding REPL (needs key) -pnpm run demo:cli -- "task" # one-shot agent (needs key) +pnpm run demo:headless -- "task" # one-shot agent (needs key) pnpm run demo:cordis # self-modifying runtime demo (needs key) pnpm run demo:acp # ACP server (needs key) ``` diff --git a/README.i18n.yaml b/README.i18n.yaml index 790812344d..15992ac276 100644 --- a/README.i18n.yaml +++ b/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -README.md: 53dd3896eb15800125673e7c44f7de02daca9376 -README.zh.md: ab826f62658248249ec18c57b35c0065c0f909d1 +README.md: 4d2d2c20a27aff67d42a4555f4e0ce410dd5d6d7 +README.zh.md: 0fb307653f978143b851ef4822d93714910043af diff --git a/README.md b/README.md index 53dd3896eb..4d2d2c20a2 100644 --- a/README.md +++ b/README.md @@ -12,6 +12,7 @@ This monorepo is built on the [Cordis](https://github.com/cordiverse/cordis) fra pnpm install pnpm run test # vitest pnpm run demo:repl # REPL agent demo (needs DEEPSEEK_API_KEY) +pnpm run demo:headless -- "task" # one-shot agent demo (needs DEEPSEEK_API_KEY) pnpm run demo:acp # ACP server agent demo (needs DEEPSEEK_API_KEY) ``` diff --git a/README.zh.md b/README.zh.md index ab826f6265..0fb307653f 100644 --- a/README.zh.md +++ b/README.zh.md @@ -12,6 +12,7 @@ pnpm install pnpm run test # vitest pnpm run demo:repl # REPL agent demo (needs DEEPSEEK_API_KEY) +pnpm run demo:headless -- "task" # one-shot agent demo (needs DEEPSEEK_API_KEY) pnpm run demo:acp # ACP server agent demo (needs DEEPSEEK_API_KEY) ``` diff --git a/docs/testing.md b/docs/testing.md index d4acdc33c4..8d318ebd60 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -7,7 +7,7 @@ How this repo tests, tier by tier, and the rules that keep a green suite meaning - **Unit** (`pnpm run test`): vitest over `packages|examples/*/tests/**/*.spec.ts`, colocated with what they test. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Prefer edge cases, error paths, event ordering, concurrency races, and permanent contract regressions (see `packages/core/agent-loop/tests/contract-regressions.spec.ts`). - **Coverage gate** (`pnpm run test:coverage`): the gating run, per-file 100% on `packages/*/*/src`. An uncovered line is often dead code the gate is correctly flagging for deletion, not a missing test to bolt on. Line coverage is necessary, never sufficient — it proves lines ran, not that the feature works as shipped. - **Real-API e2e** (`pnpm run test:e2e`): with-key tests against live provider APIs — the DeepSeek model plus provider-specific smokes that gate on their own keys (`EXA_API_KEY`, `PERPLEXITY_API_KEY`, …); each suite self-skips without its key so keyless CI stays green ([real-API e2e RFC](rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md)). -- **Snapshot** (`pnpm run test:snapshot`): boots the real example subprocess, replays a recorded session keyless, diffs normalized stdout + the re-persisted log against committed goldens ([snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)). Use `pnpm run test:snapshot:record` when the model transcript should change; use `pnpm run test:snapshot:refresh` when the committed transcript is still the right mock LLM input and replay goldens need keyless rewrite. Review the golden diff. System-prompt/tool-schema content is pinned by ONE scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). +- **Snapshot** (`pnpm run test:snapshot`): real example subprocesses replay recorded model sessions keylessly and compare normalized stdout plus re-persisted logs ([snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)). The primary suite pins ACP JSON-RPC; the headless projection reuses `advanced-toolchain` for `stream-json`. Use `pnpm run test:snapshot:record` when the model transcript changes and `pnpm run test:snapshot:refresh` when only replay outputs change; review the golden diff. One scenario per header class pins system-prompt/tool-schema content; other fixtures tokenize it ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). ## The with-key policy: inference is cheap here @@ -30,4 +30,4 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword ## When a snapshot test is required -Any change affecting the editor-facing transcript or end-to-end agent UX — the ACP bridge, the loop's observable output, tool presentation — adds or updates a scenario in the owning example's snapshot suite (`examples//tests/snapshots/`, a scenario table over the [`dsh-acp-snapshot`](../packages/support/acp-snapshot/README.md) suite factory; `examples/acp-agent` is the primary suite), or states in the PR why none applies. New capability seams, lifecycle shapes, or transcript surfaces name their coverage at every tier at plan time and verify the harness can express it — a harness gap is scheduled work, not a mid-build surprise. +A change affecting an editor transcript, headless event stream, or agent UX adds or updates the owning `examples//tests/snapshots/` scenario, or explains its omission in the PR. `examples/acp-agent` hosts the primary [`dsh-acp-snapshot`](../packages/support/acp-snapshot/README.md) table and the headless `stream-json` projection. Plans for new capability seams, lifecycle shapes, or transcript surfaces identify every test tier and any required harness work before implementation. diff --git a/examples/README.md b/examples/README.md index d9e3e544db..399769992f 100644 --- a/examples/README.md +++ b/examples/README.md @@ -17,7 +17,7 @@ Run with: `pnpm run demo:echo`. When prompted, type "echo " to trigge A REPL agent demo: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite, `subagent` delegation, and the `todo_write` task tracker on the same `@deepseek-ai/dsh-stdio-demo` app. The UI is a terminal readline REPL. -Run interactively with `pnpm run demo:repl`, or run one headless task with `pnpm run demo:cli -- "task"` (both need `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. +Run interactively with `pnpm run demo:repl`, or run one headless task with `pnpm run demo:headless -- "task"` (both need `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. Run the Code Mode overlay with `pnpm run demo:code-mode`, or pass `acp` for the ACP example. See the [Code Mode example](coding-agent/README.md#code-mode) for its composition and a sample task. diff --git a/examples/acp-agent/README.md b/examples/acp-agent/README.md index 35218f4753..427b924d45 100644 --- a/examples/acp-agent/README.md +++ b/examples/acp-agent/README.md @@ -33,7 +33,7 @@ The editor sets each session's `cwd` to the project it opens, and bash uses that ## Snapshot tests (record-once / replay-deterministic) -This example hosts the ACP snapshot suite. `dsh-llm-replay` reconstructs model streams from `assistant/chunk` events in each scenario's session JSONL, so replay is keyless. Recording runs the real agent and harvests that log; refresh keeps the committed transcript as mock input and rewrites current replay outputs. `replay.override.json` covers throw and hang cases that chunks cannot express, and an optional `workspace/` seeds files. The [snapshot RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) owns the full design. +This example hosts the ACP snapshot suite and the headless `stream-json` snapshot. Both replay through `dsh-llm-replay`, which reconstructs model streams from `assistant/chunk` events in each scenario's session JSONL. The headless snapshot reuses `advanced-toolchain` to pin the one-shot stream plus its re-persisted parent and child logs; child activity appears in the stream only through parent tool events. Recording runs the real ACP agent and harvests its logs; refresh keeps the committed transcript as mock input and rewrites current replay outputs. `replay.override.json` covers throw and hang cases that chunks cannot express, and an optional `workspace/` seeds files. The [snapshot RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) owns the ACP harness design. ## Permissions and sandboxing diff --git a/examples/acp-agent/advanced-headless.cordis.snapshot.yml b/examples/acp-agent/advanced-headless.cordis.snapshot.yml new file mode 100644 index 0000000000..5047635ddb --- /dev/null +++ b/examples/acp-agent/advanced-headless.cordis.snapshot.yml @@ -0,0 +1,32 @@ +# Replay the advanced toolchain through the headless one-shot front door. It +# receives this replay config explicitly; unlike the ACP bin, it does not swap +# a live config for a sibling snapshot overlay. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./cordis.yml + patches: + - id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + disabled: true + - id: acp-agent + name: '@deepseek-ai/dsh-acp-demo' + disabled: true + - insert: + - id: cli-agent + name: '@deepseek-ai/dsh-cli-demo' + config: + model: deepseek-v4-flash + persistenceRoot: './.sessions' + tools: + mode: both + persona: | + You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. + + Verify your work by running the code or tests. Keep answers brief and factual. + - id: code-runtime + name: '@deepseek-ai/dsh-code-runtime-worker' + - id: tool-cordis + name: '@deepseek-ai/dsh-tool-cordis' + - id: llm-replay + name: '@deepseek-ai/dsh-llm-replay' diff --git a/examples/acp-agent/tests/headless.snapshot.ts b/examples/acp-agent/tests/headless.snapshot.ts new file mode 100644 index 0000000000..a38931a8ef --- /dev/null +++ b/examples/acp-agent/tests/headless.snapshot.ts @@ -0,0 +1,140 @@ +import { readFile, readdir, writeFile } from 'node:fs/promises' +import { delimiter, dirname, join } from 'node:path' +import { fileURLToPath } from 'node:url' +import { + normalizeSessionLog, + normalizeStdout, + scrubRequestHeaders, + type NormalizeContext, +} from '@deepseek-ai/dsh-acp-snapshot' +import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke' +import { describe, expect, it } from 'vitest' + +const snapshotsDir = join(dirname(fileURLToPath(import.meta.url)), 'snapshots') +const scenarioDir = join(snapshotsDir, 'advanced-toolchain') +const sessionFixture = join(scenarioDir, 'session.jsonl') +const streamGolden = join(scenarioDir, 'stream-json.golden.jsonl') +const configPath = fileURLToPath(new URL('../advanced-headless.cordis.snapshot.yml', import.meta.url)) +const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url)) +const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) +const refreshing = process.env.DSH_SNAPSHOT === 'refresh' + +interface JsonObject { + [key: string]: unknown +} + +interface PersistedLog { + readonly content: string + readonly header: JsonObject +} + +function parseJsonl(content: string): JsonObject[] { + return content.split('\n') + .filter(line => line.trim().length > 0) + .map(line => JSON.parse(line) as JsonObject) +} + +function contextFromLogs(contents: readonly string[]): NormalizeContext { + const headers = contents.map(content => parseJsonl(content)[0]) + return { + sessionIds: headers.flatMap(header => typeof header?.id === 'string' ? [header.id] : []), + cwd: typeof headers[0]?.cwd === 'string' ? headers[0].cwd : '\0no-cwd\0', + } +} + +function normalizeHeadlessStream(rawStdout: string, cwd: string): string { + const records = parseJsonl(rawStdout) + if (records.length === 0) throw new Error('headless snapshot emitted no stream-json records') + const final = records.at(-1) + if (final?.type !== 'result') throw new Error('headless snapshot did not end with a result record') + if (records.slice(0, -1).some(record => record.type !== 'session_event')) { + throw new Error('headless snapshot emitted a non-event record before its result') + } + + const sessionIds = [...new Set(records.flatMap(record => typeof record.sessionId === 'string' ? [record.sessionId] : []))] + if (sessionIds.length !== 1) throw new Error(`headless snapshot streamed ${sessionIds.length} main session ids`) + const context: NormalizeContext = { sessionIds, cwd } + const events = records.slice(0, -1).map((record) => { + if (record.event === null || typeof record.event !== 'object' || Array.isArray(record.event)) { + throw new Error('headless snapshot emitted an invalid session event') + } + return record.event as JsonObject + }) + const normalizedEvents = parseJsonl(scrubRequestHeaders(normalizeSessionLog( + `${events.map(event => JSON.stringify(event)).join('\n')}\n`, + context, + ))) + const normalizedRecords = records.map((record, index) => index < normalizedEvents.length + ? { ...record, event: normalizedEvents[index] } + : record) + return normalizeStdout(`${normalizedRecords.map(record => JSON.stringify(record)).join('\n')}\n`, context) +} + +async function advancedPrompt(): Promise { + const input = JSON.parse(await readFile(join(scenarioDir, 'input.json'), 'utf8')) as { + steps?: { op?: unknown; text?: unknown }[] + } + const prompt = input.steps?.find(step => step.op === 'prompt')?.text + if (typeof prompt !== 'string') throw new Error('advanced-toolchain input has no prompt step') + return prompt +} + +async function persistedLogs(cwd: string): Promise { + const root = join(cwd, '.sessions') + const files = (await readdir(root, { recursive: true })).filter(file => file.endsWith('.jsonl')) + return Promise.all(files.map(async (file) => { + const content = await readFile(join(root, file), 'utf8') + return { content, header: parseJsonl(content)[0] ?? {} } + })) +} + +describe('headless stream-json snapshots', () => { + it('replays the advanced toolchain through the one-shot app', async () => { + const prompt = await advancedPrompt() + const expectedSessions = await Promise.all([ + sessionFixture, + join(scenarioDir, 'session.1.jsonl'), + join(scenarioDir, 'session.2.jsonl'), + ].map(file => readFile(file, 'utf8'))) + let runCwd = '' + const result = await runLoaderSmoke({ + label: 'advanced headless stream-json snapshot', + tempDirPrefix: 'headless-snapshot-advanced-', + binScript, + configPath, + binArgs: ['--config', configPath, '--output-format', 'stream-json', prompt], + tsconfigPath, + env: { + DSH_SNAPSHOT: 'replay', + DSH_SNAPSHOT_FILE: sessionFixture, + DSH_SNAPSHOT_CHILD_FILES: [join(scenarioDir, 'session.1.jsonl'), join(scenarioDir, 'session.2.jsonl')].join(delimiter), + NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '), + }, + prepare: (cwd) => { runCwd = cwd }, + inspect: async (cwd) => { + const logs = await persistedLogs(cwd) + expect(logs).toHaveLength(3) + const parents = logs.filter(log => typeof log.header.parentSession !== 'string') + expect(parents).toHaveLength(1) + const parent = parents[0] + if (parent === undefined) throw new Error('headless snapshot did not persist its main session') + const children = logs.filter(log => typeof log.header.parentSession === 'string') + .sort((left, right) => Number(left.header.createdAt) - Number(right.header.createdAt)) + const actualSessions = [parent, ...children] + const actualContext = contextFromLogs(actualSessions.map(log => log.content)) + const expectedContext = contextFromLogs(expectedSessions) + for (const [index, actual] of actualSessions.entries()) { + const expected = expectedSessions[index] + if (expected === undefined) throw new Error(`headless snapshot has no fixture for persisted log ${index}`) + expect(scrubRequestHeaders(normalizeSessionLog(actual.content, actualContext))) + .toBe(scrubRequestHeaders(normalizeSessionLog(expected, expectedContext))) + } + }, + }) + + expect(result.stderr).toBe('') + const normalized = normalizeHeadlessStream(result.stdout, runCwd) + if (refreshing) await writeFile(streamGolden, normalized) + expect(normalized).toBe(await readFile(streamGolden, 'utf8')) + }, LOADER_SMOKE_TEST_TIMEOUT_MS) +}) diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl new file mode 100644 index 0000000000..ea5eca3765 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl @@ -0,0 +1,64 @@ +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":12,"time":0,"data":{"turn":1,"step":1}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":13,"time":0,"data":{"turn":1,"step":2}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-code","name":"run_code","argumentsDelta":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":19,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":20,"time":0,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/code-dispatch","seq":21,"time":0,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"},"isError":false,"resultSummary":"## dynamic\n- dyn-1: snapshot-marker [active]"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}],"isError":false,"meta":{"logs":[]}},"sourceEventSeqs":[20],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":23,"time":0,"data":{"turn":1,"step":2}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":24,"time":0,"data":{"turn":1,"step":3}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":25,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-direct-child","name":"subagent","argumentsDelta":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":30,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":31,"time":0,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":32,"time":0,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"isError":false},"sourceEventSeqs":[31],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":33,"time":0,"data":{"turn":1,"step":3}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":34,"time":0,"data":{"turn":1,"step":4}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":35,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":36,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-workflow","name":"workflow","argumentsDelta":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":38,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":40,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":41,"time":0,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":42,"time":0,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-acp-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[41],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":43,"time":0,"data":{"turn":1,"step":4}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":44,"time":0,"data":{"turn":1,"step":5}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":45,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":46,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-unmount","name":"cordis_unmount","argumentsDelta":"{\"id\":\"dyn-1\"}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":47,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":48,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":49,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":50,"time":0,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":51,"time":0,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":52,"time":0,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"unmounted dyn-1 (plugin \"snapshot-marker\")"}],"isError":false},"sourceEventSeqs":[51],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":53,"time":0,"data":{"turn":1,"step":5}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":54,"time":0,"data":{"turn":1,"step":6}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":55,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":56,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"text-delta","index":0,"text":"ADVANCED_ACP_OK"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":57,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_ACP_OK"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":58,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":59,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":60,"time":0,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_ACP_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":61,"time":0,"data":{"turn":1,"step":6}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":62,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}} +{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"ADVANCED_ACP_OK","reason":{"kind":"completed"},"usage":{"inputTokens":18,"outputTokens":18}} diff --git a/examples/coding-agent/README.md b/examples/coding-agent/README.md index c9f606766d..5efe939cfe 100644 --- a/examples/coding-agent/README.md +++ b/examples/coding-agent/README.md @@ -26,9 +26,9 @@ Type a coding task. The agent works through the `read`/`write`/`edit` filesystem Run one task through all model and tool steps, flush its fresh session, print the final result, and exit: ```sh -pnpm run demo:cli -- "fix the failing test in this workspace" -pnpm run demo:cli --output-format json -- "summarize the current implementation" -pnpm run demo:cli --output-format stream-json -- "run the focused tests" +pnpm run demo:headless -- "fix the failing test in this workspace" +pnpm run demo:headless --output-format json -- "summarize the current implementation" +pnpm run demo:headless --output-format stream-json -- "run the focused tests" ``` The root command supplies `cli.cordis.yml`, which disables HMR and the REPL app and inserts [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo). Exactly one quoted positional task is required; there is no `-p` flag. `text` prints the last text-bearing assistant message, `json` prints one DSH-native result record, and `stream-json` emits the parent `main` session's canonical task-turn events before that record. Non-completed turns retain partial output but exit nonzero; argument and boot failures leave stdout empty. diff --git a/package.json b/package.json index d6f64f210b..2bf8506bf8 100644 --- a/package.json +++ b/package.json @@ -74,7 +74,7 @@ "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-cordis-config && pnpm run verify-node-next-types && pnpm run verify-runtime-closure", "demo:echo": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/echo-agent/cordis.yml", "demo:repl": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/coding-agent/cordis.yml", - "demo:cli": "node --expose-internals --import tsx packages/examples/cli-demo/src/bin.ts --config examples/coding-agent/cli.cordis.yml", + "demo:headless": "node --expose-internals --import tsx packages/examples/cli-demo/src/bin.ts --config examples/coding-agent/cli.cordis.yml", "demo:code-mode": "node scripts/demo-code-mode.mjs", "demo:cordis": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/cordis-agent/cordis.yml", "demo:acp": "node --import tsx packages/examples/acp-demo/src/bin.ts --config examples/acp-agent/cordis.yml", diff --git a/packages/examples/cli-demo/README.md b/packages/examples/cli-demo/README.md index 558c5eeff3..38c38cf69c 100644 --- a/packages/examples/cli-demo/README.md +++ b/packages/examples/cli-demo/README.md @@ -28,7 +28,7 @@ dsh-cli-demo [--config path] [--output-format text|json|stream-json] The root coding demo supplies its overlay: ```sh -pnpm run demo:cli -- "inspect the failing test and fix it" +pnpm run demo:headless -- "inspect the failing test and fix it" ``` Loader configs with bare package specifiers require `node --expose-internals` or the Loader's optional native fallback. The root command supplies the Node flag. From fb7fa980b8411e285c5e396a42868b2f72d68b92 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 22:58:44 +0800 Subject: [PATCH 158/359] test(examples): include task controls in CLI composition --- packages/examples/cli-demo/tests/cli-demo.spec.ts | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/packages/examples/cli-demo/tests/cli-demo.spec.ts b/packages/examples/cli-demo/tests/cli-demo.spec.ts index 4cb7a243a5..1fb0e09999 100644 --- a/packages/examples/cli-demo/tests/cli-demo.spec.ts +++ b/packages/examples/cli-demo/tests/cli-demo.spec.ts @@ -89,7 +89,14 @@ describe('dsh-cli-demo app composition', () => { ctx.tools.register({ name, description: name, parameters: {}, execute: async () => [] }) } expect(JSON.stringify(await composePrefix(ctx))).toContain('- `cli-skill`: CLI...') - expect((await ctx.systemPrompt.assemble()).tools.map(tool => tool.name)).toEqual(['zulu', 'alpha', 'skill']) + expect((await ctx.systemPrompt.assemble()).tools.map(tool => tool.name)).toEqual([ + 'zulu', + 'alpha', + 'skill', + 'task_kill', + 'task_list', + 'task_output', + ]) }) it('exposes the Loader-safe namespace plugin shape and schema', () => { From bb1c8fa27da12f2432afaf3d5c04fd8299df73e9 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:09:14 +0800 Subject: [PATCH 159/359] fix(llm): restore pruned status contract --- docs/cordis-catalog/services.md | 2 +- packages/llm/llm-deepseek/src/adapter.ts | 6 +++--- packages/llm/llm-deepseek/tests/adapter.spec.ts | 7 +------ packages/llm/llm-pi-ai/README.md | 2 +- packages/llm/llm/README.md | 2 +- packages/llm/llm/src/index.ts | 6 ++---- packages/llm/llm/tests/service.spec.ts | 5 +++-- packages/support/llm-replay/src/index.ts | 4 ++-- packages/support/llm-replay/tests/llm-replay.spec.ts | 10 +++++----- 9 files changed, 19 insertions(+), 25 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 18e00b7904..48fb887d27 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -128,7 +128,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:75`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:73`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index 30760a8fbc..978dec65c8 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -73,10 +73,10 @@ export class DeepSeekAdapter extends LlmAdapter { const parsed = await response.json() as WireError if (parsed.error?.message) message = parsed.error.message } catch { - // Only swallow error-body parsing: status and code are already captured, - // so malformed gateway JSON must not mask the actionable HTTP failure. + // Only swallow error-body parsing: the stable code and status-line message + // are already captured, so malformed gateway JSON must not mask the failure. } - throw new LlmError(message, code, response.status) + throw new LlmError(message, code) } if (!response.body) { throw new LlmError('DeepSeek API returned no response body', 'EMPTY_RESPONSE') diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 46f123a1c7..1f1aef3f05 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -158,7 +158,7 @@ describe('DeepSeekAdapter against a mock server', () => { status, body: JSON.stringify({ error: { message: `failed with ${status}`, type: 't', code: 'c' } }), } - const server = await mockServer([behavior, behavior, behavior]) + const server = await mockServer([behavior, behavior]) const ctx = await harness(server.url) await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })) .rejects.toThrow(`failed with ${status}`) @@ -166,11 +166,6 @@ describe('DeepSeekAdapter against a mock server', () => { assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) .catch((error: unknown) => (error as LlmError).code), ).resolves.toBe(code) - // The numeric HTTP status is carried on the error for explicit handling. - await expect( - assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - .catch((error: unknown) => (error as LlmError).status), - ).resolves.toBe(status) }) it('keeps the status-line message for JSON error bodies without a message', async () => { diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index dd1cb5b48c..281a4f13be 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -55,6 +55,6 @@ Unit suites run against a local `node:http` mock SSE server (pi-ai's openai SDK - **`tool_choice` is not mapped** — same MVP contract as llm-deepseek. - **In-history `system`-role messages fold into `user`-role wire messages** — pi-ai exposes a single `systemPrompt` slot, diverging from the hand-rolled twin's `role: 'system'` passthrough. -- **`LlmError.status` is never set** — pi-ai reports failures as in-stream events with no HTTP status, so error codes are regex-classified from the error text. +- **Provider HTTP status is unavailable** — pi-ai reports failures as in-stream events, so stable error codes are regex-classified from the error text. - **`buildModel` hardcodes descriptor metadata** — `contextWindow: 128000`, `maxTokens: 64000`, zero cost, identically for every registered model name; not configurable. - **pi-ai's built-in retries are disabled (`maxRetries: 0`)** — failures surface immediately; retry policy belongs to `llm/stream` listeners. diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 296fd0c3d3..c8f2002f9f 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -42,7 +42,7 @@ Every product adapter sends application identity on provider HTTP requests. `att - `LlmAdapter` — abstract base class for provider adapters. The only required method is `stream()`. - `BlockAssembler` — incrementally assembles raw chunks into complete content blocks and an assistant message. The agent loop feeds it raw chunks (logging them for replay) while reading the assembled blocks/message for history. - `HarnessError` — base class for the harness error taxonomy: a stable `code` string (distinct from the human `message`) plus `cause` chaining. Lives here, in the leaf package every other imports, so a single base is shared without a new dependency edge. Per-package errors (`LlmError`, `ToolArgsError`, `InvariantError`, …) extend it. `isHarnessError(value)` narrows at seams. -- `LlmError` — extends `HarnessError`; `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) plus an optional numeric `status` when the failure came from a non-2xx provider response. +- `LlmError` — extends `HarnessError`; its stable `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) is the programmatic failure contract. ### Real adapters diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 08f3f54c51..8f2c9b4f39 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -42,12 +42,10 @@ declare module 'cordis' { /** * Typed error for LLM-related failures. Extends {@link HarnessError}, so the - * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy; - * `status` carries the HTTP status when the error originated from a non-2xx - * provider response (absent for protocol/usage errors that have no HTTP status). + * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy. */ export class LlmError extends HarnessError { - constructor(message: string, code: string, public status?: number, options?: ErrorOptions) { + constructor(message: string, code: string, options?: ErrorOptions) { super(message, code, options) this.name = 'LlmError' } diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index f669069c44..125a810261 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -79,11 +79,12 @@ describe('LlmService', () => { it('LlmError extends the shared HarnessError base', async () => { const { HarnessError, isHarnessError } = await import('@deepseek-ai/dsh-llm') - const err = new LlmError('boom', 'AUTH', 401) + const cause = new Error('root cause') + const err = new LlmError('boom', 'AUTH', { cause }) expect(err).toBeInstanceOf(HarnessError) expect(isHarnessError(err)).toBe(true) expect(err.code).toBe('AUTH') - expect(err.status).toBe(401) + expect(err.cause).toBe(cause) }) it('HarnessError carries a code, names itself by subclass, and chains cause', async () => { diff --git a/packages/support/llm-replay/src/index.ts b/packages/support/llm-replay/src/index.ts index 2e509973e5..b7e4e30a46 100644 --- a/packages/support/llm-replay/src/index.ts +++ b/packages/support/llm-replay/src/index.ts @@ -20,7 +20,7 @@ import { LlmError, assertNever } from '@deepseek-ai/dsh-llm' */ export type ReplayEntry = | { kind: 'chunks'; chunks: StreamChunk[] } - | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string; status?: number } + | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string } | { kind: 'hang' } /** Resolved plugin configuration. */ @@ -221,7 +221,7 @@ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined) if (signal?.aborted) throw new Error('aborted') yield chunk } - throw new LlmError(entry.message, entry.code, entry.status) + throw new LlmError(entry.message, entry.code) case 'hang': // Replay a stream that stalls until cancelled (mirrors MockAdapter): one // chunk, then wait for abort and surface it as the consumer expects. diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index ac52ec11c9..aa3fea20d5 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -175,7 +175,7 @@ describe('loadReplayScript', () => { it('uses the sidecar override when present, ignoring the JSONL', () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') - const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH', status: 401 }] + const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH' }] writeFileSync(overrideFile, JSON.stringify(override), 'utf8') expect(loadReplayScript({ file, overrideFile })).toEqual(override) }) @@ -231,12 +231,12 @@ describe('installLlmReplay (through the real waterfall)', () => { expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(second) }) - it('replays a sidecar throw-entry as an LlmError with code/status, after its prefix chunks', async () => { + it('replays a sidecar throw-entry as an LlmError with its stable code, after its prefix chunks', async () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) @@ -245,7 +245,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const seen: StreamChunk[] = [] await expect((async () => { for await (const c of ctx.llm.stream({ model: 'm', messages: [] })) seen.push(c) - })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH', status: 401 }) + })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH' }) expect(seen).toEqual(partial) }) @@ -350,7 +350,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) From f8cc1af99b9b8a5681f93e8939bf8e93f98a4011 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:36:57 +0800 Subject: [PATCH 160/359] test(tasks): align tool fixtures with unified identity --- .../tasks/tool-tasks/tests/tool-tasks.spec.ts | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts b/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts index 1b5e221a3c..0a2d89431e 100644 --- a/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts +++ b/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts @@ -5,6 +5,7 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' import TaskService from '@deepseek-ai/dsh-tasks' import type { TaskHooks, TaskOutcome, TaskSnapshot, TaskStart } from '@deepseek-ai/dsh-tasks' import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks' @@ -23,17 +24,17 @@ async function setup(config: ToolTasks.Config = {}) { } /** - * A fake agent whose session token is `sessionId`, registered in `ctx.agents`. - * The agent id is deliberately different so session authorization and exact - * lifecycle ownership cannot be confused in tests. + * A fake agent with the shared agent/session identity, registered in + * `ctx.agents` with a dedicated lifecycle scope. */ function fakeAgent(ctx: Context, sessionId: string, inject: (...args: unknown[]) => void = () => {}): Agent { const scopeFiber = ctx.plugin(() => {}) + const id = SessionId(sessionId) const agent = { - id: `agent-${sessionId}`, + id, ctx: scopeFiber.ctx, inject, - session: { header: { version: 0, id: sessionId, createdAt: 0 } }, + session: { id, header: { version: 0, id, createdAt: 0 } }, } as unknown as Agent agentRegistryDisposers.set(agent, ctx.agents.register(agent)) return agent @@ -276,7 +277,7 @@ describe('completion notices', () => { await tick() // Disposed owner: inject throws the disposed message — contained. - const inject = vi.fn(() => { throw new Error('agent "agent-sess-1" is disposed') }) + const inject = vi.fn(() => { throw new Error('agent "sess-1" is disposed') }) const owner = fakeAgent(ctx, 'sess-1', inject) const p = producer({ owner }) ctx.tasks.start(p.spec) @@ -287,7 +288,7 @@ describe('completion notices', () => { it('does not route an old owner completion notice to a same-session replacement', async () => { const { ctx } = await setup() - const oldInject = vi.fn(() => { throw new Error('agent "agent-shared" is disposed') }) + const oldInject = vi.fn(() => { throw new Error('agent "shared" is disposed') }) const oldOwner = fakeAgent(ctx, 'shared', oldInject) const p = producer({ owner: oldOwner }) ctx.tasks.start(p.spec) From 8e37abb6c9dffa1fa2d5a24d05aa9eef4dde88e3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:50:33 +0800 Subject: [PATCH 161/359] docs: refresh module graph for unified identity --- docs/module-graph.md | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index 199f11e8d3..baa714bad1 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -205,6 +205,7 @@ flowchart TD pkg_workflow --> pkg_agent pkg_workflow --> pkg_brand pkg_workflow --> pkg_llm + pkg_workflow --> pkg_session pkg_tools --> pkg_agent pkg_tools --> pkg_code_runtime pkg_tools --> pkg_llm @@ -219,10 +220,6 @@ flowchart TD pkg_permission --> pkg_sandbox pkg_permission --> pkg_session pkg_permission --> pkg_user_approval - pkg_stdio --> pkg_agent - pkg_stdio --> pkg_llm - pkg_stdio --> pkg_session - pkg_stdio --> pkg_user_interaction pkg_agent_loop --> pkg_agent pkg_agent_loop --> pkg_llm pkg_agent_loop --> pkg_scope @@ -250,6 +247,7 @@ flowchart TD pkg_subagent --> pkg_agent pkg_subagent --> pkg_llm pkg_subagent --> pkg_scope + pkg_subagent --> pkg_session pkg_subagent --> pkg_tools pkg_tool_web --> pkg_llm pkg_tool_web --> pkg_system_prompt @@ -296,6 +294,7 @@ flowchart TD pkg_tool_workflow --> pkg_workflow pkg_subagent_acp --> pkg_agent pkg_subagent_acp --> pkg_llm + pkg_subagent_acp --> pkg_session pkg_subagent_acp --> pkg_subagent pkg_subagent_acp --> pkg_subagent_subprocess pkg_subagent_inprocess --> pkg_agent @@ -317,12 +316,18 @@ flowchart TD pkg_hooks_claude --> pkg_tools pkg_subagent_mock --> pkg_agent pkg_subagent_mock --> pkg_llm + pkg_subagent_mock --> pkg_session pkg_subagent_mock --> pkg_subagent pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm pkg_jsonrpc --> pkg_llm_deepseek pkg_jsonrpc --> pkg_session pkg_jsonrpc --> pkg_subagent + pkg_stdio --> pkg_agent + pkg_stdio --> pkg_agent_loop + pkg_stdio --> pkg_llm + pkg_stdio --> pkg_session + pkg_stdio --> pkg_user_interaction pkg_agent_spine_demo --> pkg_agent pkg_agent_spine_demo --> pkg_agent_loop pkg_agent_spine_demo --> pkg_invariants @@ -356,6 +361,7 @@ flowchart TD pkg_acp_demo --> pkg_tools pkg_acp_demo --> pkg_user_interaction pkg_stdio_demo --> pkg_agent + pkg_stdio_demo --> pkg_agent_loop pkg_stdio_demo --> pkg_agent_spine_demo pkg_stdio_demo --> pkg_app_boot pkg_stdio_demo --> pkg_llm @@ -412,16 +418,15 @@ flowchart TD | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) | | [`time-context`](../packages/context/time-context) | `context` | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt) | | [`tasks`](../packages/tasks/tasks) | `tasks` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) | -| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) | +| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) | | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) | | [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) | -| [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | -| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | +| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) | | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | @@ -433,15 +438,16 @@ flowchart TD | [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`llm`](../packages/llm/llm), [`tools`](../packages/core/tools) | | [`tool-tasks`](../packages/tasks/tool-tasks) | `tasks` | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | -| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | +| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | -| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) | +| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | +| [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | -| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | +| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | From 419b0bcf7dfd9c0e88bc15ecf303c9576a92b43f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:51:45 +0800 Subject: [PATCH 162/359] docs: refresh module graph for UI identity --- docs/module-graph.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index baa714bad1..83f98d734e 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -321,6 +321,7 @@ flowchart TD pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm pkg_jsonrpc --> pkg_llm_deepseek + pkg_jsonrpc --> pkg_scope pkg_jsonrpc --> pkg_session pkg_jsonrpc --> pkg_subagent pkg_stdio --> pkg_agent @@ -443,7 +444,7 @@ flowchart TD | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | -| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | +| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | From 867d248c2ea3147b8f25fcebf565b1d5329c283e Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:37:52 +0800 Subject: [PATCH 163/359] test(hooks): split coverage suites across workers --- .../hooks-claude/tests/coverage-cases.ts | 693 ++++++++++++++++++ .../tests/coverage-config.spec.ts | 3 + .../tests/coverage-context.spec.ts | 3 + .../tests/coverage-edge-paths.spec.ts | 3 + .../hooks-claude/tests/coverage-stop.spec.ts | 3 + .../hooks/hooks-claude/tests/coverage.spec.ts | 688 ----------------- .../hooks/hooks-codex/tests/coverage-cases.ts | 574 +++++++++++++++ .../tests/coverage-post-tool.spec.ts | 3 + .../hooks-codex/tests/coverage-prompt.spec.ts | 3 + .../tests/coverage-result-shape.spec.ts | 3 + .../hooks/hooks-codex/tests/coverage.spec.ts | 560 -------------- 11 files changed, 1288 insertions(+), 1248 deletions(-) create mode 100644 packages/hooks/hooks-claude/tests/coverage-cases.ts create mode 100644 packages/hooks/hooks-claude/tests/coverage-config.spec.ts create mode 100644 packages/hooks/hooks-claude/tests/coverage-context.spec.ts create mode 100644 packages/hooks/hooks-claude/tests/coverage-edge-paths.spec.ts create mode 100644 packages/hooks/hooks-claude/tests/coverage-stop.spec.ts delete mode 100644 packages/hooks/hooks-claude/tests/coverage.spec.ts create mode 100644 packages/hooks/hooks-codex/tests/coverage-cases.ts create mode 100644 packages/hooks/hooks-codex/tests/coverage-post-tool.spec.ts create mode 100644 packages/hooks/hooks-codex/tests/coverage-prompt.spec.ts create mode 100644 packages/hooks/hooks-codex/tests/coverage-result-shape.spec.ts delete mode 100644 packages/hooks/hooks-codex/tests/coverage.spec.ts diff --git a/packages/hooks/hooks-claude/tests/coverage-cases.ts b/packages/hooks/hooks-claude/tests/coverage-cases.ts new file mode 100644 index 0000000000..f47394a77f --- /dev/null +++ b/packages/hooks/hooks-claude/tests/coverage-cases.ts @@ -0,0 +1,693 @@ +import { afterEach, describe, expect, it, vi } from 'vitest' +import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync } from 'node:fs' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { Context } from 'cordis' +import LlmService from '@deepseek-ai/dsh-llm' +import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' +import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' +import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' +import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' + +/** Targeted branch coverage for the CC bridge: option arms, warn paths, no-agent + * fallbacks, contextFrom-empty, and the detached-listener catch handlers. */ + +const dirs: string[] = [] +afterEach(() => { for (const d of dirs.splice(0)) rmSync(d, { recursive: true, force: true }) }) + +function dir(): string { const d = mkdtempSync(join(tmpdir(), 'dsh-hc-cov-')); dirs.push(d); return d } +function sh(d: string, name: string, body: string): string { + const p = join(d, name); writeFileSync(p, body); chmodSync(p, 0o755); return p +} +function hooks(d: string, h: unknown): string { + writeFileSync(join(d, 'hooks.json'), JSON.stringify({ hooks: h })); return join(d, 'hooks.json') +} + +type HarnessOpts = { pluginRoot?: string; projectDir?: string; stderrSummaryMaxChars?: number } +async function harness(configPath: string, adapter: MockAdapter, opts: HarnessOpts = {}): Promise { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentLoop, { agents: [] }) + await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) + await ctx.plugin(HooksClaude, { configPath, ...opts }) + ctx.llm.registerAdapter(['mock'], adapter) + return ctx +} +function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { + return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) }) +} +function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] } +/** Poll until `predicate` holds or the deadline passes — robust to detached + * emit-listener hooks firing on a `.then` (a fixed sleep flakes under load). */ +async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise { + const deadline = Date.now() + timeout + while (!predicate()) { + if (Date.now() > deadline) throw new Error('waitFor: condition not met before deadline') + await new Promise(r => setTimeout(r, interval)) + } +} + +export type CoverageGroup = 'config' | 'stop' | 'context' | 'edge-paths' + +/** Register independently schedulable slices of the hooks-claude coverage matrix. */ +export function defineCoverageCases(group: CoverageGroup): void { + if (group === 'config') describe('hooks-claude coverage — config option arms + substitution + skip warning', () => { + it('honors pluginRoot + projectDir substitution and warns on a skipped non-command hook', async () => { + const d = dir() + // ${CLAUDE_PLUGIN_ROOT} resolves to d; the script writes its own cwd-independent marker. + const marker = join(d, 'ran') + sh(d, 'h.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) + const path = hooks(d, { + PreToolUse: [{ hooks: [ + { type: 'prompt', prompt: 'skipme' }, // skipped → warn loop + { type: 'command', command: '${CLAUDE_PLUGIN_ROOT}/h.sh' }, // substituted + ] }], + }) + const warn = vi.fn() + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter, { pluginRoot: d, projectDir: d }) + ctx.logger.warn = warn as never + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + expect(existsSync(marker)).toBe(true) // substituted command ran + }) + + it('warns and honors updatedInput as a no-op (input rewrite deferred)', async () => { + const d = dir() + const s = sh(d, 'u.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PreToolUse","permissionDecision":"allow","updatedInput":{"command":"rewritten"}}}\'\n') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const warn = vi.fn() + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', { command: 'original' }), textResponse('done')]) + const ctx = await harness(path, adapter) + ctx.logger.warn = warn as never + let sawArgs: unknown + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: { command: { type: 'string' } }, async execute(args) { sawArgs = args; return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + // updatedInput is NOT honored — the tool ran with the ORIGINAL args. + expect((sawArgs as { command?: string }).command).toBe('original') + expect(warn).toHaveBeenCalledWith(expect.stringContaining('updatedInput')) + }) + }) + + if (group === 'config') describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () => { + it('a clean exit-0 hook with no output is a no-op (contextFrom empty → next())', async () => { + const d = dir() + const s = sh(d, 'noop.sh', '#!/usr/bin/env bash\nexit 0\n') + const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([textResponse('ran')]) + const ctx = await harness(path, adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + // The prompt proceeded unchanged; no context/message injected. + expect(adapter.requests).toHaveLength(1) + expect(events(agent).some(e => e.type === 'context/message')).toBe(false) + }) + + it('a PreToolUse hook fires for a no-agent direct tool call (no session/turn to record into)', async () => { + const d = dir() + const s = sh(d, 'deny.sh', '#!/usr/bin/env bash\necho "no" >&2\nexit 2\n') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const ctx = await harness(path, new MockAdapter([])) + let ran = false + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) + // Call execute() directly with NO agent — the bridge's no-agent/no-turn path. + const { CallId } = await import('@deepseek-ai/dsh-llm') + const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: {} }) + expect(ran).toBe(false) + expect(result.isError).toBe(true) + }) + + it('a long stderr is truncated in the hook/result summary', async () => { + const d = dir() + // Emit >500 chars of stderr then exit 2. + const s = sh(d, 'long.sh', '#!/usr/bin/env bash\nprintf "x%.0s" {1..600} >&2\nexit 2\n') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + const res = events(agent).find(e => e.type === 'hook/result') + expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true) + expect(res?.type === 'hook/result' && res.data.stderrSummary?.length).toBe(501) // default 500-char cap + ellipsis + }) + + it('rejects a non-positive or fractional stderrSummaryMaxChars at load', async () => { + const d = dir() + const path = hooks(d, {}) + for (const bad of [0, -5, 1.5, Number.NaN]) { + const adapter = new MockAdapter([]) + await expect(harness(path, adapter, { stderrSummaryMaxChars: bad })) + .rejects.toThrow(/hooks-claude: stderrSummaryMaxChars must be a positive integer/) + } + }) + + it('the stderr summary cap is plugin config (stderrSummaryMaxChars)', async () => { + const d = dir() + const s = sh(d, 'long.sh', '#!/usr/bin/env bash\nprintf "x%.0s" {1..600} >&2\nexit 2\n') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter, { stderrSummaryMaxChars: 40 }) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + const res = events(agent).find(e => e.type === 'hook/result') + expect(res?.type === 'hook/result' && res.data.stderrSummary).toBe('x'.repeat(40) + '…') + }) + }) + + if (group === 'stop') describe('hooks-claude coverage — Stop continuation + subagent inject/catch', () => { + it('a Stop hook that blocks (exit 2) forces the turn to continue (CC dialect)', async () => { + const d = dir() + const marker = join(d, 'fired') + const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\necho "continue please" >&2\nexit 2\n`) + const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) + const ctx = await harness(path, adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + expect(adapter.requests).toHaveLength(2) + expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('continue please') + }) + + it('a Stop hook that blocks with EMPTY stderr still forces continuation (no reason required)', async () => { + // A blocking Stop hook with no stderr yields `deny` without a reason. The block still forces + // continuation; the script self-limits to one block to avoid a loop. + const d = dir() + const marker = join(d, 'fired') + const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\nexit 2\n`) + const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) + const ctx = await harness(path, adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + // A second model request ran → the empty-reason block forced continuation. + expect(adapter.requests).toHaveLength(2) + // The steering carried the fallback reason (no stderr to use). + expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('blocked by Stop hook') + }) + + it('SubagentStart additionalContext is injected into a REGISTERED live child', async () => { + const d = dir() + const s = sh(d, 'sa.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SubagentStart","additionalContext":"child guidance"}}\'\n') + const path = hooks(d, { SubagentStart: [{ hooks: [{ type: 'command', command: s }] }] }) + const ctx = await harness(path, new MockAdapter([])) + // Register a fake child agent under the id the event carries. + const injected: string[] = [] + const child = { id: AgentId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters[0] + ctx.agents.register(child) + ctx.emit('subagent/start', { provider: 'p', id: AgentId('child-x') }) + await waitFor(() => injected.includes('child guidance')) + expect(injected).toContain('child guidance') + }) + + it('a throwing SubagentStart/SubagentStop hook run is contained (logged)', async () => { + const d = dir() + // A hook command that does not exist makes runHook resolve a non-blocking + // error (not a throw), so to hit the .catch we make the .then throw: register + // a child whose inject throws for SubagentStart. + const s = sh(d, 'sa.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SubagentStart","additionalContext":"x"}}\'\n') + const path = hooks(d, { SubagentStart: [{ hooks: [{ type: 'command', command: s }] }] }) + const ctx = await harness(path, new MockAdapter([])) + const warn = vi.fn(); ctx.logger.warn = warn as never + const child = { id: AgentId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters[0] + ctx.agents.register(child) + ctx.emit('subagent/start', { provider: 'p', id: AgentId('child-y') }) + await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SubagentStart hook failed'))) + expect(warn).toHaveBeenCalledWith(expect.stringContaining('SubagentStart hook failed')) + }) + }) + + if (group === 'stop') describe('hooks-claude coverage — default reasons + sparse payloads', () => { + it('PreToolUse deny with EMPTY stderr uses the default reason', async () => { + const d = dir() + const s = sh(d, 'deny.sh', '#!/usr/bin/env bash\nexit 2\n') // exit 2, no stderr + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'x' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + const result = events(agent).find(e => e.type === 'tool/result') + expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true) + }) + + it('PostToolUse deny with EMPTY stderr + no context uses the default feedback', async () => { + const d = dir() + const s = sh(d, 'block.sh', '#!/usr/bin/env bash\nexit 2\n') + const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + const result = events(agent).find(e => e.type === 'tool/result') + expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PostToolUse hook'))).toBe(true) + }) + + it('SubagentStop with no registered child runs the hook cleanly (fire-and-forget)', async () => { + const d = dir() + // The agents registry has no entry for the id, so the child lookup yields + // undefined and the payload falls back to base(undefined) — assert the + // observe-only SubagentStop run still executes the hook without crashing. + const marker = join(d, 'stopran') + const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) + const path = hooks(d, { SubagentStop: [{ hooks: [{ type: 'command', command: s }] }] }) + const ctx = await harness(path, new MockAdapter([])) + ctx.emit('subagent/end', { provider: 'p', id: AgentId('child-z'), stopReason: 'completed' }) + await waitFor(() => existsSync(marker)) + expect(existsSync(marker)).toBe(true) + }) + }) + + if (group === 'edge-paths') describe('hooks-claude coverage — more default/sparse arms', () => { + it('UserPromptSubmit deny with EMPTY stderr uses the default block reason', async () => { + const d = dir() + const s = sh(d, 'block.sh', '#!/usr/bin/env bash\nexit 2\n') + const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([textResponse('no')]) + const ctx = await harness(path, adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + const turnEnd = events(agent).findLast(e => e.type === 'turn/end') + expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind === 'rejected' && turnEnd.data.reason.reason).toContain('blocked by UserPromptSubmit hook') + }) + + it('a PreToolUse ask with NO reason omits the reason (false arm)', async () => { + const d = dir() + const s = sh(d, 'ask.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PreToolUse","permissionDecision":"ask"}}\'\n') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter) + let ran = false + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + // ask (no reason) → degrades to deny with the registry's generic message. + expect(ran).toBe(false) + expect(events(agent).some(e => e.type === 'tool/result' && e.data.isError)).toBe(true) + }) + + it('a recorded clean exit-0 hook with no stderr omits exitCode-extra/stderrSummary fields', async () => { + const d = dir() + const s = sh(d, 'noop.sh', '#!/usr/bin/env bash\nexit 0\n') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + const res = events(agent).find(e => e.type === 'hook/result') + expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0) + expect(res?.type === 'hook/result' && 'stderrSummary' in res.data).toBe(false) + }) + }) + + if (group === 'edge-paths') describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () => { + it('a direct apply() (schema bypass) with only configPath runs', async () => { + const d = dir() + const marker = join(d, 'ran') + const s = sh(d, 'h.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) + hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentLoop, { agents: [] }) + await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) + // Direct apply with only configPath — bypasses schemastery's defaults, so + // the bridge must run on the raw minimal config (the per-hook timeout is + // the protocol lib's reference default, not a config knob). + HooksClaude.apply(ctx, { configPath: join(d, 'hooks.json') }) + ctx.llm.registerAdapter(['mock'], adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + expect(existsSync(marker)).toBe(true) + }) + + it('a non-zero non-2 hook exit (e.g. a command-not-found 127) is a non-blocking error; the tool still runs', async () => { + const d = dir() + // `bash -c` of a missing program exits 127 — a non-blocking error (not 0, not + // 2 → no decision), so the tool proceeds; the hook/result records exit 127. + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: '/nonexistent/definitely/not/a/command' }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter) + let ran = false + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + expect(ran).toBe(true) + const res = events(agent).find(e => e.type === 'hook/result') + expect(res?.type === 'hook/result' && res.data.exitCode).toBe(127) + }) + + it('a PostToolUse deny with empty stderr + no context uses the default feedback (no context arm)', async () => { + const d = dir() + const s = sh(d, 'block.sh', '#!/usr/bin/env bash\nexit 2\n') + const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + const result = events(agent).find(e => e.type === 'tool/result') + expect(result?.type === 'tool/result' && result.data.isError).toBe(true) + }) + }) + + if (group === 'context') describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => { + it('a {"continue":false} hook is RECORDED as decision "stop" but does not halt the run (TODO(hook-continue-false))', async () => { + // The seams cannot yet honor `continue:false` as a hard halt. The log must still record the + // stop decision while execution and the turn continue normally. + const d = dir() + const s = sh(d, 'stop.sh', '#!/usr/bin/env bash\necho \'{"continue":false,"stopReason":"halt"}\'\n') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter) + let ran = false + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + const res = events(agent).find(e => e.type === 'hook/result') + expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded + expect(ran).toBe(true) // NOT honored: the tool still ran (halt is deferred) + const turnEnd = events(agent).findLast(e => e.type === 'turn/end') + expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind).toBe('completed') // ran to completion + }) + + it('a PostToolUse hook that BOTH blocks AND attaches additionalContext', async () => { + const d = dir() + const s = sh(d, 'b.sh', '#!/usr/bin/env bash\necho \'{"decision":"block","reason":"bad","hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"context too"}}\'\n') + const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + const result = events(agent).find(e => e.type === 'tool/result') + expect(result?.type === 'tool/result' && result.data.isError).toBe(true) + expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('bad'))).toBe(true) + // additionalContext also injected (the block + context arm). + expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('context too')))).toBe(true) + }) + + it('a PreToolUse hook whose hookSpecificOutput names a DIFFERENT event does NOT deny the tool', async () => { + // The block's hookEventName (UserPromptSubmit) mismatches the firing event + // (PreToolUse), so its permissionDecision:"deny" is discarded — the tool runs. + const d = dir() + const s = sh(d, 'x.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","permissionDecision":"deny"}}\'\n') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter) + let ran = false + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + expect(ran).toBe(true) // the mismatched deny was discarded → the tool ran + }) + + it('defaults CLAUDE_PROJECT_DIR to the session workspace when no projectDir is configured', async () => { + // The default ACP wiring sets no projectDir. A stock CC hook that references + // $CLAUDE_PROJECT_DIR (shell expansion) must still get the session workspace, + // not an empty string. The hook echoes the var as additionalContext. + const d = dir() + const workspace = dir() + const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\nprintf \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"dir=%s"}}\' "$CLAUDE_PROJECT_DIR"\n') + const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([textResponse('ran')]) + const ctx = await harness(path, adapter) // NB: no projectDir + // The factory create() path honors meta.cwd (the plain agentLoop.create() does not). + const { SessionId } = await import('@deepseek-ai/dsh-session') + const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) + handle.agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, handle.agent as ReactLoopAgent) + expect(events(handle.agent as ReactLoopAgent).some(e => e.type === 'context/message' + && e.data.content.some(b => b.type === 'text' && b.text.includes(`dir=${workspace}`)))).toBe(true) + await handle.dispose() + }) + + it('a context-only UserPromptSubmit hook DELEGATES so a later listener can still block', async () => { + // A context-only hook delegates with `next()` and folds its context, so a downstream policy + // listener can still veto the prompt. + const d = dir() + const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"bridge ctx"}}\'\n') + const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([textResponse('should not run')]) + const ctx = await harness(path, adapter) + // A later listener that blocks every prompt (registered AFTER the bridge). + const { AgentId: AId } = await import('@deepseek-ai/dsh-agent') + ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) + const agent = ctx.agentLoop.create(AId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + // the downstream block won: the model was never called, no user/message was + // recorded, and the (sole, fully-blocked) prompt closed the turn `rejected` + expect(adapter.requests).toHaveLength(0) + expect(events(agent).some(e => e.type === 'user/message')).toBe(false) + const turnEnd = events(agent).findLast(e => e.type === 'turn/end') + expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toMatchObject({ kind: 'rejected', reason: 'policy veto' }) + }) + + it('folds the bridge additionalContext WITH a downstream listener that also adds context', async () => { + // Both the bridge hook and a later prompt-submit listener attach context; the + // request must see BOTH (concatContext keeps the downstream one too). + const d = dir() + const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"from-bridge"}}\'\n') + const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(path, adapter) + ctx.on('agent/prompt-submit', async () => ({ + kind: 'allow' as const, + content: [{ type: 'text' as const, text: 'rewritten-prompt' }], + additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, + })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + const req = JSON.stringify(adapter.requests[0]!.messages) + expect(req).toContain('from-bridge') + expect(req).toContain('from-downstream') + expect(req).toContain('rewritten-prompt') // downstream content rewrite preserved + // the original prompt was replaced by the downstream rewrite + const userMsg = events(agent).find(e => e.type === 'user/message') + expect(userMsg?.type === 'user/message' && userMsg.data.content.some(b => b.type === 'text' && b.text === 'rewritten-prompt')).toBe(true) + }) + + it('folds the bridge PostToolUse context onto a downstream ACCEPT that replaces content', async () => { + // The bridge hook adds context; a later post-execute listener accepts with a + // content rewrite. Both the rewrite and the bridge context survive. + const d = dir() + const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"bridge-note"}}\'\n') + const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + const result = events(agent).find(e => e.type === 'tool/result') + expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true) + expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) + }) + + it('folds the bridge PostToolUse context onto a downstream listener BLOCK', async () => { + // The bridge hook only adds context; a later post-execute listener blocks the + // result. The block wins AND carries the bridge context (concatContext on the + // block arm). + const d = dir() + const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"bridge-note"}}\'\n') + const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + const result = events(agent).find(e => e.type === 'tool/result') + expect(result?.type === 'tool/result' && result.data.isError).toBe(true) + expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('downstream-block'))).toBe(true) + // the bridge's context still landed (folded onto the block) + expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) + }) + + }) + + if (group === 'edge-paths') describe('hooks-claude coverage — executor reject + no-open-turn', () => { + it('when the bash executor REJECTS a hook run, the hook/result omits exitCode (non-blocking)', async () => { + const d = dir() + const s = sh(d, 'h.sh', '#!/usr/bin/env bash\nexit 0\n') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter) + // Force the executor to reject (an infrastructure fault) so runHook's catch + // yields a HookOutput with exitCode undefined → the `exitCode` spread false arm. + const bash = ctx.bash + bash.run = (() => Promise.reject(new Error('executor down'))) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + const res = events(agent).find(e => e.type === 'hook/result') + expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false) + }) + + }) + + if (group === 'edge-paths') describe('hooks-claude coverage — detached-listener catch handlers', () => { + it('a throwing SessionStart inject is contained (logged, agent still runs)', async () => { + const d = dir() + const s = sh(d, 'start.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"x"}}\'\n') + const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(path, adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + // Make inject throw, forcing the SessionStart .catch path. + const original = agent.inject.bind(agent) + let threw = false + agent.inject = (() => { threw = true; throw new Error('inject boom') }) + await waitFor(() => threw) + expect(threw).toBe(true) + agent.inject = original + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + expect(adapter.requests).toHaveLength(1) // loop survived the thrown inject + }) + }) + + if (group === 'stop') describe('hooks-claude coverage — hook runs in the session cwd, not the server cwd', () => { + it('runs an agent-scoped hook in the session workspace even when the executor default differs', async () => { + // The server launch directory and session cwd deliberately differ. The marker proves the + // bridge passes `session/new.cwd` instead of falling back to the executor default. + const serverDir = dir() + const sessionDir = dir() + const marker = join(sessionDir, 'where') + // The hook is invoked with cwd = session dir, so a relative marker path lands there. + hooks(serverDir, { PreToolUse: [{ hooks: [{ type: 'command', command: 'pwd > where' }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentLoop, { agents: [] }) + // Executor default cwd = serverDir (deliberately NOT the session cwd). + await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir }) + await ctx.plugin(HooksClaude, { configPath: join(serverDir, 'hooks.json') }) + ctx.llm.registerAdapter(['mock'], adapter) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + + const { SessionId } = await import('@deepseek-ai/dsh-session') + const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) + handle.agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, handle.agent as ReactLoopAgent) + + expect(existsSync(marker)).toBe(true) // the marker landed in the SESSION dir + const { readFileSync } = await import('node:fs') + const where = readFileSync(marker, 'utf8').trim() + // `pwd` may resolve symlinks (/var → /private/var etc.), so compare basenames. + expect(where.endsWith(sessionDir.split('/').pop()!)).toBe(true) + await handle.dispose() + }) + + it('runs a SubagentStop hook in the CHILD session workspace, not the server cwd', async () => { + // `SubagentStop` recovers the child at `subagent/end`; a relative marker proves `runPoint` + // receives that agent and runs in the child's cwd rather than the executor default. + const serverDir = dir() + const childDir = dir() + const marker = join(childDir, 'stopwhere') + hooks(serverDir, { SubagentStop: [{ hooks: [{ type: 'command', command: 'pwd > stopwhere' }] }] }) + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentLoop, { agents: [] }) + // Executor default cwd = serverDir (deliberately NOT the child session cwd). + await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir }) + await ctx.plugin(HooksClaude, { configPath: join(serverDir, 'hooks.json') }) + ctx.llm.registerAdapter(['mock'], new MockAdapter([])) + + // Register a live child on its own session cwd; emit subagent/end with its id. + const { SessionId } = await import('@deepseek-ai/dsh-session') + const childHandle = await ctx.agents.create({ agentId: AgentId('child-stop'), sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { model: 'mock' } }) + ctx.emit('subagent/end', { provider: 'inproc', id: childHandle.agent.id, stopReason: 'completed' }) + + await waitFor(() => existsSync(marker)) + expect(existsSync(marker)).toBe(true) // the marker landed in the CHILD dir + const { readFileSync } = await import('node:fs') + const where = readFileSync(marker, 'utf8').trim() + // `pwd` may resolve symlinks (/var → /private/var etc.), so compare basenames. + expect(where.endsWith(childDir.split('/').pop()!)).toBe(true) + await childHandle.dispose() + }) + }) + + if (group === 'config') describe('hooks-claude coverage — systemMessage is warned, not surfaced', () => { + it('a hook emitting a systemMessage is logged as not-yet-surfaced', async () => { + const d = dir() + const s = sh(d, 'sm.sh', '#!/usr/bin/env bash\necho \'{"systemMessage":"heads up"}\'\n') + const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(path, adapter) + const warn = vi.fn(); ctx.logger.warn = warn as never + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) + // Not surfaced: the systemMessage text never reaches the model request. + expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('heads up') + }) + }) + + if (group === 'edge-paths') describe('hooks-claude coverage — SessionStart timing is best-effort (no-wait)', () => { + it('does NOT crash or block when the prompt is sent immediately (context is best-effort, may miss the first request)', async () => { + // Session-start injection is detached, so an immediate prompt need not observe it. Assert only + // the guaranteed behavior—no crash and a completed turn—without pre-waiting away the race. + const d = dir() + const s = sh(d, 'start.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"late ctx"}}\'\n') + const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(path, adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + // Send immediately — do NOT wait for the session-start inject. + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + expect(adapter.requests).toHaveLength(1) // the turn ran regardless of hook timing + }) + }) +} diff --git a/packages/hooks/hooks-claude/tests/coverage-config.spec.ts b/packages/hooks/hooks-claude/tests/coverage-config.spec.ts new file mode 100644 index 0000000000..1afa18c4ff --- /dev/null +++ b/packages/hooks/hooks-claude/tests/coverage-config.spec.ts @@ -0,0 +1,3 @@ +import { defineCoverageCases } from './coverage-cases.ts' + +defineCoverageCases('config') diff --git a/packages/hooks/hooks-claude/tests/coverage-context.spec.ts b/packages/hooks/hooks-claude/tests/coverage-context.spec.ts new file mode 100644 index 0000000000..e0f3fb0ef8 --- /dev/null +++ b/packages/hooks/hooks-claude/tests/coverage-context.spec.ts @@ -0,0 +1,3 @@ +import { defineCoverageCases } from './coverage-cases.ts' + +defineCoverageCases('context') diff --git a/packages/hooks/hooks-claude/tests/coverage-edge-paths.spec.ts b/packages/hooks/hooks-claude/tests/coverage-edge-paths.spec.ts new file mode 100644 index 0000000000..0bbcb53b03 --- /dev/null +++ b/packages/hooks/hooks-claude/tests/coverage-edge-paths.spec.ts @@ -0,0 +1,3 @@ +import { defineCoverageCases } from './coverage-cases.ts' + +defineCoverageCases('edge-paths') diff --git a/packages/hooks/hooks-claude/tests/coverage-stop.spec.ts b/packages/hooks/hooks-claude/tests/coverage-stop.spec.ts new file mode 100644 index 0000000000..651cb1f6f0 --- /dev/null +++ b/packages/hooks/hooks-claude/tests/coverage-stop.spec.ts @@ -0,0 +1,3 @@ +import { defineCoverageCases } from './coverage-cases.ts' + +defineCoverageCases('stop') diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts deleted file mode 100644 index f376708688..0000000000 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ /dev/null @@ -1,688 +0,0 @@ -import { afterEach, describe, expect, it, vi } from 'vitest' -import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync } from 'node:fs' -import { tmpdir } from 'node:os' -import { join } from 'node:path' -import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' -import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' -import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' -import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' - -/** Targeted branch coverage for the CC bridge: option arms, warn paths, no-agent - * fallbacks, contextFrom-empty, and the detached-listener catch handlers. */ - -const dirs: string[] = [] -afterEach(() => { for (const d of dirs.splice(0)) rmSync(d, { recursive: true, force: true }) }) - -function dir(): string { const d = mkdtempSync(join(tmpdir(), 'dsh-hc-cov-')); dirs.push(d); return d } -function sh(d: string, name: string, body: string): string { - const p = join(d, name); writeFileSync(p, body); chmodSync(p, 0o755); return p -} -function hooks(d: string, h: unknown): string { - writeFileSync(join(d, 'hooks.json'), JSON.stringify({ hooks: h })); return join(d, 'hooks.json') -} - -type HarnessOpts = { pluginRoot?: string; projectDir?: string; stderrSummaryMaxChars?: number } -async function harness(configPath: string, adapter: MockAdapter, opts: HarnessOpts = {}): Promise { - const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentLoop, { agents: [] }) - await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) - await ctx.plugin(HooksClaude, { configPath, ...opts }) - ctx.llm.registerAdapter(['mock'], adapter) - return ctx -} -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { - return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) }) -} -function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] } -/** Poll until `predicate` holds or the deadline passes — robust to detached - * emit-listener hooks firing on a `.then` (a fixed sleep flakes under load). */ -async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise { - const deadline = Date.now() + timeout - while (!predicate()) { - if (Date.now() > deadline) throw new Error('waitFor: condition not met before deadline') - await new Promise(r => setTimeout(r, interval)) - } -} - -describe('hooks-claude coverage — config option arms + substitution + skip warning', () => { - it('honors pluginRoot + projectDir substitution and warns on a skipped non-command hook', async () => { - const d = dir() - // ${CLAUDE_PLUGIN_ROOT} resolves to d; the script writes its own cwd-independent marker. - const marker = join(d, 'ran') - sh(d, 'h.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) - const path = hooks(d, { - PreToolUse: [{ hooks: [ - { type: 'prompt', prompt: 'skipme' }, // skipped → warn loop - { type: 'command', command: '${CLAUDE_PLUGIN_ROOT}/h.sh' }, // substituted - ] }], - }) - const warn = vi.fn() - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter, { pluginRoot: d, projectDir: d }) - ctx.logger.warn = warn as never - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - expect(existsSync(marker)).toBe(true) // substituted command ran - }) - - it('warns and honors updatedInput as a no-op (input rewrite deferred)', async () => { - const d = dir() - const s = sh(d, 'u.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PreToolUse","permissionDecision":"allow","updatedInput":{"command":"rewritten"}}}\'\n') - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const warn = vi.fn() - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', { command: 'original' }), textResponse('done')]) - const ctx = await harness(path, adapter) - ctx.logger.warn = warn as never - let sawArgs: unknown - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: { command: { type: 'string' } }, async execute(args) { sawArgs = args; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - // updatedInput is NOT honored — the tool ran with the ORIGINAL args. - expect((sawArgs as { command?: string }).command).toBe('original') - expect(warn).toHaveBeenCalledWith(expect.stringContaining('updatedInput')) - }) -}) - -describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () => { - it('a clean exit-0 hook with no output is a no-op (contextFrom empty → next())', async () => { - const d = dir() - const s = sh(d, 'noop.sh', '#!/usr/bin/env bash\nexit 0\n') - const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([textResponse('ran')]) - const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - // The prompt proceeded unchanged; no context/message injected. - expect(adapter.requests).toHaveLength(1) - expect(events(agent).some(e => e.type === 'context/message')).toBe(false) - }) - - it('a PreToolUse hook fires for a no-agent direct tool call (no session/turn to record into)', async () => { - const d = dir() - const s = sh(d, 'deny.sh', '#!/usr/bin/env bash\necho "no" >&2\nexit 2\n') - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const ctx = await harness(path, new MockAdapter([])) - let ran = false - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - // Call execute() directly with NO agent — the bridge's no-agent/no-turn path. - const { CallId } = await import('@deepseek-ai/dsh-llm') - const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: {} }) - expect(ran).toBe(false) - expect(result.isError).toBe(true) - }) - - it('a long stderr is truncated in the hook/result summary', async () => { - const d = dir() - // Emit >500 chars of stderr then exit 2. - const s = sh(d, 'long.sh', '#!/usr/bin/env bash\nprintf "x%.0s" {1..600} >&2\nexit 2\n') - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - const res = events(agent).find(e => e.type === 'hook/result') - expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true) - expect(res?.type === 'hook/result' && res.data.stderrSummary?.length).toBe(501) // default 500-char cap + ellipsis - }) - - it('rejects a non-positive or fractional stderrSummaryMaxChars at load', async () => { - const d = dir() - const path = hooks(d, {}) - for (const bad of [0, -5, 1.5, Number.NaN]) { - const adapter = new MockAdapter([]) - await expect(harness(path, adapter, { stderrSummaryMaxChars: bad })) - .rejects.toThrow(/hooks-claude: stderrSummaryMaxChars must be a positive integer/) - } - }) - - it('the stderr summary cap is plugin config (stderrSummaryMaxChars)', async () => { - const d = dir() - const s = sh(d, 'long.sh', '#!/usr/bin/env bash\nprintf "x%.0s" {1..600} >&2\nexit 2\n') - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter, { stderrSummaryMaxChars: 40 }) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - const res = events(agent).find(e => e.type === 'hook/result') - expect(res?.type === 'hook/result' && res.data.stderrSummary).toBe('x'.repeat(40) + '…') - }) -}) - -describe('hooks-claude coverage — Stop continuation + subagent inject/catch', () => { - it('a Stop hook that blocks (exit 2) forces the turn to continue (CC dialect)', async () => { - const d = dir() - const marker = join(d, 'fired') - const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\necho "continue please" >&2\nexit 2\n`) - const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) - const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - expect(adapter.requests).toHaveLength(2) - expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('continue please') - }) - - it('a Stop hook that blocks with EMPTY stderr still forces continuation (no reason required)', async () => { - // A blocking Stop hook with no stderr yields `deny` without a reason. The block still forces - // continuation; the script self-limits to one block to avoid a loop. - const d = dir() - const marker = join(d, 'fired') - const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\nexit 2\n`) - const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) - const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - // A second model request ran → the empty-reason block forced continuation. - expect(adapter.requests).toHaveLength(2) - // The steering carried the fallback reason (no stderr to use). - expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('blocked by Stop hook') - }) - - it('SubagentStart additionalContext is injected into a REGISTERED live child', async () => { - const d = dir() - const s = sh(d, 'sa.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SubagentStart","additionalContext":"child guidance"}}\'\n') - const path = hooks(d, { SubagentStart: [{ hooks: [{ type: 'command', command: s }] }] }) - const ctx = await harness(path, new MockAdapter([])) - // Register a fake child agent under the id the event carries. - const injected: string[] = [] - const child = { id: AgentId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters[0] - ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: AgentId('child-x') }) - await waitFor(() => injected.includes('child guidance')) - expect(injected).toContain('child guidance') - }) - - it('a throwing SubagentStart/SubagentStop hook run is contained (logged)', async () => { - const d = dir() - // A hook command that does not exist makes runHook resolve a non-blocking - // error (not a throw), so to hit the .catch we make the .then throw: register - // a child whose inject throws for SubagentStart. - const s = sh(d, 'sa.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SubagentStart","additionalContext":"x"}}\'\n') - const path = hooks(d, { SubagentStart: [{ hooks: [{ type: 'command', command: s }] }] }) - const ctx = await harness(path, new MockAdapter([])) - const warn = vi.fn(); ctx.logger.warn = warn as never - const child = { id: AgentId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters[0] - ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: AgentId('child-y') }) - await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SubagentStart hook failed'))) - expect(warn).toHaveBeenCalledWith(expect.stringContaining('SubagentStart hook failed')) - }) -}) - -describe('hooks-claude coverage — default reasons + sparse payloads', () => { - it('PreToolUse deny with EMPTY stderr uses the default reason', async () => { - const d = dir() - const s = sh(d, 'deny.sh', '#!/usr/bin/env bash\nexit 2\n') // exit 2, no stderr - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - const result = events(agent).find(e => e.type === 'tool/result') - expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true) - }) - - it('PostToolUse deny with EMPTY stderr + no context uses the default feedback', async () => { - const d = dir() - const s = sh(d, 'block.sh', '#!/usr/bin/env bash\nexit 2\n') - const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - const result = events(agent).find(e => e.type === 'tool/result') - expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PostToolUse hook'))).toBe(true) - }) - - it('SubagentStop with no registered child runs the hook cleanly (fire-and-forget)', async () => { - const d = dir() - // The agents registry has no entry for the id, so the child lookup yields - // undefined and the payload falls back to base(undefined) — assert the - // observe-only SubagentStop run still executes the hook without crashing. - const marker = join(d, 'stopran') - const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) - const path = hooks(d, { SubagentStop: [{ hooks: [{ type: 'command', command: s }] }] }) - const ctx = await harness(path, new MockAdapter([])) - ctx.emit('subagent/end', { provider: 'p', id: AgentId('child-z'), stopReason: 'completed' }) - await waitFor(() => existsSync(marker)) - expect(existsSync(marker)).toBe(true) - }) -}) - -describe('hooks-claude coverage — more default/sparse arms', () => { - it('UserPromptSubmit deny with EMPTY stderr uses the default block reason', async () => { - const d = dir() - const s = sh(d, 'block.sh', '#!/usr/bin/env bash\nexit 2\n') - const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([textResponse('no')]) - const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - const turnEnd = events(agent).findLast(e => e.type === 'turn/end') - expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind === 'rejected' && turnEnd.data.reason.reason).toContain('blocked by UserPromptSubmit hook') - }) - - it('a PreToolUse ask with NO reason omits the reason (false arm)', async () => { - const d = dir() - const s = sh(d, 'ask.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PreToolUse","permissionDecision":"ask"}}\'\n') - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter) - let ran = false - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - // ask (no reason) → degrades to deny with the registry's generic message. - expect(ran).toBe(false) - expect(events(agent).some(e => e.type === 'tool/result' && e.data.isError)).toBe(true) - }) - - it('a recorded clean exit-0 hook with no stderr omits exitCode-extra/stderrSummary fields', async () => { - const d = dir() - const s = sh(d, 'noop.sh', '#!/usr/bin/env bash\nexit 0\n') - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - const res = events(agent).find(e => e.type === 'hook/result') - expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0) - expect(res?.type === 'hook/result' && 'stderrSummary' in res.data).toBe(false) - }) -}) - -describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () => { - it('a direct apply() (schema bypass) with only configPath runs', async () => { - const d = dir() - const marker = join(d, 'ran') - const s = sh(d, 'h.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) - hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentLoop, { agents: [] }) - await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) - // Direct apply with only configPath — bypasses schemastery's defaults, so - // the bridge must run on the raw minimal config (the per-hook timeout is - // the protocol lib's reference default, not a config knob). - HooksClaude.apply(ctx, { configPath: join(d, 'hooks.json') }) - ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - expect(existsSync(marker)).toBe(true) - }) - - it('a non-zero non-2 hook exit (e.g. a command-not-found 127) is a non-blocking error; the tool still runs', async () => { - const d = dir() - // `bash -c` of a missing program exits 127 — a non-blocking error (not 0, not - // 2 → no decision), so the tool proceeds; the hook/result records exit 127. - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: '/nonexistent/definitely/not/a/command' }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter) - let ran = false - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - expect(ran).toBe(true) - const res = events(agent).find(e => e.type === 'hook/result') - expect(res?.type === 'hook/result' && res.data.exitCode).toBe(127) - }) - - it('a PostToolUse deny with empty stderr + no context uses the default feedback (no context arm)', async () => { - const d = dir() - const s = sh(d, 'block.sh', '#!/usr/bin/env bash\nexit 2\n') - const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - const result = events(agent).find(e => e.type === 'tool/result') - expect(result?.type === 'tool/result' && result.data.isError).toBe(true) - }) -}) - -describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => { - it('a {"continue":false} hook is RECORDED as decision "stop" but does not halt the run (TODO(hook-continue-false))', async () => { - // The seams cannot yet honor `continue:false` as a hard halt. The log must still record the - // stop decision while execution and the turn continue normally. - const d = dir() - const s = sh(d, 'stop.sh', '#!/usr/bin/env bash\necho \'{"continue":false,"stopReason":"halt"}\'\n') - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter) - let ran = false - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - const res = events(agent).find(e => e.type === 'hook/result') - expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded - expect(ran).toBe(true) // NOT honored: the tool still ran (halt is deferred) - const turnEnd = events(agent).findLast(e => e.type === 'turn/end') - expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind).toBe('completed') // ran to completion - }) - - it('a PostToolUse hook that BOTH blocks AND attaches additionalContext', async () => { - const d = dir() - const s = sh(d, 'b.sh', '#!/usr/bin/env bash\necho \'{"decision":"block","reason":"bad","hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"context too"}}\'\n') - const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - const result = events(agent).find(e => e.type === 'tool/result') - expect(result?.type === 'tool/result' && result.data.isError).toBe(true) - expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('bad'))).toBe(true) - // additionalContext also injected (the block + context arm). - expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('context too')))).toBe(true) - }) - - it('a PreToolUse hook whose hookSpecificOutput names a DIFFERENT event does NOT deny the tool', async () => { - // The block's hookEventName (UserPromptSubmit) mismatches the firing event - // (PreToolUse), so its permissionDecision:"deny" is discarded — the tool runs. - const d = dir() - const s = sh(d, 'x.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","permissionDecision":"deny"}}\'\n') - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter) - let ran = false - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - expect(ran).toBe(true) // the mismatched deny was discarded → the tool ran - }) - - it('defaults CLAUDE_PROJECT_DIR to the session workspace when no projectDir is configured', async () => { - // The default ACP wiring sets no projectDir. A stock CC hook that references - // $CLAUDE_PROJECT_DIR (shell expansion) must still get the session workspace, - // not an empty string. The hook echoes the var as additionalContext. - const d = dir() - const workspace = dir() - const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\nprintf \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"dir=%s"}}\' "$CLAUDE_PROJECT_DIR"\n') - const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([textResponse('ran')]) - const ctx = await harness(path, adapter) // NB: no projectDir - // The factory create() path honors meta.cwd (the plain agentLoop.create() does not). - const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) - handle.agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, handle.agent as ReactLoopAgent) - expect(events(handle.agent as ReactLoopAgent).some(e => e.type === 'context/message' - && e.data.content.some(b => b.type === 'text' && b.text.includes(`dir=${workspace}`)))).toBe(true) - await handle.dispose() - }) - - it('a context-only UserPromptSubmit hook DELEGATES so a later listener can still block', async () => { - // A context-only hook delegates with `next()` and folds its context, so a downstream policy - // listener can still veto the prompt. - const d = dir() - const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"bridge ctx"}}\'\n') - const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([textResponse('should not run')]) - const ctx = await harness(path, adapter) - // A later listener that blocks every prompt (registered AFTER the bridge). - const { AgentId: AId } = await import('@deepseek-ai/dsh-agent') - ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) - const agent = ctx.agentLoop.create(AId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - // the downstream block won: the model was never called, no user/message was - // recorded, and the (sole, fully-blocked) prompt closed the turn `rejected` - expect(adapter.requests).toHaveLength(0) - expect(events(agent).some(e => e.type === 'user/message')).toBe(false) - const turnEnd = events(agent).findLast(e => e.type === 'turn/end') - expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toMatchObject({ kind: 'rejected', reason: 'policy veto' }) - }) - - it('folds the bridge additionalContext WITH a downstream listener that also adds context', async () => { - // Both the bridge hook and a later prompt-submit listener attach context; the - // request must see BOTH (concatContext keeps the downstream one too). - const d = dir() - const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"from-bridge"}}\'\n') - const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(path, adapter) - ctx.on('agent/prompt-submit', async () => ({ - kind: 'allow' as const, - content: [{ type: 'text' as const, text: 'rewritten-prompt' }], - additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, - })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - const req = JSON.stringify(adapter.requests[0]!.messages) - expect(req).toContain('from-bridge') - expect(req).toContain('from-downstream') - expect(req).toContain('rewritten-prompt') // downstream content rewrite preserved - // the original prompt was replaced by the downstream rewrite - const userMsg = events(agent).find(e => e.type === 'user/message') - expect(userMsg?.type === 'user/message' && userMsg.data.content.some(b => b.type === 'text' && b.text === 'rewritten-prompt')).toBe(true) - }) - - it('folds the bridge PostToolUse context onto a downstream ACCEPT that replaces content', async () => { - // The bridge hook adds context; a later post-execute listener accepts with a - // content rewrite. Both the rewrite and the bridge context survive. - const d = dir() - const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"bridge-note"}}\'\n') - const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - const result = events(agent).find(e => e.type === 'tool/result') - expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true) - expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) - }) - - it('folds the bridge PostToolUse context onto a downstream listener BLOCK', async () => { - // The bridge hook only adds context; a later post-execute listener blocks the - // result. The block wins AND carries the bridge context (concatContext on the - // block arm). - const d = dir() - const s = sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"bridge-note"}}\'\n') - const path = hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - const result = events(agent).find(e => e.type === 'tool/result') - expect(result?.type === 'tool/result' && result.data.isError).toBe(true) - expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('downstream-block'))).toBe(true) - // the bridge's context still landed (folded onto the block) - expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) - }) - -}) - -describe('hooks-claude coverage — executor reject + no-open-turn', () => { - it('when the bash executor REJECTS a hook run, the hook/result omits exitCode (non-blocking)', async () => { - const d = dir() - const s = sh(d, 'h.sh', '#!/usr/bin/env bash\nexit 0\n') - const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(path, adapter) - // Force the executor to reject (an infrastructure fault) so runHook's catch - // yields a HookOutput with exitCode undefined → the `exitCode` spread false arm. - const bash = ctx.bash - bash.run = (() => Promise.reject(new Error('executor down'))) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - const res = events(agent).find(e => e.type === 'hook/result') - expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false) - }) - -}) - -describe('hooks-claude coverage — detached-listener catch handlers', () => { - it('a throwing SessionStart inject is contained (logged, agent still runs)', async () => { - const d = dir() - const s = sh(d, 'start.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"x"}}\'\n') - const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - // Make inject throw, forcing the SessionStart .catch path. - const original = agent.inject.bind(agent) - let threw = false - agent.inject = (() => { threw = true; throw new Error('inject boom') }) - await waitFor(() => threw) - expect(threw).toBe(true) - agent.inject = original - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - expect(adapter.requests).toHaveLength(1) // loop survived the thrown inject - }) -}) - -describe('hooks-claude coverage — hook runs in the session cwd, not the server cwd', () => { - it('runs an agent-scoped hook in the session workspace even when the executor default differs', async () => { - // The server launch directory and session cwd deliberately differ. The marker proves the - // bridge passes `session/new.cwd` instead of falling back to the executor default. - const serverDir = dir() - const sessionDir = dir() - const marker = join(sessionDir, 'where') - // The hook is invoked with cwd = session dir, so a relative marker path lands there. - hooks(serverDir, { PreToolUse: [{ hooks: [{ type: 'command', command: 'pwd > where' }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentLoop, { agents: [] }) - // Executor default cwd = serverDir (deliberately NOT the session cwd). - await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir }) - await ctx.plugin(HooksClaude, { configPath: join(serverDir, 'hooks.json') }) - ctx.llm.registerAdapter(['mock'], adapter) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - - const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) - handle.agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, handle.agent as ReactLoopAgent) - - expect(existsSync(marker)).toBe(true) // the marker landed in the SESSION dir - const { readFileSync } = await import('node:fs') - const where = readFileSync(marker, 'utf8').trim() - // `pwd` may resolve symlinks (/var → /private/var etc.), so compare basenames. - expect(where.endsWith(sessionDir.split('/').pop()!)).toBe(true) - await handle.dispose() - }) - - it('runs a SubagentStop hook in the CHILD session workspace, not the server cwd', async () => { - // `SubagentStop` recovers the child at `subagent/end`; a relative marker proves `runPoint` - // receives that agent and runs in the child's cwd rather than the executor default. - const serverDir = dir() - const childDir = dir() - const marker = join(childDir, 'stopwhere') - hooks(serverDir, { SubagentStop: [{ hooks: [{ type: 'command', command: 'pwd > stopwhere' }] }] }) - const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentLoop, { agents: [] }) - // Executor default cwd = serverDir (deliberately NOT the child session cwd). - await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir }) - await ctx.plugin(HooksClaude, { configPath: join(serverDir, 'hooks.json') }) - ctx.llm.registerAdapter(['mock'], new MockAdapter([])) - - // Register a live child on its own session cwd; emit subagent/end with its id. - const { SessionId } = await import('@deepseek-ai/dsh-session') - const childHandle = await ctx.agents.create({ agentId: AgentId('child-stop'), sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { model: 'mock' } }) - ctx.emit('subagent/end', { provider: 'inproc', id: childHandle.agent.id, stopReason: 'completed' }) - - await waitFor(() => existsSync(marker)) - expect(existsSync(marker)).toBe(true) // the marker landed in the CHILD dir - const { readFileSync } = await import('node:fs') - const where = readFileSync(marker, 'utf8').trim() - // `pwd` may resolve symlinks (/var → /private/var etc.), so compare basenames. - expect(where.endsWith(childDir.split('/').pop()!)).toBe(true) - await childHandle.dispose() - }) -}) - -describe('hooks-claude coverage — systemMessage is warned, not surfaced', () => { - it('a hook emitting a systemMessage is logged as not-yet-surfaced', async () => { - const d = dir() - const s = sh(d, 'sm.sh', '#!/usr/bin/env bash\necho \'{"systemMessage":"heads up"}\'\n') - const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(path, adapter) - const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) - // Not surfaced: the systemMessage text never reaches the model request. - expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('heads up') - }) -}) - -describe('hooks-claude coverage — SessionStart timing is best-effort (no-wait)', () => { - it('does NOT crash or block when the prompt is sent immediately (context is best-effort, may miss the first request)', async () => { - // Session-start injection is detached, so an immediate prompt need not observe it. Assert only - // the guaranteed behavior—no crash and a completed turn—without pre-waiting away the race. - const d = dir() - const s = sh(d, 'start.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"late ctx"}}\'\n') - const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - // Send immediately — do NOT wait for the session-start inject. - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) - expect(adapter.requests).toHaveLength(1) // the turn ran regardless of hook timing - }) -}) diff --git a/packages/hooks/hooks-codex/tests/coverage-cases.ts b/packages/hooks/hooks-codex/tests/coverage-cases.ts new file mode 100644 index 0000000000..b107b09856 --- /dev/null +++ b/packages/hooks/hooks-codex/tests/coverage-cases.ts @@ -0,0 +1,574 @@ +import { afterEach, describe, expect, it, vi } from 'vitest' +import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync, readFileSync } from 'node:fs' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { Context } from 'cordis' +import LlmService from '@deepseek-ai/dsh-llm' +import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' +import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' +import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' +import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' + +const dirs: string[] = [] +afterEach(() => { for (const d of dirs.splice(0)) rmSync(d, { recursive: true, force: true }) }) +function dir(): string { const d = mkdtempSync(join(tmpdir(), 'dsh-hx-cov-')); dirs.push(d); return d } +function sh(d: string, name: string, body: string): string { + const p = join(d, name); writeFileSync(p, body); chmodSync(p, 0o755); return p +} +function hooks(d: string, h: unknown): string { + writeFileSync(join(d, 'hooks.json'), JSON.stringify({ hooks: h })); return join(d, 'hooks.json') +} + +async function harness(configPath: string, adapter: MockAdapter, opts: { stderrSummaryMaxChars?: number } = {}): Promise { + const ctx = new Context() + await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] }) + await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) + await ctx.plugin(HooksCodex, { configPath, model: 'm', ...opts }) + ctx.llm.registerAdapter(['mock'], adapter) + return ctx +} +function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { + return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) }) +} +function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] } +/** Poll until `predicate` holds or the deadline passes — robust to detached + * emit-listener hooks firing on a `.then` (a fixed sleep flakes under load). */ +async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise { + const deadline = Date.now() + timeout + while (!predicate()) { + if (Date.now() > deadline) throw new Error('waitFor: condition not met before deadline') + await new Promise(r => setTimeout(r, interval)) + } +} + +export type CoverageGroup = 'prompt' | 'post-tool' | 'result-shape' | 'edge-paths' | 'payload' + +/** Register independently schedulable slices of the hooks-codex coverage matrix. */ +export function defineCoverageCases(groups: CoverageGroup | readonly CoverageGroup[]): void { + const selected = new Set(typeof groups === 'string' ? [groups] : groups) + if (selected.has('prompt')) describe('hooks-codex coverage — prompt decision mapping', () => { + it('UserPromptSubmit block (exit 2) → rejected turn; default reason on empty stderr', async () => { + const d = dir() + hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) + const adapter = new MockAdapter([textResponse('no')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(adapter.requests).toHaveLength(0) + const te = events(agent).findLast(e => e.type === 'turn/end') + expect(te?.type === 'turn/end' && te.data.reason.kind).toBe('rejected') + }) + + it('UserPromptSubmit additionalContext is injected; a no-op hook proceeds', async () => { + const d = dir() + hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"ctx-x"}}\'\n') }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('ctx-x') + }) + + it('a context-only UserPromptSubmit hook DELEGATES so a later listener can still block', async () => { + // Context alone is not a veto: the bridge delegates with `next()` and folds its context, so a + // downstream policy listener can still block. + const d = dir() + hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"bridge ctx"}}\'\n') }] }] }) + const adapter = new MockAdapter([textResponse('should not run')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(adapter.requests).toHaveLength(0) + expect(events(agent).some(e => e.type === 'user/message')).toBe(false) + const te = events(agent).findLast(e => e.type === 'turn/end') + expect(te?.type === 'turn/end' && te.data.reason).toMatchObject({ kind: 'rejected', reason: 'policy veto' }) + }) + + it('folds the bridge additionalContext WITH a downstream listener that also adds context', async () => { + const d = dir() + hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"from-bridge"}}\'\n') }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + ctx.on('agent/prompt-submit', async () => ({ + kind: 'allow' as const, + content: [{ type: 'text' as const, text: 'rewritten-prompt' }], + additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, + })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + const req = JSON.stringify(adapter.requests[0]!.messages) + expect(req).toContain('from-bridge') + expect(req).toContain('from-downstream') + expect(req).toContain('rewritten-prompt') + }) + }) + + if (selected.has('post-tool')) describe('hooks-codex coverage — post-tool and session context mapping', () => { + it('folds the bridge PostToolUse context onto a downstream ACCEPT that replaces content', async () => { + const d = dir() + hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pc.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"bridge-note"}}\'\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + const result = events(agent).find(e => e.type === 'tool/result') + expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true) + expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) + }) + + it('folds the bridge PostToolUse context onto a downstream listener BLOCK', async () => { + const d = dir() + hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pc.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"bridge-note"}}\'\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + const result = events(agent).find(e => e.type === 'tool/result') + expect(result?.type === 'tool/result' && result.data.isError).toBe(true) + expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('downstream-block'))).toBe(true) + expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) + }) + + it('SessionStart additionalContext is injected for the first request', async () => { + const d = dir() + hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"start-ctx"}}\'\n') }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + await waitFor(() => events(agent).some(e => e.type === 'context/message' + && e.data.content.some(b => b.type === 'text' && b.text.includes('start-ctx')))) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('start-ctx') + }) + + it('PostToolUse block (exit 2) → isError feedback; default reason', async () => { + const d = dir() + hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'p.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + const r = events(agent).find(e => e.type === 'tool/result') + expect(r?.type === 'tool/result' && r.data.isError).toBe(true) + expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PostToolUse hook'))).toBe(true) + }) + + it('PostToolUse additionalContext (clean exit) is attached after the result', async () => { + const d = dir() + hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pc.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"post-ctx"}}\'\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('post-ctx')))).toBe(true) + }) + }) + + if (selected.has('result-shape')) describe('hooks-codex coverage — hook result shape and configuration', () => { + it('PreToolUse for a tool call WITHOUT a command arg passes an empty command (commandOf non-object/missing arm)', async () => { + const d = dir() + hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pre.sh', '#!/usr/bin/env bash\ncat >/dev/null\nexit 0\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', {}), textResponse('done')]) // no command arg + const ctx = await harness(join(d, 'hooks.json'), adapter) + let ran = false + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(ran).toBe(true) // clean-exit hook allows; commandOf returned '' + }) + + it('a clean exit-0 hook records exitCode 0 and omits stderrSummary', async () => { + const d = dir() + hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'n.sh', '#!/usr/bin/env bash\nexit 0\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + const res = events(agent).find(e => e.type === 'hook/result') + expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0) + expect(res?.type === 'hook/result' && 'stderrSummary' in res.data).toBe(false) + }) + + it('a long stderr is truncated in the hook/result summary', async () => { + const d = dir() + hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'l.sh', '#!/usr/bin/env bash\nprintf "x%.0s" {1..600} >&2\nexit 2\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + const res = events(agent).find(e => e.type === 'hook/result') + expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true) + expect(res?.type === 'hook/result' && res.data.stderrSummary?.length).toBe(501) // default 500-char cap + ellipsis + }) + + it('rejects a non-positive or fractional stderrSummaryMaxChars at load', async () => { + const d = dir() + hooks(d, {}) + for (const bad of [0, -5, 1.5, Number.NaN]) { + const adapter = new MockAdapter([]) + await expect(harness(join(d, 'hooks.json'), adapter, { stderrSummaryMaxChars: bad })) + .rejects.toThrow(/hooks-codex: stderrSummaryMaxChars must be a positive integer/) + } + }) + + it('the stderr summary cap is plugin config (stderrSummaryMaxChars)', async () => { + const d = dir() + hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'l.sh', '#!/usr/bin/env bash\nprintf "x%.0s" {1..600} >&2\nexit 2\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter, { stderrSummaryMaxChars: 40 }) + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + const res = events(agent).find(e => e.type === 'hook/result') + expect(res?.type === 'hook/result' && res.data.stderrSummary).toBe('x'.repeat(40) + '…') + }) + + it('warns on a skipped async hook and a direct apply() (schema bypass) runs', async () => { + const d = dir() + const marker = join(d, 'ran') + hooks(d, { UserPromptSubmit: [{ hooks: [ + { type: 'command', command: 'bg.sh', async: true }, // skipped → warn + { type: 'command', command: sh(d, 'h.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) }, + ] }] }) + const warn = vi.fn() + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = new Context() + await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] }) + await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) + ctx.logger.warn = warn as never + // Direct apply (schema bypass) → the `model ?? ''` fallback is exercised. + HooksCodex.apply(ctx, { configPath: join(d, 'hooks.json') }) + ctx.llm.registerAdapter(['mock'], adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(existsSync(marker)).toBe(true) + expect(warn).toHaveBeenCalledWith(expect.stringContaining('async hook')) + }) + + it('a no-op clean hook proceeds (contextFrom empty → next)', async () => { + const d = dir() + hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'n.sh', '#!/usr/bin/env bash\nexit 0\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + let ran = false + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(ran).toBe(true) + }) + + it('SessionStart with no additionalContext is a no-op (contextFrom empty)', async () => { + const d = dir() + // The hook touches a marker so we can wait for it to ACTUALLY FINISH before + // asserting absence — a completed turn alone would not prove the detached + // session-start hook ran, making the absence check a false pass. + const marker = join(d, 'ss-ran') + hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\ntouch "${marker}"\nexit 0\n`) }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + await waitFor(() => existsSync(marker)) // the clean no-output hook has finished + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(events(agent).some(e => e.type === 'context/message')).toBe(false) + }) + + it('a throwing SessionStart inject is contained (logged)', async () => { + const d = dir() + hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"x"}}\'\n') }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + const warn = vi.fn(); ctx.logger.warn = warn as never + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.inject = (() => { throw new Error('inject boom') }) + await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SessionStart hook failed'))) + expect(warn).toHaveBeenCalledWith(expect.stringContaining('SessionStart hook failed')) + }) + }) + + if (selected.has('edge-paths')) describe('hooks-codex coverage — matching and no-agent edge paths', () => { + it('a clean PreToolUse with no decision allows the tool (no deny)', async () => { + const d = dir() + hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'ok.sh', '#!/usr/bin/env bash\nexit 0\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + let ran = false + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(ran).toBe(true) + }) + + it('a non-matching regex matcher skips the hook (matchesMatcher false → continue)', async () => { + const d = dir() + // /^Edit$/ does not match the tool name "Bash" → the group is skipped. + hooks(d, { PreToolUse: [{ matcher: '^Edit$', hooks: [{ type: 'command', command: sh(d, 'deny.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + let ran = false + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(ran).toBe(true) // matcher didn't match → no hook ran → tool proceeded + expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) + }) + + it('a {"continue":false} hook is RECORDED as "stop" but does not halt the run (TODO(hook-continue-false))', async () => { + // Honoring `continue:false` is deferred — the seams have no hard-halt + // primitive. Assert the LOG records the halt request AND that the run is not + // actually halted (the tool still runs, the turn completes). + const d = dir() + hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"continue":false,"stopReason":"halt"}\'\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + let ran = false + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + const res = events(agent).find(e => e.type === 'hook/result') + expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded + expect(ran).toBe(true) // NOT honored: the tool still ran (halt is deferred) + }) + + it('PreToolUse deny with EMPTY stderr uses the default reason (?? right arm)', async () => { + const d = dir() + hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'd.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + const r = events(agent).find(e => e.type === 'tool/result') + expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true) + }) + + it('PostToolUse block AND additionalContext are surfaced together', async () => { + const d = dir() + hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'bc.sh', '#!/usr/bin/env bash\necho \'{"decision":"block","reason":"bad","hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"ctx too"}}\'\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + const r = events(agent).find(e => e.type === 'tool/result') + expect(r?.type === 'tool/result' && r.data.isError).toBe(true) + expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('bad'))).toBe(true) + expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('ctx too')))).toBe(true) + }) + + it('commandOf reads a non-string command arg as an empty command', async () => { + const d = dir() + // The tool-call arguments carry `command` as a NUMBER → commandOf's + // `typeof command === 'string'` false arm → '' (the payload's tool_input.command). + const cap = join(d, 'payload') + hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'cap.sh', `#!/usr/bin/env bash\ncat > "${cap}"\nexit 0\n`) }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 7 }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'number' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_input: { command: string } } + expect(payload.tool_input.command).toBe('') + }) + + it('a no-agent direct PreToolUse run uses process.cwd() and turn 0 (no session to record)', async () => { + const d = dir() + hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'd.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) + const ctx = await harness(join(d, 'hooks.json'), new MockAdapter([])) + let ran = false + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) + const { CallId } = await import('@deepseek-ai/dsh-llm') + const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'Bash', arguments: { command: 'x' } }) + expect(ran).toBe(false) // denied + expect(result.isError).toBe(true) + }) + + it('a no-agent direct PostToolUse run attaches context with no session to record', async () => { + const d = dir() + hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pc.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"x"}}\'\n') }] }] }) + const ctx = await harness(join(d, 'hooks.json'), new MockAdapter([])) + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const { CallId } = await import('@deepseek-ai/dsh-llm') + const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'Bash', arguments: { command: 'x' } }) + expect(result.isError).toBeFalsy() + expect(result.additionalContext?.content.some(b => b.type === 'text' && b.text === 'x')).toBe(true) + }) + + it('when the bash executor REJECTS, the hook/result omits exitCode (non-blocking)', async () => { + const d = dir() + hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'h.sh', '#!/usr/bin/env bash\nexit 0\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + ctx.bash.run = (() => Promise.reject(new Error('executor down'))) + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + const res = events(agent).find(e => e.type === 'hook/result') + expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false) + }) + }) + + if (selected.has('payload')) describe('hooks-codex coverage — continuation, payload, and cwd mapping', () => { + it('a blocking Stop hook with EMPTY stderr still forces continuation (no reason required)', async () => { + // Regression: an exit-2 Stop hook with no stderr yields decision 'deny' + + // reason undefined; the turn must STILL force-continue, not silently stop. + const d = dir() + const marker = join(d, 'fired') + hooks(d, { Stop: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\nexit 2\n`) }] }] }) + const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(adapter.requests).toHaveLength(2) // empty-reason block forced continuation + expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('blocked by Stop hook') + }) + + it('a clean UserPromptSubmit hook that prints PLAIN stdout injects it as context', async () => { + // Codex feeds a SessionStart/UserPromptSubmit hook's PLAIN (non-JSON) stdout + // as additionalContext (unlike CC, which needs a JSON hookSpecificOutput). + const d = dir() + hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho "extra guidance from a plain hook"\nexit 0\n') }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('extra guidance from a plain hook') + }) + + it('a NON-clean SessionStart hook (exit 2) does NOT inject its stdout as context', async () => { + // SessionStart cannot block, but non-clean stdout still must not become context. The marker + // waits for detached completion; `echo stale; exit 2` then proves the exit-code gate matches + // the codec's structured-stdout rule. + const d = dir() + const marker = join(d, 'ran') + hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', `#!/usr/bin/env bash\ntouch "${marker}"\necho "stale"\nexit 2\n`) }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + await waitFor(() => existsSync(marker)) // the exit-2 hook has finished + expect(events(agent).some(e => e.type === 'context/message' + && e.data.content.some(b => b.type === 'text' && b.text.includes('stale')))).toBe(false) + }) + + it('a UserPromptSubmit hook with a non-blocking error exit (1) + stdout does NOT inject it', async () => { + // Exit 1 is a non-blocking error (no decision), so the prompt is NOT blocked + // and the handler falls through to the context path — the gate must still + // suppress the error hook's stdout ("stale" never reaches the model). + const d = dir() + hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'e.sh', '#!/usr/bin/env bash\necho "stale"\nexit 1\n') }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(adapter.requests).toHaveLength(1) // exit 1 is non-blocking → the turn ran + expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('stale') + }) + + it('a clean SessionStart hook that prints PLAIN stdout injects it (not JSON)', async () => { + const d = dir() + hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'ss.sh', '#!/usr/bin/env bash\necho "session preamble"\nexit 0\n') }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + await waitFor(() => events(agent).some(e => e.type === 'context/message' + && e.data.content.some(b => b.type === 'text' && b.text.includes('session preamble')))) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('session preamble') + }) + + it('a clean hook that prints JSON is NOT injected as prose (plain-stdout gate)', async () => { + // A structured (JSON) stdout must go through the hookSpecificOutput path, not + // be dumped verbatim as context — the `!startsWith('{')` gate guards this. + const d = dir() + hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'j.sh', '#!/usr/bin/env bash\necho \'{"unrelated":"json"}\'\nexit 0\n') }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('unrelated') + }) + + it('the PreToolUse payload carries the REAL tool name (matches the matcher subject)', async () => { + // Regression: the payload once hardcoded tool_name "Bash", disagreeing with + // the exec.name matcher subject — a config matcher on the real name would + // then never fire. Capture the payload and assert tool_name === the real name. + const d = dir() + const cap = join(d, 'payload') + hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'cap.sh', `#!/usr/bin/env bash\ncat > "${cap}"\nexit 0\n`) }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'shell', { command: 'ls' }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_name: string; tool_input: { command: string } } + expect(payload.tool_name).toBe('shell') + expect(payload.tool_input.command).toBe('ls') + }) + + it('a Codex matcher on the REAL tool name fires (matcher subject === payload tool_name)', async () => { + // A regex matcher matching the real tool name must select the hook — proving + // the matcher subject and the payload tool_name agree. + const d = dir() + hooks(d, { PreToolUse: [{ matcher: 'shell', hooks: [{ type: 'command', command: sh(d, 'd.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'shell', { command: 'ls' }), textResponse('done')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + let ran = false + ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(ran).toBe(false) // the matcher fired → the hook denied the tool + expect(events(agent).some(e => e.type === 'hook/invoked' && e.data.point === 'PreToolUse')).toBe(true) + }) + + it('a hook emitting a systemMessage is warned as not-yet-surfaced', async () => { + const d = dir() + hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'sm.sh', '#!/usr/bin/env bash\necho \'{"systemMessage":"heads up"}\'\n') }] }] }) + const adapter = new MockAdapter([textResponse('ok')]) + const ctx = await harness(join(d, 'hooks.json'), adapter) + const warn = vi.fn(); ctx.logger.warn = warn as never + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) + expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) + expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('heads up') + }) + + it('runs an agent-scoped hook in the session cwd, not the executor default', async () => { + // Same regression as the CC bridge: the Codex bridge must thread the session + // cwd as the hook workdir. Executor default = serverDir; session cwd = + // sessionDir; the PreToolUse hook's `pwd` marker must land in sessionDir. + const serverDir = dir() + const sessionDir = dir() + const marker = join(sessionDir, 'where') + hooks(serverDir, { PreToolUse: [{ hooks: [{ type: 'command', command: 'pwd > where' }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) + const ctx = new Context() + await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] }) + await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir }) + await ctx.plugin(HooksCodex, { configPath: join(serverDir, 'hooks.json'), model: 'm' }) + ctx.llm.registerAdapter(['mock'], adapter) + ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const { SessionId } = await import('@deepseek-ai/dsh-session') + const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) + handle.agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, handle.agent as ReactLoopAgent) + expect(existsSync(marker)).toBe(true) + expect(readFileSync(marker, 'utf8').trim().endsWith(sessionDir.split('/').pop()!)).toBe(true) + await handle.dispose() + }) + }) +} diff --git a/packages/hooks/hooks-codex/tests/coverage-post-tool.spec.ts b/packages/hooks/hooks-codex/tests/coverage-post-tool.spec.ts new file mode 100644 index 0000000000..0cd39dbe20 --- /dev/null +++ b/packages/hooks/hooks-codex/tests/coverage-post-tool.spec.ts @@ -0,0 +1,3 @@ +import { defineCoverageCases } from './coverage-cases.ts' + +defineCoverageCases(['post-tool', 'payload']) diff --git a/packages/hooks/hooks-codex/tests/coverage-prompt.spec.ts b/packages/hooks/hooks-codex/tests/coverage-prompt.spec.ts new file mode 100644 index 0000000000..be18c719f6 --- /dev/null +++ b/packages/hooks/hooks-codex/tests/coverage-prompt.spec.ts @@ -0,0 +1,3 @@ +import { defineCoverageCases } from './coverage-cases.ts' + +defineCoverageCases(['prompt', 'edge-paths']) diff --git a/packages/hooks/hooks-codex/tests/coverage-result-shape.spec.ts b/packages/hooks/hooks-codex/tests/coverage-result-shape.spec.ts new file mode 100644 index 0000000000..9546872e3c --- /dev/null +++ b/packages/hooks/hooks-codex/tests/coverage-result-shape.spec.ts @@ -0,0 +1,3 @@ +import { defineCoverageCases } from './coverage-cases.ts' + +defineCoverageCases('result-shape') diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts deleted file mode 100644 index c287d86b23..0000000000 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ /dev/null @@ -1,560 +0,0 @@ -import { afterEach, describe, expect, it, vi } from 'vitest' -import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync, readFileSync } from 'node:fs' -import { tmpdir } from 'node:os' -import { join } from 'node:path' -import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' -import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' -import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' -import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' - -const dirs: string[] = [] -afterEach(() => { for (const d of dirs.splice(0)) rmSync(d, { recursive: true, force: true }) }) -function dir(): string { const d = mkdtempSync(join(tmpdir(), 'dsh-hx-cov-')); dirs.push(d); return d } -function sh(d: string, name: string, body: string): string { - const p = join(d, name); writeFileSync(p, body); chmodSync(p, 0o755); return p -} -function hooks(d: string, h: unknown): string { - writeFileSync(join(d, 'hooks.json'), JSON.stringify({ hooks: h })); return join(d, 'hooks.json') -} - -async function harness(configPath: string, adapter: MockAdapter, opts: { stderrSummaryMaxChars?: number } = {}): Promise { - const ctx = new Context() - await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] }) - await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) - await ctx.plugin(HooksCodex, { configPath, model: 'm', ...opts }) - ctx.llm.registerAdapter(['mock'], adapter) - return ctx -} -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { - return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) }) -} -function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] } -/** Poll until `predicate` holds or the deadline passes — robust to detached - * emit-listener hooks firing on a `.then` (a fixed sleep flakes under load). */ -async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise { - const deadline = Date.now() + timeout - while (!predicate()) { - if (Date.now() > deadline) throw new Error('waitFor: condition not met before deadline') - await new Promise(r => setTimeout(r, interval)) - } -} - -describe('hooks-codex coverage — decision mapping paths', () => { - it('UserPromptSubmit block (exit 2) → rejected turn; default reason on empty stderr', async () => { - const d = dir() - hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) - const adapter = new MockAdapter([textResponse('no')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(adapter.requests).toHaveLength(0) - const te = events(agent).findLast(e => e.type === 'turn/end') - expect(te?.type === 'turn/end' && te.data.reason.kind).toBe('rejected') - }) - - it('UserPromptSubmit additionalContext is injected; a no-op hook proceeds', async () => { - const d = dir() - hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"ctx-x"}}\'\n') }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('ctx-x') - }) - - it('a context-only UserPromptSubmit hook DELEGATES so a later listener can still block', async () => { - // Context alone is not a veto: the bridge delegates with `next()` and folds its context, so a - // downstream policy listener can still block. - const d = dir() - hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"bridge ctx"}}\'\n') }] }] }) - const adapter = new MockAdapter([textResponse('should not run')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(adapter.requests).toHaveLength(0) - expect(events(agent).some(e => e.type === 'user/message')).toBe(false) - const te = events(agent).findLast(e => e.type === 'turn/end') - expect(te?.type === 'turn/end' && te.data.reason).toMatchObject({ kind: 'rejected', reason: 'policy veto' }) - }) - - it('folds the bridge additionalContext WITH a downstream listener that also adds context', async () => { - const d = dir() - hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"from-bridge"}}\'\n') }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - ctx.on('agent/prompt-submit', async () => ({ - kind: 'allow' as const, - content: [{ type: 'text' as const, text: 'rewritten-prompt' }], - additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, - })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - const req = JSON.stringify(adapter.requests[0]!.messages) - expect(req).toContain('from-bridge') - expect(req).toContain('from-downstream') - expect(req).toContain('rewritten-prompt') - }) - - it('folds the bridge PostToolUse context onto a downstream ACCEPT that replaces content', async () => { - const d = dir() - hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pc.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"bridge-note"}}\'\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - const result = events(agent).find(e => e.type === 'tool/result') - expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true) - expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) - }) - - it('folds the bridge PostToolUse context onto a downstream listener BLOCK', async () => { - const d = dir() - hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pc.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"bridge-note"}}\'\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - const result = events(agent).find(e => e.type === 'tool/result') - expect(result?.type === 'tool/result' && result.data.isError).toBe(true) - expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text.includes('downstream-block'))).toBe(true) - expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('bridge-note')))).toBe(true) - }) - - it('SessionStart additionalContext is injected for the first request', async () => { - const d = dir() - hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"start-ctx"}}\'\n') }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - await waitFor(() => events(agent).some(e => e.type === 'context/message' - && e.data.content.some(b => b.type === 'text' && b.text.includes('start-ctx')))) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('start-ctx') - }) - - it('PostToolUse block (exit 2) → isError feedback; default reason', async () => { - const d = dir() - hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'p.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - const r = events(agent).find(e => e.type === 'tool/result') - expect(r?.type === 'tool/result' && r.data.isError).toBe(true) - expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PostToolUse hook'))).toBe(true) - }) - - it('PostToolUse additionalContext (clean exit) is attached after the result', async () => { - const d = dir() - hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pc.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"post-ctx"}}\'\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('post-ctx')))).toBe(true) - }) - - it('PreToolUse for a tool call WITHOUT a command arg passes an empty command (commandOf non-object/missing arm)', async () => { - const d = dir() - hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pre.sh', '#!/usr/bin/env bash\ncat >/dev/null\nexit 0\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', {}), textResponse('done')]) // no command arg - const ctx = await harness(join(d, 'hooks.json'), adapter) - let ran = false - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(ran).toBe(true) // clean-exit hook allows; commandOf returned '' - }) - - it('a clean exit-0 hook records exitCode 0 and omits stderrSummary', async () => { - const d = dir() - hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'n.sh', '#!/usr/bin/env bash\nexit 0\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - const res = events(agent).find(e => e.type === 'hook/result') - expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0) - expect(res?.type === 'hook/result' && 'stderrSummary' in res.data).toBe(false) - }) - - it('a long stderr is truncated in the hook/result summary', async () => { - const d = dir() - hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'l.sh', '#!/usr/bin/env bash\nprintf "x%.0s" {1..600} >&2\nexit 2\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - const res = events(agent).find(e => e.type === 'hook/result') - expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true) - expect(res?.type === 'hook/result' && res.data.stderrSummary?.length).toBe(501) // default 500-char cap + ellipsis - }) - - it('rejects a non-positive or fractional stderrSummaryMaxChars at load', async () => { - const d = dir() - hooks(d, {}) - for (const bad of [0, -5, 1.5, Number.NaN]) { - const adapter = new MockAdapter([]) - await expect(harness(join(d, 'hooks.json'), adapter, { stderrSummaryMaxChars: bad })) - .rejects.toThrow(/hooks-codex: stderrSummaryMaxChars must be a positive integer/) - } - }) - - it('the stderr summary cap is plugin config (stderrSummaryMaxChars)', async () => { - const d = dir() - hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'l.sh', '#!/usr/bin/env bash\nprintf "x%.0s" {1..600} >&2\nexit 2\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter, { stderrSummaryMaxChars: 40 }) - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - const res = events(agent).find(e => e.type === 'hook/result') - expect(res?.type === 'hook/result' && res.data.stderrSummary).toBe('x'.repeat(40) + '…') - }) - - it('warns on a skipped async hook and a direct apply() (schema bypass) runs', async () => { - const d = dir() - const marker = join(d, 'ran') - hooks(d, { UserPromptSubmit: [{ hooks: [ - { type: 'command', command: 'bg.sh', async: true }, // skipped → warn - { type: 'command', command: sh(d, 'h.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) }, - ] }] }) - const warn = vi.fn() - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = new Context() - await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] }) - await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) - ctx.logger.warn = warn as never - // Direct apply (schema bypass) → the `model ?? ''` fallback is exercised. - HooksCodex.apply(ctx, { configPath: join(d, 'hooks.json') }) - ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(existsSync(marker)).toBe(true) - expect(warn).toHaveBeenCalledWith(expect.stringContaining('async hook')) - }) - - it('a no-op clean hook proceeds (contextFrom empty → next)', async () => { - const d = dir() - hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'n.sh', '#!/usr/bin/env bash\nexit 0\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - let ran = false - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(ran).toBe(true) - }) - - it('SessionStart with no additionalContext is a no-op (contextFrom empty)', async () => { - const d = dir() - // The hook touches a marker so we can wait for it to ACTUALLY FINISH before - // asserting absence — a completed turn alone would not prove the detached - // session-start hook ran, making the absence check a false pass. - const marker = join(d, 'ss-ran') - hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\ntouch "${marker}"\nexit 0\n`) }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - await waitFor(() => existsSync(marker)) // the clean no-output hook has finished - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(events(agent).some(e => e.type === 'context/message')).toBe(false) - }) - - it('a throwing SessionStart inject is contained (logged)', async () => { - const d = dir() - hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"x"}}\'\n') }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.inject = (() => { throw new Error('inject boom') }) - await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SessionStart hook failed'))) - expect(warn).toHaveBeenCalledWith(expect.stringContaining('SessionStart hook failed')) - }) - - it('a clean PreToolUse with no decision allows the tool (no deny)', async () => { - const d = dir() - hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'ok.sh', '#!/usr/bin/env bash\nexit 0\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - let ran = false - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(ran).toBe(true) - }) - - it('a non-matching regex matcher skips the hook (matchesMatcher false → continue)', async () => { - const d = dir() - // /^Edit$/ does not match the tool name "Bash" → the group is skipped. - hooks(d, { PreToolUse: [{ matcher: '^Edit$', hooks: [{ type: 'command', command: sh(d, 'deny.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - let ran = false - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(ran).toBe(true) // matcher didn't match → no hook ran → tool proceeded - expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) - }) - - it('a {"continue":false} hook is RECORDED as "stop" but does not halt the run (TODO(hook-continue-false))', async () => { - // Honoring `continue:false` is deferred — the seams have no hard-halt - // primitive. Assert the LOG records the halt request AND that the run is not - // actually halted (the tool still runs, the turn completes). - const d = dir() - hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"continue":false,"stopReason":"halt"}\'\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - let ran = false - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - const res = events(agent).find(e => e.type === 'hook/result') - expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded - expect(ran).toBe(true) // NOT honored: the tool still ran (halt is deferred) - }) - - it('PreToolUse deny with EMPTY stderr uses the default reason (?? right arm)', async () => { - const d = dir() - hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'd.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - const r = events(agent).find(e => e.type === 'tool/result') - expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true) - }) - - it('PostToolUse block AND additionalContext are surfaced together', async () => { - const d = dir() - hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'bc.sh', '#!/usr/bin/env bash\necho \'{"decision":"block","reason":"bad","hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"ctx too"}}\'\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - const r = events(agent).find(e => e.type === 'tool/result') - expect(r?.type === 'tool/result' && r.data.isError).toBe(true) - expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('bad'))).toBe(true) - expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('ctx too')))).toBe(true) - }) - - it('commandOf reads a non-string command arg as an empty command', async () => { - const d = dir() - // The tool-call arguments carry `command` as a NUMBER → commandOf's - // `typeof command === 'string'` false arm → '' (the payload's tool_input.command). - const cap = join(d, 'payload') - hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'cap.sh', `#!/usr/bin/env bash\ncat > "${cap}"\nexit 0\n`) }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 7 }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'number' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_input: { command: string } } - expect(payload.tool_input.command).toBe('') - }) - - it('a no-agent direct PreToolUse run uses process.cwd() and turn 0 (no session to record)', async () => { - const d = dir() - hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'd.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) - const ctx = await harness(join(d, 'hooks.json'), new MockAdapter([])) - let ran = false - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - const { CallId } = await import('@deepseek-ai/dsh-llm') - const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'Bash', arguments: { command: 'x' } }) - expect(ran).toBe(false) // denied - expect(result.isError).toBe(true) - }) - - it('a no-agent direct PostToolUse run attaches context with no session to record', async () => { - const d = dir() - hooks(d, { PostToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'pc.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"PostToolUse","additionalContext":"x"}}\'\n') }] }] }) - const ctx = await harness(join(d, 'hooks.json'), new MockAdapter([])) - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const { CallId } = await import('@deepseek-ai/dsh-llm') - const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'Bash', arguments: { command: 'x' } }) - expect(result.isError).toBeFalsy() - expect(result.additionalContext?.content.some(b => b.type === 'text' && b.text === 'x')).toBe(true) - }) - - it('when the bash executor REJECTS, the hook/result omits exitCode (non-blocking)', async () => { - const d = dir() - hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'h.sh', '#!/usr/bin/env bash\nexit 0\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - ctx.bash.run = (() => Promise.reject(new Error('executor down'))) - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - const res = events(agent).find(e => e.type === 'hook/result') - expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false) - }) - - it('a blocking Stop hook with EMPTY stderr still forces continuation (no reason required)', async () => { - // Regression: an exit-2 Stop hook with no stderr yields decision 'deny' + - // reason undefined; the turn must STILL force-continue, not silently stop. - const d = dir() - const marker = join(d, 'fired') - hooks(d, { Stop: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\nexit 2\n`) }] }] }) - const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(adapter.requests).toHaveLength(2) // empty-reason block forced continuation - expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('blocked by Stop hook') - }) - - it('a clean UserPromptSubmit hook that prints PLAIN stdout injects it as context', async () => { - // Codex feeds a SessionStart/UserPromptSubmit hook's PLAIN (non-JSON) stdout - // as additionalContext (unlike CC, which needs a JSON hookSpecificOutput). - const d = dir() - hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho "extra guidance from a plain hook"\nexit 0\n') }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('extra guidance from a plain hook') - }) - - it('a NON-clean SessionStart hook (exit 2) does NOT inject its stdout as context', async () => { - // SessionStart cannot block, but non-clean stdout still must not become context. The marker - // waits for detached completion; `echo stale; exit 2` then proves the exit-code gate matches - // the codec's structured-stdout rule. - const d = dir() - const marker = join(d, 'ran') - hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', `#!/usr/bin/env bash\ntouch "${marker}"\necho "stale"\nexit 2\n`) }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - await waitFor(() => existsSync(marker)) // the exit-2 hook has finished - expect(events(agent).some(e => e.type === 'context/message' - && e.data.content.some(b => b.type === 'text' && b.text.includes('stale')))).toBe(false) - }) - - it('a UserPromptSubmit hook with a non-blocking error exit (1) + stdout does NOT inject it', async () => { - // Exit 1 is a non-blocking error (no decision), so the prompt is NOT blocked - // and the handler falls through to the context path — the gate must still - // suppress the error hook's stdout ("stale" never reaches the model). - const d = dir() - hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'e.sh', '#!/usr/bin/env bash\necho "stale"\nexit 1\n') }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(adapter.requests).toHaveLength(1) // exit 1 is non-blocking → the turn ran - expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('stale') - }) - - it('a clean SessionStart hook that prints PLAIN stdout injects it (not JSON)', async () => { - const d = dir() - hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'ss.sh', '#!/usr/bin/env bash\necho "session preamble"\nexit 0\n') }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - await waitFor(() => events(agent).some(e => e.type === 'context/message' - && e.data.content.some(b => b.type === 'text' && b.text.includes('session preamble')))) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('session preamble') - }) - - it('a clean hook that prints JSON is NOT injected as prose (plain-stdout gate)', async () => { - // A structured (JSON) stdout must go through the hookSpecificOutput path, not - // be dumped verbatim as context — the `!startsWith('{')` gate guards this. - const d = dir() - hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'j.sh', '#!/usr/bin/env bash\necho \'{"unrelated":"json"}\'\nexit 0\n') }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('unrelated') - }) - - it('the PreToolUse payload carries the REAL tool name (matches the matcher subject)', async () => { - // Regression: the payload once hardcoded tool_name "Bash", disagreeing with - // the exec.name matcher subject — a config matcher on the real name would - // then never fire. Capture the payload and assert tool_name === the real name. - const d = dir() - const cap = join(d, 'payload') - hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'cap.sh', `#!/usr/bin/env bash\ncat > "${cap}"\nexit 0\n`) }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'shell', { command: 'ls' }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_name: string; tool_input: { command: string } } - expect(payload.tool_name).toBe('shell') - expect(payload.tool_input.command).toBe('ls') - }) - - it('a Codex matcher on the REAL tool name fires (matcher subject === payload tool_name)', async () => { - // A regex matcher matching the real tool name must select the hook — proving - // the matcher subject and the payload tool_name agree. - const d = dir() - hooks(d, { PreToolUse: [{ matcher: 'shell', hooks: [{ type: 'command', command: sh(d, 'd.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'shell', { command: 'ls' }), textResponse('done')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - let ran = false - ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(ran).toBe(false) // the matcher fired → the hook denied the tool - expect(events(agent).some(e => e.type === 'hook/invoked' && e.data.point === 'PreToolUse')).toBe(true) - }) - - it('a hook emitting a systemMessage is warned as not-yet-surfaced', async () => { - const d = dir() - hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'sm.sh', '#!/usr/bin/env bash\necho \'{"systemMessage":"heads up"}\'\n') }] }] }) - const adapter = new MockAdapter([textResponse('ok')]) - const ctx = await harness(join(d, 'hooks.json'), adapter) - const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) - expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) - expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('heads up') - }) - - it('runs an agent-scoped hook in the session cwd, not the executor default', async () => { - // Same regression as the CC bridge: the Codex bridge must thread the session - // cwd as the hook workdir. Executor default = serverDir; session cwd = - // sessionDir; the PreToolUse hook's `pwd` marker must land in sessionDir. - const serverDir = dir() - const sessionDir = dir() - const marker = join(sessionDir, 'where') - hooks(serverDir, { PreToolUse: [{ hooks: [{ type: 'command', command: 'pwd > where' }] }] }) - const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) - const ctx = new Context() - await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] }) - await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir }) - await ctx.plugin(HooksCodex, { configPath: join(serverDir, 'hooks.json'), model: 'm' }) - ctx.llm.registerAdapter(['mock'], adapter) - ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) - handle.agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, handle.agent as ReactLoopAgent) - expect(existsSync(marker)).toBe(true) - expect(readFileSync(marker, 'utf8').trim().endsWith(sessionDir.split('/').pop()!)).toBe(true) - await handle.dispose() - }) -}) From a28d95afb2c7f0f71ee297f93ae2506a3e0f41a5 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:38:30 +0800 Subject: [PATCH 164/359] perf(snapshot): parallelize replay scenarios --- packages/support/acp-snapshot/src/suite.ts | 15 +++++++------ vitest.snapshot.config.ts | 25 ++++++++++++++++++++-- 2 files changed, 32 insertions(+), 8 deletions(-) diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts index dc1675eac0..7bd457b7b4 100644 --- a/packages/support/acp-snapshot/src/suite.ts +++ b/packages/support/acp-snapshot/src/suite.ts @@ -3,6 +3,8 @@ * compares normalized stdout; comparable session fixtures are both replay input and expected * output. Record mode refreshes reproducible model scenarios from the live API, while refresh * mode replays committed scripts and rewrites derived artifacts without a key. + * Replay scenarios run concurrently because each subprocess owns unique temp cwd and persistence + * roots and only reads committed fixtures. Record and refresh scenarios stay serial while writing. * * Exactly one scenario per header-composition class pins the system prompt and tool schemas in * dedicated sidecars. Every live header is checked against that pin, so session-dependent @@ -461,7 +463,7 @@ export function stabilizeRefreshLog(fresh: string, existing: string, replacement } /** - * Register the suite: one `describe` per scenario (the golden/log compares and + * Register the suite: one test per scenario (the golden/log compares and * the header-uniformity guard) plus the fixture guard block (no orphan * scenario dirs, required files present, exactly one pin per header class, * pinning fixtures well-formed, every JSONL prompt-scrubbed, non-pinning @@ -477,6 +479,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { const RECORDING = mode === 'record' const REFRESHING = mode === 'refresh' const childMode: 'replay' | 'record' = RECORDING ? 'record' : 'replay' + const scenarioSuite = mode === 'replay' ? describe.concurrent : describe /** The class a scenario's header composition belongs to (see {@link Scenario.headerClass}). */ const classOf = (scenario: Scenario): string => scenario.headerClass ?? 'default' @@ -496,11 +499,11 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { } } - for (const scenario of scenarios) { - describe(`snapshot: ${scenario.name}`, () => { + scenarioSuite('snapshot scenarios', () => { + for (const scenario of scenarios) { // In RECORD mode, only re-run the `recorded` (live-API) scenarios; the `authored` ones // (sidecar-driven errors/cancel) are never re-recorded. - it.skipIf(RECORDING && !scenario.recorded)('matches the goldens', async () => { + it.skipIf(RECORDING && !scenario.recorded)(`snapshot: ${scenario.name} matches the goldens`, async ({ expect }) => { const dir = join(snapshotsDir, scenario.name) const input = JSON.parse(await readFile(join(dir, 'input.json'), 'utf8')) as InputScript const overrideFile = join(dir, 'replay.override.json') @@ -658,8 +661,8 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { } } }) - }) - } + } + }) describe('snapshot fixtures', () => { it('every scenario directory is registered (no orphans)', async () => { diff --git a/vitest.snapshot.config.ts b/vitest.snapshot.config.ts index dbc51eae41..9753176f9d 100644 --- a/vitest.snapshot.config.ts +++ b/vitest.snapshot.config.ts @@ -1,6 +1,25 @@ +import { availableParallelism } from 'node:os' import tsconfigPaths from 'vite-tsconfig-paths' import { defineConfig } from 'vitest/config' +const DEFAULT_SNAPSHOT_MAX_CONCURRENCY = 5 + +function positiveIntFromEnv(name: string, fallback: number): number { + const raw = process.env[name] + if (raw === undefined || raw === '') return fallback + + const value = Number(raw) + if (!Number.isInteger(value) || value < 1) { + throw new Error(`${name} must be a positive integer, got ${JSON.stringify(raw)}`) + } + return value +} + +const snapshotMaxConcurrency = positiveIntFromEnv( + 'DSH_SNAPSHOT_MAX_CONCURRENCY', + Math.min(DEFAULT_SNAPSHOT_MAX_CONCURRENCY, availableParallelism()), +) + // Replay is the keyless default: boot the real ACP subprocess from recorded model scripts and diff // normalized transcript plus persisted-log goldens. `record` calls the real API and updates fixtures // and goldens; `refresh` replays committed scripts and updates only current goldens. Replay/refresh @@ -21,10 +40,12 @@ export default defineConfig({ plugins: [tsconfigPaths({ projects: ['./tsconfig.json'] })], test: { include: ['examples/*/tests/**/*.snapshot.ts', 'packages/sdk/*/tests/**/*.snapshot.ts'], - // Each test boots a subprocess; give it room, and run files one at a time - // (a record run hits the live API, and replay subprocess boot is heavy). + // Each test boots a subprocess; give it room and keep the worker file singular. Replay tests + // opt into bounded in-file concurrency, while record/refresh stay serial because they write + // fixtures. The environment knob restores serial replay with value 1 on constrained machines. testTimeout: 120_000, hookTimeout: 30_000, fileParallelism: false, + maxConcurrency: snapshotMaxConcurrency, }, }) From 5039c4ae40835a23db8a4876d1352eba9dd6d092 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:38:57 +0800 Subject: [PATCH 165/359] fix(snapshot): include agent stderr in failures --- packages/support/acp-snapshot/README.md | 2 +- packages/support/acp-snapshot/src/harness.ts | 4 ++++ .../support/acp-snapshot/tests/fixtures/fake-acp-agent.ts | 3 +++ packages/support/acp-snapshot/tests/harness.spec.ts | 8 ++++++++ 4 files changed, 16 insertions(+), 1 deletion(-) diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 03254a17a0..55e9aadf4d 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -4,7 +4,7 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tie Three layers, importable separately: -- **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). +- **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). Startup failures preserve captured agent stderr in the rejected diagnostic. - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}`), `scrubToolSchemas` (schema bulk → `{{tools}}`), and `scrubRequestHeaders` (all header bulk → `{{system}}`/`{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, rejection of structured `UNKNOWN_TOOL` results, the per-header-class pin (`system-prompt.golden.md` plus `tool-schemas.golden.json`) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt/schema-scrubbed, non-pinning fixtures fully header-scrubbed). Must be called at vitest collection time. diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index 3bae0ba279..4933e11e88 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -281,6 +281,10 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise // Harvest EVERY persisted log (parent + any subagent children) while the // temp dirs still exist, ordered primary-first. sessionLogs = await harvestSessionLogs(sessionsRoot) + } catch (error: unknown) { + const stderr = stderrChunks.join('') + if (stderr === '') throw error + throw new Error(`snapshot-harness: scenario failed: ${String(error)}\nagent stderr:\n${stderr}`, { cause: error }) } finally { // Failure-safe teardown: kill a still-running child and drop the temp dirs // even if seeding/spawn/a step/harvest threw, so a flaky run never leaks a diff --git a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts index d5fcd75a93..fccd1d6fcc 100644 --- a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts +++ b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts @@ -24,6 +24,8 @@ interface ScriptedLog { /** The whole scripted behavior for one run. Every field defaults to the least surprising choice. */ interface Behavior { + /** Exit during startup after writing any configured stderr note. */ + failOnBoot?: boolean /** Reject every `session/new` (exercises the expect-error step without extra dirs). */ rejectNewSession?: boolean /** Reject `session/new` only when `additionalDirectories` is non-empty (the real bridge's rule). */ @@ -62,6 +64,7 @@ const behavior: Behavior = fixtureFile === '' : JSON.parse(readFileSync(join(dirname(fixtureFile), 'behavior.json'), 'utf8')) as Behavior if (behavior.stderrNote !== undefined) process.stderr.write(`${behavior.stderrNote}\n`) +if (behavior.failOnBoot === true) process.exit(7) let nextOutboundId = 1000 let sessionId = '' diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 01b93dc81e..42ccbd7de4 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -38,6 +38,14 @@ async function scenario(behavior: object): Promise<{ dir: string; fixtureFile: s const boot: InputStep[] = [{ op: 'initialize' }, { op: 'newSession' }] describe('runScenario', () => { + it('includes agent stderr when the ACP connection closes during startup', { timeout: 20_000 }, async () => { + const { fixtureFile } = await scenario({ failOnBoot: true, stderrNote: 'fake agent requested startup failure' }) + await expect(runScenario( + { steps: [{ op: 'initialize' }] }, + { agent: AGENT, mode: 'replay', fixtureFile }, + )).rejects.toThrow(/agent stderr:\nfake agent requested startup failure/) + }) + it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ permissionProbe: true, From 092126ae5035106178c4f518271758ee7ee08af8 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:40:22 +0800 Subject: [PATCH 166/359] perf(docs): reuse built declarations for typecheck --- scripts/doc-typecheck.ts | 203 ++++++++++++++++++++++++++++----------- 1 file changed, 148 insertions(+), 55 deletions(-) diff --git a/scripts/doc-typecheck.ts b/scripts/doc-typecheck.ts index 86266f89b2..94c9dc0723 100644 --- a/scripts/doc-typecheck.ts +++ b/scripts/doc-typecheck.ts @@ -1,7 +1,7 @@ /** - * Typecheck Markdown `ts` fences against workspace sources. `ignore-check` - * fences are reported as opt-outs; generated catalog fragments and - * `type-equiv` blocks are skipped here because their owning gates verify them. + * Typecheck Markdown `ts` fences against the workspace API. `ignore-check` fences are reported as + * opt-outs; generated catalog fragments and `type-equiv` blocks are skipped here because their + * owning gates verify them. A build-coordinated mode consumes existing declarations without emit. */ import { execFileSync } from 'node:child_process' @@ -62,25 +62,106 @@ function extractBlocks(absPath: string): Block[] { return blocks } +const configHost: ts.ParseConfigFileHost = { + ...ts.sys, + getCurrentDirectory: () => root, + onUnRecoverableConfigFileDiagnostic(diagnostic) { + throw new Error(ts.flattenDiagnosticMessageText(diagnostic.messageText, '\n')) + }, +} + +/** Load root settings and redirect workspace aliases to declarations from the coordinated build. */ +function builtTypeCompilerOptions(): ts.CompilerOptions { + const configPath = join(root, 'tsconfig.json') + const parsed = ts.getParsedCommandLineOfConfigFile(configPath, {}, configHost) + if (!parsed) throw new Error(`doc-typecheck: cannot parse ${configPath}`) + if (parsed.errors.length > 0) { + throw new Error(parsed.errors.map(error => ts.flattenDiagnosticMessageText(error.messageText, '\n')).join('\n')) + } + if (parsed.options.paths === undefined) throw new Error('doc-typecheck: root tsconfig has no workspace paths') + const paths = Object.fromEntries(Object.entries(parsed.options.paths).map(([specifier, candidates]) => [ + specifier, + candidates.map((candidate) => { + if (!candidate.endsWith('/src')) { + throw new Error(`doc-typecheck: cannot map workspace source path to built declarations: ${candidate}`) + } + return `${candidate.slice(0, -'/src'.length)}/lib/types` + }), + ])) + const options: ts.CompilerOptions = { + ...parsed.options, + paths, + noEmit: true, + composite: false, + incremental: false, + declaration: false, + declarationMap: false, + sourceMap: false, + noUnusedLocals: false, + noUnusedParameters: false, + } + delete options.tsBuildInfoFile + return options +} + +/** Compile Markdown blocks as virtual files against declarations from the coordinated build. */ +function compileBlocksAgainstBuiltTypes(blocks: Block[]): readonly ts.Diagnostic[] { + const options = builtTypeCompilerOptions() + const sources = new Map() + for (const [index, block] of blocks.entries()) { + const fileName = resolve(root, '.doc-typecheck', `block-${index}.ts`) + sources.set(fileName, block.code.endsWith('\n') ? block.code : `${block.code}\n`) + } + + const baseHost = ts.createCompilerHost(options, true) + const host: ts.CompilerHost = { + ...baseHost, + fileExists(fileName) { + return sources.has(resolve(fileName)) || baseHost.fileExists(fileName) + }, + readFile(fileName) { + return sources.get(resolve(fileName)) ?? baseHost.readFile(fileName) + }, + getSourceFile(fileName, languageVersion, onError, shouldCreateNewSourceFile) { + const source = sources.get(resolve(fileName)) + if (source !== undefined) return ts.createSourceFile(fileName, source, languageVersion, true) + return baseHost.getSourceFile(fileName, languageVersion, onError, shouldCreateNewSourceFile) + }, + writeFile() { + throw new Error('doc-typecheck: noEmit compilation attempted to write output') + }, + } + const program = ts.createProgram([...sources.keys()], options, host) + return ts.getPreEmitDiagnostics(program) +} + +/** Render compiler diagnostics with virtual block paths mapped back to Markdown. */ +function formatDiagnostics(diagnostics: readonly ts.Diagnostic[], blocks: Block[]): string { + const formatted = ts.formatDiagnostics(diagnostics, { + getCanonicalFileName: fileName => fileName, + getCurrentDirectory: () => root, + getNewLine: () => ts.sys.newLine, + }) + return remapBlockPaths(formatted, blocks) +} + /** Reuse the repo typecheck graph references from a temp project one directory below root. */ function workspaceReferences(): { path: string }[] { const file = join(root, 'tsconfig.json') - // Parse with TypeScript's own JSONC reader, not a hand-rolled comment strip: - // a regex strip mistakes the `/*/` in a wildcard path candidate - // (`./packages/core/*/src`) for a block comment and corrupts the map. - const result = ts.readConfigFile(file, p => readFileSync(p, 'utf8')) + // Parse with TypeScript's own JSONC reader: a regex comment stripper corrupts the `/*/` path + // candidate in the workspace wildcard. + const result = ts.readConfigFile(file, path => readFileSync(path, 'utf8')) if (result.error) { throw new Error(`doc-typecheck: cannot read ${file}: ${ts.flattenDiagnosticMessageText(result.error.messageText, '\n')}`) } - // `config` is typed `any` by the TS API; narrow it to the one field we read. - const { references } = result.config as { compilerOptions: { paths: Record }; references: { path: string }[] } - return references.map(({ path }) => { - const relativeToTemp = path.startsWith('./') ? `../${path.slice(2)}` : `../${path}` - return { path: relativeToTemp } - }) + // `config` is typed `any` by the TS API; narrow it to the one field read here. + const { references } = result.config as { references: { path: string }[] } + return references.map(({ path }) => ({ + path: path.startsWith('./') ? `../${path.slice(2)}` : `../${path}`, + })) } -/** The standalone tsconfig for the temp typecheck project. */ +/** The standalone temp project used when no coordinated build owns declaration freshness. */ function tempTsconfig(): string { return JSON.stringify({ extends: '../tsconfig.json', @@ -94,6 +175,39 @@ function tempTsconfig(): string { }) } +/** Compile blocks through project references for the standalone command. */ +function compileBlocksStandalone(blocks: Block[]): string | undefined { + const tmp = mkdtempSync(join(root, '.doc-typecheck-')) + try { + writeFileSync(join(tmp, 'tsconfig.json'), tempTsconfig()) + for (const [index, block] of blocks.entries()) { + writeFileSync(join(tmp, `block-${index}.ts`), block.code.endsWith('\n') ? block.code : `${block.code}\n`) + } + try { + // Invoke tsc's JS entry through Node instead of a platform-specific shell shim. + execFileSync(process.execPath, ['node_modules/typescript/bin/tsc', '-b', join(tmp, 'tsconfig.json')], { + cwd: root, + stdio: 'pipe', + }) + return undefined + } catch (error: unknown) { + const failed = error as { stdout?: Buffer; stderr?: Buffer } + return remapBlockPaths(`${failed.stdout?.toString() ?? ''}${failed.stderr?.toString() ?? ''}`, blocks) + } + } finally { + rmSync(tmp, { recursive: true, force: true }) + } +} + +/** Map virtual or temporary block paths back to their owning Markdown fences. */ +function remapBlockPaths(output: string, blocks: Block[]): string { + return output.replace(/(?:[^\s:()]*[/\\])?block-(\d+)\.ts\((\d+),(\d+)\)/g, (_match, index: string, line: string, column: string) => { + const block = blocks[Number(index)] + if (!block) return `block-${index}.ts(${line},${column})` + return `${block.file} (block at line ${block.line}, +${line}:${column})` + }) +} + const markdownGlobs = ['README.md', 'docs/**/*.md', 'packages/*/*.md', 'packages/*/*/*.md'] const files: string[] = [] @@ -114,45 +228,24 @@ if (checked.length === 0) { process.exit(0) } -const tmp = mkdtempSync(join(root, '.doc-typecheck-')) -try { - writeFileSync(join(tmp, 'tsconfig.json'), tempTsconfig()) - const fileForBlock = new Map() - checked.forEach((block, i) => { - const name = `block-${i}.ts` - writeFileSync(join(tmp, name), block.code.endsWith('\n') ? block.code : `${block.code}\n`) - fileForBlock.set(name, block) - }) - - try { - // tsc's JS entry via the current node, not the .bin shim: the extensionless - // shim is not spawnable on Windows (the CVE-2024-27980 class the sibling - // scripts hit), and the .cmd variant would need shell:true, which - // concatenates args UNESCAPED — a hazard for the temp project path. The JS - // entry behaves identically on every platform. - execFileSync(process.execPath, ['node_modules/typescript/bin/tsc', '-b', join(tmp, 'tsconfig.json')], { cwd: root, stdio: 'pipe' }) - } catch (error: unknown) { - const failed = error as { stdout?: Buffer; stderr?: Buffer } - const out = `${failed.stdout?.toString() ?? ''}${failed.stderr?.toString() ?? ''}` - // Rewrite "block-N.ts(line,col)" to the real "file:fenceLine" for triage. - const remapped = out.replace(/(?:[^\s:()]*[/\\])?block-(\d+)\.ts\((\d+),(\d+)\)/g, (_m, idx: string, ln: string, col: string) => { - const block = fileForBlock.get(`block-${idx}.ts`) - if (!block) return `block-${idx}.ts(${ln},${col})` - return `${block.file} (block at line ${block.line}, +${ln}:${col})` - }) - console.error('doc-typecheck: documentation code blocks failed to compile.\n') - console.error(remapped) - process.exit(1) - } - - const ratio = ignored.length / ratioDenominator - const skipped = all.length - ratioDenominator - console.log(`doc-typecheck: ${checked.length} block(s) compiled, ${ignored.length} ignored (${(ratio * 100).toFixed(0)}% opt-out), ${skipped} type-equiv/catalog (checked elsewhere).`) - // Guard against the escape hatch becoming the norm. - if (ratioDenominator >= 4 && ratio > 0.5) { - console.error(`doc-typecheck: too many blocks opt out of checking (${ignored.length}/${ratioDenominator}). Make them compile or delete them.`) - process.exit(1) - } -} finally { - rmSync(tmp, { recursive: true, force: true }) +const useBuiltTypes = process.env.DSH_DOC_TYPECHECK_USE_BUILD_OUTPUT === '1' +const compilationError = useBuiltTypes + ? (() => { + const diagnostics = compileBlocksAgainstBuiltTypes(checked) + return diagnostics.length === 0 ? undefined : formatDiagnostics(diagnostics, checked) + })() + : compileBlocksStandalone(checked) +if (compilationError !== undefined) { + console.error('doc-typecheck: documentation code blocks failed to compile.\n') + console.error(compilationError) + process.exit(1) +} + +const ratio = ignored.length / ratioDenominator +const skipped = all.length - ratioDenominator +console.log(`doc-typecheck: ${checked.length} block(s) compiled, ${ignored.length} ignored (${(ratio * 100).toFixed(0)}% opt-out), ${skipped} type-equiv/catalog (checked elsewhere).`) +// Guard against the escape hatch becoming the norm. +if (ratioDenominator >= 4 && ratio > 0.5) { + console.error(`doc-typecheck: too many blocks opt out of checking (${ignored.length}/${ratioDenominator}). Make them compile or delete them.`) + process.exit(1) } From cb153f3df8edaf41e08080f94dae03dfacc08425 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:42:00 +0800 Subject: [PATCH 167/359] perf(gates): cap workers and reuse build output --- scripts/run-gates.ts | 40 +++++++++++++++++++++++++++++++++------- 1 file changed, 33 insertions(+), 7 deletions(-) diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index d103f11461..d714dda0dd 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -47,13 +47,23 @@ interface RunningGate { promise: Promise } +interface ConcurrencyDefault { + workers: number + source: string +} + const root = resolve(import.meta.dirname, '..') const mode = parseMode(process.argv[2]) const gates = gatesForMode(mode) -const maxConcurrency = concurrencyFromEnv('DSH_GATE_CONCURRENCY', defaultConcurrency(gates.length)) +const concurrencyDefault = defaultConcurrency(mode, gates.length) +const concurrencyOverride = process.env.DSH_GATE_CONCURRENCY +const maxConcurrency = concurrencyFromEnv('DSH_GATE_CONCURRENCY', concurrencyDefault.workers) const startedAt = performance.now() -console.log(`run-gates: ${mode} running ${gates.length} gate(s) with ${maxConcurrency} worker(s).`) +const concurrencySource = concurrencyOverride === undefined || concurrencyOverride === '' + ? concurrencyDefault.source + : '$DSH_GATE_CONCURRENCY' +console.log(`run-gates: ${mode} running ${gates.length} gate(s) with ${maxConcurrency} worker(s) from ${concurrencySource}.`) const results = await runGates(gates, maxConcurrency) printSummary(results, performance.now() - startedAt) @@ -78,8 +88,15 @@ function parseMode(raw: string | undefined): Mode { } } -function defaultConcurrency(total: number): number { - return Math.min(total, Math.max(4, availableParallelism())) +function defaultConcurrency(selectedMode: Mode, total: number): ConcurrencyDefault { + const available = availableParallelism() + const modeLimit = selectedMode === 'pre-push' ? Math.min(4, available) : available + return { + workers: Math.min(total, modeLimit), + source: selectedMode === 'pre-push' + ? `${available} available CPU(s), pre-push cap 4` + : `${available} available CPU(s)`, + } } function concurrencyFromEnv(name: string, fallback: number): number { @@ -162,7 +179,10 @@ function gatesForMode(selected: Mode): Gate[] { pnpmScript('snapshot', 'test:snapshot'), pnpmScript('build', 'build'), ...hygieneLeafGates({ artifactNeeds: ['build'] }), - ...docSyncLeafGates(), + ...docSyncLeafGates({ + docTypecheckNeeds: ['build'], + docTypecheckEnv: { DSH_DOC_TYPECHECK_USE_BUILD_OUTPUT: '1' }, + }), pnpmScript('module-graph', 'verify-module-graph', { label: 'module graph' }), ] } @@ -275,9 +295,15 @@ function hygieneLeafGates(options: { artifactNeeds?: string[] } = {}): Gate[] { ] } -function docSyncLeafGates(): Gate[] { +function docSyncLeafGates(options: { + docTypecheckNeeds?: string[] + docTypecheckEnv?: Record +} = {}): Gate[] { + const docTypecheckOptions: Partial = {} + if (options.docTypecheckNeeds !== undefined) docTypecheckOptions.needs = options.docTypecheckNeeds + if (options.docTypecheckEnv !== undefined) docTypecheckOptions.env = options.docTypecheckEnv return [ - pnpmScript('doc-typecheck', 'doc-typecheck'), + pnpmScript('doc-typecheck', 'doc-typecheck', docTypecheckOptions), pnpmScript('cordis-catalog', 'verify-cordis-catalog', { label: 'cordis catalog' }), pnpmScript('export-jsdoc', 'verify-export-jsdoc', { label: 'export jsdoc' }), pnpmScript('tool-catalog', 'verify-tool-catalog', { label: 'tool catalog' }), From bff3f0a8db53d842f445a1b34803cd3ddbf45a1e Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:43:10 +0800 Subject: [PATCH 168/359] feat(gates): print actionable failure output --- scripts/run-gates.ts | 69 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 59 insertions(+), 10 deletions(-) diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index d714dda0dd..f2bea88cca 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -24,6 +24,7 @@ type GateStatus = 'pending' | 'running' | 'passed' | 'failed' | 'skipped' interface Gate { id: string label: string + displayCommand: string command: string args: string[] needs?: string[] @@ -38,10 +39,16 @@ interface GateResult { durationMs: number stdout: string stderr: string + output: GateOutputChunk[] exitCode: number | null error?: string } +interface GateOutputChunk { + stream: 'stdout' | 'stderr' + text: string +} + interface RunningGate { gate: Gate promise: Promise @@ -58,6 +65,7 @@ const gates = gatesForMode(mode) const concurrencyDefault = defaultConcurrency(mode, gates.length) const concurrencyOverride = process.env.DSH_GATE_CONCURRENCY const maxConcurrency = concurrencyFromEnv('DSH_GATE_CONCURRENCY', concurrencyDefault.workers) +const verbose = process.env.DSH_GATE_VERBOSE === '1' const startedAt = performance.now() const concurrencySource = concurrencyOverride === undefined || concurrencyOverride === '' @@ -113,6 +121,7 @@ function pnpmScript(id: string, script: string, options: Partial = {}): Ga return { id, label: options.label ?? script, + displayCommand: `pnpm run ${script}`, ...pnpmInvocation(['run', script]), ...options, } @@ -122,6 +131,7 @@ function pnpmExec(id: string, args: string[], options: Partial = {}): Gate return { id, label: options.label ?? `pnpm exec ${args.join(' ')}`, + displayCommand: `pnpm exec ${args.join(' ')}`, ...pnpmInvocation(['exec', ...args]), ...options, } @@ -332,6 +342,7 @@ function demoSmokeGate(options: { needs?: string[] } = {}): Gate { return { id: 'demo-smoke', label: 'demo smoke', + displayCommand: 'pnpm run demo:echo', ...pnpmInvocation(['run', 'demo:echo']), input: 'echo ci smoke\n', ...dependencyOptions, @@ -408,6 +419,7 @@ async function runGates(allGates: Gate[], maxActive: number): Promise { const started = performance.now() let stdout = '' let stderr = '' + const output: GateOutputChunk[] = [] + let spawnError: string | undefined - const exitCode = await new Promise((resolveExit, reject) => { + const exitCode = await new Promise((resolveExit) => { const child = spawn(gate.command, gate.args, { cwd: root, env: { ...process.env, ...gate.env }, @@ -451,19 +465,28 @@ async function runGate(gate: Gate): Promise { }) child.stdout.setEncoding('utf8') child.stderr.setEncoding('utf8') - child.stdout.on('data', (chunk: string) => { stdout += chunk }) - child.stderr.on('data', (chunk: string) => { stderr += chunk }) - child.on('error', reject) + child.stdout.on('data', (chunk: string) => { + stdout += chunk + output.push({ stream: 'stdout', text: chunk }) + }) + child.stderr.on('data', (chunk: string) => { + stderr += chunk + output.push({ stream: 'stderr', text: chunk }) + }) + child.on('error', (error) => { + spawnError = `failed to start command: ${error.message}` + resolveExit(null) + }) child.on('close', resolveExit) if (gate.input !== undefined) child.stdin.end(gate.input) else child.stdin.end() }) - let status: GateStatus = exitCode === 0 ? 'passed' : 'failed' - let error: string | undefined + let status: GateStatus = exitCode === 0 && spawnError === undefined ? 'passed' : 'failed' + let error = spawnError if (status === 'passed' && gate.verify !== undefined) { try { - await gate.verify({ gate, status, durationMs: performance.now() - started, stdout, stderr, exitCode }) + await gate.verify({ gate, status, durationMs: performance.now() - started, stdout, stderr, output, exitCode }) } catch (verifyError: unknown) { status = 'failed' error = verifyError instanceof Error ? verifyError.message : String(verifyError) @@ -476,6 +499,7 @@ async function runGate(gate: Gate): Promise { durationMs: performance.now() - started, stdout, stderr, + output, exitCode, } if (error !== undefined) result.error = error @@ -484,9 +508,16 @@ async function runGate(gate: Gate): Promise { function printResult(result: GateResult): void { const seconds = (result.durationMs / 1000).toFixed(2) - console.log(`\n== ${result.status.toUpperCase()} ${result.gate.label} (${seconds}s) ==`) - process.stdout.write(result.stdout) - process.stderr.write(result.stderr) + if (result.status === 'passed' && !verbose) { + console.log(`run-gates: PASS ${result.gate.label} (${seconds}s)`) + return + } + + const heading = `${result.status.toUpperCase()} ${result.gate.label} (${seconds}s)` + const writeHeading = result.status === 'passed' ? console.log : console.error + writeHeading(`\n== ${heading} ==`) + if (result.status !== 'passed') console.error(`command: ${result.gate.displayCommand}`) + printOutput(result.output) if (result.error !== undefined) console.error(result.error) } @@ -496,4 +527,22 @@ function printSummary(results: GateResult[], durationMs: number): void { const skipped = results.filter(result => result.status === 'skipped').length const seconds = (durationMs / 1000).toFixed(2) console.log(`\nrun-gates: ${passed} passed, ${failed} failed, ${skipped} skipped in ${seconds}s.`) + + const unsuccessful = results.filter(result => result.status === 'failed' || result.status === 'skipped') + if (unsuccessful.length === 0) return + + console.error('run-gates: unsuccessful gates:') + for (const result of unsuccessful) { + const duration = (result.durationMs / 1000).toFixed(2) + const reason = result.error ?? (result.exitCode === null ? 'no exit code' : `exit ${result.exitCode}`) + console.error(` - ${result.status.toUpperCase()} ${result.gate.label} (${duration}s, ${reason})`) + console.error(` ${result.gate.displayCommand}`) + } +} + +function printOutput(output: GateOutputChunk[]): void { + for (const chunk of output) { + if (chunk.stream === 'stdout') process.stdout.write(chunk.text) + else process.stderr.write(chunk.text) + } } From 0fc163453e93d6c4c4b1afdac8e534f72f7c4398 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:43:46 +0800 Subject: [PATCH 169/359] chore: ignore NodeNext typecheck temp dirs --- .gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/.gitignore b/.gitignore index 90709e81c0..bb700f23e5 100644 --- a/.gitignore +++ b/.gitignore @@ -11,6 +11,7 @@ examples/*/*.jsonl examples/*/.sessions/ coverage/ .doc-typecheck-*/ +.node-next-types-*/ .humanize/ tmp/ .claude/commands/ From 8d4f64e5ce1c51a7347c66e118910a57d16defb8 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:44:13 +0800 Subject: [PATCH 170/359] docs: update pre-push scheduler contract --- .../implemented/process/2026-07-06-parallel-pre-push-gates.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/rfc/implemented/process/2026-07-06-parallel-pre-push-gates.md b/docs/rfc/implemented/process/2026-07-06-parallel-pre-push-gates.md index f3a7b1e83c..4e27b111d6 100644 --- a/docs/rfc/implemented/process/2026-07-06-parallel-pre-push-gates.md +++ b/docs/rfc/implemented/process/2026-07-06-parallel-pre-push-gates.md @@ -14,9 +14,9 @@ Flattening those members directly into `lefthook.yml` solves the local hook only [lefthook.yml](../../../../lefthook.yml) keeps one pre-push job named `full check` and runs `pnpm run check:pre-push`. That package script delegates to [scripts/run-gates.ts](../../../../scripts/run-gates.ts), the same bounded scheduler CI uses. -The `pre-push` mode expands into leaf gates for the unit suite, snapshot suite, build, `hygiene` members, `doc-sync` members, and module-graph freshness. The leaf list keeps the same gate vocabulary as the package scripts, including RFC classification and RFC format, while the runner schedules independent checks concurrently and prints one timing/output block per gate. +The `pre-push` mode expands into leaf gates for the unit suite, snapshot suite, build, `hygiene` members, `doc-sync` members, and module-graph freshness. The leaf list keeps the same gate vocabulary as the package scripts, including RFC classification and RFC format, while the runner schedules independent checks with four active top-level workers by default; `DSH_GATE_CONCURRENCY` overrides that bound. -The build gate makes the hook self-contained from a clean worktree. `publint` and `verify-node-next-types` wait for that build output, while source-only gates continue in parallel. +The build gate makes the hook self-contained from a clean worktree. `publint`, `verify-node-next-types`, and the pre-push form of `doc-typecheck` wait for that build output, while source-only gates continue in parallel. [scripts/publint-all.ts](../../../../scripts/publint-all.ts) discovers the package list from `packages//` and runs `publint` with a worker pool sized from `availableParallelism()`. `DSH_PUBLINT_CONCURRENCY` can cap or raise the worker count for local machines and CI runners with different resource profiles. Results are buffered per package and printed in deterministic package order, so parallel execution does not scramble each package's log block. From 828d6004ba35737a5887def0ce3c32b1c84b77ea Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 00:51:12 +0800 Subject: [PATCH 171/359] fix(sdk): share generated session identity --- packages/sdk/create-sdk/tests/create.spec.ts | 1 + packages/sdk/helper/src/features/builtin/app.ts | 7 ++++--- .../sdk/helper/src/templates/assets/index.ts.tpl | 14 +++++++------- packages/sdk/helper/tests/project.spec.ts | 15 +++++++++++++-- 4 files changed, 25 insertions(+), 12 deletions(-) diff --git a/packages/sdk/create-sdk/tests/create.spec.ts b/packages/sdk/create-sdk/tests/create.spec.ts index 9d75700bb9..04a251351d 100644 --- a/packages/sdk/create-sdk/tests/create.spec.ts +++ b/packages/sdk/create-sdk/tests/create.spec.ts @@ -257,6 +257,7 @@ describe('CreateWizard and scaffolder', () => { expect(index).toContain('SdkBootContext') expect(index).toContain('ctx.agents.create') expect(index).toContain('agentOptions: { model: "deepseek-v4-flash" }') + expect(index).not.toContain('AgentId') const tsconfig = parseGeneratedTsConfig(await readFile(join(target, 'tsconfig.base.json'), 'utf8')) const manifest = parseGeneratedPackageManifest(await readFile(join(target, 'package.json'), 'utf8')) expect(tsconfig.compilerOptions.types).toEqual(['node']) diff --git a/packages/sdk/helper/src/features/builtin/app.ts b/packages/sdk/helper/src/features/builtin/app.ts index a89f2c84ae..e4ff11af20 100644 --- a/packages/sdk/helper/src/features/builtin/app.ts +++ b/packages/sdk/helper/src/features/builtin/app.ts @@ -4,6 +4,7 @@ * @module @deepseek-ai/dsh-helper/features/builtin/app */ +import { JsExpression } from '../../documents/cordis-yaml-file.ts' import { featureId } from '../../ids.ts' import type { ProjectProfile } from '../../project/types.ts' import { @@ -94,11 +95,11 @@ class AppOption extends FeatureOption { name: '@deepseek-ai/dsh-stdio', config: { welcome: 'agent REPL ready. Give it a coding task.', - agent: 'main', + sessionId: new JsExpression('process.env.DSH_SDK_SESSION_ID'), }, - }, ['welcome', 'agent'], config => [ + }, ['welcome', 'sessionId'], config => [ ...optionalString(config, 'welcome'), - ...requiredString(config, 'agent'), + ...config.sessionId instanceof JsExpression ? [] : requiredString(config, 'sessionId'), ]), ]) case 'embed': diff --git a/packages/sdk/helper/src/templates/assets/index.ts.tpl b/packages/sdk/helper/src/templates/assets/index.ts.tpl index d0315db80c..4c3099199c 100644 --- a/packages/sdk/helper/src/templates/assets/index.ts.tpl +++ b/packages/sdk/helper/src/templates/assets/index.ts.tpl @@ -2,14 +2,12 @@ import { startSDK, type SdkBootContext } from '@deepseek-ai/dsh-scripts' {{else}} import { randomUUID } from 'node:crypto' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { startSDK, type SdkBootContext } from '@deepseek-ai/dsh-scripts' {{/if}} /** Boot this project's cordis.yml when invoked by dsh-scripts. */ export async function main(boot: SdkBootContext) { - const ctx = await startSDK(new URL('./cordis.yml', import.meta.url)) {{#if isStdio}} const model = boot.args.model if (typeof model !== 'string' || model.length === 0) throw new Error('stdio startup requires --model=') @@ -17,24 +15,26 @@ export async function main(boot: SdkBootContext) { if (resume !== undefined && (typeof resume !== 'string' || resume.length === 0)) { throw new Error('stdio startup requires --resume=') } + const sessionId = SessionId(resume ?? `main-session-${randomUUID()}`) + process.env.DSH_SDK_SESSION_ID = sessionId +{{/if}} + const ctx = await startSDK(new URL('./cordis.yml', import.meta.url)) +{{#if isStdio}} if (resume === undefined) { await ctx.agents.create({ - agentId: AgentId('main'), - sessionId: SessionId(`main-session-${randomUUID()}`), + sessionId, meta: { cwd: boot.cwd }, agentOptions: { model }, }) } else { await ctx.agents.resume({ - agentId: AgentId('main'), - resumeSessionId: SessionId(resume), + resumeSessionId: sessionId, agentOptions: { model }, }) } {{else}} {{#if isEmbed}} await ctx.agents.create({ - agentId: AgentId('main'), sessionId: SessionId(`main-session-${randomUUID()}`), meta: { cwd: boot.cwd }, agentOptions: { model: {{modelLiteral}} }, diff --git a/packages/sdk/helper/tests/project.spec.ts b/packages/sdk/helper/tests/project.spec.ts index d55bb16be9..13fc046a04 100644 --- a/packages/sdk/helper/tests/project.spec.ts +++ b/packages/sdk/helper/tests/project.spec.ts @@ -167,6 +167,10 @@ describe('SdkProject and ProjectEditSession', () => { expect(index).toContain('SdkBootContext') expect(index).toContain('agents.create') expect(index).toContain('boot.args.resume') + expect(index).not.toContain('AgentId') + expect(index).toContain('const sessionId = SessionId(resume ?? `main-session-${randomUUID()}`)') + expect(index).toContain('process.env.DSH_SDK_SESSION_ID = sessionId') + expect(index).toContain('resumeSessionId: sessionId') expect(project.packageManifest().scripts).toEqual({ dev: 'dsh-sdk dev index.ts -- --model="deepseek-v4-flash"', build: 'dsh-sdk build', @@ -175,7 +179,11 @@ describe('SdkProject and ProjectEditSession', () => { config: 'dsh-sdk config', }) expect(await readFile(join(project.root, '.env.example'), 'utf8')).toContain('EXA_API_KEY=') - expect(project.cordis.entry('stdio')?.config).toMatchObject({ agent: 'main' }) + expect(project.cordis.entry('stdio')?.config?.sessionId).toMatchObject({ + source: 'process.env.DSH_SDK_SESSION_ID', + }) + expect(await readFile(join(project.root, 'cordis.yml'), 'utf8')) + .toContain('sessionId: !!js process.env.DSH_SDK_SESSION_ID') expect(project.cordis.entry('stdio')?.config).not.toHaveProperty('model') expect(project.cordis.entry('agent-loop')?.config).toEqual({ agents: [] }) expect(project.cordis.entry('system-prompt')?.config?.persona).toContain('{{cwd}}') @@ -286,7 +294,10 @@ describe('SdkProject and ProjectEditSession', () => { const embed = (await embedEdit.commit()).project expect(embed.profile.runInterface).toBe('embed') expect(await readFile(join(embed.root, 'README.md'), 'utf8')).toContain('Embed the harness') - expect(await readFile(join(embed.root, 'index.ts'), 'utf8')).toContain('agents.create') + const embedIndex = await readFile(join(embed.root, 'index.ts'), 'utf8') + expect(embedIndex).toContain('agents.create') + expect(embedIndex).toContain("import { SessionId } from '@deepseek-ai/dsh-session'") + expect(embedIndex).not.toContain('AgentId') await writeFile(join(embed.root, 'README.md'), '# Custom README\n') const modified = await SdkProject.open(embed.root) From 336f4e51ba0b7fe0c79abbd7d617f6597f0fd7fb Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 00:51:52 +0800 Subject: [PATCH 172/359] docs(acp): align identity routing contract --- packages/ui/acp/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 3650cf27d4..923c0178fa 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -8,7 +8,7 @@ It is a **client-driver / UI plugin**, the structured analogue of the readline ` `apply(ctx, config)` — wires an `AgentSideConnection` (from `@agentclientprotocol/sdk`) to `process.stdin`/`process.stdout` and implements the ACP `Agent` method surface. -The plugin injects `agents`, `sessions`, `sessionPersistence`, `tools`, and `userInteraction`, never the concrete loop. Persistence backs `session/load`; tool definitions own presentation; user interaction maps agent questions to ACP forms. +The plugin injects `agents`, `sessionPersistence`, `tools`, and `userInteraction`, never the concrete loop. Persistence backs `session/load`; tool definitions own presentation; user interaction maps agent questions to ACP forms. ### Config @@ -36,7 +36,7 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name: ## Multi-session -Forward and reverse indexes route every event, prompt, cancel, and approval to one session. Each session permits one in-flight prompt; teardown drains all sessions in parallel. See the [multi-session RFC](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md). +One id-keyed record map plus exact agent-object checks route every event, prompt, cancel, and approval to one session. Each session permits one in-flight prompt; teardown drains all sessions in parallel. See the [multi-session RFC](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md). ## Session config options From 2a6fef66ef3d55aff250f31f3d728f15e15f5269 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 00:52:49 +0800 Subject: [PATCH 173/359] test(agent-loop): remove review bookkeeping --- packages/core/agent-loop/tests/agent.spec.ts | 3 +-- .../tests/contract-regressions.spec.ts | 18 +++++++++--------- 2 files changed, 10 insertions(+), 11 deletions(-) diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 7969d18200..91fc1a891d 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -401,8 +401,7 @@ describe('Agent', () => { // The waiter is internal agent state, NOT an effect-scoped ctx.on listener: // disposing the OWNING fiber runs the agent's listener disposers, which would // have dropped a ctx.on-based waiter before the 'disposed' transition and - // hung the promise. With internal waiters, the fiber disposer still settles - // it. Regression for the round-3 whenIdle finding. + // hung the promise. With internal waiters, the fiber disposer still settles it. const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) let agent!: Agent diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index ec2412aff5..00eafa18cb 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -44,7 +44,7 @@ function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } -describe('HIGH: session log records what agent/step-result actually produced', () => { +describe('session log records what agent/step-result actually produced', () => { it('a step-result rewrite is what the log, derived history, and tool dispatch all see', async () => { const adapter = new MockAdapter([textResponse('original'), textResponse('done')]) const ctx = await harness(adapter) @@ -94,7 +94,7 @@ describe('HIGH: session log records what agent/step-result actually produced', ( }) }) -describe('HIGH: abort during tool execution ends the turn', () => { +describe('abort during tool execution ends the turn', () => { it('aborting the in-flight step inside a tool prevents both remaining tools and the next model step', async () => { const adapter = new MockAdapter([ // model asks for two tool calls in one step @@ -146,7 +146,7 @@ describe('HIGH: abort during tool execution ends the turn', () => { }) }) -describe('HIGH: steering from late extension points is never stranded', () => { +describe('steering from late extension points is never stranded', () => { it('steer() from an agent/turn-continuation listener overrides a stop decision', async () => { const adapter = new MockAdapter([ textResponse('no tools, would stop here'), @@ -268,7 +268,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { }) }) -describe('HIGH: plugin exceptions are contained', () => { +describe('plugin exceptions are contained', () => { it('a throwing agent/turn-continuation listener ends the turn with an error, loop survives', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) @@ -323,7 +323,7 @@ describe('HIGH: plugin exceptions are contained', () => { }) }) -describe('MEDIUM: disposed status is part of the agent/status contract', () => { +describe('disposed status is part of the agent/status contract', () => { it('disposing the fiber emits agent/status(disposed) and ends the turn with reason disposed', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) @@ -370,7 +370,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { }) }) -describe('MEDIUM: misc registry and config fixes', () => { +describe('misc registry and config fixes', () => { it('duplicate adapter registration is rejected', async () => { const ctx = new Context() await ctx.plugin(LlmService) @@ -529,7 +529,7 @@ describe('MEDIUM: misc registry and config fixes', () => { }) }) -describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () => { +describe('turn numbering continues across seeded (forked) sessions', () => { it('a forked agent continues turn numbers after the seed log', async () => { const first = new MockAdapter([textResponse('turn one')]) const ctx = await harness(first) @@ -567,7 +567,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () }) }) -describe('LOW: discriminated SessionEvent narrows without casts', () => { +describe('discriminated SessionEvent narrows without casts', () => { it('narrows event.data from event.type', () => { const session = new Session(SessionId('s')) const appended: SessionEvent = session.append('tool/call', { @@ -585,7 +585,7 @@ describe('LOW: discriminated SessionEvent narrows without casts', () => { }) }) -describe('HIGH: a finish-error stream chunk ends the turn as error, not completed', () => { +describe('a finish-error stream chunk ends the turn as error, not completed', () => { it('translates finish {kind:error} into a turn error with a logged error event', async () => { // The second sanctioned adapter error path (besides throwing): an // adapter that cannot throw mid-stream ends the stream with a From 60c4d523d1a868d6766b828a2e5a0771f7c42205 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 00:59:24 +0800 Subject: [PATCH 174/359] docs(tools): align schema default contract --- packages/core/tools/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/core/tools/README.md b/packages/core/tools/README.md index 0f7974e0f9..00bbb67ff5 100644 --- a/packages/core/tools/README.md +++ b/packages/core/tools/README.md @@ -142,7 +142,7 @@ The available tools: - **Native tool calls execute sequentially** — `ToolDefinition` carries no concurrency-safety metadata; adding it (and parallel execution in the loop) waits on the deferred tool-shapes review (`TODO(review)`). - **`tools/pre-execute` deliberately cannot rewrite `exec.arguments`** — logged and rendered args would desync from what ran; the rewrite design is [a proposed RFC](../../../docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md). -- **`defineTool`'s schema DSL is a deliberate subset** — string/number/boolean/object/array with string-only `enum`; `validateArgs` tolerates extra keys and never applies `default` (`XXX(unused-default)` flags removing that field); raw-registered JSON-Schema tools validate their own input. +- **`defineTool`'s schema DSL is a deliberate subset** — string/number/boolean/object/array with string-only `enum`; `validateArgs` tolerates extra keys and preserves `default` as a model-visible JSON Schema annotation without applying it during validation; dynamic Cordis mounts may supply defaults even though first-party definitions do not, while raw-registered JSON-Schema tools validate their own input. - **`timeoutMs` on a definition is declarative only** — the registry never enforces deadlines; enforcement requires the `@deepseek-ai/dsh-timeout-policy` wrapper. - **Code Mode is TypeScript-only and the presentation mode is service-wide** — `mode: code`/`both` rejects prompt assembly unless `ctx.codeRuntime.language === 'typescript'`; scoped restrictions/shadows still choose each agent's visible bindings, but one tool cannot be native-only while another is code-only. - **Code Mode bindings return text only** — non-text content blocks in a sub-call result collapse to `[ content]` placeholders. From c148090961bf8de680f6b210e5d0532b23c174b8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:07:59 +0800 Subject: [PATCH 175/359] test(sdk): cover invalid generated session ids --- packages/sdk/helper/tests/project.spec.ts | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/packages/sdk/helper/tests/project.spec.ts b/packages/sdk/helper/tests/project.spec.ts index 13fc046a04..bfaa8cbf77 100644 --- a/packages/sdk/helper/tests/project.spec.ts +++ b/packages/sdk/helper/tests/project.spec.ts @@ -873,6 +873,12 @@ describe('extension points', () => { resource.kind === 'cordis-config-entry' && resource.entry.id === 'acp') expect(acpEntry?.entry.id).toBe('acp') expect(acpEntry?.validateConfig?.({ model: '' })).toHaveLength(1) + const stdioEntry = builtins.get(featureId('app')).contribution(selection('app', ['stdio']), profile).resources + .find((resource): resource is CordisConfigEntryResource => + resource.kind === 'cordis-config-entry' && resource.entry.id === 'stdio') + expect(stdioEntry?.validateConfig?.({ welcome: 'ready', sessionId: 1 })).toEqual([ + 'sessionId must be a non-empty string', + ]) const embedOption = app.options.find(option => option.id === 'embed') expect(embedOption?.markerConfigEntries(profile)).toEqual([]) expect(embedOption?.contribution(profile, {}).resources.map(resource => resource.kind)).toEqual([ From a6e406a7782303ea5838007e8e85401e95ce4e01 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:16:52 +0800 Subject: [PATCH 176/359] docs(agent-loop): correct identity limitations --- packages/core/agent-loop/README.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 9a165fd66a..6028b2f97f 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -126,7 +126,6 @@ Everything that goes beyond "call the model, run the tools, repeat" belongs to p ## Known Limitations and Deferred Work - **Tool calls within a step execute sequentially** — parallel execution waits on concurrency-safety metadata in the tool contract (see `dsh-tools`). -- **No resume-or-create policy on the config path** — config-driven `create()` starts a fresh `${id}-session-` every run (`TODO(demo)`), and a config `resumeSessionId` whose resume fails logs a warning and creates no agent. +- **Config labels are fresh by default** — omitting `sessionId` creates a fresh `${id}-session-` on every startup; exact resume-or-create behavior requires an explicit stable `sessionId`, while `resumeSessionId` requires existing persisted history. - **Config agents have no per-agent persona field or setup hook** — they use the deployment persona; scoped persona/tool composition is available only through the programmatic `ctx.agents.create()` / `resume()` factory options. - **No built-in turn budget** — the default continuation is `continue` whenever a step had tool calls or steering; bounding a runaway turn requires an `agent/turn-continuation` force-stop plugin. -- **`runLoop`/`Inbox`/`InboxMessage` stay exported with no outside consumer** — [removal is proposed](../../../docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md). From 1a111654ae13b9dd448cc7166499c45247e20731 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:17:26 +0800 Subject: [PATCH 177/359] docs(subagent): restore local run identity contract --- packages/subagent/subagent/src/types.ts | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 67fcc99600..b0f228da96 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -134,9 +134,9 @@ export interface SubagentResult { */ export interface SubagentRun { /** - * Parent-scoped run id. A local run publishes a child session whose - * `parentSession` records `request.parent`; a remote provider mints an id - * unique in the parent namespace. + * Parent-scoped run id. For a local run, this MUST equal the published child + * session id, whose `parentSession` records `request.parent`; a remote + * provider mints an id unique in the parent namespace. */ readonly id: SessionId /** From 90220b235fcbdc506c6106a4c33cddd3faebacb1 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:17:46 +0800 Subject: [PATCH 178/359] docs(core): describe the public loop contract --- packages/core/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/core/README.md b/packages/core/README.md index 921591d85e..fdd8e3669e 100644 --- a/packages/core/README.md +++ b/packages/core/README.md @@ -9,7 +9,7 @@ The session log, system-prompt assembly, tool registry, agent vocabulary, and co | `system-prompt/` | Prompt-section + tool-schema assembly registry | `ctx.systemPrompt` | | `tools/` | Scoped tool registry + pre-policy, guards, around-dispatch, post-policy, and final-result observation | `ctx.tools` | | `agent/` | Agent interface, registry, `agent/*` event vocabulary | `ctx.agents` | -| `agent-loop/` | The concrete loop plugin: `ReactLoopAgent` + the loop driver | `ctx.agentLoop` | +| `agent-loop/` | Concrete plugin implementing the public `Agent` contract and owning the loop driver | `ctx.agentLoop` | `scope/` is the one non-service package here: a dependency-free library (`createScope`/`scopeOf`/`scopeTarget`) the registries and the loop build per-agent scoping on — it sits below `session/` and `system-prompt/` in the module graph precisely so they can consume it without a cycle. From d56cc8d42417c45c835c2f7576d16bab980eb428 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:00:56 +0800 Subject: [PATCH 179/359] fix(stdio): close startup failure gaps --- .../helper/src/templates/assets/index.ts.tpl | 31 ++++++++++++------- packages/sdk/helper/tests/project.spec.ts | 2 ++ packages/ui/stdio/README.md | 6 ++-- packages/ui/stdio/package.json | 5 +++ 4 files changed, 30 insertions(+), 14 deletions(-) diff --git a/packages/sdk/helper/src/templates/assets/index.ts.tpl b/packages/sdk/helper/src/templates/assets/index.ts.tpl index 4c3099199c..a79818908c 100644 --- a/packages/sdk/helper/src/templates/assets/index.ts.tpl +++ b/packages/sdk/helper/src/templates/assets/index.ts.tpl @@ -20,17 +20,26 @@ export async function main(boot: SdkBootContext) { {{/if}} const ctx = await startSDK(new URL('./cordis.yml', import.meta.url)) {{#if isStdio}} - if (resume === undefined) { - await ctx.agents.create({ - sessionId, - meta: { cwd: boot.cwd }, - agentOptions: { model }, - }) - } else { - await ctx.agents.resume({ - resumeSessionId: sessionId, - agentOptions: { model }, - }) + try { + if (resume === undefined) { + await ctx.agents.create({ + sessionId, + meta: { cwd: boot.cwd }, + agentOptions: { model }, + }) + } else { + await ctx.agents.resume({ + resumeSessionId: sessionId, + agentOptions: { model }, + }) + } + } catch (error) { + try { + await ctx.fiber.dispose() + } catch (disposeError) { + throw new AggregateError([error, disposeError], 'stdio startup and cleanup failed') + } + throw error } {{else}} {{#if isEmbed}} diff --git a/packages/sdk/helper/tests/project.spec.ts b/packages/sdk/helper/tests/project.spec.ts index bfaa8cbf77..655b308911 100644 --- a/packages/sdk/helper/tests/project.spec.ts +++ b/packages/sdk/helper/tests/project.spec.ts @@ -171,6 +171,8 @@ describe('SdkProject and ProjectEditSession', () => { expect(index).toContain('const sessionId = SessionId(resume ?? `main-session-${randomUUID()}`)') expect(index).toContain('process.env.DSH_SDK_SESSION_ID = sessionId') expect(index).toContain('resumeSessionId: sessionId') + expect(index).toContain('await ctx.fiber.dispose()') + expect(index).toContain("new AggregateError([error, disposeError], 'stdio startup and cleanup failed')") expect(project.packageManifest().scripts).toEqual({ dev: 'dsh-sdk dev index.ts -- --model="deepseek-v4-flash"', build: 'dsh-sdk build', diff --git a/packages/ui/stdio/README.md b/packages/ui/stdio/README.md index b7d320880d..f9cebe11e6 100644 --- a/packages/ui/stdio/README.md +++ b/packages/ui/stdio/README.md @@ -9,7 +9,7 @@ This package owns the terminal channel only. It injects `agents` and `userIntera | Key | Default | Meaning | |---|---|---| | `welcome` | `ready.` | Banner printed before the first prompt | -| `agent` | `main` | Agent id driven by stdin and observed for EOF shutdown | +| `sessionId` | `main` | Exact agent/session identity driven by stdin and observed for EOF shutdown | The plugin seeds display labels from the live agent registry, then tracks `agent/created` and `agent/disposed` so HMR and externally managed agents render consistently. Disposal closes readline and unregisters every listener/provider through Cordis effects. @@ -18,7 +18,7 @@ The plugin seeds display labels from the live agent registry, then tracks `agent name: '@deepseek-ai/dsh-stdio' config: welcome: 'agent REPL ready. Give it a coding task.' - agent: main + sessionId: main ``` ## Model Experience @@ -37,6 +37,6 @@ The plugin seeds display labels from the live agent registry, then tracks `agent ## Known Limitations and Deferred Work -- **One configured agent receives stdin** — the session/event renderer can print output from any session, but input lines always drive the configured `agent` id rather than routing by the visible label. +- **One configured session receives stdin** — the session/event renderer can print output from any session, but input lines always drive the configured `sessionId` rather than routing by the visible label. - **Terminal questions are text-only and sequential** — the provider queues asks, supports option labels plus custom text, and has no richer UI shapes such as file pickers or diff previews. - **Closed stdin ends the terminal channel** — EOF rejects active or queued questions and exits after submitted work reaches idle; there is no reconnect path for a long-lived process. diff --git a/packages/ui/stdio/package.json b/packages/ui/stdio/package.json index 1c7311d0cb..e1bffdf171 100644 --- a/packages/ui/stdio/package.json +++ b/packages/ui/stdio/package.json @@ -29,6 +29,11 @@ "@deepseek-ai/dsh-user-interaction": "^0.0.1", "cordis": "^4.0.0-rc.7" }, + "peerDependenciesMeta": { + "@deepseek-ai/dsh-agent-loop": { + "optional": true + } + }, "dependencies": { "schemastery": "^3.18.0" }, From 3855a77e7d8b779c74c53cbbe7736a6a29563ba2 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:04:04 +0800 Subject: [PATCH 180/359] docs(approval): qualify audit guarantees --- .../implemented/feature/2026-07-06-approval-seam.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 9f4968c3a4..0945228593 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -25,7 +25,7 @@ One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-ou The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-demo`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its bridge registers an answerer that prompts the owning editor session via `session/request_permission`, so a hook's `ask` or an escalation request surfaces as a one-shot Allow/Reject prompt attached to the already-streamed tool call. `policy: never` is the unattended stance — every ask auto-rejects deterministically, stated in the system prompt, no human in the loop. `policy` is validated against the closed list at plugin load; anything else throws. -What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; every ask lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. +What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; a successful in-turn request lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. An idle request or audit append failure rejects instead of returning an unaudited decision. One ask under this composition, verbatim from the sandbox example's recorded `escalation-approved` scenario — the model requests a sandbox escalation, the gate asks, the bridge prompts the owning editor, the user clicks Allow once: @@ -71,7 +71,7 @@ The answerer routes through the bridge's exact-agent ownership check described b #### Audit, and what the model sees -`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. One `decided` lands per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. +`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. Successful request completion commits one `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. An idle request appends neither event; a pre-commit append failure rejects, and failure of the second append can leave the already-committed `asked` without a `decided`. #### Entities and dependencies @@ -105,7 +105,7 @@ The implemented contract is pinned by the suites in Testing: - With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason. - A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)). - Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection. -- Every `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; post-append observer failures cannot split the pair. +- Every successful `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; idle and pre-commit failures reject, while post-append observer failures cannot split the pair. - Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor. - A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request. @@ -113,7 +113,7 @@ Costs and accepted limits: - **Two decide-eager answerers race for the slot.** Sibling-plugin listener order is not deterministic, so the seam cannot referee competing terminal answerers — mitigated by convention (one terminal answerer per deployment; `prepend` only for decide-or-delegate gates) rather than a priority mechanism the event bus does not have. - **Production exercise rests on one composition.** `ask` has two producer families — the hook bridges through `tools/pre-execute`, and sandbox escalation through its own gate — with the wire recorded in the sandbox example's snapshot suite, so the seam's real-world coverage is that one composition until more deployments compose it. -- **Ownership keys on `Agent` object identity.** The answerer resolves sessions through the bridge's existing WeakMap; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need session-id matching instead. +- **Ownership keys on `Agent` object identity.** The answerer resolves the forward session-map record at `agent.session.id`, then requires that record to own the exact agent object; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need a different ownership contract. ## FAQ @@ -123,10 +123,10 @@ Behavioral and usage questions only — every "why not X?" design question lives - **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred). - **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel. - **Who decides whether a call asks in the first place?** Policy producers: a hook returning `permissionDecision: ask`, any `tools/pre-execute` listener, or the sandbox escalation gate. The seam and the bridge only route and answer; neither injects its own judgment about what deserves a prompt. -- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer — one audit pair either way, never two. +- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer. When both audit appends commit, either path records one pair, never two. - **What if the client answers with an option the harness never offered?** Any selection other than the offered `allow_once` maps to `rejected` — an unknown optionId from a non-conforming client can never grant. - **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are deliberately unanswerable. `subagent-acp`'s child-side auto-answer is separate; routing a child's asks to the parent's editor is deferred (§ Deferred). -- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; the audit pair still lands for every auto-rejection. +- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; each successful auto-rejection records the audit pair. - **What happens across a hot reload, or when the UI plugin unloads mid-session?** Answerers dispose with their owning fiber, so the next ask degrades to `unavailable` instead of hanging on a dead channel; remounting re-registers the answerer with no catch-up state. - **Where does the user see what they are approving?** On the tool call itself: the prompt attaches to the already-streamed call via `callId` — arguments included — and adds the asker's human-readable `reason`; the request carries no argument copy of its own. From 3befcfc566b4deec276d600df993949f6e49facc Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:04:47 +0800 Subject: [PATCH 181/359] Revert "docs(approval): qualify audit guarantees" This reverts commit 14439a93c2bb915441e7b59f505d94a79b22d4af. --- .../implemented/feature/2026-07-06-approval-seam.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 0945228593..9f4968c3a4 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -25,7 +25,7 @@ One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-ou The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-demo`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its bridge registers an answerer that prompts the owning editor session via `session/request_permission`, so a hook's `ask` or an escalation request surfaces as a one-shot Allow/Reject prompt attached to the already-streamed tool call. `policy: never` is the unattended stance — every ask auto-rejects deterministically, stated in the system prompt, no human in the loop. `policy` is validated against the closed list at plugin load; anything else throws. -What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; a successful in-turn request lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. An idle request or audit append failure rejects instead of returning an unaudited decision. +What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; every ask lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. One ask under this composition, verbatim from the sandbox example's recorded `escalation-approved` scenario — the model requests a sandbox escalation, the gate asks, the bridge prompts the owning editor, the user clicks Allow once: @@ -71,7 +71,7 @@ The answerer routes through the bridge's exact-agent ownership check described b #### Audit, and what the model sees -`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. Successful request completion commits one `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. An idle request appends neither event; a pre-commit append failure rejects, and failure of the second append can leave the already-committed `asked` without a `decided`. +`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. One `decided` lands per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. #### Entities and dependencies @@ -105,7 +105,7 @@ The implemented contract is pinned by the suites in Testing: - With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason. - A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)). - Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection. -- Every successful `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; idle and pre-commit failures reject, while post-append observer failures cannot split the pair. +- Every `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; post-append observer failures cannot split the pair. - Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor. - A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request. @@ -113,7 +113,7 @@ Costs and accepted limits: - **Two decide-eager answerers race for the slot.** Sibling-plugin listener order is not deterministic, so the seam cannot referee competing terminal answerers — mitigated by convention (one terminal answerer per deployment; `prepend` only for decide-or-delegate gates) rather than a priority mechanism the event bus does not have. - **Production exercise rests on one composition.** `ask` has two producer families — the hook bridges through `tools/pre-execute`, and sandbox escalation through its own gate — with the wire recorded in the sandbox example's snapshot suite, so the seam's real-world coverage is that one composition until more deployments compose it. -- **Ownership keys on `Agent` object identity.** The answerer resolves the forward session-map record at `agent.session.id`, then requires that record to own the exact agent object; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need a different ownership contract. +- **Ownership keys on `Agent` object identity.** The answerer resolves sessions through the bridge's existing WeakMap; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need session-id matching instead. ## FAQ @@ -123,10 +123,10 @@ Behavioral and usage questions only — every "why not X?" design question lives - **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred). - **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel. - **Who decides whether a call asks in the first place?** Policy producers: a hook returning `permissionDecision: ask`, any `tools/pre-execute` listener, or the sandbox escalation gate. The seam and the bridge only route and answer; neither injects its own judgment about what deserves a prompt. -- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer. When both audit appends commit, either path records one pair, never two. +- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer — one audit pair either way, never two. - **What if the client answers with an option the harness never offered?** Any selection other than the offered `allow_once` maps to `rejected` — an unknown optionId from a non-conforming client can never grant. - **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are deliberately unanswerable. `subagent-acp`'s child-side auto-answer is separate; routing a child's asks to the parent's editor is deferred (§ Deferred). -- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; each successful auto-rejection records the audit pair. +- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; the audit pair still lands for every auto-rejection. - **What happens across a hot reload, or when the UI plugin unloads mid-session?** Answerers dispose with their owning fiber, so the next ask degrades to `unavailable` instead of hanging on a dead channel; remounting re-registers the answerer with no catch-up state. - **Where does the user see what they are approving?** On the tool call itself: the prompt attaches to the already-streamed call via `callId` — arguments included — and adds the asker's human-readable `reason`; the request carries no argument copy of its own. From 70c6c0ac39aacf14ab0b627319b192fd1ca6f03b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:04:04 +0800 Subject: [PATCH 182/359] docs(approval): qualify audit guarantees --- .../implemented/feature/2026-07-06-approval-seam.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 9f4968c3a4..0945228593 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -25,7 +25,7 @@ One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-ou The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-demo`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its bridge registers an answerer that prompts the owning editor session via `session/request_permission`, so a hook's `ask` or an escalation request surfaces as a one-shot Allow/Reject prompt attached to the already-streamed tool call. `policy: never` is the unattended stance — every ask auto-rejects deterministically, stated in the system prompt, no human in the loop. `policy` is validated against the closed list at plugin load; anything else throws. -What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; every ask lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. +What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; a successful in-turn request lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. An idle request or audit append failure rejects instead of returning an unaudited decision. One ask under this composition, verbatim from the sandbox example's recorded `escalation-approved` scenario — the model requests a sandbox escalation, the gate asks, the bridge prompts the owning editor, the user clicks Allow once: @@ -71,7 +71,7 @@ The answerer routes through the bridge's exact-agent ownership check described b #### Audit, and what the model sees -`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. One `decided` lands per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. +`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. Successful request completion commits one `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. An idle request appends neither event; a pre-commit append failure rejects, and failure of the second append can leave the already-committed `asked` without a `decided`. #### Entities and dependencies @@ -105,7 +105,7 @@ The implemented contract is pinned by the suites in Testing: - With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason. - A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)). - Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection. -- Every `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; post-append observer failures cannot split the pair. +- Every successful `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; idle and pre-commit failures reject, while post-append observer failures cannot split the pair. - Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor. - A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request. @@ -113,7 +113,7 @@ Costs and accepted limits: - **Two decide-eager answerers race for the slot.** Sibling-plugin listener order is not deterministic, so the seam cannot referee competing terminal answerers — mitigated by convention (one terminal answerer per deployment; `prepend` only for decide-or-delegate gates) rather than a priority mechanism the event bus does not have. - **Production exercise rests on one composition.** `ask` has two producer families — the hook bridges through `tools/pre-execute`, and sandbox escalation through its own gate — with the wire recorded in the sandbox example's snapshot suite, so the seam's real-world coverage is that one composition until more deployments compose it. -- **Ownership keys on `Agent` object identity.** The answerer resolves sessions through the bridge's existing WeakMap; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need session-id matching instead. +- **Ownership keys on `Agent` object identity.** The answerer resolves the forward session-map record at `agent.session.id`, then requires that record to own the exact agent object; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need a different ownership contract. ## FAQ @@ -123,10 +123,10 @@ Behavioral and usage questions only — every "why not X?" design question lives - **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred). - **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel. - **Who decides whether a call asks in the first place?** Policy producers: a hook returning `permissionDecision: ask`, any `tools/pre-execute` listener, or the sandbox escalation gate. The seam and the bridge only route and answer; neither injects its own judgment about what deserves a prompt. -- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer — one audit pair either way, never two. +- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer. When both audit appends commit, either path records one pair, never two. - **What if the client answers with an option the harness never offered?** Any selection other than the offered `allow_once` maps to `rejected` — an unknown optionId from a non-conforming client can never grant. - **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are deliberately unanswerable. `subagent-acp`'s child-side auto-answer is separate; routing a child's asks to the parent's editor is deferred (§ Deferred). -- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; the audit pair still lands for every auto-rejection. +- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; each successful auto-rejection records the audit pair. - **What happens across a hot reload, or when the UI plugin unloads mid-session?** Answerers dispose with their owning fiber, so the next ask degrades to `unavailable` instead of hanging on a dead channel; remounting re-registers the answerer with no catch-up state. - **Where does the user see what they are approving?** On the tool call itself: the prompt attaches to the already-streamed call via `callId` — arguments included — and adds the asker's human-readable `reason`; the request carries no argument copy of its own. From c2cf2cbbd846f477e6b3674b095a87e5ed0aa2c0 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:05:44 +0800 Subject: [PATCH 183/359] test(agent-loop): name regression contracts --- packages/core/agent-loop/tests/contract-regressions.spec.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 00eafa18cb..098a53261c 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -370,7 +370,7 @@ describe('disposed status is part of the agent/status contract', () => { }) }) -describe('misc registry and config fixes', () => { +describe('registration, request routing, and queued-input ownership contracts', () => { it('duplicate adapter registration is rejected', async () => { const ctx = new Context() await ctx.plugin(LlmService) From b2064cba10f3a0c19ca24472f0ee7d7f81c1816f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:26:57 +0800 Subject: [PATCH 184/359] fix(agent-loop): reject duplicate configured identities --- packages/core/agent-loop/src/index.ts | 22 ++++++++++++++++--- .../tests/config-session-id.spec.ts | 19 ++++++++++++++++ 2 files changed, 38 insertions(+), 3 deletions(-) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 325ba7b92d..7144ae8dfb 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -369,6 +369,24 @@ export interface Config { })[] } +/** Reject self-contained identity conflicts before any configured agent starts. */ +function validateConfiguredAgents(agents: Config['agents']): void { + const exactIdentities = new Map() + for (const { id, sessionId, resumeSessionId } of agents) { + const hasResumeId = resumeSessionId !== undefined && resumeSessionId !== '' + if (sessionId !== undefined && hasResumeId) { + throw new Error(`agent "${id}": sessionId and resumeSessionId are mutually exclusive`) + } + const exactIdentity = hasResumeId ? resumeSessionId : sessionId + if (exactIdentity === undefined) continue + const firstId = exactIdentities.get(exactIdentity) + if (firstId !== undefined) { + throw new Error(`agents "${firstId}" and "${id}" use duplicate exact session identity "${exactIdentity}"`) + } + exactIdentities.set(exactIdentity, id) + } +} + /** Concrete ReactLoopAgent factory and driver service. */ export class AgentLoop extends Service implements AgentFactory { static inject = ['agents', 'sessions', 'llm', 'tools', 'systemPrompt'] @@ -390,6 +408,7 @@ export class AgentLoop extends Service implements AgentFactory { constructor(ctx: Context, public config: Config) { super(ctx, 'agentLoop') + validateConfiguredAgents(config.agents) this.ownership = new FactoryOwnership(ctx.fiber) this.runtime = { ctx } ctx.effect(() => () => this.ownership.dispose(), 'agentLoop.transactions()') @@ -412,9 +431,6 @@ export class AgentLoop extends Service implements AgentFactory { } continue } - if (sessionId !== undefined) { - throw new Error(`agent "${id}": sessionId and resumeSessionId are mutually exclusive`) - } ctx.effect(() => { const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => { void this.resumeWith(ctx, childCtx.sessionPersistence, { diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index bd2a5522df..56cc0bee40 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -64,6 +64,25 @@ describe('config-driven session id', () => { await conflicting.fiber.dispose() }) + it('rejects duplicate exact ids before asynchronous configured startup', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-duplicate-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + + const outcome = await ctx.plugin(AgentLoop, { + agents: [ + { id: 'first', sessionId: SessionId('shared'), model: 'mock' }, + { id: 'second', sessionId: SessionId('shared'), model: 'mock' }, + ], + }).then(() => undefined, (error: unknown) => error) + const published = ctx.agents.get(SessionId('shared')) + await ctx.fiber.dispose() + + expect(outcome).toEqual(new Error('agents "first" and "second" use duplicate exact session identity "shared"')) + expect(published).toBeUndefined() + }) + it('restores a materialized exact id across an AgentLoop-only reload', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-reload-')) dirs.push(root) From 042d752fd2ca7f8699011275b03a952935a0a54a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:26:57 +0800 Subject: [PATCH 185/359] docs(repeat-guard): trim module orientation --- packages/guard/repeat-tool-guard/src/index.ts | 37 ++----------------- 1 file changed, 4 insertions(+), 33 deletions(-) diff --git a/packages/guard/repeat-tool-guard/src/index.ts b/packages/guard/repeat-tool-guard/src/index.ts index d51df1d829..bd6c5a4404 100644 --- a/packages/guard/repeat-tool-guard/src/index.ts +++ b/packages/guard/repeat-tool-guard/src/index.ts @@ -1,37 +1,8 @@ /** - * Repeat-tool-call guard: advisory loop-breaker for agents stuck re-issuing - * the same tool call with identical arguments. - * - * Not a model-facing tool — it registers no tool, never vetoes or rewrites a - * call, and adds exactly one behavior: watch each agent's stream of tool calls - * through the `tools/post-execute` waterfall, count runs of consecutive calls - * to the same tool with identical canonicalized arguments, and at configured - * run lengths fold an escalating advisory reminder onto the decision's - * `additionalContext`. The loop appends that context as a logged - * `context/message` after the step's tool results, so the reminder is - * model-visible, source-attributed, and reconstructable from the session log - * with no new session event. Decision record: - * docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md. - * - * ```yaml - * - id: repeat-tool-guard - * name: '@deepseek-ai/dsh-repeat-tool-guard' - * config: - * thresholds: [3, 5, 8] # consecutive counts that trigger a reminder - * include: [] # tool-name patterns to track; empty = all tools - * exclude: [todo_write] # tool-name patterns transparent to the chain - * ``` - * - * Chain state is keyed by the live agent object — the tool registry is a - * context-level singleton whose waterfalls interleave every agent's calls, so - * a shared counter would let one agent's repetition trip another's reminder. - * State is in-memory only: a session resumed from persistence starts with a - * fresh chain (the guard is a heuristic nudge, not a logged invariant). - * - * Plugin export shape: named exports, NO default. The cordis Loader's - * `unwrapExports` does `exports.default ?? exports`, so a stray default would - * collapse the module to the bare `apply` (see docs/postmortem/0001). - * + * Advisory per-agent repeat-call detector. It enriches post-execute decisions + * with logged model context without vetoing or rewriting calls. Configuration + * and chain semantics live in the package README; rationale lives in the + * repeat-tool-guard RFC. * @module @deepseek-ai/dsh-repeat-tool-guard */ From 68b5c716b1265590f5f2936c33f9760b12c8d1db Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:29:08 +0800 Subject: [PATCH 186/359] docs(catalog): refresh AgentLoop source link --- docs/cordis-catalog/services.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 85e07f8191..f83f2bf616 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:373`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:391`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` From b77cfd64a1cba70c1c2168d370aeab3108989a12 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:29:32 +0800 Subject: [PATCH 187/359] docs(catalog): refresh repeat guard source link --- docs/config-catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 46645b0575..29d37dd6db 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -548,7 +548,7 @@ export interface Config { } ``` -Source: [`packages/guard/repeat-tool-guard/src/index.ts:55`](../packages/guard/repeat-tool-guard/src/index.ts) +Source: [`packages/guard/repeat-tool-guard/src/index.ts:26`](../packages/guard/repeat-tool-guard/src/index.ts) ## `@deepseek-ai/dsh-sandbox-local` From 69c36e4fb5a6bceff4f44a8ba81ee8deb68fc1e8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:31:20 +0800 Subject: [PATCH 188/359] docs(subagent): name parent session lineage --- packages/subagent/subagent/src/types.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index b0f228da96..e5ba8fd84d 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -135,8 +135,8 @@ export interface SubagentResult { export interface SubagentRun { /** * Parent-scoped run id. For a local run, this MUST equal the published child - * session id, whose `parentSession` records `request.parent`; a remote - * provider mints an id unique in the parent namespace. + * session id, whose `parentSession` records `request.parent.session.id`; a + * remote provider mints an id unique in the parent namespace. */ readonly id: SessionId /** From 9366baf39fd84f169e1df7f42048088b5cc0c790 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:31:26 +0800 Subject: [PATCH 189/359] docs(acp): describe session terminal rendering --- packages/ui/acp/src/index.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 8bb25df579..d9c53cebf0 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -1049,7 +1049,7 @@ function validateMcpServers(params: { mcpServers?: unknown[] }): void { * zero or more times per event (best-effort UI feed, never load-bearing). * @param presenter - resolves tool-owned render intent for tool events; * defaults to the generic-fallback {@link nullToolPresenter}. - * @param terminal - the connection's terminal-rendering context; defaults to + * @param terminal - the session's terminal-rendering context; defaults to * disabled (the plain-text console-block fallback). * @param options - `includeUserMessages` (default `true`): live streaming * passes `false` so a prompt the client just sent is not echoed back. @@ -1122,7 +1122,7 @@ export function todosToPlan(todos: TodoItem[]): Plan { } /** - * Per-connection terminal-rendering context threaded into + * Per-session terminal-rendering context threaded into * {@link streamSessionEventUpdate}: whether the client advertised the * `_meta.terminal_output` capability, and the session's workspace cwd (the * default terminal-card header when a tool doesn't supply its own). Kept out of From 2f1a40d9381aea67badc63f7c1d30e5cda5c0f02 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:35:31 +0800 Subject: [PATCH 190/359] docs(catalog): refresh AgentLoop source link --- docs/cordis-catalog/services.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 7cc00a407a..44490c39f0 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,9 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:391`](../../packages/core/agent-loop/src/index.ts) +Types: [Agent](../core-data-structures/core.md) + +Source: [`packages/core/agent-loop/src/index.ts:390`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` From 4c08629b58ef493da1a02e0dcff9eed4d4eb1980 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:56:12 +0800 Subject: [PATCH 191/359] docs(acp): describe concurrent update routing --- packages/ui/acp/src/index.ts | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index d9c53cebf0..7b5cb11324 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -20,11 +20,12 @@ * Multi-session (RFC 011): N concurrent sessions per connection, each mapped to * its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id; * every `session/event` and `agent/*` event is routed strictly to its owning - * session record, so two sessions streaming at once never interleave their - * `session/update` notifications. Permission prompts use the same identity: the - * bridge answers `approval/request` for its own agents over - * `session/request_permission` (see the approval answerer below) — whether a - * call ASKS is policy (a hook or plugin returning `ask`), not the bridge's. + * session record, and each `session/update` carries that id. Concurrent updates + * may alternate on the shared connection without crossing session attribution. + * Permission prompts use the same identity: the bridge answers + * `approval/request` for its own agents over `session/request_permission` (see + * the approval answerer below) — whether a call ASKS is policy (a hook or + * plugin returning `ask`), not the bridge's. * * stdout is the protocol: this plugin must run in an example that loads NO * stdout logger (the console logger writes to stdout and would corrupt the @@ -483,8 +484,8 @@ export function apply(ctx: Context, config: AcpConfig): void { // whose end arrives late is ignored (see // SessionRecord.inflight). A turn that ends `error` REJECTS the prompt (ACP // has no error stop reason); other reasons resolve via the codec. Demux - // strictly by session id: a `session/event` is routed to its own record, so - // two sessions streaming at once never cross-settle or interleave updates. + // strictly by session id: concurrent updates may alternate on the shared + // connection, but they retain the owning id and never cross-settle. ctx.on('session/event', (session, event: SessionEvent) => { const rec = sessions.get(session.header.id) if (rec === undefined) return From 486362d2f8a6de1aee998cee320046d5c3db1a8d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:57:32 +0800 Subject: [PATCH 192/359] docs(catalog): refresh ACP config source link --- docs/config-catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 4300404cfb..cb5aebbdf8 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -31,7 +31,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:244`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:245`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-demo` From f7af6a87dcf06397bb66b91fd851572e31385815 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 03:25:21 +0800 Subject: [PATCH 193/359] docs(acp): describe terminal capability lifetime --- packages/ui/acp/src/index.ts | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 7b5cb11324..a12249d0b5 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -359,10 +359,10 @@ export function apply(ctx: Context, config: AcpConfig): void { // await and NOT install a record (which would resurrect a live agent/listeners // after the bridge closed). Checked after every load await. let closed = false - // Whether the client advertised the Zed `_meta.terminal_output` capability in - // `initialize`. When true, a tool's terminal presentation is rendered as a - // terminal card (content + `_meta.terminal_*`); when false, the bridge uses - // the tool's text fallback. Set once in `initialize`, read on every tool event. + // Connection-level terminal capability from the latest `initialize`; false + // before initialization. Each `session/new` or `session/load` snapshots it in + // `SessionRecord.terminalEnabled`, so later initialization affects only future + // sessions. let terminalOutputCap = false // Assigned at the bottom, before any agent event can fire (a session only From 7250aaea7eabbe4de1a32075f4f785870d38e5c2 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 10:07:11 +0800 Subject: [PATCH 194/359] fix(sdk): compose token meter for compact projects --- docs/architecture.md | 6 +++--- packages/sdk/helper/package.json | 1 - pnpm-lock.yaml | 32 +++++++++++++++----------------- 3 files changed, 18 insertions(+), 21 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index b5dc852a6b..63a5f07a61 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -24,7 +24,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service | ctx key | Package family | Role | |---|---|---| | `ctx.llm` | [`llm/`](../packages/llm/README.md) | adapter registry and streaming model calls | -| `ctx.tokenMeter` | [`llm/token-meter`](../packages/llm/token-meter/README.md) | replay-aware per-model request and surface pressure | +| `ctx.tokenMeter` | [`llm/token-meter`](../packages/llm/token-meter/README.md) | replay-aware request/surface pressure per model | | `ctx.bash` | [`bash/`](../packages/bash/README.md) | foreground/background command execution | | `ctx.sandbox` | [`sandbox/`](../packages/sandbox/README.md) | same-world process confinement (argv wrapping, per-call policy) | | `ctx.codeRuntime` | [`code-runtime/`](../packages/code-runtime/README.md) | model-written program execution | @@ -82,7 +82,7 @@ forever: agent/request (config only) -> log request/header -> llm/stream (frozen) 'assistant/chunk' agent/step-result - 'assistant/message' (transformed content, or an empty successful-call anchor if step-result rejects) + 'assistant/message' (transformed content or empty success anchor after step-result rejection) each tool call: 'tool/call' tools/pre-execute -> monotonic guards -> tools/execute -> tools/post-execute -> tools/result @@ -126,7 +126,7 @@ Durability is a plugin concern. Persistence backends buffer synchronous `session ### Model Content -Messages are arrays of typed content blocks (`text`, `reasoning`, `tool-call`, `tool-result`). The union derives from the merge-extensible `ContentBlockMap`; the same pattern types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New block types are coordinated across adapters, UI bridges, token metering, and persistence, so block types remain a repo-wide contract. Replay measurement types are cataloged in [token-meter.md](core-data-structures/token-meter.md). +Messages are arrays of typed content blocks (`text`, `reasoning`, `tool-call`, `tool-result`). The union derives from the merge-extensible `ContentBlockMap`; the same pattern types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New block types require coordinated adapter, UI, token-meter, and persistence changes; replay measurement types live in [token-meter.md](core-data-structures/token-meter.md). Streaming is a raw chunk protocol (`block-start` through `finish`) with `BlockAssembler` as the shared chunk-to-block assembler. The loop logs raw chunks while assembling them for dispatch. `LlmAdapter` is the provider seam: subclass, implement `stream()`, and register with `ctx.llm.registerAdapter(models, adapter)`. StreamChunk conventions live in [llm-streaming.md](core-data-structures/llm-streaming.md). diff --git a/packages/sdk/helper/package.json b/packages/sdk/helper/package.json index 1452a1dbee..8d95dafe66 100644 --- a/packages/sdk/helper/package.json +++ b/packages/sdk/helper/package.json @@ -33,7 +33,6 @@ }, "devDependencies": { "@deepseek-ai/dsh-brand": "workspace:^", - "@deepseek-ai/dsh-compact-basic": "workspace:^", "@deepseek-ai/dsh-hooks-claude": "workspace:^", "@deepseek-ai/dsh-hooks-codex": "workspace:^", "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 0440d83eb0..334a95346d 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -832,7 +832,7 @@ importers: dependencies: '@earendil-works/pi-ai': specifier: ^0.79.1 - version: 0.79.3(ws@8.21.0)(zod@4.4.3) + version: 0.79.3(@modelcontextprotocol/sdk@1.29.0(zod@4.4.3))(ws@8.21.0)(zod@4.4.3) schemastery: specifier: ^3.18.0 version: 3.18.0 @@ -953,9 +953,6 @@ importers: '@deepseek-ai/dsh-brand': specifier: workspace:^ version: link:../../util/brand - '@deepseek-ai/dsh-compact-basic': - specifier: workspace:^ - version: link:../../compact/compact-basic '@deepseek-ai/dsh-hooks-claude': specifier: workspace:^ version: link:../../hooks/hooks-claude @@ -3091,6 +3088,10 @@ packages: cpu: [x64] os: [win32] + '@pkgjs/parseargs@0.11.0': + resolution: {integrity: sha512-+1VkjdD0QBLPodGrJUeqarH8VAIvQODIbwh9XpP5Syisf7YoQgsJKPNFoqqLQlu+VQ/tVSshMR6loPMn8U+dPg==} + engines: {node: '>=14'} + '@protobufjs/aspromise@1.1.2': resolution: {integrity: sha512-j+gKExEuLmKwvz3OgROXtrJ2UG2x8Ch2YZUxahh+s1F2HZ+wAceUNLkvy6zKCPVRkU++ZWQrdxsUeQXmcg4uoQ==} @@ -5557,11 +5558,6 @@ packages: engines: {node: '>=14.17'} hasBin: true - uglify-js@3.19.3: - resolution: {integrity: sha512-v3Xu+yuwBXisp6QYTcH4UbH+xYJXqnq2m/LtQVWKWzYc1iehYnLixoQDN9FH6/j9/oybfd6W9Ghwkl8+UMKTKQ==} - engines: {node: '>=0.8.0'} - hasBin: true - unbash@3.0.0: resolution: {integrity: sha512-FeFPZ/WFT0mbRCuydiZzpPFlrYN8ZUpphQKoq4EeElVIYjYyGzPMxQR/simUwCOJIyVhpFk4RbtyO7RuMpMnHA==} engines: {node: '>=14'} @@ -6169,11 +6165,11 @@ snapshots: '@csstools/css-tokenizer@4.0.0': {} - '@earendil-works/pi-ai@0.79.3(ws@8.21.0)(zod@4.4.3)': + '@earendil-works/pi-ai@0.79.3(@modelcontextprotocol/sdk@1.29.0(zod@4.4.3))(ws@8.21.0)(zod@4.4.3)': dependencies: '@anthropic-ai/sdk': 0.91.1(zod@4.4.3) '@aws-sdk/client-bedrock-runtime': 3.1048.0 - '@google/genai': 1.52.0 + '@google/genai': 1.52.0(@modelcontextprotocol/sdk@1.29.0(zod@4.4.3)) '@mistralai/mistralai': 2.2.1 '@smithy/node-http-handler': 4.7.3 http-proxy-agent: 7.0.2 @@ -6331,12 +6327,14 @@ snapshots: '@exodus/bytes@1.15.1': {} - '@google/genai@1.52.0': + '@google/genai@1.52.0(@modelcontextprotocol/sdk@1.29.0(zod@4.4.3))': dependencies: google-auth-library: 10.7.0 p-retry: 4.6.2 protobufjs: 7.6.4 ws: 8.21.0 + optionalDependencies: + '@modelcontextprotocol/sdk': 1.29.0(zod@4.4.3) transitivePeerDependencies: - bufferutil - supports-color @@ -6595,6 +6593,9 @@ snapshots: '@oxc-resolver/binding-win32-x64-msvc@11.20.0': optional: true + '@pkgjs/parseargs@0.11.0': + optional: true + '@protobufjs/aspromise@1.1.2': {} '@protobufjs/base64@1.1.2': {} @@ -7959,8 +7960,6 @@ snapshots: neo-async: 2.6.2 source-map: 0.6.1 wordwrap: 1.0.0 - optionalDependencies: - uglify-js: 3.19.3 has-flag@4.0.0: {} @@ -8066,6 +8065,8 @@ snapshots: jackspeak@3.4.3: dependencies: '@isaacs/cliui': 8.0.2 + optionalDependencies: + '@pkgjs/parseargs': 0.11.0 jiti@2.7.0: {} @@ -9306,9 +9307,6 @@ snapshots: typescript@6.0.3: {} - uglify-js@3.19.3: - optional: true - unbash@3.0.0: {} unconfig-core@7.5.0: From 4bf36e4dd153e97d47118881e96134f494da4671 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 10:29:08 +0800 Subject: [PATCH 195/359] docs: condense tool-context lifecycle contract --- docs/architecture.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/architecture.md b/docs/architecture.md index ce3f4898a2..2637f09f71 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -97,7 +97,7 @@ forever: The loop renders one prompt assembly per step. Plugins contribute ordered sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn instead of shipping a hole. `dsh-system-prompt` owns the harness identity and default deployment persona; an agent-scoped persona may shadow the default. The loop supplies `model` and `cwd`. See the [prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md). -Context that arrives while the current tool-call batch executes—including asynchronous `agent.inject()` notices and post-tool `additionalContext`—waits until execution settles and lands after every recorded result; successful batches keep call/result adjacency stable, while interrupted batches drain accepted context before the turn closes. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved. +Context accepted during tool execution—including async `agent.inject()` notices and post-tool `additionalContext`—waits for settlement, then follows every recorded result. Successful batches preserve call/result adjacency; interrupted batches drain that context before turn closure. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved. ### Failure Boundaries From a6c8775f121abb846f1dab0e3b5c09a40f45632f Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 11:08:59 +0800 Subject: [PATCH 196/359] fix(session): reject sparse provenance arrays --- packages/core/session/src/surface.ts | 79 ++++++++++--------- packages/core/session/tests/surface.spec.ts | 1 + .../session-query/tests/tracing.spec.ts | 3 + 3 files changed, 46 insertions(+), 37 deletions(-) diff --git a/packages/core/session/src/surface.ts b/packages/core/session/src/surface.ts index d585ab9798..1662d2d80d 100644 --- a/packages/core/session/src/surface.ts +++ b/packages/core/session/src/surface.ts @@ -123,8 +123,8 @@ function isReplaceOp(value: object): value is Extract= event.seq) { - throw new Error(`sourceEventSeqs must reference earlier events: ${source} >= current seq ${event.seq}`) + const raw = (event as SessionEvent & { sourceEventSeqs?: unknown }).sourceEventSeqs + const sources = new Set() + if (raw !== undefined) { + if (!Array.isArray(raw)) { + throw new Error(`sourceEventSeqs on event at seq ${event.seq} must be an array when present`) + } + if (raw.length === 0) { + throw new Error('sourceEventSeqs must not be empty when present') + } + let nonEarlierSource: number | undefined + for (const source of raw) { + if (!isEventSeq(source)) { + throw new Error(`session event "${event.type}" sourceEventSeqs must densely contain non-negative safe integers`) + } + sources.add(source) + if (nonEarlierSource === undefined && source >= event.seq) nonEarlierSource = source + } + if (sources.size !== raw.length) { + throw new Error('sourceEventSeqs must not contain duplicates') + } + if (nonEarlierSource !== undefined) { + throw new Error(`sourceEventSeqs must reference earlier events: ${nonEarlierSource} >= current seq ${event.seq}`) } } - const missing = shadowedSeqs.filter(seq => !sourceSet.has(seq)) + const missing = shadowedSeqs.filter(seq => !sources.has(seq)) if (missing.length > 0) { throw new Error(`surface replace: sourceEventSeqs must include every shadowed surface node; missing ${missing.join(', ')}`) } @@ -213,19 +218,19 @@ function planSurfaceEvent( if (event.seq !== expectedSeq) { throw new Error(`session event seq ${event.seq} is not contiguous; expected ${expectedSeq}`) } - const surfaceEvent = surfaceEventOf(event) - if (surfaceEvent === undefined) return - if (surfaceEvent.surfaceOp === 'append') { - assertProvenance(surfaceEvent, []) + const surfaceOp = surfaceOpOf(event) + if (surfaceOp === undefined) return + if (surfaceOp === 'append') { + assertProvenance(event, []) return { kind: 'append', seq: event.seq } } - const range = replacementRange(state, surfaceEvent.surfaceOp) - assertProvenance(surfaceEvent, range.shadowedSeqs) + const range = replacementRange(state, surfaceOp) + assertProvenance(event, range.shadowedSeqs) return { kind: 'replace', seq: event.seq, - start: surfaceEvent.surfaceOp.start, - end: surfaceEvent.surfaceOp.end, + start: surfaceOp.start, + end: surfaceOp.end, ...range, } } diff --git a/packages/core/session/tests/surface.spec.ts b/packages/core/session/tests/surface.spec.ts index 87012b668d..1615e12f4b 100644 --- a/packages/core/session/tests/surface.spec.ts +++ b/packages/core/session/tests/surface.spec.ts @@ -58,6 +58,7 @@ describe('foldSurface provenance', () => { ['a non-array', [{ ...provenanceEvent(0, undefined), sourceEventSeqs: 'invalid' }], /must be an array/], ['an empty array', [provenanceEvent(0, [])], /must not be empty/], ['duplicates', [provenanceEvent(0, undefined), provenanceEvent(1, [0, 0])], /must not contain duplicates/], + ['a sparse array', [provenanceEvent(0, Array(1))], /densely contain/], ['a non-number', [{ ...provenanceEvent(0, undefined), sourceEventSeqs: ['0'] }], /non-negative safe integers/], ['a fractional number', [provenanceEvent(0, [0.5])], /non-negative safe integers/], ['a negative number', [provenanceEvent(0, [-1])], /non-negative safe integers/], diff --git a/packages/session-query/session-query/tests/tracing.spec.ts b/packages/session-query/session-query/tests/tracing.spec.ts index efc32d2216..eb22a9f95c 100644 --- a/packages/session-query/session-query/tests/tracing.spec.ts +++ b/packages/session-query/session-query/tests/tracing.spec.ts @@ -358,6 +358,9 @@ describe('session event tracing', () => { ['empty sources', [ appendEvent(0, []), ]], + ['sparse sources', [ + appendEvent(0, Array(1)), + ]], ['duplicate sources', [ appendEvent(0), appendEvent(1, [0, 0]), From 04df615dd64f204e62cc865e00620f4e236c87c1 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Thu, 16 Jul 2026 11:08:43 +0800 Subject: [PATCH 197/359] docs(rfc): propose agent execution context --- docs/rfc/INDEX.md | 1 + ...26-07-15-agent-execution-context.i18n.yaml | 6 + .../2026-07-15-agent-execution-context.md | 207 ++++++++++++++++++ .../2026-07-15-agent-execution-context.zh.md | 207 ++++++++++++++++++ 4 files changed, 421 insertions(+) create mode 100644 docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.i18n.yaml create mode 100644 docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.md create mode 100644 docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.zh.md diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index a60579ef4c..2660132fb2 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -28,6 +28,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | Title | First proposed | |---|---| | [Runtime schemas for the event vocabulary (Zod vs the merge-extensible-map pattern)](proposed/architecture/2026-06-16-typed-event-schemas.md) | 2026-06-16 | +| [Agent execution context over AsyncLocalStorage](proposed/architecture/2026-07-15-agent-execution-context.md) | 2026-07-15 | | [SDK project editing architecture](proposed/architecture/2026-07-15-sdk-project-editing-architecture.md) | 2026-07-15 | ### Process diff --git a/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.i18n.yaml b/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.i18n.yaml new file mode 100644 index 0000000000..65be95551b --- /dev/null +++ b/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-15-agent-execution-context.md: 7bea10fb1268c91a7668f7d269f83ae1250c373c +2026-07-15-agent-execution-context.zh.md: 5a7b12974818a076434ff1a1b3b4ab819866b3d7 diff --git a/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.md b/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.md new file mode 100644 index 0000000000..7bea10fb12 --- /dev/null +++ b/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.md @@ -0,0 +1,207 @@ +# RFC: Agent execution context over AsyncLocalStorage + +Status: proposed + +English | [中文](2026-07-15-agent-execution-context.zh.md) + +## Problem + +The harness has two useful but different notions of context: + +- A Cordis `Context` is a composition and lifetime object. The deployment context exposes shared services, while `agent.ctx` exposes the flat registration layer owned by one live Agent. +- Agent, Session, turn, step, and tool identity are execution subjects. The loop passes them explicitly through events, prompt assembly, LLM requests, and `ToolExecution`. + +These concepts must not be conflated. In particular, `agent.ctx.agent` is a static association on the Agent's scoped composition context. A plain root context deliberately returns `undefined`; it cannot be changed to mean "whichever Agent happens to be running now" because one Node process may run many Agents concurrently. + +This leaves a practical gap for deeply nested infrastructure. A capability transport, skill provider, tracing helper, logger, or gateway client may need to know which Agent initiated the current asynchronous operation. Passing `agent` through every intermediate helper is noisy, while deriving identity from a process-global mutable slot is incorrect as soon as two Agents overlap. Model-visible tool arguments are also the wrong carrier: the model must not be able to choose a trusted Session or sandbox-routing header. + +The gap becomes important when a single Harness runtime multiplexes Sessions for a multi-tenant hosting platform. Outbound capability requests must automatically carry the current Harness Session ID so the host can resolve the correct tenant and sandbox owner. Model-facing skills and tools should not know host-specific routing, but the selected capability implementation still needs a trusted current Agent at the transport boundary. + +## Proposal + +Add a narrow Agent execution-context facility backed by Node `AsyncLocalStorage`. It provides ambient access to the Agent associated with the current asynchronous execution chain without replacing Cordis contexts, explicit protocol fields, or durable Session state. + +The first version stores only the Agent: + +```text +export interface AgentExecution { + readonly agent: Agent +} + +export interface AgentExecutionService { + current(): AgentExecution | undefined + require(): AgentExecution + run(execution: AgentExecution | undefined, operation: () => T): T +} +``` + +`Session` is derived as `execution.agent.session`; it is not duplicated in the store. Turn, step, tool call, model, cwd, and sandbox identity remain outside the first version because they already have authoritative owners and no confirmed ambient consumer requires them yet. The single-field wrapper is deliberate: a later execution-frame refinement extends `AgentExecution` without changing `run()` callers, so implementations must not flatten the store to a bare `Agent`. + +`AgentExecution` deliberately retains the exact live `Agent`, not an id snapshot. This is the one capability admitted to the first-version store because it is the subject whose driver establishes the boundary and because existing scoped helpers operate on that exact object. Ambient presence is not proof of liveness or authorization: consumers must still honor the Agent lifecycle and the explicit capability contract before performing lifecycle-sensitive work. + +The API must always establish an ALS boundary, including when the supplied execution is `undefined`. This provides an explicit way to clear inherited context for unrelated detached work. A comparable implementation observed an uncleared ambient value crossing scheduled work into a later turn; the explicit undefined boundary prevents that class of leak. + +### Package and service placement + +Create `packages/core/agent-execution/` as `@deepseek-ai/dsh-agent-execution`. The package owns the Node-specific ALS implementation and augments Cordis with the mandatory `ctx.agentExecution` service. It belongs to `core/` because it is part of the stable Agent control spine that every concrete Agent loop and ambient-identity consumer programs against. + +The public key is `ctx.agentExecution`, settled here so every surface — service key, interface name, and package name — shares one word root. It names the Agent-owned asynchronous chain rather than one turn or tool call. `ctx.execution` is too broad; a runtime-flavored name would collide with `packages/code-runtime/` and with "Harness runtime" meaning the whole process; and changing `ctx.agent` is excluded because it already means the static Agent association of `agent.ctx`. + +The package exposes the service through Cordis rather than a mutable module-global slot: + +- the Agent Loop can inject the service explicitly; +- tests can mount an isolated service per Harness context; +- service disposal can disable its ALS instance after dependent Agent drivers quiesce; +- the dependency remains visible in Cordis configuration and generated catalogs. + +The service loads mandatorily with the standard agent composition bundle, and `dsh-agent-loop` declares it in `inject`: a composition that drives agents without it fails at load, per the fail-loud rule, rather than degrading to absent ambient identity at the first deep consumer. Configuration tests pin this policy. The facility relies only on stable Node `AsyncLocalStorage`, available without a polyfill across the supported `node ^22.19 || >=24` range. Node 24+ uses an `AsyncContextFrame`-backed implementation, while Node 22 uses the earlier implementation; this RFC accepts the always-on propagation cost for the invariant and makes no zero-overhead claim. + +Service teardown is ordered rather than transparent. The Agent Loop stops accepting new work, cancels and drains every driver, and only then may the service disable its ALS instance. HMR of the service rebuilds that dependent subtree; it does not preserve an in-flight turn across reload. A retained reference to a disposed service throws a stable disposed-service error from both `current()` and `require()` instead of silently returning `undefined`. + +### Lifecycle boundary + +Bind the execution context around each concrete Agent driver's `runLoop` lifetime: + +```text +agentExecution.run({ agent }, () => runLoop(ctx, agent, handle)) +``` + +This gives every operation initiated by that driver the same trusted Agent: + +- prompt interception and prompt assembly; +- LLM adapter calls; +- tool policy and tool bodies; +- capability providers and transports; +- synchronous and asynchronous helpers awaited by those operations. + +Concurrent drivers receive distinct ALS stores. A child Agent's own driver establishes a new boundary with the child, so child operations do not inherit the parent Agent merely because child creation started inside a parent tool call. When a nested boundary returns, ALS restores the parent automatically. + +Agent creation setup is deliberately outside this dynamic boundary. Setup already receives `agentCtx`, whose `agentCtx.agent` is the correct unpublished Agent. Publication and lifecycle ownership continue to use the existing explicit Agent and scoped carrier. One consequence is a defined contract, not an accident: when child creation starts inside a parent tool call, the child's setup and persistence load run under the PARENT's ambient identity, because the child's driver has not started. A transport reached during that window routes under the parent's Session — correct for trusted routing, since the parent initiated and owns the creation work. Setup code that needs the child's identity uses the explicit `agentCtx.agent`, never the ambient store. + +### Explicit subjects remain authoritative + +Ambient identity is a convenience for deep infrastructure, not a replacement for existing contracts: + +- `AgentEventDispatch` continues to carry the explicit Agent subject and scope. +- `AssembleContext.agent` remains explicit. +- `ToolExecution.agent` remains explicit and continues to select the scoped tool and policy view. +- `GenerateOptions.sessionId` remains explicit at the LLM boundary. +- Subagent requests and lifecycle events continue to carry explicit parent and child identity. +- Session events remain the durable truth for replay and resume. + +Code at a public service, process, worker, persistence, or wire boundary must materialize the identity it needs into that boundary's typed request. A remote process cannot access the parent's ALS store. + +### Trusted transport use + +A host-aware capability transport may read `ctx.agentExecution.require().agent.session.id` when constructing an outbound request and add a deployment-owned trusted header such as `X-Harness-Session-Id`. The header is not present in model-visible tool arguments and cannot be overridden by the model. Ambient presence alone does not authorize a request; the transport still runs inside its normal explicit capability and Agent-lifecycle contracts. + +The bash seam's existing `OwnerToken` is the nearest explicit-identity precedent and shows why it does not close this gap: `BashExecSpec.owner` is a background-task isolation key that `dsh-tool-bash` casts from the session id, foreground `run()` deliberately ignores it, and the filesystem seam has no counterpart — its provider methods carry no identity parameter at all. Extending every capability seam with a routing-identity parameter would push hosting concerns into seam vocabularies that are otherwise deployment-neutral; ambient identity lets the transport implementation own routing without widening any seam. + +The hosting platform remains responsible for resolving the Harness runtime Session ID to its product Session and sandbox owner. Harness does not learn the host's sandbox identifier, sandbox provider, or persistence model. + +Model-facing skill and tool plugins should not add hosting-specific headers themselves. They call a capability service; the selected provider owns remote execution and identity propagation. This preserves the separation between model behavior and backend routing. + +### Detached asynchronous work + +Node ALS is inherited by asynchronous resources created inside `run()`, even when callers do not await them. This is useful for an Agent-owned background operation, but it can also retain a stale turn's context in unrelated work. + +Identity inheritance does not replace cancellation ownership. Work started inside an Agent's boundary is either **foreground** — it inherits `{ agent }` and separately receives the explicit cancellation signal owned by its execution seam — or **detached** — it starts under `run(undefined, operation)` and owns its own lifecycle with an explicit stop. The caller must keep those choices aligned. The implementation must document and test these rules: + +- Work logically owned by the Agent is foreground: it may inherit `{ agent }`, receives cancellation through the existing explicit seam, and must honor the Agent's disposal contract. +- Long-lived deployment infrastructure, timers, and work queues unrelated to that Agent are detached: they must start under `run(undefined, operation)` and be stopped by their own owner, never implicitly by a turn ending. +- Code that enqueues data for later processing must serialize the required identity into the queue item; it must not expect ALS to cross the queue, process, or worker boundary. +- Consumers must not treat an ambient Agent reference as proof that the Agent is still live. Lifecycle-sensitive operations still check `agent.status`, an explicit signal, or the owning service's contract. + +`turn` and `step` remain outside the first version; they can join later as a separate immutable execution-frame refinement if a real cross-cutting consumer (tracing, logging) cannot use the existing explicit fields. The full `Agent` is the deliberate capability exception because it is the execution subject that establishes the boundary. Every additional field must be a stale-safe label whose stale copy can at worst mislabel a trace; another capability or control channel requires its own RFC. `AbortSignal` is excluded from the first version under that rule; see Alternatives considered. + +## Current Harness evidence + +The implementation Session should re-check these symbols on its target branch before editing because this handoff was prepared against a local source snapshot and the branch may have advanced. + +- `packages/core/agent/src/types.ts`: `Agent` already owns `session`, `status`, and `ctx`. Its `ctx` documentation defines a registration scope, not a dynamic request context. +- `packages/core/agent/src/index.ts`: Cordis `Context.agent` is installed as an Agent-scope DX association and defaults to `undefined` on a plain context. Do not change this semantic. +- `packages/core/agent-loop/src/agent.ts`: `ReactLoopAgent` already owns inbox, cancellation, per-step abort, status, and driver lifetime. Do not create a parallel mutable runtime-state object. +- `packages/core/agent-loop/src/loop.ts`: `runLoop(ctx, agent, handle)` has the exact lifetime boundary to wrap. It passes Agent, turn, step, and signal explicitly to narrower operations. +- `packages/core/tools/src/index.ts`: `ToolExecutionInput.agent` is explicit and selects scoped policy and tool resolution. It remains in the contract after ALS is added. +- `packages/core/agent/src/dispatch.ts`: `agentEvents()` deliberately fuses the Agent subject with its scoped carrier. Ambient context must not replace this correctness mechanism. +- `packages/core/README.md` and the existing core packages: they show that stable Agent control contracts belong in `core/`; `agent-execution` is mandatory control infrastructure rather than optional model-visible context enrichment. + +This proposal extends, rather than supersedes, [the Agent registration-scope decision](../../implemented/architecture/2026-07-08-agent-scope-contexts.md) and its [runtime design](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md). + +## Claude Code reference implementation + +| Claude Code | Harness translation | +|---|---| +| AppState store | Cordis deployment services and their owned live state | +| QueryEngine | `ReactLoopAgent` plus its loop-owned runtime state | +| ToolUseContext | Explicit Agent/tool/request parameters at capability seams | +| AgentContext ALS | Proposed narrow `AgentExecution` carrier | +| Transcript | Event-sourced `Session` and persistence backends | + +## Implementation handoff + +The implementation Session should perform the work in this order: + +1. Switch to the intended target branch and inspect the current versions of the files listed under "Current Harness evidence". Do not merge or copy changes from the branch on which this handoff was authored. +2. Add `packages/core/agent-execution/` with package metadata, README, exported types, the Cordis service, module augmentation, and focused tests. +3. Add the package to TypeScript project references, path candidates, runtime closure/configuration, and generated catalogs according to existing package gates. Prefer repository generators over hand-editing generated files. Also update the `core/` repository-layout line in root `AGENTS.md`, the package table in `packages/core/README.md`, and the package-group description in `packages/README.md`. +4. Make the Agent Loop declare and consume the service. Wrap each Agent driver's complete `runLoop` invocation in `{ agent }` without changing public Agent, event, tool, LLM, or Session signatures. +5. Add an integration test that overlaps two Agents in one process and observes the correct ambient Agent from inside asynchronous tool execution after at least one `await`. +6. Add nested-Agent coverage proving a child sees itself and the parent context is restored after the child boundary settles. +7. Add clearing and failure coverage: outside a boundary returns `undefined`, `require()` fails clearly, `run(undefined, ...)` masks an inherited Agent, and thrown/rejected operations do not contaminate later unrelated work. +8. Add a test-double capability transport to the integration suite. Keep the model-facing schema unchanged and assert that a trusted Session header is generated internally. Adapting a production remote backend is follow-up work outside this RFC. +9. Run typecheck, targeted tests, documentation gates, generated-catalog checks, and then the repository's normal CI/pre-push gate. + +Suggested focused test matrix: + +| Scenario | Required observation | +|---|---| +| Outside driver | `current()` is `undefined` | +| One Agent across awaits | Every continuation sees the same exact Agent | +| Two concurrent Agents | A never observes B and B never observes A | +| Nested child | Child sees child; parent is restored afterward | +| Child creation window | Setup inside a parent tool call sees the parent ambiently; `agentCtx.agent` is the child | +| Direct Agent-less tool call | Explicit tool behavior remains valid; ambient identity is absent | +| Cleared detached work | `run(undefined, ...)` hides the inherited Agent | +| Failure and cancellation | Context restores after throw, rejection, and abort | +| Agent disposal | Lifecycle-sensitive consumers reject work from a captured Agent after disposal | +| Service reload | Agent drivers drain before ALS disable; retained disposed-service calls throw the documented stable error | +| Capability transport boundary | Session identity is materialized into the typed request/header by the test-double transport | + +## Alternatives considered + +**Pass Agent through every function.** This remains the right choice at public and authority-bearing boundaries, but forcing it through every private helper creates plumbing that ambient execution context is designed to remove. The proposal keeps explicit subjects at seams and uses ALS only within one trusted asynchronous process. + +**Change `ctx.agent` to return the currently executing Agent.** Rejected because `ctx.agent` already denotes the static association of an Agent-scoped Cordis context. Making a root context dynamic would combine registration scope with execution scope, produce surprising behavior under concurrency, and break the implemented Agent-scope RFCs. + +**Store a complete mutable runtime object in ALS.** Rejected because Agent, Session, inbox, cancellation, turn/step state, tool execution, and durable log already have authoritative owners. Duplicating them creates stale snapshots, write-order questions, and another lifecycle to clean up. + +**Carry the step `AbortSignal` in the first-version ALS frame.** Rejected for this RFC. The signal is per-step while the proposed boundary is per-driver, so carrying it requires nested step and tool boundaries plus explicit rules for detached work, deadline ownership, and restoration. Existing execution seams already pass cancellation explicitly. A future RFC may revisit this only with a concrete cross-cutting consumer and tests that establish those nested lifecycle semantics. + +**Use one process-global mutable `currentAgent`.** Rejected because concurrent Agents and subagents overwrite one another across awaits. It is correct only under serialization, which multi-Agent execution explicitly does not guarantee. + +**Infer the Session from model-visible tool arguments.** Rejected because the model can alter those arguments. Sandbox routing and authorization require a trusted in-process identity, not user/model input. + +**Put a hosting platform's sandbox-owner identifier or provider data in Harness context.** Rejected because sandbox ownership is hosting-product state resolved outside Harness. Harness should carry only its own Session identity across the trusted transport boundary. + +## Acceptance criteria + +- One Node Harness process can execute at least two Agents concurrently, and asynchronous consumers always observe the exact initiating Agent. +- Outside Agent driver execution, ambient lookup returns `undefined` and `require()` throws a stable, actionable error. +- Nested Agent execution restores the parent context after the child settles. +- `agent.ctx`, `ctx.agent`, Agent events, prompt assembly, `ToolExecution.agent`, LLM `sessionId`, and Session persistence retain their existing semantics. +- No Agent, Session, turn, step, sandbox, or authorization identity becomes model-controlled. +- The implementation provides an explicit undefined boundary for unrelated detached work and tests it against context leakage without changing existing explicit cancellation contracts. +- The service loads with the standard agent bundle and `dsh-agent-loop` fails at load without it; a configuration test pins the policy. +- Disposal/HMR drains every dependent Agent driver before disabling ALS; retained calls on the disposed service fail with the documented stable error, and no active ALS state remains reachable through the disposed Cordis context. +- A test-double capability transport proves trusted Session ID propagation without adding a model-visible schema field. +- Package catalogs, dependency graphs, API docs, and relevant architecture docs are regenerated or updated, and the repository's documentation gates pass. + +## Risks + +- Ambient context hides a dependency from function signatures. Restricting it to deep cross-cutting infrastructure and retaining explicit public subjects limits that cost. +- ALS inheritance into detached promises and timers can retain semantically stale identity. An explicit undefined boundary, documentation, and regression tests are required rather than assumed cleanup. +- ALS does not cross worker threads, subprocesses, Redis, HTTP, or persisted queues. Every such boundary must serialize the required identity explicitly. +- The ambient store intentionally carries the full live Agent capability. A captured reference can outlive publication, so ambient presence alone never authorizes lifecycle-sensitive work and consumers must still honor Agent lifecycle and cancellation contracts. +- Mandatory loading adds a core runtime dependency to every agent composition; the RFC accepts that cost because an optional service would make ambient identity composition-dependent. Propagation cost remains measurable across supported Node versions and should be benchmarked separately. +- Adding turn, step, signal, cwd, or tool details prematurely would expand inheritance and staleness hazards. The first version deliberately accepts the limitation of Agent-only ambient identity; any additional capability or control field requires a separate RFC. diff --git a/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.zh.md b/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.zh.md new file mode 100644 index 0000000000..5a7b129748 --- /dev/null +++ b/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.zh.md @@ -0,0 +1,207 @@ +# RFC：基于 AsyncLocalStorage 的 agent（智能体）执行上下文 + +Status: proposed + +[English](2026-07-15-agent-execution-context.md) | 中文 + +## 问题 + +harness 中存在两种有用但含义不同的上下文： + +- Cordis `Context` 是依赖组合和生命周期对象。部署上下文暴露共享服务，`agent.ctx` 则暴露某个存活 Agent 所拥有的扁平注册层。 +- Agent、会话、轮次、步骤和工具身份是执行主体。agent loop（智能体循环）通过事件、提示词组装、LLM（大语言模型）请求和 `ToolExecution` 显式传递这些信息。 + +这两类概念不能混为一谈。尤其是，`agent.ctx.agent` 是 Agent 作用域组合上下文上的静态关联。普通根上下文会有意返回 `undefined`；不能把它改成“当前恰好正在运行的 Agent”，因为一个 Node 进程可能并发运行多个 Agent。 + +这给深层基础设施留下了一个实际缺口。能力传输层、skill（技能）提供方、追踪辅助函数、日志记录器或网关客户端，可能需要知道当前异步操作由哪个 Agent 发起。让每一层中间辅助函数都继续传递 `agent` 会产生大量样板代码，而从进程级可变全局槽推导身份，会在两个 Agent 并发后立即出错。模型可见的工具参数也不是合适的载体：模型不能选择可信的会话或沙箱路由请求头。 + +当单个 Harness 运行时为多租户宿主平台复用多个会话时，这个缺口会变得尤其重要。对外能力请求必须自动携带当前 Harness 会话 ID，以便宿主平台解析正确的租户和沙箱归属。模型侧的 skill 和工具不应理解宿主平台特有的路由，但所选能力实现仍需要在传输边界获得可信的当前 Agent。 + +## 提案 + +新增一套由 Node `AsyncLocalStorage` 支撑的窄粒度 Agent 执行上下文能力。它允许代码在当前异步执行链内访问关联的 Agent，但不会取代 Cordis 上下文、显式协议字段或持久化会话状态。 + +第一版只保存 Agent： + +```text +export interface AgentExecution { + readonly agent: Agent +} + +export interface AgentExecutionService { + current(): AgentExecution | undefined + require(): AgentExecution + run(execution: AgentExecution | undefined, operation: () => T): T +} +``` + +`Session` 通过 `execution.agent.session` 推导，不在存储中重复保存。轮次、步骤、工具调用、模型、cwd 和沙箱身份不进入第一版，因为它们已经有各自的真源，而且目前没有已确认的隐式上下文消费方需要这些信息。单字段包装是有意为之：后续的执行帧扩展可以在不改动 `run()` 调用方的前提下扩展 `AgentExecution`，因此实现不得把存储简化成裸 `Agent`。 + +`AgentExecution` 有意保留准确的存活 `Agent`，而不是 ID 快照。这是第一版存储中唯一获准的能力对象，因为它正是由驱动建立边界的执行主体，而且现有作用域辅助函数依赖这个准确对象。隐式存在不代表仍然存活或已经获得授权：消费方执行生命周期敏感工作前，仍须遵循 Agent 生命周期和显式能力契约。 + +API 必须始终建立 ALS 边界，即使传入的 execution 是 `undefined` 也不例外。这样可以显式清除无关分离任务继承到的上下文。一个同类实现曾观察到未清空的隐式值穿过已调度工作泄漏进后续轮次；显式 undefined 边界可以防止这类泄漏。 + +### 包与服务位置 + +在 `packages/core/agent-execution/` 新建 `@deepseek-ai/dsh-agent-execution`。该包拥有 Node 专用的 ALS 实现，并通过必载的 `ctx.agentExecution` 服务扩展 Cordis。它属于 `core/`，因为这是每个具体 Agent loop 和隐式身份消费方所依赖的稳定 Agent 控制主干。 + +公开键名在此定为 `ctx.agentExecution`，服务键、接口名和包名共用同一个词根。它表示某个 Agent 所拥有的异步调用链，而不是单个轮次、步骤或工具调用；名字也直接说明存储的内容。`ctx.execution` 含义过宽；带 runtime 字样的名字会与 `packages/code-runtime/` 以及指整个进程的 “Harness 运行时” 冲突；修改 `ctx.agent` 被排除，因为它已经表示 `agent.ctx` 与 Agent 之间的静态关联。 + +该包通过 Cordis 暴露服务，而不是使用可变模块全局槽： + +- Agent Loop 可以显式注入该服务； +- 测试可以为每个 Harness 上下文挂载隔离的服务； +- 服务 dispose（资源释放）时可以在依赖它的 Agent 驱动静止后禁用其 ALS 实例； +- 依赖关系在 Cordis 配置和生成目录中保持可见。 + +该服务随标准 agent 组合包强制加载，`dsh-agent-loop` 在 `inject` 中声明它：缺少该服务的 agent 组合按快速失败规则在加载时报错，而不是等到第一个深层消费方读取时才发现隐式身份缺失。配置测试锁定这一策略。该能力只依赖稳定的 Node `AsyncLocalStorage`，支持范围 `node ^22.19 || >=24` 全部可原生使用且无需 polyfill。Node 24 及以上使用基于 `AsyncContextFrame` 的实现，Node 22 使用此前的实现；本 RFC 为保证该不变量接受常驻传播成本，不作零开销承诺。 + +服务关闭是有顺序的，不提供透明的进行中延续。Agent Loop 必须先停止接受新驱动并取消或等待所有进行中的驱动收敛，随后 Cordis 才 dispose 服务并调用 `disable()`。HMR（热模块替换）会重建依赖该服务的子树，不承诺让进行中的轮次跨服务替换继续执行。如果旧调用方保留了已 dispose 的服务引用，`current()` 和 `require()` 都会抛出稳定的 “service disposed” 错误，而不是返回模糊的 `undefined`。 + +### 生命周期边界 + +在每个具体 Agent 驱动的 `runLoop` 整个生命周期外围绑定执行上下文： + +```text +agentExecution.run({ agent }, () => runLoop(ctx, agent, handle)) +``` + +这样，由该驱动发起的每项操作都能获得同一个可信 Agent： + +- 提示词拦截和提示词组装； +- LLM 适配器调用； +- 工具策略和工具主体； +- 能力提供方和传输层； +- 这些操作所等待的同步和异步辅助函数。 + +并发驱动会获得彼此独立的 ALS 存储。子 Agent 自己的驱动会用该子 Agent 建立新边界，因此即使子 Agent 是在父 Agent 的工具调用中创建的，其操作也不会错误继承父 Agent。嵌套边界返回后，ALS 会自动恢复父 Agent。 + +Agent 创建阶段有意置于这个动态边界之外。创建过程已经接收 `agentCtx`，其中 `agentCtx.agent` 就是正确的、尚未发布的 Agent。发布流程和生命周期归属继续使用现有的显式 Agent 与作用域载体。由此产生一条明确契约，而非偶然行为：当子 Agent 的创建发生在父 Agent 的工具调用内时，子 Agent 的创建流程和持久化加载运行在**父 Agent** 的隐式身份之下，因为子驱动尚未启动。这个窗口内触达的传输层按父会话路由——对可信路由而言这是正确的，因为创建工作由父 Agent 发起并归它所有。创建代码需要子身份时使用显式的 `agentCtx.agent`，绝不读隐式存储。 + +### 显式主体仍是真源 + +隐式身份只是深层基础设施的便利能力，不会取代现有契约： + +- `AgentEventDispatch` 继续携带显式 Agent 主体和作用域。 +- `AssembleContext.agent` 保持显式传递。 +- `ToolExecution.agent` 保持显式传递，并继续选择作用域内的工具和策略视图。 +- `GenerateOptions.sessionId` 在 LLM 边界上保持显式传递。 +- subagent 请求和生命周期事件继续携带显式的父子身份。 +- 会话事件仍然是回放和恢复的持久化真源。 + +代码跨越公开服务、进程、worker、持久化或协议边界时，必须把边界所需身份写入其类型化请求。远程进程无法访问父进程的 ALS 存储。 + +### 可信传输层用途 + +能力传输层可以在构造对外请求时读取 `ctx.agentExecution.require().agent.session.id`，并添加由部署方控制的可信身份，例如 `X-Harness-Session-Id` 请求头。该身份不出现在模型可见的参数中，模型也不能覆盖它。传输层仍须执行自身的能力和生命周期授权；隐式 Agent 只提供发起方身份，不授予调用权限。 + +bash seam 现有的 `OwnerToken` 是最接近的显式身份先例，它也说明了为什么显式方案补不上这个缺口：`BashExecSpec.owner` 是一个后台任务隔离键，由 `dsh-tool-bash` 从会话 id 转换而来，前台 `run()` 有意忽略它，而文件系统 seam 没有对应物——其提供方方法完全不携带身份参数。给每个能力 seam 都加一个路由身份参数，会把宿主平台的关注点塞进本应与部署无关的 seam 词汇；隐式身份让传输层实现自己拥有路由逻辑，而不必加宽任何 seam。 + +宿主平台继续负责把 Harness 运行时会话 ID 解析成产品会话和沙箱归属方。Harness 不需要理解宿主平台的沙箱标识、沙箱提供方或持久化模型。 + +模型侧 skill 和工具插件不应自行添加宿主平台特有的请求头。它们调用能力服务；所选提供方负责远程执行和身份传播。这样可以保持模型行为与后端路由之间的职责分离。 + +### 分离异步工作 + +Node ALS 会被 `run()` 内创建的异步资源继承，即使调用方没有等待它们。这对 Agent 所拥有的后台操作很有用，但也可能让无关任务保留陈旧轮次的上下文。 + +身份继承不取代取消归属。在 Agent 边界内启动的工作要么是**前台**的——继承 `{ agent }`，并通过其执行 seam 单独接收显式取消信号；要么是**分离**的——在 `run(undefined, operation)` 下启动，并拥有独立生命周期和显式停止操作。调用方必须让这两个选择保持一致。实现必须记录并测试以下规则： + +- 逻辑上归 Agent 所有的工作是前台工作：可以继承 `{ agent }`，通过现有显式 seam 接收取消，并且必须遵守该 Agent 的 dispose 契约。 +- 与该 Agent 无关的长生命周期部署基础设施、定时器和工作队列是分离工作：必须在 `run(undefined, operation)` 下启动，由自己的归属方停止，绝不因某个轮次结束而被隐式终止。 +- 把数据入队并留待后续处理的代码必须将所需身份序列化到队列项中；不能期待 ALS 跨越队列、进程或 worker 边界。 +- 消费方不能把隐式 Agent 引用视为 Agent 仍然存活的证明。生命周期敏感的操作仍须检查 `agent.status`、显式 signal 或归属服务的契约。 + +`turn` 和 `step` 不进入第一版；如果未来出现真实的横切消费方（追踪、日志）无法使用现有显式字段，可以再将它们作为独立的不可变执行帧扩展引入。完整 `Agent` 是刻意允许的能力例外，因为它就是建立边界的执行主体。每个额外字段都必须是陈旧安全的标签，其陈旧副本最坏只能误标一条追踪记录；其他能力或控制通道需要独立 RFC。第一版不携带 `AbortSignal`；见「考虑过的替代方案」。 + +## 当前 Harness 依据 + +由于这份交接基于本地源码快照编写，目标分支可能已经前进，后续实现会话应在编辑前重新检查这些符号。 + +- `packages/core/agent/src/types.ts`：`Agent` 已经拥有 `session`、`status` 和 `ctx`。其中 `ctx` 的文档将它定义为注册作用域，而不是动态请求上下文。 +- `packages/core/agent/src/index.ts`：Cordis `Context.agent` 作为 Agent 作用域的开发体验关联被安装，在普通上下文上默认返回 `undefined`。不要改变这一语义。 +- `packages/core/agent-loop/src/agent.ts`：`ReactLoopAgent` 已经拥有 inbox、取消逻辑、每步骤 abort、状态和驱动生命周期。不要再创建一套并行的可变运行时状态对象。 +- `packages/core/agent-loop/src/loop.ts`：`runLoop(ctx, agent, handle)` 正好是需要包裹的生命周期边界。它会将 Agent、轮次、步骤和 signal 显式传给更窄的操作。 +- `packages/core/tools/src/index.ts`：`ToolExecutionInput.agent` 是显式字段，并用于选择作用域内的策略和工具解析。增加 ALS 后，它仍然保留在契约中。 +- `packages/core/agent/src/dispatch.ts`：`agentEvents()` 有意把 Agent 主体与其作用域载体融合。隐式上下文不能取代这套正确性机制。 +- `packages/core/README.md` 和现有 core 包：它们表明稳定的 Agent 控制契约位于 `core/`；`agent-execution` 是必载控制基础设施，而不是模型可见的可选上下文增强。 + +本提案扩展而非取代[关于 Agent 注册作用域的既有决策](../../implemented/architecture/2026-07-08-agent-scope-contexts.md)及其[运行时设计](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md)。 + +## Claude Code 参考实现 + +| Claude Code | Harness 中的对应设计 | +|---|---| +| AppState store | Cordis 部署服务及其拥有的实时状态 | +| QueryEngine | `ReactLoopAgent` 及其 loop 所拥有的运行时状态 | +| ToolUseContext | 能力边界上的显式 Agent、工具和请求参数 | +| AgentContext ALS | 本提案的窄粒度 `AgentExecution` 载体 | +| Transcript | 事件溯源 `Session` 与持久化后端 | + +## 实现交接步骤 + +后续实现会话应按以下顺序开展工作： + +1. 切换到预期目标分支，检查“当前 Harness 依据”中列出文件的当前版本。不要合并或复制编写本交接文档所在分支的修改。 +2. 新增 `packages/core/agent-execution/`，包含包元数据、README、导出类型、Cordis 服务、模块扩展和聚焦测试。 +3. 按照现有包门禁，把该包加入 TypeScript 项目引用、路径候选、运行时闭包或配置以及生成目录。优先使用仓库生成器，不要手工编辑生成文件。同时更新根 `AGENTS.md` 中 repository layout 的 `core/` 行、`packages/core/README.md` 中的包表，以及 `packages/README.md` 中的包组说明。 +4. 让 Agent Loop 声明并消费该服务。在不改变公开 Agent、事件、工具、LLM 或会话签名的前提下，用 `{ agent }` 包裹每个 Agent 驱动的完整 `runLoop` 调用。 +5. 增加集成测试：让同一进程中的两个 Agent 重叠执行，并在至少一次 `await` 后从异步工具执行内部观察到正确的隐式 Agent。 +6. 增加嵌套 Agent 覆盖：证明子 Agent 能看到自己，且子边界结束后父上下文得到恢复。 +7. 增加清除和失败覆盖：边界外返回 `undefined`，`require()` 清晰失败，`run(undefined, ...)` 屏蔽继承的 Agent，抛出异常或 rejected 操作不会污染后续无关工作。 +8. 在集成测试中增加一个能力传输测试替身。保持模型侧 schema 不变，并断言可信会话请求头由内部生成。适配真实生产远程后端属于本 RFC 之外的后续工作。 +9. 运行类型检查、定向测试、文档门禁、生成目录检查，最后运行仓库常规 CI 或 pre-push 门禁。 + +建议的聚焦测试矩阵： + +| 场景 | 必须观察到的结果 | +|---|---| +| 驱动之外 | `current()` 为 `undefined` | +| 一个 Agent 跨越 await | 每个 continuation 都看到完全相同的 Agent | +| 两个并发 Agent | A 永远看不到 B，B 永远看不到 A | +| 嵌套子 Agent | 子 Agent 看到自己；随后恢复父 Agent | +| 子 Agent 创建窗口 | 父工具调用内的创建流程隐式看到父 Agent；`agentCtx.agent` 是子 Agent | +| 直接调用无 Agent 工具 | 显式工具行为仍然有效；隐式身份不存在 | +| 已清除的分离工作 | `run(undefined, ...)` 隐藏继承的 Agent | +| 失败和取消 | throw、rejection 和 abort 后上下文均得到恢复 | +| Agent dispose | 隐式引用不赋予 dispose 后的能力 | +| 服务重载 | Agent 驱动在 ALS disable 前收敛；保留的已 dispose 服务调用抛出文档约定的稳定错误 | +| 能力传输边界 | 会话身份由测试替身传输层写入类型化请求或请求头 | + +## 考虑过的替代方案 + +**让每个函数都传递 Agent。** 对公开边界和承载权限的边界而言，这仍然是正确选择；但如果要求每个私有辅助函数都传递 Agent，就会产生大量样板代码，而隐式执行上下文正适合消除这些代码。本提案在边界处保留显式主体，只在单个可信异步进程内部使用 ALS。 + +**修改 `ctx.agent`，让它返回当前正在执行的 Agent。** 拒绝此方案，因为 `ctx.agent` 已经表示 Agent 作用域 Cordis 上下文的静态关联。让根上下文变成动态语义，会把注册作用域和执行作用域混合起来，在并发时产生意外行为，并破坏已经实现的 Agent 作用域 RFC。 + +**在 ALS 中存储完整的可变运行时对象。** 拒绝此方案，因为 Agent、会话、inbox、取消状态、轮次或步骤状态、工具执行和持久化日志已经有各自的真源。重复保存会产生陈旧快照、写入顺序问题，以及另一套需要清理的生命周期。 + +**在第一版 ALS 帧中携带步骤级 `AbortSignal`。** 本 RFC 拒绝此方案。signal 的生命周期是每步骤，而提议的 ALS 边界是每驱动，因此携带它需要嵌套的步骤和工具边界，还要明确规定分离工作、deadline 归属和恢复语义。现有执行 seam 已经显式传递取消。未来只有在出现具体横切消费方，并通过测试建立这些嵌套生命周期语义后，才可由独立 RFC 重新评估。 + +**使用一个进程级可变 `currentAgent`。** 拒绝此方案，因为并发 Agent 和 subagent 会在 await 边界间相互覆盖。它只有在所有工作严格串行时才正确，而多 Agent 执行明确不保证这一点。 + +**从模型可见的工具参数推导会话。** 拒绝此方案，因为模型可以修改这些参数。沙箱路由和授权需要可信的进程内身份，而不是用户或模型输入。 + +**把宿主平台的沙箱归属标识或提供方数据放入 Harness 上下文。** 拒绝此方案，因为沙箱归属是由 Harness 外部解析的宿主产品状态。Harness 在可信传输边界上传递自己的会话身份即可。 + +## 验收标准 + +- 一个 Node Harness 进程至少能并发执行两个 Agent，异步消费方始终观察到准确的发起 Agent。 +- 在 Agent 驱动执行之外，隐式查询返回 `undefined`，且 `require()` 抛出稳定、可操作的错误。 +- 嵌套 Agent 执行结束后会恢复父上下文。 +- `agent.ctx`、`ctx.agent`、Agent 事件、提示词组装、`ToolExecution.agent`、LLM `sessionId` 和会话持久化保持现有语义。 +- Agent、会话、轮次、步骤、沙箱和授权身份都不能由模型控制。 +- 实现为无关分离任务提供显式 undefined 边界，并通过测试防止上下文泄漏，且不改变现有显式取消契约。 +- 该服务随标准 agent 组合包加载，缺少它时 `dsh-agent-loop` 在加载阶段失败；配置测试锁定这一策略。 +- dispose 或 HMR（热模块替换）会先让所有依赖的 Agent 驱动收敛，再禁用 ALS；已 dispose 服务上的保留调用会抛出文档约定的稳定错误，且已 dispose 的 Cordis 上下文不能继续访问活跃 ALS 状态。 +- 一个能力传输测试替身能证明可信会话 ID 得到传播，同时不新增模型可见的 schema 字段。 +- 包目录、依赖图、API 文档和相关架构文档得到重新生成或更新，仓库文档门禁通过。 + +## 风险 + +- 隐式上下文会从函数签名中隐藏依赖。将它限制在深层横切基础设施，并保留显式公开主体，可以控制这一成本。 +- ALS 对分离 promise 和定时器的继承可能保留语义上陈旧的身份。实现必须提供显式 undefined 边界、文档和回归测试，而不能假设清理会自然发生。 +- ALS 不会跨越 worker thread、子进程、Redis、HTTP 或持久化队列。每个此类边界都必须显式序列化所需身份。 +- 隐式存储有意携带完整的存活 Agent 能力。被捕获的引用可能比 Agent 的发布状态活得更久，因此隐式存在本身绝不授权生命周期敏感工作，消费方仍须遵循 Agent 生命周期和取消契约。 +- 强制加载给每个 agent 组合新增一个核心运行时依赖；本 RFC 接受这一成本，因为可选服务会让隐式身份依赖具体组合。支持范围内的 Node 版本仍存在可测量的传播成本，应另行基准测试。 +- 过早加入轮次、步骤、signal、cwd 或工具细节会扩大继承范围和陈旧状态风险。第一版有意接受只提供 Agent 隐式身份的限制；未来任何额外的能力或控制字段都需要独立 RFC。 From 6825918eaddca6bb7113f5a889a95ffc9f386470 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 11:15:58 +0800 Subject: [PATCH 198/359] docs: finish session simplification prose cleanup --- .../2026-07-05-reconstructable-requests.md | 20 +++++----- .../2026-06-18-compaction-capability-seam.md | 14 +++---- .../implemented/feature/2026-07-06-sandbox.md | 14 +++---- packages/compact/compact-basic/src/index.ts | 18 ++------- .../compact-basic/tests/compact-basic.spec.ts | 26 +----------- .../tests/request-reconstruction.spec.ts | 11 ++--- packages/core/session/README.md | 40 +++++++++---------- packages/core/session/tests/surface.spec.ts | 4 -- packages/ui/user-approval/README.md | 12 +++--- 9 files changed, 56 insertions(+), 103 deletions(-) diff --git a/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md b/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md index a5bc946af4..e93b4e0bd9 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md +++ b/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md @@ -20,35 +20,35 @@ Prefix-cache stability is corollary #1, not the headline: an append-only log pro **Messages.** `Session.deriveMessages()` is cached: each surface entry is projected exactly once, when first seen, through the public per-event function `deriveEventMessage(event)`; a surface rewrite (a compaction `replace` — `SurfaceManager.replaceGeneration`) rebuilds. Callers get a fresh array per call over shared, deep-frozen messages: mutating logged history through a projection is unrepresentable (it throws), replacing the old clone-per-call isolation. External reconstructors fold the same public function over a log prefix, so no two paths can disagree. -**The header.** The request's non-history half — `EpochHeader`: call config (`LlmCallConfig`: model + sampling scalars), rendered system prompt, assembled tool schemas, and the session prefix (`messagePrefix`, below) — is logged session state in canonical form (empty system/tools/prefix ≡ absent). One log-only, turn-enclosed event carries it: `request/header`, always a full snapshot. Each loop instance appends one on its first request (`'initial'` when the log has none, `'resume'` otherwise, even when nothing changed: the boundary itself is a recorded fact and cross-restart drift becomes attributable); a later request whose canonical header differs appends another with reason `'change'`. `foldRequestHeader` reconstructs by selecting the latest snapshot, and the live session tracks that fold with the same lazy cursor as the message cache. Legacy v0 logs containing the removed delta representation are rejected at seed and persistence-load boundaries rather than partially replayed. +`EpochHeader` records the request's non-history state: call config, rendered system prompt, tool schemas, and session prefix, with empty values canonicalized to absence. `request/header` always writes a full snapshot: the first loop instance uses reason `initial`, later instances use `resume`, and an in-instance change uses `change`. `foldRequestHeader` selects the latest snapshot. Legacy `request/header-delta` events and the removed `fallback` reason are rejected when appended or loaded. -**The loop, transmission-stateless.** Per step: render assembly (every step — value comparison needs no change-signal discipline, and a section that varies per step surfaces as a *logged* header event per step instead of a silent bust) → on the instance's FIRST step only, the `agent/session-prefix` waterfall — request-ONLY messages fronting the entire derived history (a frozen empty seed, contributions returned as an extension of `next()`; the home for session-stable openers that must NOT become history — a skills catalog, an AGENTS.md digest), deep-frozen and cached on the instance so reuse is structural and the prefix cannot drift mid-session — → `agent/pre-step`, carrying the composed prefix (compaction's surface mutations land before derivation, and its pressure gate counts the prefix this instance will actually send — never a previous instance's logged one, which could under-gate a resumed/forked instance whose contributor grew) → **messages snapshot, then `step/start` appended as the next operation in the same synchronous frame** → seed the call config (first request of the instance: from `AgentOptions`, so explicit options always beat the logged baseline — fork model-overrides and resume reconfiguration stay correct; afterwards: from the folded header) → the `agent/request` waterfall, re-typed `(agent, turn, step, config: LlmCallConfig, next) → LlmCallConfig` — a frozen seed and a returned replacement are ALL a listener shapes; durable content flows through the log channels (`inject()`, steering, prompt-submit `additionalContext`, sections via `system-prompt/assemble`) — → the header event the request owes the log, carrying the prefix as `messagePrefix` (no session event carries it, so the header is its only durable record; resume = a new instance = a recompose, anchored by its `'resume'` snapshot) → build `GenerateOptions` from `messagePrefix + snapshot` + header, deep-freeze (`deepFreeze` exempts the `AbortSignal`, the one live control channel — freezing one breaks `AbortController.abort()`), dispatch. The loop's per-instance bookkeeping is one boolean plus the cached prefix: whether this instance has logged its anchoring snapshot, and what it composed. +Each step rebuilds prompt assembly. On the instance's first step, `agent/session-prefix` extends a frozen empty seed with request-only opener messages; the result is frozen and cached for that loop instance. `agent/pre-step` then receives the composed prefix before messages are snapshotted immediately ahead of `step/start`. The first call config starts from explicit `AgentOptions`, preserving fork overrides and resume reconfiguration; later calls start from the folded header. `agent/request` may replace only that frozen config seed, while model-visible content enters through logged channels. The loop records the owed header event—the prefix's only durable home—builds `GenerateOptions` from prefix, snapshot, and header, and deep-freezes it while leaving `AbortSignal` live. Per-instance state is only the cached prefix and whether its anchoring snapshot has been written. -**The reconstruction boundary is `step/start`, unconditionally.** A step's messages are the derivation over `events[0..stepStartSeq)`. Because the snapshot precedes the `step/start` append in the same synchronous frame, an `agent.inject()` from an `agent/request` listener or any concurrent task lands after the boundary and joins the NEXT request. `session/event` is observe-only during publication: a reentrant append is rejected until the current callback list drains, preventing nested event delivery from overtaking the event being observed. `agent/pre-step` is the sanctioned seam for content that must affect the CURRENT request. A step's header for reconstruction is the latest `request/header` at or after its `step/start` (before the first response event), or the fold carried forward when the request header is unchanged. +**`step/start` is the reconstruction boundary.** A step derives messages from events before that sequence. Injection after the snapshot joins the next request, and reentrant appends are rejected during event publication. `agent/pre-step` is the seam for content needed by the current request. Header reconstruction selects the step's `request/header`, or carries the prior snapshot when no new header is written. -**Enforcement.** Dev-mode ([dsh-invariants](../../../../packages/support/invariants/src/index.ts)), on `llm/stream`: a frozen request with a live `sessionId` — the loop-built marker; hand-built one-shots are unfrozen and skipped — must carry messages deep-equal to the folded header's `messagePrefix` followed by the boundary derivation — the derivation rebuilt through a FRESH `Session` over `events[0..stepStartSeq)` so the live cache cannot vouch for itself — and header fields equal to `foldRequestHeader` over the log. There is no divergence allowance and nothing to allow: no seam can put unlogged content into a request — the `agent/session-prefix` seam's product enters only because the header event records it first. `prepend: true` only defends against the replay adapter's short-circuit (an append-registered listener); two prepended listeners have no defined mutual order in cordis, so correctness rests on the seq-bounded fold, never on listener timing. Measurement stays lean: the with-key e2e ([request-cache.e2e.ts](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts)) proves `usage.cacheReadTokens > 0` on every request after the first against the live API, and per-step usage in the log is the production observable — a header event or compaction shows up as a cache-read collapse on the next step. +**Enforcement.** In development, `dsh-invariants` independently rebuilds each loop request through a fresh `Session`, so the live cache cannot vouch for itself, then compares messages and folded header fields at `llm/stream`. Loop requests are identified by their frozen shape and session id; direct one-shots are excluded. Correctness depends on sequence-bounded reconstruction rather than listener order. A with-key e2e requires positive cache-read tokens after the first request; per-step usage is the production signal, and a header change or compaction appears as a cache-read drop on the next step. ### The MiniCode shape: adopted, with the provenance arrow inverted -What survives from `LLMClient`: the conversation is maintained, not rebuilt — one projection per message, ever; requests advance append-only; resets happen only for a system-prompt/tool change, a config change, or compaction, each now a *logged* fact. What is deliberately inverted: MiniCode's client is the source of truth and its event stream derives from client appends (`on_event(MessageAdded)`), which suits an advisory event stream. Here the log is contractual — persistence, crash recovery, fork seeding, transcript rendering, and the snapshot harness all replay it — and it carries strictly more than a message list (turn/step boundaries, raw chunk streams, tool-call pairing, provenance, log-only records), so a message-list client cannot generate it. The arrow therefore points log → client: the conversation state IS the log plus two cached folds inside `Session` (messages, header), and the "client" the loop talks to is the session itself. What the inversion buys over the original: the reconstruction is *checkable* against an independent record on every request — MiniCode's client has nothing to check itself against. +Like MiniCode, the conversation advances append-only and resets only when model-visible state changes. Unlike MiniCode, the event log remains the source of truth because it also owns persistence, recovery, boundaries, tool pairing, and provenance. `Session` caches message and header folds derived from that log, making every request independently checkable. ## Alternatives considered - **Client as source of truth** (literal MiniCode): a second operative truth beside the log — the two drift and nothing notices; see the section above. -- **A stateful transmission client mirroring the log** (a `PromptPrefix` class holding committed/open message zones with an append/editTail/reset vocabulary, the log pushed into it per event): behaviorally equivalent on the happy path, but it duplicates conversation state outside the session, needs transactional rollback around listener seams, keeps an unlogged content-shaping surface (`editTail`) whose divergence the invariant must specially allow, and still cannot answer "what header did the model see" from the log. Dissolving it into the session's own caches plus logged header events made every one of those problems unrepresentable instead of guarded. (PR #162 is the archaeology of this alternative, three designs deep.) +- **A stateful transmission client mirroring the log** — duplicates conversation state, needs rollback around listeners, leaves an unlogged edit surface, and still cannot reconstruct request headers. Session-owned caches plus logged headers avoid those split truths. - **Per-call request scalars** (a freely mutable config handed to each `agent/request` dispatch): a listener flips the model per call with zero accounting, silently abandoning the provider cache this design exists to protect. Config is per-conversation logged state; the waterfall proposes, the log records. - **Detect-and-report** (compare consecutive requests, warn on divergence): catches violations after the fact; a violating request is still constructible and ships. Rejected for interface-level unrepresentability. - **Event-driven assembly** (re-render only on change signals): a missed-signal bug class — a tool registered mid-session emits `tools/change`, not `system-prompt/change`, and a third-party provider may emit nothing. Per-step render + value compare is robust with zero signal discipline. -- **A custom header-delta codec** (system line edits, name-keyed tool edits, whole config/prefix replacements): it reduced repeated header bytes but duplicated state across codec types, diff/apply machinery, and fallback handling. Full changed snapshots preserve reconstructability with one representation; compression remains available if measured logs justify it. -- **Narrative changed-field lists on header snapshots**: derivable by diffing consecutive snapshots — one home per fact. Snapshots keep a reason because an instance boundary versus an in-instance change is not derivable from data alone. +- **A custom header-delta codec** (system line edits, name-keyed tool edits, whole config/prefix replacements): reduced repeated bytes but duplicated the representation and its diff/apply/fallback machinery. Full snapshots retain one replay representation. +- **Narrative changed-field lists on header snapshots**: derivable by comparing consecutive snapshots. The `reason` remains because an instance boundary is not derivable from the snapshot values. ## Consequences - A request that is not explained by the log cannot be constructed by accident — not by the loop, not by a listener; mutating a built request throws; every header change is a durable, diffable log event. - Choosing between the advisory channels is a change-frequency decision, and the design makes the stable one structural: an `agent/session-prefix` contribution is composed once per loop instance and reused verbatim, so it extends the cacheable prefix at zero marginal cost and CANNOT bust the provider cache mid-session; content that changes mid-session flows through the append-only history channels — `agent.inject()`, a `tools/post-execute` decision's `additionalContext`, prompt-submit `additionalContext` — each a durable `context/message` paid once and prefix-cached thereafter, at the price of accumulating in history and the log. Route session-frozen openers to the prefix and change notices to the history channels; a per-step request-only tail slot was deliberately dropped (no consumer, and a durable append covers every current update pattern). -- What still costs full price at the provider is inherent and logged: compaction (its `compact/*` events and surface replacement), a real prompt/tool/config change (`request/header` with reason `'change'`), or a process boundary with drift (`'resume'` snapshot differing from its predecessor). The provider's own reasoning-content exclusion is managed server-side. +- What still costs full price at the provider is inherent and logged: compaction (its `compact/*` events and replacement entry), a real prompt/tool/config change (`request/header` with reason `change`), or a process boundary with drift (a differing `resume` snapshot). The provider's own reasoning-content exclusion is managed server-side. - The `step/start`-listener behavior change (above) is the one observable semantics change for plugins; `agent/pre-step` is the current-request seam. - Tool-result trimming (planned) needs no new mechanism: a logged single-entry surface replace (`start === end`) carrying a trimmed `tool/result` under the same `callId` — compaction-family, replay-correct, cache-bust batched by the same pressure logic. -- Session logs grow one `request/header` snapshot per loop instance plus full snapshots on real changes. This spends more bytes than a custom delta codec but stays small beside chunk-heavy logs and leaves one replay representation. `SESSION_FORMAT_VERSION` stays `0`; a legacy v0 delta event is rejected rather than migrated. +- Session logs grow one `request/header` snapshot per loop instance plus snapshots on real changes. This is larger than a delta codec but small beside chunk-heavy logs and retains one replay representation. `SESSION_FORMAT_VERSION` stays `0`; legacy delta events are rejected rather than migrated. - Snapshot goldens changed once (every transcript gains its header events); the fs-writing fixtures are stored in the normalized authored form with cwd-relative tool arguments, because replay only round-trips cwd-independent argument paths. - FIXME(call-config-shape): revisit `LlmCallConfig`'s exact field set — which fields are genuinely epoch-level for cache purposes (`model` certainly; the sampling scalars sit there out of caution), and where provider-specific extras (reasoning options, extra body params) belong when an adapter needs them. diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index a9efbee2b4..955a39fcf6 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -46,19 +46,17 @@ messages = session.deriveMessages() ⟵ single derive, reflects the compaction request = waterfall agent/request ⟵ pure request transform (hooks, model switch) ``` -This makes the layering correct *by construction*: compaction mutates the surface, the loop derives **once** from the result (no double-derive), and at `pre-step` the assembled `messages` do not yet exist — so a listener structurally *cannot* see or be expected to act on downstream-injected context. `agent/request` reverts to a pure request transformer. Firing the seam **before** `step/start` (not inside the open step) is load-bearing for crash-safety: compaction's log-only `compact/*` records and its replacement node land *outside* any step, so the honest log structure a crash leaves (a dangling `compact/start` sitting before the synthetic `turn/end` that turn-repair appends) holds without a half-open step to reconcile. The seam is `serial` (awaited, in registration order), not `parallel`: a listener mutates the surface as a side effect — there is nothing to transform or return — and serial isolates listeners from each other so two surface-mutating listeners can never interleave their `session.append`s. Cordis `serial` does bail early if a listener returns a bail value, so `agent/pre-step` listeners are typed/documented to return `void` and must not use that bail channel as a semantic veto surface. - -This **amends** the original RFC's claim of "NO changes to `dsh-agent-loop`; compaction is a pure plugin." That claim was load-bearing for a wrong design — reusing `agent/request` was the mistake. Per the pre-release "foundation over blast radius" stance, adding the correct seam (one event declaration in `dsh-agent`, one awaited emit in the loop) beats preserving a no-change boast that locked in the double-derive. +The loop derives messages once after `agent/pre-step`. Running before `step/start` keeps compaction records outside any half-open step, simplifying crash repair. The seam is awaited and serial so surface mutations cannot interleave; listeners return `void` and do not use Cordis bail values as vetoes. ### Retention is turn-agnostic; tool-pairing balance is the only structural guard Auto-compaction fires before **every** step, not once per turn. This is **load-bearing for runaway-turn survival**: a tool-heavy ReAct turn appends an `assistant/message` + a `tool/result` per step, so the surface grows *within* a turn. A single turn can grow past the window on its own (a "runaway turn") — and the only moment to rescue it before the next model call overflows is the next step's `pre-step` checkpoint. Gating compaction to a turn's first step (or, worse, retaining the whole in-flight turn verbatim) re-opens exactly the hole compaction exists to close: the harness would die when compaction is most needed. -So retention does **not** protect the in-flight turn, and turn boundaries play no role in it. `compactIfNeeded` walks the surface entries tail→head, summing per-entry token estimates, and retains the smallest tail-run of **whole units** whose total reaches `retainTokens`; everything older is compacted (head-anchored — see below). A *unit* is either a whole closed step (its `assistant/message` plus its `tool/result`s) or a single no-step entry (a pre-step `user/message`, inter-step `steering/message`, or injection `context/message`). The walk rounds toward retaining *more*: when the raw token cutoff lands mid-step, it extends the retained side head-ward until the cut before the retained entry is **tool-pairing balanced**. The single structural guard is therefore **tool-pairing balance** — a region's edges are balanced cuts on the *surface* (no unanswered `tool-call` crosses either edge), so a compacted region never splits a step's tool-calls from their `tool/result`s (which would produce a transcript every provider rejects). The check is decided over surface order, **not** the log's `step/*` markers: a compaction lands a replacement at a high log seq whose surface position is the head, so a log-position scan misreads its neighbours — `dsh-session` exports `isToolPairingBalanced(nodes, events, beforeSeq)` for the surface-anchored check. `compactRegion` enforces it strictly, throwing on a boundary that would split a step. +`compactIfNeeded` retains the smallest tail of whole surface units whose estimated size reaches `retainTokens` and compacts older nodes. A unit is a complete closed step or one no-step message. If the token cutoff lands inside a step, retention expands until the cut is tool-pairing balanced. Balance is checked on surface order, not log sequence, because replacement summaries have new sequence numbers at old surface positions. `compactRegion` rejects boundaries that split a tool call from its result. The in-flight turn receives no special retention. A runaway turn thus compacts exactly like any other history: its early *closed* steps get summarized while its recent steps stay verbatim. When the only compactable content left is an un-splittable open tail step (its tool-calls have no results yet), compaction declines (`null`) and retries once that step closes. -**Single-unit overflow is out of scope, by design.** If a single retained unit — one closed step, or a large free node such as a pasted `user/message` — *alone* exceeds the budget, compaction cannot help and the next model call may go out over-budget. Bounding an individual unit's size is a separate concern (output truncation), handled elsewhere; compaction makes no promise about it, and the harness without such a mechanism can still break on a single oversized unit. This is named honestly rather than papered over. +**Single-unit overflow is out of scope, by design.** If a single retained unit — one closed step, or a large free entry such as a pasted `user/message` — *alone* exceeds the budget, compaction cannot help and the next model call may go out over-budget. Bounding an individual unit's size is a separate concern (output truncation), handled elsewhere; compaction makes no promise about it, and the harness without such a mechanism can still break on a single oversized unit. This is named honestly rather than papered over. ### Head-anchoring: one auto checkpoint, always at the head @@ -70,7 +68,7 @@ Auto-compaction always starts at the surface head, merging the prior checkpoint ### Surface replacement: `compact/*` events are log-only; one `user/message` carries the summary -Because `SurfaceEventType` is closed, the summary cannot ride on a `compact/*` event. The backend instead appends a **single `user/message`** with `surfaceOp: { op: 'replace', start, end }` whose `content` is the (framed) summary and whose `sourceEventSeqs` covers the shadowed nodes *and* the bookkeeping events. The `compact/*` events are pure log records (lock + provenance). The surface mutation sits **inside** the lock — `compact/end` is the last event appended: +Because `SurfaceEventType` is closed, the summary cannot ride on a `compact/*` event. The backend instead appends a **single `user/message`** with `surfaceOp: { op: 'replace', start, end }` whose `content` is the (framed) summary and whose `sourceEventSeqs` covers the shadowed entries *and* the bookkeeping events. The `compact/*` events are pure log records (lock + provenance). The surface mutation sits **inside** the lock — `compact/end` is the last event appended: ``` compact/start → log-only. Acquires the lock. @@ -81,7 +79,7 @@ user/message → surfaceOp { op:'replace', start, end }. THE surface mutatio compact/end → log-only. Releases the lock (carries `error` on a recoverable failure). ``` -`deriveMessages()` then yields `[summary_as_user_message, ...retained_nodes]`. Reusing `user/message` is honest rather than a workaround: a summary genuinely *is* user-role context. +`deriveMessages()` then yields `[summary_as_user_message, ...retained_entries]`. Reusing `user/message` is honest rather than a workaround: a summary genuinely *is* user-role context. ### Checkpoint framing + incremental merge (backend-private) @@ -116,7 +114,7 @@ Two failure paths, both documented: - **New loop seam**: `agent/pre-step` (`@mode serial`) declared in `dsh-agent` and emitted by `dsh-agent-loop` after system assembly and before `step/start`. This is a documented change to the loop — `docs/architecture.md` records it and the generated cordis catalog carries its signature. - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry. - **`dsh-session`** gains the tool-pairing balance predicate (`isToolPairingBalanced`, in `tool-pairing.ts`, exported from the package index) that `compactRegion`/`compactIfNeeded` use to keep a collapsed region from splitting a step's tool-call/result pair. The surface `replace` op and the surface-metadata runtime guard already existed and are reused. -- **`dsh-invariants`** drops its `surface replace: start must be <= end` assertion: a head-anchored compaction lands a high-seq replacement node at an older range's *position*, so `start > end` numerically is normal and valid (the range is positional, validated by the surface's `indexOf` checks that remain). The turn-enclosure invariant is reused unchanged. +- **`dsh-invariants`** drops its `surface replace: start must be <= end` assertion: a head-anchored compaction lands a high-seq replacement entry at an older range's *position*, so `start > end` numerically is normal and valid (the range is positional, validated by the surface's `indexOf` checks that remain). The turn-enclosure invariant is reused unchanged. - **Wiring**: `dsh-compact-basic` is loaded in `examples/coding-agent`'s `cordis.yml`, so the seam ships in the real demo (it was previously loaded nowhere). ## Testing diff --git a/docs/rfc/implemented/feature/2026-07-06-sandbox.md b/docs/rfc/implemented/feature/2026-07-06-sandbox.md index 3e2180484e..e236154cdc 100644 --- a/docs/rfc/implemented/feature/2026-07-06-sandbox.md +++ b/docs/rfc/implemented/feature/2026-07-06-sandbox.md @@ -105,11 +105,11 @@ interface SessionEventMap { Each owner exports the same three-piece kit: the event declaration, a pure fold (`effectiveSandboxMode(events)` / `effectiveApprovalPolicy(events)` — a `findLast`, typed to the domain's closed union), and THE write path (`setSandboxMode(session, mode)` / `setApprovalPolicy(session, policy)` — a switch IS its event; nothing mutates state out of band). No shared owner service, no generic facts map, no registry: a third knob copies the ~40-line pattern into its own package. Execution follows the fold on both sides — the bash tool's per-call stamp reads it as the middle rung of the § Escalation precedence chain, and the approval seam's `'never'` gate is [the approval RFC](2026-07-06-approval-seam.md)'s side of the same pattern. -**Visibility is deliberately asymmetric between the knobs.** The SANDBOX mode is stated nowhere and its switches are not narrated: a standing "you are read-only" declaration teaches the model to refuse preemptively (observed live: sessions where the model would not even attempt a write it could have escalated), while the denial marker already names the mode the command ran under at exactly the moment the boundary matters — behavior, not belief, carries the state, and a switch simply changes what the next command does. The APPROVAL policy keeps both layers, because its failure mode is the opposite: an auto-rejected ask under `'never'` returns "the user rejected …" wording no behavior can disambiguate, so the prompt states `'never'` (and ONLY `'never'` — an `'ask'` promise is unknowable without asking, and absence under a logged header is how the narrator reads `'ask'` back), and an `agent/pre-step` narrator injects at most one coalesced notice per policy switch: idle flip-flops collapse to one notice at the next turn's first step, a net-zero round trip to none, and a mid-turn change is narrated no later than the next step. Its "last told" is in-memory with a log-derived fallback (the folded header's system text parsed against the closed candidate sentence; LAST occurrence wins, so a persona quoting it cannot shadow the real section), so restarts lose nothing; attribution is positional (a knob event after the log's last `request/header` reads `changed by the user`, a drift with no such event reads `changed by the operator/config`). +Sandbox mode is not narrated in the prompt; denial results report the mode when it matters, avoiding preemptive refusal based on a standing label. Approval policy is different: only `'never'` is stated because automatic rejection otherwise looks like a user decision. Policy-change notices are coalesced and delivered by the next pre-step, with log-derived fallback after restart. The notice source is inferred from event position: a knob event after the last request header is user-driven; unlogged drift is operator or config driven. **The editor surface** is protocol-native [Session Config Options](https://agentclientprotocol.com/protocol/session-config-options) — the spec's replacement for session modes (slated for removal in ACP v2), already SDK-typed. When `ctx.permission` is composed, the bridge advertises one `permission` select (category `mode`) in `session/new` and `session/load`; its options are the deployment's preset table, and its `currentValue` is `PermissionService.current()` over the session log plus composition defaults. The shipped `workspace-write` and `danger-full-access` presets each bundle a sandbox mode with an approval policy and write through to both domain setters; a knob combination outside the table is reported as switch-away-only `custom`. `session/set_config_option` validates and switches through the permission service, then returns the complete refreshed state (the spec contract). -**Anchoring: turn-enclosure is the commit boundary.** The turn-enclosure contract makes a bare between-turns append invalid (the JSONL backend treats a post-`turn/end` tail as crash garbage; dev invariants throw). A switch while a turn is open appends immediately — openness read from the LOG (last boundary event is `turn/start`), not `agent.status`, which stays `running` between queued turns. An idle switch is held on the bridge's session record and anchored at the next turn's `agent/prompt-submit` — inside the turn, before anything in it assembles or executes, last write per knob, and OUTSIDE any `session/event` emit (appending from inside that feed reorders events for later-registered listeners — a bug the dev invariants caught live). Until anchored, the switch exists only in bridge memory: responses overlay it truthfully, and a crash before the next turn reverts it — `session/load` then reports the fold's truth, so the editor UI self-corrects rather than lies. +**Turn enclosure is the commit boundary.** A switch during an open turn appends immediately. An idle switch remains pending on the bridge record and is appended at the next prompt submission, before assembly or execution; last write wins per knob. Openness comes from log boundaries rather than `agent.status`, and setters do not append from inside a `session/event` listener because that would reorder later observers. Until anchoring, responses overlay the pending value. A crash discards it, and reload returns the durable fold. #### In-process tools @@ -119,10 +119,10 @@ FIXME: Revisit this tool-local boundary. The follow-up design needs to determine ### Testing -- Unit tier (no real runner anywhere): profile dialects, per-platform chain selection (sole candidate unprobed, no chain fails closed, multi-candidate probe order), verdict caching, the fail-closed end, probe-report parsing, and the launcher/`sandbox-exec` CLI contracts via fake runner scripts in `dsh-sandbox-local`; wrapping, policy hand-off, fact stamping, and runner-failure-outranks-denial classification (foreground throw, background `runnerFailed` fact) against a fake provider in `dsh-bash-sandbox`; the error's structured identity in `dsh-sandbox`. The escalation matrix spans the three bash packages: verbatim carry-through in `dsh-bash-local`, stamp/branch/per-task-facts in `dsh-bash-sandbox`, and the capability gate, `justification` pairing, fail-closed texts (pinned verbatim), and grant stamping in `dsh-tool-bash`. The switching surface pins the folds, the stamping precedence, the `'never'` gate, per-session section rendering, the full narrator matrix (cold start, coalescing, net-zero, resume drift with operator wording, positional attribution, persona-shadow hardening), and the bridge's advertisement gating, validation rejections, idle-vs-mid-turn anchoring (dev invariants mounted), and `session/load` reporting over a real two-process JSONL round trip. -- Keyless real-runner e2e, split along the seam and per rung: CI's `sandbox-e2e` matrix runs bwrap and Landlock on Linux (the Landlock leg once per architecture, each confining through the registry-installed launcher) and Seatbelt on macOS against real kernels, failing on a silent all-skip. World-proofs live in `dsh-sandbox-local` (denied writes absent on disk, workspace writes landing, temp-area grants pinned, kernel denial text matching the advertised dialect) and `dsh-bash-sandbox` (the through-`ctx.bash` consumer proofs, including denied-then-overridden-write-lands). This package's own publish path is rehearsed without publishing (`packed-install.e2e.ts`): `pnpm pack`, tarballs installed into a throwaway consumer with the launcher family resolving from the registry, plain `node` confining through the INSTALLED launcher — asserted executable apart, so a mode-stripped binary can never masquerade as a non-enforcing kernel. The switching surface has its own keyless e2e (the acp-agent example's `escalation.e2e.ts`): the real default `cordis.yml` tree advertises the one permission option, honors switches end to end, and rejects out-of-vocabulary values. -- With-key e2e (`examples/acp-agent/tests/escalation.e2e.ts`): real model + real runner + the REAL bridge answerer, world-verified — denied under `read-only`, escalates with justification, the scripted editor grants and the retried write lands on disk, while a rejected escalation leaves no write. Self-skips without `DEEPSEEK_API_KEY` or a usable runner (e2e.yml installs bubblewrap so it actually executes in CI). -- Snapshot tier (`examples/acp-agent/tests/acp.snapshot.ts`): the keyless config-option wire; the recorded permission-switching arc as the pinned header of its class — necessarily, since mid-session switches emit the changed `request/header` snapshot the uniformity guard licenses only in the pin — committing one `workspace-write`→`danger-full-access` preset switch (the `permission/preset` event written through to both knobs), the changed approval prompt section and its "changed by the user" notice; and both recorded escalation branches over scripted `permissionAnswers` (grant runs under the granted `danger-full-access`; rejection executes nothing and pins the fail-closed text). Snapshot mode starts the shared example tree at `danger-full-access` so established fixtures remain runner-independent; the switching and escalation inputs explicitly select `workspace-write` before exercising the policy path. Deliberately absent: a fixture carrying a real DENIAL — denial stderr is the backend's dialect and would pin a fixture to its recording platform; the escalation prompts assert the prior denial instead, and the denial→marker path stays on the real-runner tiers above. +- **Unit:** pin platform selection and profiles, fail-closed runner classification, per-call facts, escalation validation and outcomes, permission preset folding and write-through, narrator coalescing, ACP advertisement and validation, and turn-enclosed config writes. +- **Keyless real-runner:** exercise bwrap, Landlock, and Seatbelt against real filesystem effects at provider and bash-consumer layers; packed-install coverage proves the registry launcher remains executable. The real ACP composition pins permission switching and rejects unknown presets. CI rejects a silent all-skip. +- **With-key:** drive a real model, runner, bridge answerer, and disk effect through granted and rejected escalation; unavailable credentials or runners self-skip. +- **Snapshot:** pin the permission config-option wire, preset and knob events, prompt deltas and notices, and both scripted approval branches. Snapshot mode starts unconfined so unrelated fixtures remain platform-independent; policy scenarios switch explicitly. Real denial stderr stays on platform tests because its dialect is runner-specific. ## Deferred phases @@ -155,7 +155,7 @@ Each phase gets its full design when picked up, validated against the code at th - **A generic `env/state` facts map with an owner service** — rejected: approval and sandbox compose independently, so neither's state may drag in a third package; single-key folds are one `findLast` each, dissolving the owner service; no invariant spans the knobs, so atomic multi-key patches bought nothing. - **Narrate via `agent/user-message` + a bus event** — rejected: it presupposes a turn-entry seam that does not exist (the real seam is `agent/prompt-submit`), and pre-step's position serves both the coalesced turn-entry notice and the mid-turn immediacy bound with one listener. - **A standing prompt statement of the sandbox mode (+ a switch narrator)** — shipped first, then removed on live evidence: with `Bash commands run under the "read-only" file sandbox.` in every request, the model refused to ATTEMPT denied-then-escalatable work (five of twelve turns in the first manual session ended with zero tool calls), turning the sandbox into a soft lockout. The denial marker names the mode at the moment it matters and the escalation fields carry the recovery; the approval knob keeps its statement because an auto-rejection is behaviorally indistinguishable from a human "no". -- **Track "last told" with its own bookkeeping events** — rejected: the latest `request/header` already records the exact prompt the model saw; parsing the closed candidate sentences back replaces a second bookkeeping stream — events are needed only where they ARE the store. +- **Track "last told" with its own bookkeeping events** — rejected: the `request/header` fold already records the exact prompt the model saw; parsing the closed candidate sentences back replaces a second bookkeeping stream — events are needed only where they ARE the store. - **ACP session modes instead of config options** — rejected: the preset is already one deployment-defined config-option select, and modes are slated for removal in ACP v2. ## Consequences diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index c879dabfa1..d32264cd2f 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -337,13 +337,7 @@ export class BasicCompactService extends CompactService { agent: Agent, signal?: AbortSignal, ): Promise { - // Resolve the range by surface POSITION, not numeric seq interval. A prior - // replace lands a fresh high-seq summary node AT the shadowed range's - // position, so the surface order (head→tail) no longer tracks seq order — - // `[newSummarySeq, olderRetainedSeq, …]` is normal. Indexing into the - // ordered node list and slicing it is the only correct way to read a range; - // a `seq >= start && seq <= end` interval test would mis-collect - // nodes (and `start > end` would falsely reject) once that happens. + // Resolve by surface position: a newer replacement seq may occupy an older slot. const nodes = session.surface.nodes const startIdx = nodes.indexOf(start) const endIdx = nodes.indexOf(end) @@ -510,14 +504,8 @@ export class BasicCompactService extends CompactService { // The whole surface fits the retain budget — nothing to compact. if (keepFromIdx === 0) return null - // Round the cutoff to a tool-pairing boundary: if the cut before - // `nodes[keepFromIdx]` is unbalanced (an unanswered tool-call sits before - // it — i.e. it is mid-step), extend the retained side head-ward until the - // cut is balanced, so the compacted range ends without splitting an - // assistant↔result pair. A node that belongs to no step is already a - // balanced (free) boundary. Decline if no balanced cut exists at or below - // `keepFromIdx` (the compactable range is only an un-splittable open tail - // step — retry once it closes). + // Round the cutoff head-ward to a tool-pairing boundary; decline when no + // safe compactable prefix exists. while (keepFromIdx > 0) { // eslint-disable-next-line @typescript-eslint/no-non-null-assertion if (isToolPairingBalanced(nodes, events, nodes[keepFromIdx]!)) break diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 44ae51ccad..140ad5efb0 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -1548,40 +1548,23 @@ describe('BasicCompactService edge cases', () => { describe('BasicCompactService positional range (surface seqs are not monotonic after a replace)', () => { it('compacts a second region after the first replace lands a high-seq summary at the head position', async () => { - // A replace inserts the new summary node (a high seq) AT the shadowed - // range's surface position, so the surface becomes - // [highSeqSummary, …olderRetainedLowerSeqs]. A second compaction over a - // range whose start node has a HIGHER seq than its end node must still - // succeed — the range is positional, not a numeric seq interval. + // Replacement can make surface seqs non-monotonic; ranges remain positional. const svc = createTestService({ auto: false }) const session = multiTurnSession(4, 1) - // First compaction: shadow the two oldest surface nodes. const nodes0 = session.surface.nodes const first = await compactRegion(svc, session, nodes0[0]!, nodes0[1]!, 'm') - // The summary node now sits at the head with a seq HIGHER than the - // retained older nodes that follow it — the non-monotonic surface. (The - // head is the user/message replace node, appended after the compact/summary - // provenance event, so its seq is at least first.summarySeq.) const nodes1 = session.surface.nodes expect(nodes1[0]!).toBeGreaterThanOrEqual(first.summarySeq) expect(nodes1[0]!).toBeGreaterThan(nodes1[1]!) - // Second compaction: shadow [summary(head) … turn-2's step end]. The start - // seq (the head summary node) is GREATER than the end seq (an older retained - // node), so the range is a SURFACE-POSITION span, not a numeric seq interval. - // The end must land on a step boundary (turn-2's assistant message closes - // its step). const startSeq = nodes1[0]! const endSeq = nodes1[2]! expect(startSeq).toBeGreaterThan(endSeq) const second = await compactRegion(svc, session, startSeq, endSeq, 'm') - // Exactly the three nodes at surface positions [0..2] are shadowed, in - // surface order — the positional slice, regardless of their seq values. expect(second.shadowedSeqs).toEqual([nodes1[0]!, nodes1[1]!, nodes1[2]!]) - // The surface still derives cleanly: a new head replace node + the rest. const finalNodes = session.surface.nodes expect(finalNodes[0]!).toBeGreaterThanOrEqual(second.summarySeq) expect(session.deriveMessages().length).toBe(finalNodes.length) @@ -1591,20 +1574,13 @@ describe('BasicCompactService positional range (surface seqs are not monotonic a const svc = createTestService({ auto: false }) const session = multiTurnSession(3, 1) - // First compaction shadows the oldest two surface nodes, landing a high-seq - // summary node at the head. const n0 = session.surface.nodes await compactRegion(svc, session, n0[0]!, n0[1]!, 'm') - // Second compaction spans [head summary … turn-2's step end]. The head's seq - // is higher than the older retained nodes' seqs, so a log-seq-order walk - // would emit the older messages BEFORE the checkpoint. const n1 = session.surface.nodes svc.summarizeCalls = [] await compactRegion(svc, session, n1[0]!, n1[2]!, 'm') - // The extracted transcript follows surface order: the checkpoint (head) - // first, then the older retained messages — matching deriveMessages(). const { text } = svc.summarizeCalls[0]! const checkpointIdx = text.indexOf('compacted-summary') const olderIdx = text.indexOf('turn 2 user') diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index 7054b683cb..721c2a1eff 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -1,11 +1,8 @@ /** - * Loop-level reconstructability: every request the loop sends is a pure - * function of the session log — messages are the derivation at the step/start - * boundary, the header is the latest request/header snapshot — and every - * request is an append-extension of its predecessor unless a logged event - * (compaction replace, header change) explains the difference. The requests - * recorded by the mock adapter are the observable; the offline-rebuild test - * at the bottom is the theorem stated end-to-end. + * Loop-level reconstructability: every request the loop sends is a pure function of the + * session log — messages derive at the step/start boundary and the header is the latest + * request/header snapshot. Each request extends its predecessor unless a logged compaction + * replacement or header change explains the difference. */ import { describe, expect, it } from 'vitest' diff --git a/packages/core/session/README.md b/packages/core/session/README.md index 3f11876c3b..a65765df39 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -1,6 +1,6 @@ # dsh-session -Event-sourced session log and in-memory store. A `Session` is the append-only source of truth for an agent's whole interaction history — the LLM message history is *derived* from it. A **surface** layer (an ordered sequence of message-producing event seqs) is maintained on top of the raw log for efficient derivation and compaction. +Event-sourced session log and in-memory store. A `Session` is the append-only source of truth for an agent's whole interaction history — the LLM message history is *derived* from it. A **surface** layer (an ordered projection of message-producing events) is maintained on top of the raw log for efficient derivation and compaction. ## Service: `SessionStore` (ctx key: `sessions`) @@ -8,35 +8,35 @@ Creates and holds event-sourced `Session` instances. Persistence is intentionall ### Public API -- `ctx.sessions.create(id?: SessionId, options?: { seed?: readonly SessionEvent[]; meta?: { cwd?: string; parentSession?: SessionId; createdAt?: number; seedLength?: number } }): Session` — Create a session. The persistence/replay seed and resulting header are validated, detached, and deep-frozen at this durable boundary. The store fills `version`/`id` and defaults `createdAt` to now; a persisted reconstruction supplies the original `createdAt` and `seedLength`. Disposed with the calling fiber. -- `ctx.sessions.flush(session: Session): Promise` Dispatch the awaited `session/flush` durability checkpoint with the carrier captured at enter — THE flush entry point (the loop's turn-end checkpoint and idle injection call it; never dispatch a raw `ctx.parallel`). Every captured listener starts, the call waits for all of them to settle, and a failure rejects only after the other listeners finish. Rejects a prepared, detached, or stale same-id object instead of inventing a subject-less carrier. +- `ctx.sessions.create(id?, { seed?, meta? }?)` validates and detaches durable seed/header data, fills the version and id, defaults `createdAt` to now, publishes the session, and binds it to the calling fiber. Persisted reconstruction supplies its original `createdAt` and `seedLength`. +- `ctx.sessions.flush(session)` dispatches the awaited parallel durability checkpoint through the session's captured scope. Every listener starts and the call waits for all to settle before reporting failure; unpublished, detached, and stale objects reject. - `ctx.sessions.fork(source, boundary?, childSessionId?): Session` — Resolve a live session object or id, select a seed through the inclusive `boundary` event seq (default: current last event), require that boundary to be `turn/end`, and create a live child session with lineage metadata. - `ctx.sessions.get(id: SessionId): Session | undefined` - `ctx.sessions.list(): Session[]` #### Advanced: ordered-teardown lifecycle primitives -`create()` covers the common case (the session is owned by the calling fiber). When a session must be torn down **in order with another resource** — so a final flush is captured before the store attachment and publication hooks are removed — `create()`'s self-contained effect is wrong, because a fiber unload disposes sibling effects *concurrently*. For that, split the lifecycle and fold it into the owner's single effect: +Use the split lifecycle only when teardown must be ordered with another resource: -- `ctx.sessions.prepare(id?, options?): Session` — validate durable seed/header data and construct the `Session` WITHOUT entering it into the store. Same options as `create`. -- `ctx.sessions.enter(session): () => void` — perform the authoritative ID collision check, install append publication state, and insert the exact session without announcing it. Returns an idempotent detach bound to the captured entry object, so a stale disposer cannot remove a later same-ID replacement. Concurrent same-ID preparation is allowed; only one final entry succeeds. -- `ctx.sessions.announce(session): void` — begin the one allowed `session/created` announcement for an entered session; repeat and reentrant calls reject before dispatch. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, so another creation listener cannot observe `session/disposed` before its own `session/created` callback. Detach emits `session/disposed` exactly once, including rollback after a partially delivered creation notification; a never-announced entry emits neither edge. +- `prepare(id?, options?)` validates and constructs without publication. +- `enter(session)` performs the collision check, publishes without announcing, and returns an entry-bound idempotent detach. Concurrent same-id preparations are allowed, but only one entry succeeds; a stale detach cannot remove its replacement. +- `announce(session)` emits the single creation edge and rejects repeat or reentrant announcements. Detach during that dispatch is deferred and later emits the paired disposal edge; an unannounced entry emits neither lifecycle edge. -`dsh-agent-loop` is the canonical consumer: after unpublished agent setup it enters both session and agent before announcing either, then nests loop stop, agent removal, session detach, and scope unwind in one ordered lifecycle. The final flush therefore settles before this package detaches the session, whether teardown starts from an `AgentHandle` or owner-fiber unload. +`dsh-agent-loop` uses this split so final loop flush precedes session detach; see the [ownership RFC](../../../docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md). ### Live service events -The store pairs announced creation with disposal, publishes each append, and provides an awaited durability checkpoint. Before the log push it resolves the scoped `session/event` callback list. The push is the commit point; callback throws or returned-promise rejections are logged and contained per observer. A committed append therefore returns normally, later observers still run, and detach waits until publication unwinds. Exact `session/*` signatures, modes, and scope-carrier behavior live in the generated [Cordis event catalog](../../../docs/cordis-catalog/events.md); the append-only payload vocabulary is separately generated into the [persistence catalog](../../../docs/persistence-catalog.md). +The store pairs announced creation with disposal, publishes post-commit append notifications with per-listener containment, and provides an awaited durability checkpoint. Exact signatures and scope behavior live in the generated [event catalog](../../../docs/cordis-catalog/events.md); payloads live in the [persistence catalog](../../../docs/persistence-catalog.md). ### Class: `Session` Plain class (not a Cordis Service). Create via `ctx.sessions.create()`. -- `session.append(type, data, opts?): SessionEvent` — synchronous, never blocks on I/O. At this durable boundary, data and surface metadata are lossless-JSON snapshotted and deep-frozen. For an attached session, a reentrant append during dispatch/observer publication rejects, and detach waits for that publication to unwind. Callbacks resolve before the log push; the push is the commit point, after which each observer failure is contained independently. Runtime surface validation covers widened unions and raw seed/load logs. -- `session.deriveMessages(): Message[]` — the LLM message history, CACHED: each surface entry is projected exactly once, when first seen (O(new entries) per call; a surface rewrite rebuilds via `surface.replaceGeneration`). Returns a fresh array per call over shared, deep-frozen `Message` objects. Each projection reuses the already deep-frozen content in its durable log event, so no second deep clone is needed and a consumer still cannot mutate logged data. The surface is the single source of derived history — there is no raw-log fallback. -- `session.deriveEventMessage(event): Message | null` — the per-event projection `deriveMessages()` folds: a fresh message wrapper that reuses the event's already frozen content, or `null` when the event produces none (a non-surface event, or an empty-content `assistant/message` hosting only usage). External reconstructors and the dev invariant fold the same function over a log prefix's surface, so no two paths can disagree about what a request's messages were (the reconstructability RFC). -- `session.surface: SurfaceManager` — the derived surface, lazily folded from `surfaceOp` markers in the log. Processes only new events (delta) on each access — the log is append-only, so prior events never change. `surface.replaceGeneration` is the rewrite signal: bumped by every folded `replace` and never reset, so an incremental consumer comparing generations cannot be fooled. -- `session.events` — a cached, frozen array snapshot over deep-frozen events. Repeated reads without an append return the same array; an append invalidates the cache and the next read returns a new snapshot, while earlier snapshots stay unchanged. Neither a cast nor a retained reference can push into the live log or rewrite an accepted event. +- `session.append(type, data, opts?)` snapshots and freezes durable data and surface metadata, commits synchronously, then notifies observers with independent failure containment. Reentrant attached-session appends reject, and runtime checks cover widened unions and loaded logs. +- `session.deriveMessages()` incrementally projects each new surface entry once and returns a fresh array over shared frozen messages. A surface rewrite rebuilds the projection; there is no raw-log fallback. +- `session.deriveEventMessage(event)` is the canonical per-event projection used by reconstruction and invariants. +- `session.surface` lazily folds only new `surfaceOp` markers; `replaceGeneration` changes on every rewrite. +- `session.events` is a cached frozen snapshot invalidated by append; accepted events remain deeply frozen. - `session.seq`, `session.id` — current sequence and readonly typed identity. - `session.header: SessionHeader` — detached, deep-frozen creation metadata (`version`, `id`, `createdAt`, optional `cwd`/`parentSession`/`seedLength`). Construction validates the durable record and requires its id to match `session.id`. @@ -49,11 +49,11 @@ Durable values need one accepted representation, not a check followed by a secon - `SurfaceOp` — how an event entered the ordered surface: `'append'` (normal tail append) or `{ op: 'replace', start, end }` (replace entries from `start` through `end` inclusive — both must be valid surface seqs; `start === end` replaces one entry). Used by compaction to shadow old events without deleting them. - `SurfaceIntent` — `{ surfaceOp: SurfaceOp; sourceEventSeqs?: number[] }`, the required third parameter to `session.append()` for surface-eligible types. - `foldSurface(events)` — replay the canonical surface transitions into detached current event sequences and actual replacement ranges, rejecting surface-eligible events that lack their mandatory marker. `SurfaceManager` shares the same transitions while retaining only its incremental sequence cache. -- `isSurfaceEvent(event)` / `isSurfaceEligibleType(type)` — the first narrows a `SessionEvent` to a fully formed surface event (type is surface-eligible AND `surfaceOp` present); the second is the type-only check, used to detect a surface-eligible event MISSING its marker when validating a seed or loaded log. +- `isSurfaceEvent(event)` / `isSurfaceEligibleType(type)` — the first narrows a `SessionEvent` to a fully formed surface event; the second is the type-only check used to detect a surface-eligible event missing its marker when validating a seed or loaded log. ### Request-header reconstruction (`request-header.ts`) -The `request/header` event records a full canonical `EpochHeader` snapshot with reason `initial`, `resume`, or `change`, making the request envelope logged session state and every conversation request a pure function of the log. `foldRequestHeader(events)` selects the latest snapshot from a log or prefix; `canonicalHeader` pins the one representation of absence (empty system/tools/messagePrefix ≡ absent fields), and `headerEquals` compares canonical headers. `EpochHeader.messagePrefix` is the durable record of the `agent/session-prefix` waterfall's product — composed once per loop instance, the request is `messagePrefix + derived history`, and `deriveMessages()` never returns it. Legacy v0 seeds containing the removed `request/header-delta` event or its full-snapshot `fallback` reason are rejected rather than partially replayed. +`request/header` records a full canonical snapshot of the non-history request envelope with reason `initial`, `resume`, or `change`. `foldRequestHeader()` selects the latest snapshot; legacy delta events and the removed `fallback` reason are rejected. `messagePrefix` remains separate from derived history. See the [reconstructable-requests RFC](../../../docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md). ### Session event vocabulary (`types.ts`) @@ -65,7 +65,7 @@ Also defines `TurnTriggerMap` and `TurnEndReasonMap` (merge-extensible sum types Every `SessionEvent` carries two optional top-level fields (structural metadata): -- `sourceEventSeqs?: number[]` — seq numbers of provenance sources (e.g., the `assistant/chunk` seqs behind an `assistant/message`, or the shadowed nodes behind a compaction replace node). +- `sourceEventSeqs?: number[]` — seq numbers of provenance sources (e.g., the `assistant/chunk` seqs behind an `assistant/message`, or the shadowed entries behind a compaction replacement entry). - `surfaceOp?: SurfaceOp` — how this event entered the surface. Absent for non-surface events (boundaries, chunks, usage, errors). ### Metadata types (`types.ts`) @@ -76,15 +76,15 @@ Every `SessionEvent` carries two optional top-level fields (structural metadata) - Persistence plugins: subscribe to `session/event` (write-behind) and drain on `session/flush` (awaited) and fiber dispose. A durable backend reads the log and reloads it into a live session; the metadata seam (`SessionHeader`, `session.header`) is what such a backend stores beside the log. - Replay/fork: `create(id, { seed })` validates and freezes a contiguous log and rebuilds its surface. `fork(source, boundary?, childSessionId?)` selects a completed-turn prefix and records lineage. -- Compaction: the `dsh-compact-basic` plugin appends a `user/message` with `surfaceOp: { op: 'replace', start, end }` to shadow old surface nodes behind a summary checkpoint. +- Compaction: the `dsh-compact-basic` plugin appends a `user/message` with `surfaceOp: { op: 'replace', start, end }` to shadow old surface entries behind a summary checkpoint. ## Model Experience ### Derived message history -**What the model sees**: The model receives projections of `user/message`, `assistant/message`, and `tool/result` surface nodes verbatim. A `context/message` is a user-role message containing exactly ``, its content blocks, and ``; `steering/message` uses the identical `` / `` wrapper. Tool calls live inside assistant messages. Chunks, boundaries, usage, hook records, todo records, and other log-only events add no message. +**What the model sees**: The model receives projections of `user/message`, `assistant/message`, and `tool/result` surface entries verbatim. A `context/message` is a user-role message containing exactly ``, its content blocks, and ``; `steering/message` uses the identical `` / `` wrapper. Tool calls live inside assistant messages. Chunks, boundaries, usage, hook records, todo records, and other log-only events add no message. -**Token effect**: Appended surface nodes are resent on later steps. A `replace` surface operation removes the shadowed nodes from future inputs without deleting their raw log records. +**Token effect**: Appended surface entries are resent on later steps. A `replace` surface operation removes the shadowed entries from future inputs without deleting their raw log records. ### Crash-repair result diff --git a/packages/core/session/tests/surface.spec.ts b/packages/core/session/tests/surface.spec.ts index 5f09efe089..53c9abfccc 100644 --- a/packages/core/session/tests/surface.spec.ts +++ b/packages/core/session/tests/surface.spec.ts @@ -108,14 +108,10 @@ describe('SurfaceManager', () => { it('rebuild with replace operation splices out shadowed nodes', () => { const s = surfaceSession() - // seq: 0=turn/start, 1=user, 2=assistant, 3=turn/end - // Surface nodes: seq 1 (user), seq 2 (assistant). - // Replace both with a compaction marker. Both 1 and 2 are valid surface seqs. s.append('assistant/message', { turn: 2, step: 1, content: [{ type: 'text', text: 'summary' }] }, { surfaceOp: { op: 'replace', start: 1, end: 2 }, sourceEventSeqs: [1, 2] }, ) - // Now the surface should have just the compaction node. expect(s.surface.nodes).toEqual([4]) }) diff --git a/packages/ui/user-approval/README.md b/packages/ui/user-approval/README.md index b4fe3420ef..cebd25275e 100644 --- a/packages/ui/user-approval/README.md +++ b/packages/ui/user-approval/README.md @@ -1,16 +1,14 @@ # @deepseek-ai/dsh-user-approval -User-approval seam. Owns the `ctx.approval` service ([`ApprovalService`](src/index.ts)) and the one-shot permission vocabulary the harness shares: `ApprovalRequest` (agent + tool identity + reason + abort signal), the closed `ApprovalOutcome` union (`allowed-once` / `rejected` / `cancelled` / `unavailable`), the `ApprovalRequestId` brand pairing the two log-only audit events (`approval/asked` / `approval/decided`), and the `approval/request` waterfall the answerers listen on. It lives in the UI group because its purpose is human permission, while remaining channel-neutral: it depends only on Cordis and core vocabulary packages, never on a concrete UI. +Channel-neutral one-shot approval seam. `ctx.approval.request(req)` returns `allowed-once`, `rejected`, `cancelled`, or `unavailable`; missing or failing answerers fail closed, and a grant applies only to the requested action. Exact event signatures live in the generated [Cordis catalog](../../../docs/cordis-catalog/events.md). -The contract in one line: `ctx.approval.request(req)` puts exactly one question — "may this specific action proceed?" — to whatever answerers the deployment composed, and its answerer phase always produces an outcome: an aborted signal yields `cancelled`, a throwing or missing answerer yields `unavailable`, and `allowed-once` is a grant for the single asked-about action, never a class of future ones. `ApprovalRequest` is a readonly same-process contract: the service borrows the exact request, agent, session, and abort signal rather than cloning or freezing them. The request requires an open turn because the audit pair is turn-enclosed by contract (the turn is the durable log's commit/replay boundary; a bare event between turns is crash-tail garbage on reload), so an idle ask rejects before appending. Either audit append may reject before commit because returning an unlogged decision would violate the pair. Session contains post-commit observer failures, so an authoritative audit append cannot reject the request or suppress its matching event. +Each request must belong to an open agent turn. The service appends a paired `approval/asked` and `approval/decided` audit record, while the model sees only the resulting logged tool outcome. An aborted request resolves `cancelled`; an audit append that fails before commit rejects rather than returning an unlogged decision. -The service is the mechanism, answerers are the policy. Answerers are `approval/request` waterfall listeners occupying a single decision slot: answer for an agent you own by returning an outcome without calling `next()`, or delegate an agent you don't recognize by calling `next()` — the chain's built-in default is `unavailable`, so a deployment with no answerer (headless, CI) fails closed with zero configuration. Dispatch is keyed by `req.agent`: a listener registered through `agent.ctx` receives only that agent's questions, while a plain-context listener receives every agent's. Registration order across sibling plugins is not load-order deterministic; compose one terminal answerer per deployment and use `prepend` listeners only for decide-or-delegate gates. +Answerers are `approval/request` waterfall listeners. Return an outcome to answer for an owned agent or call `next()` to delegate. Agent-scoped listeners receive only that agent's requests; compose one terminal answerer per deployment because sibling listener order is not a policy priority mechanism. The ACP bridge is the shipped human answerer. -The seam also owns the per-session POLICY tier ([the sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)): `ApprovalPolicy` is `'ask'` (delegate to the answerers) or `'never'` (deterministically reject without prompting anyone; the strict CI/unattended stance), with `effective = fold(the session's 'approval/policy' events, last one wins) ?? Config.policy` — the session log is the store, written only through `setApprovalPolicy(session, policy)`, which rejects any value outside that closed vocabulary before appending. The service decides `'never'` inside `request()` itself, before dispatching the waterfall (`'never'` → `'rejected'` with the audit pair still landing; no listener registration, including a later `prepend`, can precede it), states `'never'` — and only `'never'` in prose — in a per-agent prompt section, records either value with a source-owned header marker, and narrates a policy switch to the model in at most one coalesced `agent/pre-step` notice. The restart fallback reads the marker rather than deployment-controlled persona prose; attribution is positional (an override event after the last `request/header` reads `changed by the user`, otherwise `changed by the operator/config`). +`ApprovalPolicy` is `'ask'` or `'never'`. The effective value is the last `approval/policy` event, falling back to config; `setApprovalPolicy()` is the write path. `'never'` rejects before interactive dispatch and is the only policy stated in the prompt. Switches produce at most one coalesced notice, attributed to the user when the override follows the last `request/header` and to operator/config otherwise. -One seam serves both ask paths of [the sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md): the `tools/pre-execute` `ask` decision (routed by [`@deepseek-ai/dsh-tools`](../../core/tools/) when this service is mounted; degrading to deny when it is not), and the sandbox post-denial escalated retry (the bash tool's `sandbox_permissions` gate in [`@deepseek-ai/dsh-tool-bash`](../../bash/tool-bash/) — [the sandbox RFC § Escalation](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)). The full design: [the approval-seam RFC](../../../docs/rfc/implemented/feature/2026-07-06-approval-seam.md). - -Answerers today: the ACP bridge ([`@deepseek-ai/dsh-acp`](../../ui/acp/)) forwards to the editor's `session/request_permission` prompt for agents it owns. The audit events are log-only session records — the model only ever sees the tool result the asker derives from the outcome. +The tools pipeline routes `ask` decisions through this seam and fails closed when it is absent; the sandboxed bash tool also uses it for escalated retries. The ACP bridge is the shipped human answerer for calls it owns. Audit events remain log-only, so the model sees only the asking consumer's result. See the [approval-seam RFC](../../../docs/rfc/implemented/feature/2026-07-06-approval-seam.md) and [sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). ## Model Experience From 3b1d1bfa1207ebd9344fe87115102e9b10863e5e Mon Sep 17 00:00:00 2001 From: Dudu-0223 Date: Thu, 16 Jul 2026 11:36:16 +0800 Subject: [PATCH 199/359] refactor(agent-loop): unify tool-call scheduling on one rolling pool + factory cap default MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Run every ordered group through the same rolling pool: an exclusive call is a pool of one (a barrier), dropping the separate runExclusive path and the redundant post-grouping executionMode re-query. Behavior is unchanged — the parallel-tool-calls snapshot and the full scheduler unit suite (barriers, cap, abort, model-order results) stay green. Add AgentLoop.Config.maxParallelToolCalls as a factory-wide default applied to every agent create/createAgent/resume mints (per-agent option overrides it), forwarded through agent-core so it reaches front doors that expose no cap field of their own. Trim the isConcurrencySafe JSDoc to the local contract and link the parallel-tool-call RFC for the full rationale; document the field on the canonical core-data-structures page. --- docs/config-catalog.md | 17 ++++- docs/cordis-catalog/services.md | 4 +- docs/core-data-structures/core.md | 2 +- docs/core-data-structures/tools.md | 22 +++---- ...2026-07-10-parallel-tool-call-execution.md | 6 +- packages/core/agent-core/README.md | 6 +- packages/core/agent-core/src/index.ts | 10 ++- .../core/agent-core/tests/agent-core.spec.ts | 10 +++ packages/core/agent-loop/src/index.ts | 44 +++++++++++-- packages/core/agent-loop/src/tool-calls.ts | 65 +++++-------------- .../core/agent-loop/tests/tool-calls.spec.ts | 42 ++++++++++++ packages/core/tools/src/index.ts | 22 +++---- 12 files changed, 162 insertions(+), 88 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 9a586fa495..dbee6b350f 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -76,6 +76,11 @@ Source: [`packages/ui/acp-agent/src/index.ts:31`](../packages/ui/acp-agent/src/i export interface Config { /** The agent-loop `agents` list (see dsh-agent-loop's `Config`). */ agents?: AgentLoopConfig['agents'] + /** + * The factory-wide default concurrent tool-call cap applied to every agent + * this bundle creates (see dsh-agent-loop's `Config.maxParallelToolCalls`). + */ + maxParallelToolCalls?: AgentLoopConfig['maxParallelToolCalls'] /** The deployment persona (see dsh-system-prompt's `Config`). */ persona?: SystemPromptConfig['persona'] /** The explicit model-facing tool order (see dsh-system-prompt's `Config`). */ @@ -108,6 +113,16 @@ Requires: `agents` · `sessions` · `llm` · `tools` · `systemPrompt` ```ts config-catalog /** Plugin configuration for declarative startup agents. */ export interface Config { + /** + * Default concurrent tool-call cap applied to every agent this factory + * creates (declarative startup agents and factory callers such as the ACP, + * stdio, and SDK front doors that go through `create`/`createAgent`/`resume`). + * A positive integer; a per-agent `maxParallelToolCalls` overrides it, and an + * agent with neither falls back to {@link DEFAULT_MAX_PARALLEL_TOOL_CALLS}. + * This is the single `cordis.yml` knob that reaches agents whose front door + * does not expose its own cap field. + */ + maxParallelToolCalls?: number /** Agents created or resumed at plugin startup. */ agents: (AgentOptions & { /** Registry identity for the live agent. */ @@ -964,7 +979,7 @@ export interface Config { export type ToolPresentationMode = 'native' | 'code' | 'both' ``` -Source: [`packages/core/tools/src/index.ts:391`](../packages/core/tools/src/index.ts) +Source: [`packages/core/tools/src/index.ts:389`](../packages/core/tools/src/index.ts) ## `@deepseek-ai/dsh-user-approval` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 864a89dbfa..830184e804 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:364`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:374`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` @@ -257,7 +257,7 @@ async execute(exec: ToolExecutionInput): Promise Types: [ToolDefinition](../core-data-structures/tools.md) · [ToolExecutionInput](../core-data-structures/tools.md) · [ToolExecutionMode](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) -Source: [`packages/core/tools/src/index.ts:447`](../../packages/core/tools/src/index.ts) +Source: [`packages/core/tools/src/index.ts:445`](../../packages/core/tools/src/index.ts) ## `ctx.userInteraction` — `UserInteractionService` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 9a9a1706fc..42c11a84f0 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -347,7 +347,7 @@ interface Agent { } ``` -`AgentStatus` is `'idle' | 'running' | 'disposed'`, and `AgentId` is branded. `AgentOptions` is merge-extensible and currently includes `model?`. Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default. +`AgentStatus` is `'idle' | 'running' | 'disposed'`, and `AgentId` is branded. `AgentOptions` is merge-extensible and currently includes `model?` and `maxParallelToolCalls?` (the loop's per-agent concurrent tool-call cap; the owning field, defaulted by `AgentLoop.Config` and, absent that, by `DEFAULT_MAX_PARALLEL_TOOL_CALLS`). Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default. The [event taxonomy](../architecture.md#event) owns the `agent/*` lifecycle, checkpoint, and waterfall contracts. Turn and step boundaries are durable session events rather than agent emits. diff --git a/docs/core-data-structures/tools.md b/docs/core-data-structures/tools.md index 078e10ac29..5d4973ffe8 100644 --- a/docs/core-data-structures/tools.md +++ b/docs/core-data-structures/tools.md @@ -30,20 +30,18 @@ interface ToolDefinition extends ToolSchema { * * It may inspect the parsed `args` (`unknown` — a hand-rolled definition * receives the raw parsed value; `defineTool` schema-validates first and - * returns `false` on invalid args, so an eventual `ToolArgsError` is produced - * only if the tool actually executes). The check performs no I/O and receives - * no live `Agent` or mutable `ToolExecution`. + * returns `false` on invalid args). The check performs no I/O and receives no + * live `Agent` or mutable `ToolExecution`. * - * Declaring `true` is a contract: the tool body must NOT mutate the parent - * agent's session or other parent-owned async state during `execute` (no - * `exec.agent.session.append(...)`, no `agent.inject(...)`). Its only parent- + * Declaring `true` is a contract: during `execute` the tool body must NOT + * mutate the parent agent's session or other parent-owned async state (no + * `exec.agent.session.append(...)`, no `agent.inject(...)`); its only parent- * step outputs are the returned content, `meta`, structured error, and - * `additionalContext` carried through the loop's ordered post-execute path. - * The narrow exception is a synchronous, side-effect-only recorder whose - * updates are commutative OR fail closed for concurrent calls by the same - * session (the `fs/observed` version recorder is the worked example: its - * WeakMap record is last-writer-wins, and a stale observation only makes a - * later write/edit fail closed at its in-lock version CAS). + * `additionalContext` on the loop's ordered post-execute path. A synchronous, + * side-effect-only recorder whose updates are commutative or fail closed for + * concurrent same-session calls is the one exception (`fs/observed` is the + * worked example). Full contract and rationale: the parallel-tool-call RFC + * (docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md). */ isConcurrencySafe?(args: unknown): boolean /** diff --git a/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md b/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md index c8cd96622a..23e0f0d22e 100644 --- a/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md +++ b/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md @@ -45,11 +45,11 @@ A parallel-safe declaration is a contract. The tool body must not mutate the par The loop waits for the model stream to finish and logs one authoritative `assistant/message` before scheduling tools. Streaming tool execution is out of scope. -For each assistant step, `packages/core/agent-loop/src/tool-calls.ts` parses each call's raw JSON arguments exactly once, creates one distinct `ToolExecution` object per call, asks `ctx.tools.executionMode(exec)`, and partitions calls into ordered groups. A group is either one exclusive call or a run of consecutive parallel calls. `loop.ts` calls the helper so the turn/step lifecycle remains readable. +For each assistant step, `packages/core/agent-loop/src/tool-calls.ts` parses each call's raw JSON arguments exactly once, creates one distinct `ToolExecution` object per call, asks `ctx.tools.executionMode(exec)`, and partitions calls into ordered groups. A group is either one exclusive call or a run of consecutive parallel calls; grouping classifies each call exactly once. `loop.ts` calls the helper so the turn/step lifecycle remains readable. -Parallelism is per agent. `AgentOptions.maxParallelToolCalls` is a positive integer, defaults to `DEFAULT_MAX_PARALLEL_TOOL_CALLS` (`10`), and is accepted through the config-created agent path. Setting it to `1` preserves serial execution for that agent. Both the TypeScript `AgentOptions` vocabulary and the `AgentLoop.Config` schemastery object validate the cap, so invalid `cordis.yml` values fail during config validation. +Parallelism is per agent. `AgentOptions.maxParallelToolCalls` is a positive integer, defaults to `DEFAULT_MAX_PARALLEL_TOOL_CALLS` (`10`), and reaches an agent three ways in precedence order: the per-agent option, the factory-wide `AgentLoop.Config.maxParallelToolCalls` applied to every agent the loop creates (declarative startup agents and factory callers such as the ACP, stdio, and SDK front doors), then the built-in default. The factory default is the single `cordis.yml` knob for agents whose front door exposes no cap field of its own. Setting the value to `1` preserves serial execution for that agent. The TypeScript `AgentOptions` vocabulary and both `AgentLoop.Config` fields validate the cap, so invalid `cordis.yml` values fail during config validation. -Within a parallel group, execution uses a rolling pool: start calls in model order up to `maxParallelToolCalls`, and whenever one call settles, start the next unstarted call until the group is exhausted. A group larger than the cap is not truncated; the cap limits simultaneous in-flight calls only. +Every group runs through the same rolling pool: start calls in model order up to `maxParallelToolCalls`, and whenever one call settles, start the next unstarted call until the group is exhausted. An exclusive group is a pool of one — a barrier — so the loop needs no separate serial path. A group larger than the cap is not truncated; the cap limits simultaneous in-flight calls only. Only the dispatch/body stage runs concurrently. Generic middleware that can shape ordering-sensitive state remains ordered: `tools/pre-execute` and `tools/post-execute` run in model call order. `@deepseek-ai/dsh-tools` exposes the symbol-keyed internal `TOOL_REGISTRY_SCHEDULER` view so `dsh-agent-loop` can split prepare, dispatch, and finalize without adding named staged service methods to `ctx.tools`; ordinary callers still use the one-call `execute(exec)` API. `tools/execute` around-dispatch listeners run with the dispatch they wrap, so wrappers must be reentrant across distinct `ToolExecution` objects. The shipped timeout policy is per-call: every call owns its mutable `exec` and deadline. diff --git a/packages/core/agent-core/README.md b/packages/core/agent-core/README.md index fac4f4819a..594c4a8c82 100644 --- a/packages/core/agent-core/README.md +++ b/packages/core/agent-core/README.md @@ -39,11 +39,11 @@ This is the [interface/implementation/consumer seam](../../../docs/rfc/implement ```ts import type { Config } from '@deepseek-ai/dsh-agent-core' -// { agents?, persona?, toolOrder?, tools?, skills? } — the schema intersects the owner schemas, -// so validation and defaulting can never drift from the owners. +// { agents?, maxParallelToolCalls?, persona?, toolOrder?, tools?, skills? } — the schema +// intersects the owner schemas, so validation and defaulting can never drift from the owners. ``` -The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure. +The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `maxParallelToolCalls` to `agent-loop` as the factory-wide default concurrent tool-call cap for every agent it creates; `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure. ## Why a code bundle, not a shared YAML include diff --git a/packages/core/agent-core/src/index.ts b/packages/core/agent-core/src/index.ts index 14ffbd6133..fcb4e87f1e 100644 --- a/packages/core/agent-core/src/index.ts +++ b/packages/core/agent-core/src/index.ts @@ -46,6 +46,11 @@ export interface SkillConfig { export interface Config { /** The agent-loop `agents` list (see dsh-agent-loop's `Config`). */ agents?: AgentLoopConfig['agents'] + /** + * The factory-wide default concurrent tool-call cap applied to every agent + * this bundle creates (see dsh-agent-loop's `Config.maxParallelToolCalls`). + */ + maxParallelToolCalls?: AgentLoopConfig['maxParallelToolCalls'] /** The deployment persona (see dsh-system-prompt's `Config`). */ persona?: SystemPromptConfig['persona'] /** The explicit model-facing tool order (see dsh-system-prompt's `Config`). */ @@ -95,5 +100,8 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(invariants) ctx.plugin(toolBash) ctx.plugin(toolSkill, config.skills?.tool ?? {}) - ctx.plugin(AgentLoop, { agents: config.agents ?? [] }) + ctx.plugin(AgentLoop, { + agents: config.agents ?? [], + ...config.maxParallelToolCalls !== undefined ? { maxParallelToolCalls: config.maxParallelToolCalls } : {}, + }) } diff --git a/packages/core/agent-core/tests/agent-core.spec.ts b/packages/core/agent-core/tests/agent-core.spec.ts index 0bf0660364..fe240da8ed 100644 --- a/packages/core/agent-core/tests/agent-core.spec.ts +++ b/packages/core/agent-core/tests/agent-core.spec.ts @@ -117,6 +117,16 @@ describe('dsh-agent-core bundle', () => { await ctx.fiber.dispose() }) + it('forwards the factory-wide maxParallelToolCalls default to agents without a per-agent cap', async () => { + const ctx = await mount({ + agents: [{ id: AgentId('main'), model: 'mock' }], + maxParallelToolCalls: 3, + }) + const main = ctx.get('agents')?.get(AgentId('main')) + expect(main?.options.maxParallelToolCalls).toBe(3) + await ctx.fiber.dispose() + }) + it('tolerates a schema-bypassing direct apply (the ?? fallbacks fire)', async () => { // ctx.plugin validates + defaults the bundle config first; a direct apply // skips the schema, so the forwarding `?? []` / `?? ''` are what fire. diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 17447a0b1d..86df80cd8e 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -344,6 +344,16 @@ export { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from './constants.ts' /** Plugin configuration for declarative startup agents. */ export interface Config { + /** + * Default concurrent tool-call cap applied to every agent this factory + * creates (declarative startup agents and factory callers such as the ACP, + * stdio, and SDK front doors that go through `create`/`createAgent`/`resume`). + * A positive integer; a per-agent `maxParallelToolCalls` overrides it, and an + * agent with neither falls back to {@link DEFAULT_MAX_PARALLEL_TOOL_CALLS}. + * This is the single `cordis.yml` knob that reaches agents whose front door + * does not expose its own cap field. + */ + maxParallelToolCalls?: number /** Agents created or resumed at plugin startup. */ agents: (AgentOptions & { /** Registry identity for the live agent. */ @@ -366,6 +376,9 @@ export class AgentLoop extends Service implements AgentFactory { /** Runtime schema for declarative agents. */ static Config = z.object({ + // The factory-wide default cap; a per-agent value overrides it. A positive + // integer, validated here so a bad cordis.yml value fails at load. + maxParallelToolCalls: z.number().step(1).min(1), agents: z.array(z.object({ id: z.string().required(), model: z.string(), @@ -410,6 +423,22 @@ export class AgentLoop extends Service implements AgentFactory { } } + /** + * Merge the factory-wide default cap into one agent's options. A per-agent + * `maxParallelToolCalls` wins; otherwise the `Config.maxParallelToolCalls` + * default applies, reaching factory callers (ACP/stdio/SDK front doors) whose + * own config does not set a cap. Absent both, the loop falls back to + * {@link DEFAULT_MAX_PARALLEL_TOOL_CALLS} at schedule time. + * @param options - the caller-supplied agent options. + * @returns options with the default cap applied when the caller omitted one. + */ + private withFactoryDefaults(options: AgentOptions): AgentOptions { + if (options.maxParallelToolCalls !== undefined || this.config.maxParallelToolCalls === undefined) { + return options + } + return { ...options, maxParallelToolCalls: this.config.maxParallelToolCalls } + } + /** * Create an agent on a fresh per-run session, owned by the accessing fiber. * Constructor-driven config calls use the loop fiber itself. @@ -419,13 +448,14 @@ export class AgentLoop extends Service implements AgentFactory { * @returns the published running agent. */ create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent { - validateAgentOptions(options) + const resolved = this.withFactoryDefaults(options) + validateAgentOptions(resolved) const loopCtx = this.runtime.ctx const transaction = new AgentCreationTransaction(loopCtx, this.ctx, this.ownership, id) try { const sessionId = SessionId(`${id}-session-${randomUUID()}`) const session = loopCtx.sessions.prepare(sessionId, { meta }) - const agent = transaction.prepare(options, session) + const agent = transaction.prepare(resolved, session) transaction.publish('startup') return agent } catch (error: unknown) { @@ -443,7 +473,8 @@ export class AgentLoop extends Service implements AgentFactory { * @returns the published handle. */ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise { - validateAgentOptions(options.agentOptions ?? {}) + const agentOptions = this.withFactoryDefaults(options.agentOptions ?? {}) + validateAgentOptions(agentOptions) const transaction = new AgentCreationTransaction( this.runtime.ctx, ownerCtx, @@ -456,7 +487,7 @@ export class AgentLoop extends Service implements AgentFactory { ...options.seed === undefined ? {} : { seed: options.seed }, ...options.meta === undefined ? {} : { meta: options.meta }, }) - const agent = transaction.prepare(options.agentOptions ?? {}, session) + const agent = transaction.prepare(agentOptions, session) await transaction.waitFor(options.setup?.(agent.ctx)) transaction.assertActive() return transaction.publish('startup') @@ -475,7 +506,6 @@ export class AgentLoop extends Service implements AgentFactory { * @returns the published handle. */ async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise { - validateAgentOptions(options.agentOptions ?? {}) const persistence = this.runtime.ctx.get('sessionPersistence') if (persistence === undefined) { throw new Error('cannot resume: session persistence is not configured (load a dsh-session-persistence backend)') @@ -489,6 +519,8 @@ export class AgentLoop extends Service implements AgentFactory { persistence: SessionPersistence, options: ResumeAgentOptions, ): Promise { + const agentOptions = this.withFactoryDefaults(options.agentOptions ?? {}) + validateAgentOptions(agentOptions) const transaction = new AgentCreationTransaction( this.runtime.ctx, ownerCtx, @@ -508,7 +540,7 @@ export class AgentLoop extends Service implements AgentFactory { ...loaded.meta.seedLength === undefined ? {} : { seedLength: loaded.meta.seedLength }, }, }) - const agent = transaction.prepare(options.agentOptions ?? {}, session) + const agent = transaction.prepare(agentOptions, session) await transaction.waitFor(options.setup?.(agent.ctx)) transaction.assertActive() return transaction.publish('resume') diff --git a/packages/core/agent-loop/src/tool-calls.ts b/packages/core/agent-loop/src/tool-calls.ts index 6ee1dc5906..d117823a43 100644 --- a/packages/core/agent-loop/src/tool-calls.ts +++ b/packages/core/agent-loop/src/tool-calls.ts @@ -3,8 +3,9 @@ * the assistant message's `tool-call` blocks; this module parses each call's * arguments once, classifies it via `ctx.tools.executionMode`, partitions the * calls into ordered groups (one exclusive call, or a run of consecutive - * parallel-safe calls), and executes each group — a parallel group through a - * rolling pool bounded by the agent's `maxParallelToolCalls`. + * parallel-safe calls), and runs every group through the same rolling pool + * bounded by the agent's `maxParallelToolCalls` — an exclusive group is a pool + * of one. * * The session log stays the source of truth and is reconstructable regardless * of dispatch timing: each STARTED call appends its own `tool/call` before its @@ -95,16 +96,13 @@ export async function executeToolCalls( // separate ordered groups (no read/write race inside one assistant step). const groups = groupByMode(ctx, planned) + // Every group runs through the same rolling pool: an exclusive call is a + // singleton group (pool of one, a barrier), a parallel-safe run is one group + // bounded by the cap. `groupByMode` already classified each call, so the loop + // does not re-query `executionMode` here. const pendingContext: HookContext[] = [] for (const group of groups) { - // Groups are never empty (groupByMode only pushes non-empty runs/singletons). - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- non-empty group - const first = group[0]! - if (group.length === 1 && ctx.tools.executionMode(first.exec).kind === 'exclusive') { - await runExclusive(ctx, session, turn, step, first, signal, pendingContext) - } else { - await runParallelGroup(ctx, session, turn, step, group, signal, maxParallel, pendingContext) - } + await runGroup(ctx, session, turn, step, group, signal, maxParallel, pendingContext) } return pendingContext } @@ -135,8 +133,8 @@ function parseArguments(raw: string): unknown { /** * Group planned calls into ordered runs: each exclusive call is a singleton * group; consecutive parallel-safe calls coalesce into one group. `executionMode` - * is queried once per call here and again by the caller to pick the exclusive - * fast-path — both reads are pure and cheap. + * is the sole classification point — the caller runs every group through the + * rolling pool without re-querying it. The read is pure and cheap. */ function groupByMode(ctx: Context, planned: PlannedCall[]): PlannedCall[][] { const groups: PlannedCall[][] = [] @@ -167,46 +165,19 @@ function assertMaxParallelToolCalls(maxParallel: number): void { } /** - * The exclusive single-call path keeps the public one-call pipeline sequential: - * abort-check, `tool/call`, pre/dispatch/post via `ctx.tools.execute`, - * `tool/result`, buffer context, post-await abort-check. - */ -async function runExclusive( - ctx: Context, - session: Session, - turn: number, - step: number, - call: PlannedCall, - signal: AbortSignal, - pendingContext: HookContext[], -): Promise { - /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ - if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) - const callSeq = appendToolCall(session, turn, step, call.block) - const result = await ctx.tools.execute(call.exec) - appendToolResult(session, turn, step, call.block, result, callSeq) - if (result.additionalContext) pendingContext.push(result.additionalContext) - // signal CAN flip during the await above (abort() inside a tool); the analyzer - // can't see through the await boundary. - /* v8 ignore start -- signal.reason default unreachable: cancel()/disposal always set it */ - // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition - if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) - /* v8 ignore stop */ -} - -/** - * The rolling-pool path for a group of parallel-safe calls. Starts calls in - * model order up to `maxParallel`, and whenever one settles starts the next - * unstarted call until the group is exhausted. Settled dispatches land in - * model-order slots; a commit cursor appends `tool/result` (and collects - * `additionalContext`) only while the next slot is ready, so the log stays - * model-ordered regardless of completion order. + * The rolling-pool path for one ordered group. A singleton exclusive group runs + * as a pool of one (a barrier); a parallel-safe run starts calls in model order + * up to `maxParallel`, and whenever one settles starts the next unstarted call + * until the group is exhausted. Settled dispatches land in model-order slots; a + * commit cursor appends `tool/result` (and collects `additionalContext`) only + * while the next slot is ready, so the log stays model-ordered regardless of + * completion order. * * Abort: an already-aborted signal starts nothing and throws before any * `tool/call`. An abort mid-group stops replenishment, awaits only the started * calls, commits their results in order, drops buffered context, and throws. */ -async function runParallelGroup( +async function runGroup( ctx: Context, session: Session, turn: number, diff --git a/packages/core/agent-loop/tests/tool-calls.spec.ts b/packages/core/agent-loop/tests/tool-calls.spec.ts index 987b358720..a270ad6da1 100644 --- a/packages/core/agent-loop/tests/tool-calls.spec.ts +++ b/packages/core/agent-loop/tests/tool-calls.spec.ts @@ -274,6 +274,48 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => gated.release('2') await waitForIdle(ctx, agent) }) + + it('applies the factory-wide Config default to agents that set no per-agent cap', async () => { + const adapter = new MockAdapter([ + multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]), + textResponse('done'), + ]) + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt, { persona: '' }) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + // Factory default of 1 (no per-agent cap set below) must serialize. + await ctx.plugin(AgentLoop, { agents: [], maxParallelToolCalls: 1 }) + ctx.llm.registerAdapter(['mock'], adapter) + const gated = gatedParallelTool('p') + ctx.tools.register(gated.tool) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + expect(agent.options.maxParallelToolCalls).toBe(1) + + agent.send([{ type: 'text', text: 'go' }]) + await until(() => gated.started.length === 1) + await new Promise(r => setTimeout(r, 5)) + expect(gated.started).toEqual(['1']) + gated.release('1') + await until(() => gated.started.length === 2) + gated.release('2') + await waitForIdle(ctx, agent) + }) + + it('lets a per-agent cap override the factory-wide Config default', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt, { persona: '' }) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentLoop, { agents: [], maxParallelToolCalls: 1 }) + ctx.llm.registerAdapter(['mock'], new MockAdapter([])) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock', maxParallelToolCalls: 4 }) + expect(agent.options.maxParallelToolCalls).toBe(4) + }) }) describe('tool-call scheduler: ordered middleware and additionalContext', () => { diff --git a/packages/core/tools/src/index.ts b/packages/core/tools/src/index.ts index 3575554ac1..4f1741ab39 100644 --- a/packages/core/tools/src/index.ts +++ b/packages/core/tools/src/index.ts @@ -142,20 +142,18 @@ export interface ToolDefinition extends ToolSchema { * * It may inspect the parsed `args` (`unknown` — a hand-rolled definition * receives the raw parsed value; `defineTool` schema-validates first and - * returns `false` on invalid args, so an eventual `ToolArgsError` is produced - * only if the tool actually executes). The check performs no I/O and receives - * no live `Agent` or mutable `ToolExecution`. + * returns `false` on invalid args). The check performs no I/O and receives no + * live `Agent` or mutable `ToolExecution`. * - * Declaring `true` is a contract: the tool body must NOT mutate the parent - * agent's session or other parent-owned async state during `execute` (no - * `exec.agent.session.append(...)`, no `agent.inject(...)`). Its only parent- + * Declaring `true` is a contract: during `execute` the tool body must NOT + * mutate the parent agent's session or other parent-owned async state (no + * `exec.agent.session.append(...)`, no `agent.inject(...)`); its only parent- * step outputs are the returned content, `meta`, structured error, and - * `additionalContext` carried through the loop's ordered post-execute path. - * The narrow exception is a synchronous, side-effect-only recorder whose - * updates are commutative OR fail closed for concurrent calls by the same - * session (the `fs/observed` version recorder is the worked example: its - * WeakMap record is last-writer-wins, and a stale observation only makes a - * later write/edit fail closed at its in-lock version CAS). + * `additionalContext` on the loop's ordered post-execute path. A synchronous, + * side-effect-only recorder whose updates are commutative or fail closed for + * concurrent same-session calls is the one exception (`fs/observed` is the + * worked example). Full contract and rationale: the parallel-tool-call RFC + * (docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md). */ isConcurrencySafe?(args: unknown): boolean /** From 2793325df0b0bc0354068b1dbedb4751edce04da Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 11:40:00 +0800 Subject: [PATCH 200/359] refactor(compact): store tool-pairing balance once per surface cut toolPairingBalancedAfter previously answered by resolving a cached positional successor and reading its before-balance, with a null-successor depth fallback. Both queries are the same prefix property sampled at adjacent cuts, so the cache now holds one per-cut balance sequence (N nodes -> N+1 cuts) plus a seq->position index; before/after differ only by a cut offset. The successor map, the duplicate rebuild/extend fold loops, and the non-null assertion are gone, and the running counter is named inProgressToolCalls. Docs describing the successor mechanism are updated in place. --- docs/core-data-structures/session.md | 2 +- .../2026-06-18-compaction-capability-seam.md | 4 +- ...-12-simplify-session-log-representation.md | 2 +- packages/compact/compact/README.md | 4 +- packages/compact/compact/src/tool-pairing.ts | 116 +++++++----------- .../compact/tests/tool-pairing.spec.ts | 2 +- 6 files changed, 51 insertions(+), 79 deletions(-) diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index 174f06602e..616370fb84 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -196,7 +196,7 @@ export interface SurfaceNode { } ``` -`SurfaceNode` is positional state, not durable identity. A replacement can remove a caller-retained node or make a copied `next` stale; consumers that cross a surface mutation validate membership and resolve successors from `Session.surface.nodes`. `SurfaceManager.replaceGeneration` increments for each replacement so incremental consumers can distinguish pure tail growth from a rewrite. +`SurfaceNode` is positional state, not durable identity. A replacement can remove a caller-retained node or make a copied `next` stale; consumers that cross a surface mutation validate membership and answer positional queries from `Session.surface.nodes`. `SurfaceManager.replaceGeneration` increments for each replacement so incremental consumers can distinguish pure tail growth from a rewrite. ### `SurfaceFoldReplacement` and `SurfaceFoldResult` — a complete surface replay diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index 29e3347759..75eaf3207f 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -52,7 +52,7 @@ The loop derives messages once after `agent/pre-step`. Running before `step/star Auto-compaction fires before **every** step, not once per turn. This is **load-bearing for runaway-turn survival**: a tool-heavy ReAct turn appends an `assistant/message` + a `tool/result` per step, so the surface grows *within* a turn. A single turn can grow past the window on its own (a "runaway turn") — and the only moment to rescue it before the next model call overflows is the next step's `pre-step` checkpoint. Gating compaction to a turn's first step (or, worse, retaining the whole in-flight turn verbatim) re-opens exactly the hole compaction exists to close: the harness would die when compaction is most needed. -`compactIfNeeded` retains the smallest tail of whole surface units whose estimated size reaches `retainTokens` and compacts older nodes. A unit is a complete closed step or one no-step message. If the token cutoff lands inside a step, retention expands until the cut is tool-pairing balanced. Balance is checked on surface order, not log sequence, because replacement summaries have new sequence numbers at old surface positions. `dsh-compact` exports the before/after edge helpers; their per-session cache folds only appended surface-tail nodes while `replaceGeneration` is unchanged, does no event reads for log-only growth, and rebuilds current membership, positional successors, and balances after replacement. `compactRegion` rejects boundaries that split a tool call from its result. The in-flight turn receives no special retention. +`compactIfNeeded` retains the smallest tail of whole surface units whose estimated size reaches `retainTokens` and compacts older nodes. A unit is a complete closed step or one no-step message. If the token cutoff lands inside a step, retention expands until the cut is tool-pairing balanced. Balance is checked on surface order, not log sequence, because replacement summaries have new sequence numbers at old surface positions. `dsh-compact` exports the before/after edge helpers; their per-session cache folds only appended surface-tail nodes while `replaceGeneration` is unchanged, does no event reads for log-only growth, and rebuilds current membership and balances after replacement. `compactRegion` rejects boundaries that split a tool call from its result. The in-flight turn receives no special retention. A runaway turn thus compacts exactly like any other history: its early *closed* steps get summarized while its recent steps stay verbatim. When the only compactable content left is an un-splittable open tail step (its tool-calls have no results yet), compaction declines (`null`) and retries once that step closes. @@ -113,7 +113,7 @@ Two failure paths, both documented: - **New packages**: `packages/compact/compact` (interface) and a sibling `compact-basic` (backend) under `packages/compact/`, wired into the root tsconfigs. The consumer tier is deferred. - **New loop seam**: `agent/pre-step` (`@mode serial`) declared in `dsh-agent` and emitted by `dsh-agent-loop` after system assembly and before `step/start`. This is a documented change to the loop — `docs/architecture.md` records it and the generated cordis catalog carries its signature. - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry. -- **`dsh-compact`** owns `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)`, the cached surface-edge checks that `compactRegion` and `compactIfNeeded` use to avoid splitting a tool-call/result pair. The cache validates current membership by seq and resolves after-edges from its positional successor map instead of trusting a caller-retained `node.next`; stale or missing seqs and orphan results reject. `dsh-session` continues to own the surface `replace` operation, positional nodes, and rewrite generation. +- **`dsh-compact`** owns `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)`, the cached surface-edge checks that `compactRegion` and `compactIfNeeded` use to avoid splitting a tool-call/result pair. The cache validates current membership by seq and answers both edges from one per-cut balance sequence instead of trusting a caller-retained `node.next`; stale or missing seqs and orphan results reject. `dsh-session` continues to own the surface `replace` operation, positional nodes, and rewrite generation. - **`dsh-invariants`** drops its `surface replace: start must be <= end` assertion: a head-anchored compaction lands a high-seq replacement node at an older range's *position*, so `start > end` numerically is normal and valid (the range is positional, validated by the surface's `indexOf` checks that remain). The turn-enclosure invariant is reused unchanged. - **Wiring**: `dsh-compact-basic` is loaded in `examples/coding-agent`'s `cordis.yml`, so the seam ships in the real demo (it was previously loaded nowhere). diff --git a/docs/rfc/proposed/simplification/2026-07-12-simplify-session-log-representation.md b/docs/rfc/proposed/simplification/2026-07-12-simplify-session-log-representation.md index 715ce93924..1cb8d5708a 100644 --- a/docs/rfc/proposed/simplification/2026-07-12-simplify-session-log-representation.md +++ b/docs/rfc/proposed/simplification/2026-07-12-simplify-session-log-representation.md @@ -6,7 +6,7 @@ Status: proposed The session log maintains two representations that cost more machinery than their consumers require: a pseudo-linked surface and custom request-header deltas. -`SurfaceManager` stores the same order in an array, a seq map, and mutable `prev`/`next` links. Production never reads `prev`; compact's sole `next` read is the successor of an array position. Replacement already uses `indexOf`, so the links do not make its dominant operation constant-time. A seq array with linear replacement lookup has the same asymptotic replacement cost and one representation to validate. +`SurfaceManager` stores the same order in an array, a seq map, and mutable `prev`/`next` links. Production never reads either link: compact's tool-pairing balance answers from per-cut balances cached in surface order. Replacement already uses `indexOf`, so the links do not make its dominant operation constant-time. A seq array with linear replacement lookup has the same asymptotic replacement cost and one representation to validate. The request-header subsystem implements a custom system/tool delta codec and transmission-decision layer even though its contract says deltas are an encoding optimization, not a reconstructability requirement. Retaining the initial/resume full snapshot at each loop-instance boundary, then writing a canonical full `request/header` whenever that instance's assembled header changes, preserves replay while deleting `SystemDelta`, `ToolsDelta`, round-trip fallback, and the durable `request/header-delta` variant. Codec-only vocabulary disappears with the codec, not because its individual arms were invalid. diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index 5b59893561..ef8c300856 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -25,9 +25,9 @@ Both methods are **abstract** — the backend owns the entire strategy (token es ## Tool-pairing boundaries -The interface exports `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)` for snapping and validating compaction edges. A safe edge has no unanswered assistant tool call crossing it. Each helper validates the node's seq against current surface membership and resolves the trailing edge from its cached positional successor, so a stale caller-held `node.next` cannot choose the cut. +The interface exports `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)` for snapping and validating compaction edges. A safe edge has no unanswered assistant tool call crossing it. Each helper identifies the node by seq alone and answers from balances cached per cut in current surface order, so a stale caller-held `node.next` cannot choose the cut. -The private per-session cache is keyed by `session.surface.replaceGeneration` and the processed surface-node count. An unchanged generation extends the fold with unseen tail nodes only; a log-only append with no new surface node does no event reads, while a replacement generation rebuilds current membership, successors, and balances. Missing event seqs and a `tool/result` without a preceding open call reject as corrupt surface state. +The private per-session cache is keyed by `session.surface.replaceGeneration` and the processed surface-node count. An unchanged generation extends the fold with unseen tail nodes only; a log-only append with no new surface node does no event reads, while a replacement generation rebuilds current membership and balances. Missing event seqs and a `tool/result` without a preceding open call reject as corrupt surface state. ## Surface contract diff --git a/packages/compact/compact/src/tool-pairing.ts b/packages/compact/compact/src/tool-pairing.ts index a9fca01bf6..0fc0f68dc8 100644 --- a/packages/compact/compact/src/tool-pairing.ts +++ b/packages/compact/compact/src/tool-pairing.ts @@ -12,19 +12,21 @@ import type { Session, SessionEvent, SurfaceNode } from '@deepseek-ai/dsh-sessio interface BalanceCache { /** Surface rewrite generation this state describes. */ generation: number - /** Number of surface nodes already folded into the state. */ - processedNodes: number - /** Balance of the cut immediately before each current surface node. */ - beforeSeq: Map - /** Current positional successor of each surface node. */ - successorBySeq: Map - /** Unanswered tool-call count after the processed surface tail. */ - depth: number + /** + * Balance of every surface cut in current order: a surface of N nodes has + * N + 1 cuts, entry `i` being the cut before node `i` and the final entry + * the cut after the surface tail. + */ + cutBalanced: readonly boolean[] + /** Current surface position of each node seq, indexing {@link cutBalanced}. */ + indexBySeq: Map + /** In-progress tool-call count after the processed surface tail. */ + inProgressToolCalls: number } const balanceCacheBySession = new WeakMap() -/** Return how one surface event changes the unanswered tool-call count. */ +/** Return how one surface event changes the in-progress tool-call count. */ function nodeDelta(event: SessionEvent): number { switch (event.type) { case 'assistant/message': @@ -45,61 +47,30 @@ function eventForNode(events: readonly SessionEvent[], node: SurfaceNode): Sessi return event } -/** Build balance state for a complete current surface. */ -function rebuildCache( - session: Session, - nodes: readonly SurfaceNode[], - generation: number, -): BalanceCache { - const beforeSeq = new Map() - const successorBySeq = new Map() - const events = session.events - let depth = 0 - let previousSeq: number | undefined - - for (const node of nodes) { - beforeSeq.set(node.seq, depth === 0) - successorBySeq.set(node.seq, null) - if (previousSeq !== undefined) successorBySeq.set(previousSeq, node.seq) - depth += nodeDelta(eventForNode(events, node)) - if (depth < 0) { - throw new Error(`tool-pairing balance: tool/result at surface seq ${node.seq} has no matching tool-call (corrupt surface)`) - } - previousSeq = node.seq - } - - return { generation, processedNodes: nodes.length, beforeSeq, successorBySeq, depth } -} - -/** Fold a pure surface tail append into existing balance state. */ +/** Fold surface nodes not yet in the cache into its balance state. */ function extendCache( session: Session, cache: BalanceCache, nodes: readonly SurfaceNode[], ): BalanceCache { - const tail = nodes.slice(cache.processedNodes) + const processed = cache.cutBalanced.length - 1 + const tail = nodes.slice(processed) // Validate the unseen tail before mutating the live cache, so a corrupt // append cannot leave a partially advanced state behind. const events = session.events - const pending: Array<{ seq: number; before: boolean }> = [] - let depth = cache.depth + const pendingCuts: boolean[] = [] + let inProgressToolCalls = cache.inProgressToolCalls for (const node of tail) { - pending.push({ seq: node.seq, before: depth === 0 }) - depth += nodeDelta(eventForNode(events, node)) - if (depth < 0) { + inProgressToolCalls += nodeDelta(eventForNode(events, node)) + if (inProgressToolCalls < 0) { throw new Error(`tool-pairing balance: tool/result at surface seq ${node.seq} has no matching tool-call (corrupt surface)`) } + pendingCuts.push(inProgressToolCalls === 0) } - let previousSeq = nodes[cache.processedNodes - 1]?.seq - for (const entry of pending) { - if (previousSeq !== undefined) cache.successorBySeq.set(previousSeq, entry.seq) - cache.beforeSeq.set(entry.seq, entry.before) - cache.successorBySeq.set(entry.seq, null) - previousSeq = entry.seq - } - cache.processedNodes = nodes.length - cache.depth = depth + tail.forEach((node, offset) => cache.indexBySeq.set(node.seq, processed + offset)) + cache.cutBalanced = cache.cutBalanced.concat(pendingCuts) + cache.inProgressToolCalls = inProgressToolCalls return cache } @@ -110,15 +81,32 @@ function balanceCache(session: Session): BalanceCache { const generation = surface.replaceGeneration const cached = balanceCacheBySession.get(session) - if (cached === undefined || cached.generation !== generation || cached.processedNodes > nodes.length) { - const rebuilt = rebuildCache(session, nodes, generation) + if (cached === undefined || cached.generation !== generation || cached.cutBalanced.length - 1 > nodes.length) { + // A rebuild is the same fold started from the empty-surface state, whose + // single leading cut is trivially balanced. + const rebuilt = extendCache(session, { + generation, + cutBalanced: [true], + indexBySeq: new Map(), + inProgressToolCalls: 0, + }, nodes) balanceCacheBySession.set(session, rebuilt) return rebuilt } - if (cached.processedNodes < nodes.length) return extendCache(session, cached, nodes) + if (cached.cutBalanced.length - 1 < nodes.length) return extendCache(session, cached, nodes) return cached } +/** Balance of the cut at a node's position plus offset, rejecting seqs outside current membership. */ +function cutBalance(cache: BalanceCache, seq: number, offset: 0 | 1): boolean { + const index = cache.indexBySeq.get(seq) + const balanced = index === undefined ? undefined : cache.cutBalanced[index + offset] + if (balanced === undefined) { + throw new Error(`tool-pairing balance: surface seq ${seq} not found`) + } + return balanced +} + /** * Whether the cut immediately before a current surface node is tool-pairing balanced. * @param session - session whose surface is checked. @@ -128,12 +116,7 @@ function balanceCache(session: Session): BalanceCache { * matching log event, or a tool result has no preceding open call. */ export function toolPairingBalancedBefore(session: Session, node: SurfaceNode): boolean { - const cache = balanceCache(session) - const balanced = cache.beforeSeq.get(node.seq) - if (balanced === undefined) { - throw new Error(`tool-pairing balance: surface seq ${node.seq} not found`) - } - return balanced + return cutBalance(balanceCache(session), node.seq, 0) } /** @@ -145,16 +128,5 @@ export function toolPairingBalancedBefore(session: Session, node: SurfaceNode): * matching log event, or a tool result has no preceding open call. */ export function toolPairingBalancedAfter(session: Session, node: SurfaceNode): boolean { - const cache = balanceCache(session) - const successor = cache.successorBySeq.get(node.seq) - if (successor === undefined) { - throw new Error(`tool-pairing balance: surface seq ${node.seq} not found`) - } - if (successor === null) return cache.depth === 0 - // Current membership and positional successors are cache-owned. A caller may - // retain a node across surface changes, so its mutable-looking `next` field is - // never authoritative for this query. - // The successor map and balance map are committed together. - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - return cache.beforeSeq.get(successor)! + return cutBalance(balanceCache(session), node.seq, 1) } diff --git a/packages/compact/compact/tests/tool-pairing.spec.ts b/packages/compact/compact/tests/tool-pairing.spec.ts index dfde2bd2ba..bd74faeec5 100644 --- a/packages/compact/compact/tests/tool-pairing.spec.ts +++ b/packages/compact/compact/tests/tool-pairing.spec.ts @@ -131,7 +131,7 @@ describe('tool-pairing surface identity', () => { expect(() => toolPairingBalancedAfter(session, staleTail)).toThrow(/surface seq .* not found/) }) - it('uses the cached positional successor instead of a caller node next field', () => { + it('ignores a caller-held node next field and answers from cached balances', () => { const session = closedToolStep() const assistant = nodeAt(session, seqOf(session, 'assistant/message')) expect(toolPairingBalancedAfter(session, { ...assistant, next: null })).toBe(false) From 5c243e8a8dfda41e7d17b98a77a84046de237434 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 12:58:07 +0800 Subject: [PATCH 201/359] refactor(token-meter): simplify singleton service (round 1) --- docs/architecture.md | 2 +- docs/capability-seams.md | 2 +- docs/config-catalog.md | 28 +- docs/cordis-catalog/services.md | 10 +- docs/core-data-structures/compaction.md | 2 +- docs/core-data-structures/token-meter.md | 6 +- ...07-15-replay-token-meter-service.i18n.yaml | 4 +- .../2026-07-15-replay-token-meter-service.md | 32 +- ...026-07-15-replay-token-meter-service.zh.md | 44 +- .../2026-06-18-compaction-capability-seam.md | 4 +- examples/coding-agent/cordis.yml | 4 +- examples/coding-agent/tests/compaction.e2e.ts | 9 +- examples/coding-agent/tests/harness.ts | 4 +- packages/compact/compact-basic/README.md | 12 +- .../compact/compact-basic/src/automatic.ts | 8 - packages/compact/compact-basic/src/config.ts | 89 +-- packages/compact/compact-basic/src/index.ts | 58 +- packages/compact/compact-basic/src/region.ts | 4 +- packages/compact/compact-basic/src/types.ts | 25 +- .../compact-basic/tests/compact-basic.spec.ts | 169 +++--- .../tests/compact-loop-repro.spec.ts | 11 +- .../tests/loader-composition.spec.ts | 5 +- .../cordis/tool-cordis/src/api-catalog.ts | 14 +- packages/llm/README.md | 2 +- packages/llm/token-meter/README.md | 29 +- packages/llm/token-meter/package.json | 2 +- packages/llm/token-meter/src/index.ts | 510 +++++++++++++----- packages/llm/token-meter/src/replay.ts | 367 ------------- packages/llm/token-meter/src/types.ts | 58 +- .../llm/token-meter/tests/token-meter.spec.ts | 214 +++----- scripts/gen-doc-graphs.ts | 2 +- 31 files changed, 653 insertions(+), 1077 deletions(-) delete mode 100644 packages/llm/token-meter/src/replay.ts diff --git a/docs/architecture.md b/docs/architecture.md index 63a5f07a61..9c31495f87 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -24,7 +24,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service | ctx key | Package family | Role | |---|---|---| | `ctx.llm` | [`llm/`](../packages/llm/README.md) | adapter registry and streaming model calls | -| `ctx.tokenMeter` | [`llm/token-meter`](../packages/llm/token-meter/README.md) | replay-aware request/surface pressure per model | +| `ctx.tokenMeter` | [`llm/token-meter`](../packages/llm/token-meter/README.md) | singleton replay-aware request/surface pressure | | `ctx.bash` | [`bash/`](../packages/bash/README.md) | foreground/background command execution | | `ctx.sandbox` | [`sandbox/`](../packages/sandbox/README.md) | same-world process confinement (argv wrapping, per-call policy) | | `ctx.codeRuntime` | [`code-runtime/`](../packages/code-runtime/README.md) | model-written program execution | diff --git a/docs/capability-seams.md b/docs/capability-seams.md index 398c265cf0..9d8c612bdb 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -194,7 +194,7 @@ flowchart LR | ctx key | Role | Owner | Implementations | Direct consumers | Companion plugins | Note | | --- | --- | --- | --- | --- | --- | --- | | `ctx.llm` | `seam` | [`llm`](../packages/llm/llm) | [`llm-deepseek`](../packages/llm/llm-deepseek), [`llm-pi-ai`](../packages/llm/llm-pi-ai), [`llm-replay`](../packages/support/llm-replay) | [`agent-loop`](../packages/core/agent-loop), [`compact-basic`](../packages/compact/compact-basic) | - | Adapters register provider implementations; the loop and compaction call the provider-neutral stream service. | -| `ctx.tokenMeter` | `core` | [`token-meter`](../packages/llm/token-meter) | - | [`compact-basic`](../packages/compact/compact-basic) | - | Owns isolated per-model/session replay folds; pressure consumers share immutable revisioned measurements. | +| `ctx.tokenMeter` | `core` | [`token-meter`](../packages/llm/token-meter) | - | [`compact-basic`](../packages/compact/compact-basic) | - | Owns isolated per-session replay folds; pressure consumers share immutable revisioned measurements. | | `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. | | `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`session-query`](../packages/session-query/session-query) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. | | `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | - | - | - | Resolves live and optional persisted logs into one logical corpus for exact reads. | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 23dedc5a8b..3ef87c2d44 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -226,8 +226,10 @@ Requires: `llm` · `tokenMeter` ```ts config-catalog /** Basic compaction configuration; every common field has a deployment default. */ export interface BasicCompactConfig { - /** Field-wise pressure/retention overrides keyed by configured token-meter model name. */ - models?: Record + /** Compact at this fraction of the token meter's context window. Defaults to `0.8`. */ + thresholdRatio?: number + /** Recent surface tokens retained verbatim. Defaults to `floor(contextWindow * 0.16)`. */ + retainTokens?: number /** Summary model; `''` resolves the latest routed model, then `AgentOptions.model`. Defaults to `''`. */ summarizationModel?: string /** Provider generation cap for summarization. Defaults to `8192`. */ @@ -237,17 +239,9 @@ export interface BasicCompactConfig { /** Enable the automatic `agent/pre-step` pressure listener. Defaults to `true`. */ auto?: boolean } - -/** Optional pressure and retention policy for one metered model. */ -export interface ModelCompactConfig { - /** Compact at this fraction of the model's configured context window. Defaults to `0.8`. */ - thresholdRatio?: number - /** Recent surface tokens retained verbatim. Defaults to `floor(contextWindow * 0.16)`. */ - retainTokens?: number -} ``` -Source: [`packages/compact/compact-basic/src/types.ts:16`](../packages/compact/compact-basic/src/types.ts) +Source: [`packages/compact/compact-basic/src/types.ts:8`](../packages/compact/compact-basic/src/types.ts) ## `@deepseek-ai/dsh-fs-local` @@ -875,20 +869,12 @@ Source: [`packages/context/time-context/src/index.ts:22`](../packages/context/ti ```ts config-catalog /** Token-meter plugin configuration. */ export interface TokenMeterConfig { - /** Built-in field overrides and custom model profiles, keyed by routed model name. */ - models?: Record -} - -/** Optional pricing fields for one configured model. */ -export interface ModelTokenMeterConfig { - /** Provider context-window capacity in tokens. Required for a custom model. */ + /** Service-wide context-window capacity in tokens. Defaults to `128000`. */ contextWindow?: number - /** Heuristic text density in characters per token. Defaults to `4`. */ - charsPerToken?: number } ``` -Source: [`packages/llm/token-meter/src/types.ts:19`](../packages/llm/token-meter/src/types.ts) +Source: [`packages/llm/token-meter/src/types.ts:10`](../packages/llm/token-meter/src/types.ts) ## `@deepseek-ai/dsh-tool-bash` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index b4ce033f36..5805ae130d 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -263,13 +263,17 @@ Source: [`packages/tasks/tasks/src/index.ts:76`](../../packages/tasks/tasks/src/ ## `ctx.tokenMeter` — `TokenMeterService` -Concrete registry and replay owner for all configured model meters. +Replay owner for one service-wide estimator and isolated per-session folds. ```ts cordis-catalog -resolve(model: string): ModelTokenMeter +measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement +measureSurface(session: Session): TokenSurfaceMeasurement +estimateMessage(message: Message): number ``` -Source: [`packages/llm/token-meter/src/index.ts:145`](../../packages/llm/token-meter/src/index.ts) +Types: [Message](../core-data-structures/core.md) + +Source: [`packages/llm/token-meter/src/index.ts:92`](../../packages/llm/token-meter/src/index.ts) ## `ctx.tools` — `ToolRegistry` diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 50a80208a9..3b861d5de4 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -50,7 +50,7 @@ interface CompactionResult { ## The service -`CompactService` exposes `compactIfNeeded(...)` for pressure-triggered compaction, returning `null` when no compaction is needed, and `compactRegion(...)` for an explicit inclusive surface range. The pre-step caller supplies the agent, full prompt, session prefix, and abort signal; implementations must forward that signal to summarization. The seam owns no pricing API: `dsh-compact-basic` resolves the routed model through [`ctx.tokenMeter`](token-meter.md), whose model-bound handle owns estimation and replay, while the backend owns retention, event sequencing, and summarization. +`CompactService` exposes `compactIfNeeded(...)` for pressure-triggered compaction, returning `null` when no compaction is needed, and `compactRegion(...)` for an explicit inclusive surface range. The pre-step caller supplies the agent, full prompt, session prefix, and abort signal; implementations must forward that signal to summarization. The seam owns no pricing API: [`ctx.tokenMeter`](token-meter.md) directly owns estimation and replay, while `dsh-compact-basic` owns retention, event sequencing, routed summarization calls, and their configuration. Auto-compaction runs at serial `agent/pre-step`, before the step and request derivation, so it can replace surface nodes while keeping trace events outside the step. Region boundaries preserve tool-call/result pairing but do not preserve whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns the retention and failure details. diff --git a/docs/core-data-structures/token-meter.md b/docs/core-data-structures/token-meter.md index 98467f3715..eee01c27b8 100644 --- a/docs/core-data-structures/token-meter.md +++ b/docs/core-data-structures/token-meter.md @@ -8,8 +8,6 @@ Source: [`packages/llm/token-meter/src/types.ts`](../../packages/llm/token-meter ```ts type-equiv interface TokenMeasurement { - /** Model profile used for every heuristic component. */ - readonly model: string /** Number of durable events consumed; equal to the next unread event seq. */ readonly logRevision: number /** Provider or heuristic anchor used for this measurement. */ @@ -21,7 +19,7 @@ interface TokenMeasurement { } ``` -`baseline.kind === 'usage'` means a successful provider call has the same model and canonical envelope. `estimated` means the meter repriced the complete envelope and surface. Signed `surfaceDeltaTokens` preserves growth and shrinkage relative to a matching provider or estimated anchor. +`baseline.kind === 'usage'` means the latest successful provider call has the same canonical request envelope. `estimated` means the service priced the complete envelope and surface with its fixed heuristic. A later successful request replaces the earlier anchor; signed `surfaceDeltaTokens` preserves growth and shrinkage relative to a matching anchor. ## `TokenSurfaceNode` @@ -38,8 +36,6 @@ interface TokenSurfaceNode { ```ts type-equiv interface TokenSurfaceMeasurement { - /** Model profile used to price every node. */ - readonly model: string /** Number of durable events consumed; equal to the next unread event seq. */ readonly logRevision: number /** Total heuristic tokens across the current surface. */ diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml index 99c6301f25..afd99ac686 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-replay-token-meter-service.md: 4452c151e122c4a4ad72e3f0bc2616cd2fa28b9d -2026-07-15-replay-token-meter-service.zh.md: 23edc11ffd19b9cfaeb794f3608e9ced4e7dbb7b +2026-07-15-replay-token-meter-service.md: 981e789a51bbe7e2b09d47a76d71ac79fe14c999 +2026-07-15-replay-token-meter-service.zh.md: 85565b6f3db77ab81712f9c128e570c7a16bae8d diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md index 4452c151e1..981e789a51 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md @@ -6,52 +6,52 @@ English | [中文](2026-07-15-replay-token-meter-service.zh.md) ## Problem -Context pressure is useful outside compaction. A compaction backend, an overflow guard, or a future request-policy plugin can all need the same answer: how much of one model's window does the durable request consume? Keeping that fold inside `dsh-compact-basic` duplicates replay logic, makes measurement unavailable without compaction, and encourages callers to reuse accounting from the wrong model. +Context pressure is useful outside compaction. A compaction backend, an overflow guard, or a future request-policy plugin can all need the same answer: how much of the configured context window does the durable request consume? Keeping that fold inside `dsh-compact-basic` duplicates replay logic, makes measurement unavailable without compaction, and encourages callers to reuse stale accounting. -Provider usage is not a complete answer. It describes one successful call under one exact request envelope, while the current surface can grow, shrink, or be replaced afterward. Sessions also switch models, old logs can lack chunk provenance, and provider fields separate input, cache-read, cache-write, output, and reasoning counts. A useful service therefore combines exact anchors with conservative model-specific repricing and exposes the log revision consumed by each result. +Provider usage is not a complete answer. It describes one successful call under one exact request envelope, while the current surface can grow, shrink, or be replaced afterward. Sessions also switch models, old logs can lack chunk provenance, and provider fields separate input, cache-read, cache-write, output, and reasoning counts. A useful service therefore combines the latest exact anchor with conservative heuristic repricing and exposes the log revision consumed by each result. ## Decision ### One concrete LLM-family service -`@deepseek-ai/dsh-token-meter` is one concrete package under `packages/llm/` and registers `ctx.tokenMeter`. It is not split into an interface and backend before a second implementation exists. Its public entry point resolves an exact model name to a stable `ModelTokenMeter`; unknown names throw `TokenMeterError` with `TOKEN_METER_MODEL_UNCONFIGURED` instead of inheriting a universal window. +`@deepseek-ai/dsh-token-meter` is one concrete package under `packages/llm/` and registers `ctx.tokenMeter`. It is not split into an interface and backend before a second implementation exists. `TokenMeterService` itself exposes `contextWindow`, `measure(session, requestHeader?)`, `measureSurface(session)`, and `estimateMessage(message)`; consumers call the singleton service directly. -The built-in `deepseek-v4-flash` and `deepseek-v4-pro` profiles use a 128,000-token context window and four characters per estimated token. `models` overrides merge field-by-field. A custom name requires `contextWindow`, while `charsPerToken` defaults to four. Direct construction reports typed profile errors; Loader mounts first apply the package's Schemastery shape validation. +The service has one `contextWindow`, defaulting to 128,000 tokens and configurable as a positive integer. Estimation uses a fixed four-characters-per-token heuristic plus structural overhead. There are no model profiles, density settings, tokenizer backends, or language-specific strategies. -### Model-bound replay folds +### Per-session replay folds -Each model/session pair owns an isolated incremental fold. Active folds advance from `session/event`; every read catches up through the durable tail, so listener ordering, seeded sessions, and service reload do not change the answer. The fold tracks canonical request headers and deltas, step boundaries, surface appends and replacements, assistant usage, and assistant-chunk provenance. A malformed next event fails transactionally and remains unread rather than partially mutating state. +Each session owns one isolated incremental fold. Active folds advance from `session/event`; every read catches up through the durable tail, so listener ordering, seeded sessions, and service reload do not change the answer. The fold tracks canonical request headers and deltas, step boundaries, surface appends and replacements, assistant usage, and assistant-chunk provenance. A malformed next event fails transactionally and remains unread rather than partially mutating state. -`measure(session, requestHeader?)` returns scalar pressure. `measureSurface(session)` returns positional per-node prices for retention and replacement decisions. `estimateMessage(message)` applies the handle's profile without session state. Results are detached, deeply immutable snapshots carrying `logRevision`; a consumer compares scalar and surface revisions before making one decision. +`measure(session, requestHeader?)` returns scalar pressure. `measureSurface(session)` returns positional per-node prices for retention and replacement decisions. `estimateMessage(message)` applies the fixed heuristic without session state. Results are detached, deeply immutable snapshots carrying `logRevision`; a consumer compares scalar and surface revisions before making one decision. -Provider usage is reused only when the handle's model and canonical request envelope equal the successful-call anchor. Any system, prefix, tool, or call-config change causes complete repricing under the requested model. Surface changes remain a signed delta from a matching anchor, including negative values after a shrinking replacement. A success by another model changes the shared surface but never overwrites this model's anchor. +Provider usage is reused only when the measured canonical request envelope equals the latest successful-call anchor. Any model, system, prefix, tool, or call-config change causes complete heuristic repricing. Surface changes remain a signed delta from a matching anchor, including negative values after a shrinking replacement. A later successful request replaces the earlier anchor, including across model switches. Usage sums the disjoint input, cache-read, cache-write, and output buckets. Reasoning is not added a second time. Every successful model call records an `assistant/message`, including content-less and max-token calls, with its exact earlier chunk seqs. An explicit empty provenance list means a known empty provider stream; absent legacy provenance conservatively treats the durable assistant output as provider output. ### Compact-basic consumes, but does not own, measurement -`dsh-compact-basic` requires `ctx.tokenMeter`; `CompactService` gains no token methods or types. The backend is factored into configuration, automatic triggering, region transaction, and summarizer modules, while `summarize()` remains its sole subclass hook. The conversation model's meter consistently prices pressure, retention, shadowed content, provenance, and non-shrinking-summary rejection. +`dsh-compact-basic` requires `ctx.tokenMeter`; `CompactService` gains no token methods or types. The backend is factored into configuration, automatic triggering, region transaction, and summarizer modules, while `summarize()` remains its sole subclass hook. The singleton service consistently prices pressure, retention, shadowed content, provenance, and non-shrinking-summary rejection. -Every metered model receives a compact policy with defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, summarization model `''`, maximum summary output `8192`, one extra compaction attempt, and automatic triggering enabled. Per-model compact overrides merge `thresholdRatio` and `retainTokens`; retention must remain below the resulting threshold. Empty summarization model resolves the latest logged routed model, then `AgentOptions.model`. +Compact policy has service-wide defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, summarization model `''`, maximum summary output `8192`, one extra compaction attempt, and automatic triggering enabled. Top-level `thresholdRatio` and `retainTokens` override the pressure policy; retention must remain below the resulting threshold. Empty summarization model resolves the latest logged routed model, then `AgentOptions.model`. -The pre-step trigger measures a provisional envelope: the current prompt and prefix override logged values, while the latest logged header supplies model, tools, and other call config. A model-less router-only agent skips that provisional check because `agent/request` can route later; naming an unknown model remains an error. +The pre-step trigger measures a provisional envelope: the current prompt and prefix override logged values, while the latest logged header supplies model, tools, and other call config. A model-less router-only agent skips that provisional check because `agent/request` can route later; any routed model name can use the singleton estimator. ## Testing -Unit coverage pins profiles, field-wise overrides, custom and unknown models, envelope invalidation, model switching, usage and missing-usage paths, seeded append/replace replay, signed deltas, provenance modes, malformed boundaries, immutable snapshots, listener ordering, reload, compact defaults, routing fallback, retention, convergence, and transaction rollback. A real Loader/Include YAML fixture loads the exact zero-config token-meter and compact-basic package names in dependency order. +Unit coverage pins service configuration, fixed estimation, envelope invalidation, latest-anchor replacement across model switches, usage and missing-usage paths, seeded append/replace replay, signed deltas, provenance modes, malformed boundaries, immutable snapshots, listener ordering, reload, compact defaults, routing fallback, retention, convergence, and transaction rollback. A real Loader/Include YAML fixture loads the exact zero-config token-meter and compact-basic package names in dependency order. ## Alternatives considered - **Keep estimation inside `CompactService`** — rejected because measurement has consumers and replay semantics independent of compaction; it would also force every compactor to expose the same unrelated API. - **Split a token-meter interface from a heuristic backend immediately** — rejected because only one implementation exists. One concrete service preserves the future seam without speculative packages or configuration. -- **Give unknown models a 128,000-token fallback** — rejected because a plausible but wrong capacity can trigger destructive policy at the wrong point. Unknown routed names fail with their exact name. +- **Keep model-keyed windows and density profiles** — rejected because the deployment currently has one context policy and one estimator. Model registries, unknown-model failures, and configurable density add branches without a second behavior to select. - **Copy complete history into each scalar result** — rejected because below-threshold reads are common. Immutable revisioned scalars and a separate surface snapshot preserve consistency without an O(history) copy. -- **Treat provider usage as portable between models or envelopes** — rejected because tokenization, context capacity, tools, prefixes, and call config are model/request facts. Mismatch reprices the whole current request. +- **Treat provider usage as portable between envelopes** — rejected because model, tools, prefixes, and call config are request facts. Mismatch reprices the whole current request. ## Consequences - Token pressure has one replay-aware owner that compaction and future plugins can share. -- Defaults make the bundled DeepSeek composition usable with two zero-config plugin entries, while custom models must state the one fact that cannot be guessed safely: context capacity. -- Heuristic density and provider usage remain estimates of provider behavior. Maintainers must update built-in profiles and overflow wording as models evolve. +- The default makes the bundled composition usable with two zero-config plugin entries; deployments override one context capacity when needed. +- Fixed heuristic pricing remains an estimate of provider behavior and is not an exact tokenizer or request serializer. - Measurements fail loudly on malformed durable boundaries. This turns corrupted replay into a named integration failure instead of silently drifting pressure. - The pre-step compact integration can skip a router-only first check and can miss tool or routing changes applied later in request middleware. diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md index 23edc11ffd..85565b6f3d 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md @@ -1,4 +1,4 @@ -# RFC: 重放式 token 计量服务 +# RFC: 回放式 token 计量服务 Status: implemented @@ -6,52 +6,52 @@ Status: implemented ## 问题 -上下文压力并不只对压缩有用。压缩后端、溢出保护或未来的请求策略插件都可能需要回答同一个问题：持久请求占用了某个模型多少上下文窗口？如果把该折叠逻辑留在 `dsh-compact-basic` 内部，就会重复实现重放逻辑，使未加载压缩的调用方无法使用计量，并诱使调用方错误复用其他模型的核算结果。 +上下文压力并不只对压缩有用。压缩后端、溢出保护或未来的请求策略插件都可能需要回答同一个问题：持久请求占用了已配置上下文窗口的多少容量？如果把该折叠逻辑留在 `dsh-compact-basic` 内部，就会重复实现回放逻辑，使未加载压缩的调用方无法使用计量，并诱使调用方复用陈旧的核算结果。 -提供方 usage 也不是完整答案。它只描述某个精确请求信封下的一次成功调用，而当前表层之后还可能增长、缩小或被替换。会话也可能切换模型，旧日志可能缺少 chunk 来源，提供方字段还会分别报告输入、缓存读取、缓存写入、输出与推理计数。因此，可用的服务必须把精确锚点与保守的逐模型重新定价结合起来，并公开每个结果已经消费的日志修订号。 +提供方 usage 也不是完整答案。它只描述某个精确请求信封下的一次成功调用，而当前表层之后还可能增长、缩小或被替换。会话也可能切换模型，旧日志可能缺少分片来源，提供方字段还会分别报告输入、缓存读取、缓存写入、输出与推理计数。因此，可用的服务必须把最新精确锚点与保守的启发式重新定价结合起来，并公开每个结果已经消费的日志修订号。 ## 决策 ### 一个具体的 LLM 家族服务 -`@deepseek-ai/dsh-token-meter` 是 `packages/llm/` 下的单个具体 package，并注册 `ctx.tokenMeter`。在第二种实现出现之前，它不会被拆成接口与后端。公开入口把精确模型名解析为稳定的 `ModelTokenMeter`；未知名称抛出带 `TOKEN_METER_MODEL_UNCONFIGURED` 的 `TokenMeterError`，而不是继承通用窗口。 +`@deepseek-ai/dsh-token-meter` 是 `packages/llm/` 下的单个具体包，并注册 `ctx.tokenMeter`。在第二种实现出现之前，它不会被拆成接口与后端。`TokenMeterService` 本身公开 `contextWindow`、`measure(session, requestHeader?)`、`measureSurface(session)` 与 `estimateMessage(message)`；消费方直接调用这个单例服务。 -内置的 `deepseek-v4-flash` 与 `deepseek-v4-pro` profile 都采用 128,000 token 上下文窗口，以及每 token 四个字符的估算密度。`models` 覆盖按字段合并。自定义名称必须提供 `contextWindow`，而 `charsPerToken` 默认为四。直接构造会报告类型化 profile 错误；Loader 挂载则先应用 package 的 Schemastery 形状校验。 +服务只有一个 `contextWindow`，默认值为 128,000 token，并允许配置为正整数。估算采用固定的每 token 四个字符启发式规则，并加上结构开销。服务不提供模型 profile、密度设置、分词器后端或语言专用策略。 -### 绑定模型的重放折叠 +### 逐会话回放折叠 -每个模型/会话对都有隔离的增量折叠。活跃折叠通过 `session/event` 前进；每次读取都会追到持久日志尾部，因此监听器顺序、种子会话与服务重载不会改变答案。折叠跟踪规范请求头及其增量、步骤边界、表层追加与替换、assistant usage，以及 assistant chunk 来源。下一个畸形事件会以事务方式失败并保持未读，不会让状态只修改一半。 +每个会话都有一个隔离的增量折叠。活跃折叠通过 `session/event` 前进；每次读取都会追到持久日志尾部，因此监听器顺序、种子会话与服务重载不会改变答案。折叠跟踪规范请求头及其增量、步骤边界、表层追加与替换、assistant usage，以及 assistant 分片来源。下一个畸形事件会以事务方式失败并保持未读，不会让状态只修改一半。 -`measure(session, requestHeader?)` 返回标量压力。`measureSurface(session)` 返回用于保留与替换决策的逐位置节点价格。`estimateMessage(message)` 不依赖会话状态，直接应用该 handle 的 profile。结果是分离且深度不可变的快照，并携带 `logRevision`；消费者在一次联合决策前比较标量与表层修订号。 +`measure(session, requestHeader?)` 返回标量压力。`measureSurface(session)` 返回用于保留与替换决策的逐位置节点价格。`estimateMessage(message)` 不依赖会话状态，直接应用固定启发式规则。结果是分离且深度不可变的快照，并携带 `logRevision`；消费方在一次联合决策前比较标量与表层修订号。 -只有当 handle 的模型与规范请求信封都等于成功调用锚点时，服务才复用提供方 usage。系统提示词、前缀、工具或调用配置任一变化都会在请求模型下重新定价完整当前请求。表层变化相对匹配锚点保留有符号增量，包括缩小替换后的负值。其他模型的成功调用会改变共享表层，但绝不会覆盖当前模型的锚点。 +只有当待计量的规范请求信封等于最近一次成功调用的锚点时，服务才复用提供方 usage。模型、系统提示词、前缀、工具或调用配置任一变化都会触发完整的启发式重新定价。表层变化相对匹配锚点保留有符号增量，包括缩小替换后的负值。后续成功请求会替换先前锚点，模型切换时也一样。 -Usage 会对互不重叠的输入、缓存读取、缓存写入与输出 bucket 求和，不会再次加入推理计数。每次成功模型调用都会记录 `assistant/message`，包括无内容调用与达到 token 上限的调用，并带上精确的更早 chunk seq。显式空来源列表表示已知为空的提供方流；旧日志中缺失的来源则保守地把持久 assistant 输出视为提供方输出。 +Usage 会对互不重叠的输入、缓存读取、缓存写入与输出 bucket 求和，不会再次加入推理计数。每次成功模型调用都会记录 `assistant/message`，包括无内容调用与达到 token 上限的调用，并带上精确的更早分片 seq。显式空来源列表表示已知为空的提供方流；旧日志中缺失的来源则保守地把持久 assistant 输出视为提供方输出。 ### compact-basic 消费计量，但不拥有计量 -`dsh-compact-basic` 要求 `ctx.tokenMeter`；`CompactService` 不增加 token 方法或类型。后端拆分为配置、自动触发、区域事务与摘要器模块，而 `summarize()` 仍是唯一的子类 hook。会话模型的 meter 一致用于压力、保留、被遮蔽内容、来源以及非缩小摘要拒绝。 +`dsh-compact-basic` 要求 `ctx.tokenMeter`；`CompactService` 不增加 token 方法或类型。后端拆分为配置、自动触发、区域事务与摘要器模块，而 `summarize()` 仍是唯一的子类 hook。单例服务一致用于压力、保留、被遮蔽内容、来源以及非缩小摘要拒绝的定价。 -每个已计量模型都会获得默认压缩策略：阈值比例 `0.8`、保留尾部 `floor(contextWindow × 0.16)`、摘要模型 `''`、摘要最大输出 `8192`、一次额外压缩尝试，以及启用自动触发。逐模型压缩覆盖按字段合并 `thresholdRatio` 与 `retainTokens`；保留值必须小于最终阈值。空摘要模型先解析最近记录的实际路由模型，再使用 `AgentOptions.model`。 +压缩策略采用服务级默认值：阈值比例 `0.8`、保留尾部 `floor(contextWindow × 0.16)`、摘要模型 `''`、摘要最大输出 `8192`、一次额外压缩尝试，以及启用自动触发。顶层 `thresholdRatio` 与 `retainTokens` 覆盖压力策略；保留值必须小于最终阈值。空摘要模型先解析最近记录的实际路由模型，再使用 `AgentOptions.model`。 -pre-step 触发器计量临时请求信封：当前提示词与前缀覆盖日志值，最近记录的请求头提供模型、工具及其他调用配置。没有模型的纯路由 agent 会跳过该临时检查，因为 `agent/request` 仍可稍后路由；显式命名未知模型仍然报错。 +pre-step 触发器计量临时请求信封：当前提示词与前缀覆盖日志值，最近记录的请求头提供模型、工具及其他调用配置。没有模型的纯路由 agent（智能体）会跳过该临时检查，因为 `agent/request` 仍可稍后路由；任意路由模型名都可使用这个单例估算器。 ## 测试 -单元覆盖固定 profile、按字段覆盖、自定义与未知模型、信封失效、模型切换、有无 usage 的路径、种子追加/替换重放、有符号增量、来源模式、畸形边界、不可变快照、监听器顺序、重载、压缩默认值、路由回退、保留、收敛与事务回滚。真实 Loader/Include YAML fixture 按依赖顺序加载精确的零配置 token-meter 与 compact-basic package 名称。 +单元覆盖固定服务配置、固定估算、信封失效、模型切换时替换最新锚点、有无 usage 的路径、种子追加/替换回放、有符号增量、来源模式、畸形边界、不可变快照、监听器顺序、重载、压缩默认值、路由回退、保留、收敛与事务回滚。真实 Loader/Include YAML fixture 按依赖顺序加载精确的零配置 token-meter 与 compact-basic 包名称。 ## 考虑过的替代方案 -- **把估算保留在 `CompactService` 内**——不予采纳，因为计量拥有独立于压缩的消费者与重放语义；它还会强迫每个压缩器暴露同一套无关 API。 -- **立即把 token meter 拆成接口与启发式后端**——不予采纳，因为目前只有一种实现。单个具体服务保留未来接缝，同时避免推测性的 package 与配置。 -- **给未知模型提供 128,000 token 回退**——不予采纳，因为看似合理但错误的容量会在错误时点触发破坏性策略。未知路由名称会携带精确名称失败。 +- **把估算保留在 `CompactService` 内**——不予采纳，因为计量拥有独立于压缩的消费方与回放语义；它还会强迫每个压缩器暴露同一套无关 API。 +- **立即把 token meter 拆成接口与启发式后端**——不予采纳，因为目前只有一种实现。单个具体服务保留未来接缝，同时避免推测性的包与配置。 +- **保留模型键控的窗口与密度 profile**——不予采纳，因为当前部署只有一种上下文策略与一个估算器。模型注册表、未知模型错误和可配置密度只增加分支，却没有第二种行为可供选择。 - **在每个标量结果中复制完整历史**——不予采纳，因为低于阈值的读取很常见。不可变且带修订号的标量与独立表层快照，在不进行 O(history) 复制的情况下保持一致性。 -- **在模型或信封之间移用提供方 usage**——不予采纳，因为分词、上下文容量、工具、前缀与调用配置都是模型/请求事实。不匹配时会重新定价完整当前请求。 +- **在不同信封之间移用提供方 usage**——不予采纳，因为模型、工具、前缀与调用配置都是请求事实。不匹配时会重新定价完整当前请求。 ## 后果 -- Token 压力拥有一个可供压缩与未来插件共享的重放感知所有者。 -- 默认值让内置 DeepSeek 组合只需两个零配置插件条目即可使用，而自定义模型必须声明唯一不能安全猜测的事实：上下文容量。 -- 启发式密度与提供方 usage 仍然只是提供方行为的估计。随着模型演进，维护者必须更新内置 profile 与溢出措辞。 -- 遇到畸形持久边界时，计量会明确失败。这会把损坏的重放转化为具名集成错误，而不是让压力静默漂移。 +- Token 压力拥有一个可供压缩与未来插件共享的回放感知所有者。 +- 默认值让内置组合只需两个零配置插件条目即可使用；部署需要时只覆盖一个上下文容量。 +- 固定启发式定价仍然只是提供方行为的估计，并不是精确分词器或请求序列化器。 +- 遇到畸形持久边界时，计量会明确失败。这会把损坏的回放转化为具名集成错误，而不是让压力静默漂移。 - pre-step 压缩集成可能跳过纯路由的首次检查，也可能错过请求中间件稍后应用的工具或路由变化。 diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index 42b93f1225..77f836e8e3 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -64,7 +64,7 @@ Auto-compaction always starts at the surface head, merging the prior checkpoint ### Approximate convergence invariant -`resolveConfig` supplies usable common defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, empty summarization-model override, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. Optional per-model threshold/retention fields merge over those defaults and must name a configured meter profile; retained tokens must be below the resulting threshold. Convergence remains dynamic because provider output caps can be spent on hidden or surfaced reasoning tokens and summary size is unpredictable. If the compacted surface remains over threshold, `compactIfNeeded()` re-compacts the head checkpoint up to the configured retry count, but each committed summary must be smaller than what it shadows. +`resolveConfig` supplies usable defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, empty summarization-model override, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. Optional top-level `thresholdRatio` and `retainTokens` override the policy for the token meter's single context window; retention must remain below the resulting threshold. Convergence remains dynamic because provider output caps can be spent on hidden or surfaced reasoning tokens and summary size is unpredictable. If the compacted surface remains over threshold, `compactIfNeeded()` re-compacts the head checkpoint up to the configured retry count, but each committed summary must be smaller than what it shadows. ### Surface replacement: `compact/*` events are log-only; one `user/message` carries the summary @@ -115,7 +115,7 @@ Two failure paths, both documented: - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry. - **`dsh-compact`** owns `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)`, the cached surface-edge checks that `compactRegion` and `compactIfNeeded` use to avoid splitting a tool-call/result pair. The cache validates current membership by seq and resolves after-edges from its positional successor map instead of trusting a caller-retained `node.next`; stale or missing seqs and orphan results reject. `dsh-session` continues to own the surface `replace` operation, positional nodes, and rewrite generation. - **`dsh-invariants`** drops its `surface replace: start must be <= end` assertion: a head-anchored compaction lands a high-seq replacement node at an older range's *position*, so `start > end` numerically is normal and valid (the range is positional, validated by the surface's `indexOf` checks that remain). The turn-enclosure invariant is reused unchanged. -- **Wiring**: `examples/coding-agent/cordis.yml` loads zero-config `dsh-token-meter` before `dsh-compact-basic`; bundled DeepSeek profiles and compact defaults make the pair usable without repeated numeric policy. +- **Wiring**: `examples/coding-agent/cordis.yml` loads zero-config `dsh-token-meter` before `dsh-compact-basic`; the service-wide window and compact defaults make the pair usable without repeated numeric policy. ## Testing diff --git a/examples/coding-agent/cordis.yml b/examples/coding-agent/cordis.yml index 881399f64e..5a85c3488f 100644 --- a/examples/coding-agent/cordis.yml +++ b/examples/coding-agent/cordis.yml @@ -46,12 +46,12 @@ Verify your work by running the code or tests. Keep answers brief and factual. -# Replay-aware request pressure for the bundled DeepSeek model profiles. +# Replay-aware request pressure with one service-wide context window. - id: token-meter name: '@deepseek-ai/dsh-token-meter' # Summarize an older range when measured history approaches the context window. -# Built-in model policies provide the ordinary threshold and retained-tail defaults. +# Service-wide policy provides the ordinary threshold and retained-tail defaults. - id: compact-basic name: '@deepseek-ai/dsh-compact-basic' diff --git a/examples/coding-agent/tests/compaction.e2e.ts b/examples/coding-agent/tests/compaction.e2e.ts index c2aa809327..aa9fda68e2 100644 --- a/examples/coding-agent/tests/compaction.e2e.ts +++ b/examples/coding-agent/tests/compaction.e2e.ts @@ -34,14 +34,11 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT, tokenMeter: { - models: { - 'deepseek-v4-flash': { contextWindow: 2000 }, - }, + contextWindow: 2000, }, compact: { - models: { - 'deepseek-v4-flash': { thresholdRatio: 0.5, retainTokens: 400 }, - }, + thresholdRatio: 0.5, + retainTokens: 400, summarizationModel: '', maxTokens: 1024, compactionRetries: 1, diff --git a/examples/coding-agent/tests/harness.ts b/examples/coding-agent/tests/harness.ts index 923b5efe84..cf79809f0c 100644 --- a/examples/coding-agent/tests/harness.ts +++ b/examples/coding-agent/tests/harness.ts @@ -48,7 +48,7 @@ export interface CodingHarnessOptions { * compaction plugin (the default suites run without it). */ compact?: BasicCompactConfig - /** Optional meter profiles loaded before compact-basic. */ + /** Optional token-meter capacity loaded before compact-basic. */ tokenMeter?: TokenMeterConfig } @@ -65,7 +65,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio await ctx.plugin(ToolBash) await ctx.plugin(ToolTodo) // Compaction is opt-in: only the compaction e2e loads the reusable meter and - // backend, with a lowered profile window so a short real session crosses the threshold. + // backend, with a lower context window so a short real session crosses the threshold. if (options.compact !== undefined) { await ctx.plugin(TokenMeterService, options.tokenMeter) await ctx.plugin(BasicCompactService, options.compact) diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index c9264e2e99..b166636a5f 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -8,7 +8,7 @@ This is the implementation tier of the compaction capability — see the [interf This backend owns the compaction policy: -- **Measurement** — the effective conversation model's `ModelTokenMeter` prices the provisional request envelope and current surface at one consumed-log revision. The current prompt and prefix override their logged values; the pre-step boundary reuses logged tools and call config. +- **Measurement** — the singleton `ctx.tokenMeter` prices the provisional request envelope and current surface at one consumed-log revision. The current prompt and prefix override their logged values; the pre-step boundary reuses logged tools and call config. - **Retention** — compact the oldest whole surface units while preserving a recent tail and balanced tool-call/result cuts through the [`dsh-compact` boundary helpers](../compact/README.md#tool-pairing-boundaries). Turn boundaries do not protect old steps inside a runaway turn. An open indivisible tail declines until it closes; a single unit larger than the budget remains out of scope. - **Convergence** — retry head-checkpoint compaction up to `compactionRetries`; reject a summary that does not shrink its source, and throw if retries cannot return below threshold. - **Summarization** — a direct `llm/stream` call uses the configured model and cap without running the loop-only `agent/request` seam. The input transcript preserves non-text blocks as tagged placeholders; only returned text enters the checkpoint, excluding reasoning and tool calls that would leak private reasoning or create an orphaned call. @@ -16,16 +16,16 @@ This backend owns the compaction policy: - **Lifecycle** — `compactRegion()` requires its agent to own the exact target session and rejects mismatch before resolution or mutation; a valid call records its start, summary, replacement, and end. The serial `agent/pre-step` listener checks pressure before every step, outside an open step, so a tool-heavy turn remains compactable and the loop derives history once after mutation. - **Failure handling** — an unmatched `compact/start` is an inert crash marker because no replacement landed. Recoverable failure records an error end and leaves the surface unchanged. -`summarize()` is the sole subclass hook. A template- or remote-summarizer subclass can override it while pressure, retention, provenance, shrink validation, and shadowed-token accounting stay on the conversation model's meter. The hook returns the summary blocks together with the call envelope it used (`{ summary, model, maxTokens? }`), which is logged on `compact/summary`. +`summarize()` is the sole subclass hook. A template- or remote-summarizer subclass can override it while pressure, retention, provenance, shrink validation, and shadowed-token accounting stay on `ctx.tokenMeter`. The hook returns the summary blocks together with the call envelope it used (`{ summary, model, maxTokens? }`), which is logged on `compact/summary`. ## Config (`BasicCompactConfig`) -Every common setting is optional. Every model known to `ctx.tokenMeter` receives the default compact policy lazily; named overrides merge only the fields supplied and must name a configured meter profile. +Every setting is optional. The pressure and retention policy applies to the token meter's single context window. | Key | Required | Meaning | |---|---|---| -| `models..thresholdRatio` | no (default `0.8`) | Compact at `floor(contextWindow × ratio)`. | -| `models..retainTokens` | no (default `floor(contextWindow × 0.16)`) | Recent surface budget kept verbatim; must be below the threshold. | +| `thresholdRatio` | no (default `0.8`) | Compact at `floor(contextWindow × ratio)`. | +| `retainTokens` | no (default `floor(contextWindow × 0.16)`) | Recent surface budget kept verbatim; must be below the threshold. | | `summarizationModel` | no (default `''`) | Empty resolves the latest logged routed model, then `AgentOptions.model`. | | `maxTokens` | no (default `8192`) | Provider generation cap for the summarization call; may include reasoning tokens. | | `compactionRetries` | no (default `1`) | Extra attempts after the first when pressure remains above threshold. | @@ -116,7 +116,7 @@ Rules: ## Known Limitations and Deferred Work - **Pre-step sees a provisional request envelope** — the current prompt and prefix are exact, but routing and tool changes made later in `agent/request` are not logged yet. A router-only agent with no provisional model skips that check. -- **Meter accuracy follows the selected profile** — missing provider usage falls back to the token meter's configured character density and structural overhead. +- **Meter accuracy follows the fixed heuristic** — missing reusable provider usage falls back to character count plus structural overhead rather than exact tokenization. - **`compactRegion` requires an open turn** — a manual call on a fully-closed session throws ("no open turn") rather than compacting. - **Summarization failure fails closed with full, over-budget history** — including truncation at the summarization `maxTokens`, which hidden reasoning tokens can consume; the auto path logs a warning and proceeds. - **The summarization call has no transcript-snapshot coverage** — `dsh-llm-replay` derives calls from `assistant/chunk` events, so this chunk-less direct `ctx.llm.stream()` call cannot replay (named deferred replay infrastructure in [the seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)). diff --git a/packages/compact/compact-basic/src/automatic.ts b/packages/compact/compact-basic/src/automatic.ts index 504b0d8a9f..edb317d270 100644 --- a/packages/compact/compact-basic/src/automatic.ts +++ b/packages/compact/compact-basic/src/automatic.ts @@ -7,10 +7,6 @@ import type { Context } from 'cordis' import type { CompactionResult } from '@deepseek-ai/dsh-compact' import type { Message } from '@deepseek-ai/dsh-llm' -import { - TOKEN_METER_MODEL_UNCONFIGURED, - TokenMeterError, -} from '@deepseek-ai/dsh-token-meter' import type { Agent } from '@deepseek-ai/dsh-agent' interface AutomaticCompactor { @@ -49,10 +45,6 @@ export function registerAutomaticCompaction( ) } } catch (error: unknown) { - // A named routed model without a meter profile is configuration failure, - // not an optional operational compaction miss. - if (error instanceof TokenMeterError - && error.code === TOKEN_METER_MODEL_UNCONFIGURED) throw error const message = error instanceof Error ? error.message : String(error) ctx.logger.warn(`compaction failed: ${message}; proceeding with full history`) } diff --git a/packages/compact/compact-basic/src/config.ts b/packages/compact/compact-basic/src/config.ts index 3169d7f5aa..da2cd7bea7 100644 --- a/packages/compact/compact-basic/src/config.ts +++ b/packages/compact/compact-basic/src/config.ts @@ -1,63 +1,49 @@ /** - * Runtime defaulting and per-model policy validation for compact-basic. + * Runtime defaulting and policy validation for compact-basic. * * @module @deepseek-ai/dsh-compact-basic/config */ import { deepFreeze } from '@deepseek-ai/dsh-llm' -import type { ModelTokenMeter, TokenMeterService } from '@deepseek-ai/dsh-token-meter' -import type { - BasicCompactConfig, - ModelCompactConfig, - ResolvedConfig, - ResolvedModelCompactConfig, -} from './types.ts' +import type { TokenMeterService } from '@deepseek-ai/dsh-token-meter' +import type { BasicCompactConfig, ResolvedConfig } from './types.ts' -/** Default request-pressure fraction for every metered model. */ +/** Default request-pressure fraction of the token meter's context window. */ const DEFAULT_THRESHOLD_RATIO = 0.8 -/** Default verbatim-tail fraction of a model's context window. */ +/** Default verbatim-tail fraction of the token meter's context window. */ const DEFAULT_RETAIN_RATIO = 0.16 /** - * Resolve common defaults and validate every named model override. + * Resolve defaults and validate the service-wide compaction policy. * @param config - raw compact-basic configuration. - * @param tokenMeter - owning meter service used to reject unknown override names. - * @returns a detached deeply immutable top-level configuration. + * @param tokenMeter - token meter supplying the context capacity. + * @returns a detached deeply immutable configuration. */ export function resolveConfig( config: BasicCompactConfig = {}, tokenMeter: TokenMeterService, ): ResolvedConfig { - const configuredModels: unknown = config.models - const models = configuredModels === undefined ? {} : configuredModels - if (typeof models !== 'object' || models === null || Array.isArray(models)) { - throw new Error('BasicCompactConfig: models must be an object') - } - - const detachedModels: Record = {} - for (const [model, override] of Object.entries(models as Record)) { - if (typeof override !== 'object' || override === null || Array.isArray(override)) { - throw new Error(`BasicCompactConfig: models.${model} must be an object`) - } - const meter = tokenMeter.resolve(model) - detachedModels[model] = { ...override as ModelCompactConfig } - resolveModelConfig({ - models: detachedModels, - summarizationModel: '', - maxTokens: 8192, - compactionRetries: 1, - auto: true, - }, meter) - } - + const thresholdRatio = config.thresholdRatio ?? DEFAULT_THRESHOLD_RATIO + const retainTokens = config.retainTokens + ?? Math.floor(tokenMeter.contextWindow * DEFAULT_RETAIN_RATIO) const resolved: ResolvedConfig = { - models: detachedModels, + thresholdRatio, + retainTokens, summarizationModel: config.summarizationModel ?? '', maxTokens: config.maxTokens ?? 8192, compactionRetries: config.compactionRetries ?? 1, auto: config.auto ?? true, } + + assertRatio('thresholdRatio', resolved.thresholdRatio) + assertNonNegativeInteger('retainTokens', resolved.retainTokens) + const thresholdTokens = Math.floor(tokenMeter.contextWindow * resolved.thresholdRatio) + if (resolved.retainTokens >= thresholdTokens) { + throw new Error( + `BasicCompactConfig: retainTokens (${resolved.retainTokens}) must be less than threshold tokens ${thresholdTokens}`, + ) + } assertPositiveInteger('maxTokens', resolved.maxTokens) assertNonNegativeInteger('compactionRetries', resolved.compactionRetries) if (typeof resolved.summarizationModel !== 'string') { @@ -66,36 +52,7 @@ export function resolveConfig( if (typeof resolved.auto !== 'boolean') { throw new Error('BasicCompactConfig: auto must be a boolean') } - return deepFreeze(structuredClone(resolved)) -} - -/** - * Resolve one effective model's default policy plus optional field overrides. - * @param config - validated compact-basic configuration. - * @param meter - effective model's token-meter handle and context capacity. - * @returns a detached immutable model policy. - */ -export function resolveModelConfig( - config: ResolvedConfig, - meter: ModelTokenMeter, -): ResolvedModelCompactConfig { - const override = config.models[meter.model] - const thresholdRatio = override?.thresholdRatio ?? DEFAULT_THRESHOLD_RATIO - const retainTokens = override?.retainTokens ?? Math.floor(meter.contextWindow * DEFAULT_RETAIN_RATIO) - assertRatio(`models.${meter.model}.thresholdRatio`, thresholdRatio) - assertNonNegativeInteger(`models.${meter.model}.retainTokens`, retainTokens) - const thresholdTokens = Math.floor(meter.contextWindow * thresholdRatio) - if (retainTokens >= thresholdTokens) { - throw new Error( - `BasicCompactConfig: models.${meter.model}.retainTokens (${retainTokens}) must be less than threshold tokens ${thresholdTokens}`, - ) - } - return deepFreeze({ - model: meter.model, - contextWindow: meter.contextWindow, - thresholdRatio, - retainTokens, - }) + return deepFreeze(resolved) } function assertPositiveInteger(name: string, value: number): void { diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index cd4ea5d1d5..16387c5e09 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -11,24 +11,20 @@ import type { CompactionResult } from '@deepseek-ai/dsh-compact' import { canonicalHeader } from '@deepseek-ai/dsh-session' import type { EpochHeader, Session } from '@deepseek-ai/dsh-session' import type { ContentBlock, Message } from '@deepseek-ai/dsh-llm' -import type { ModelTokenMeter } from '@deepseek-ai/dsh-token-meter' import type { Agent } from '@deepseek-ai/dsh-agent' import { registerAutomaticCompaction } from './automatic.ts' -import { resolveConfig, resolveModelConfig } from './config.ts' +import { resolveConfig } from './config.ts' import { compactSurfaceRegion, selectCompactableRange } from './region.ts' import { summarizeWithLlm } from './summarizer.ts' import type { BasicCompactConfig, ResolvedConfig, - ResolvedModelCompactConfig, } from './types.ts' -export { resolveConfig, resolveModelConfig } from './config.ts' +export { resolveConfig } from './config.ts' export type { BasicCompactConfig, - ModelCompactConfig, ResolvedConfig, - ResolvedModelCompactConfig, } from './types.ts' /** Resolve the latest actual routed model, then the agent's configured fallback. */ @@ -61,28 +57,24 @@ function provisionalHeader( * retention, provenance, and summary-convergence pricing. * * `summarize()` is the sole subclass customization hook; the replay and durable - * mutation strategy stays fixed so every pricing decision uses one effective - * conversation-model meter. + * mutation strategy stays fixed so every pricing decision uses the singleton + * token meter. */ export class BasicCompactService extends CompactService { static inject = ['llm', 'tokenMeter'] static Config: z = z.object({ - models: z.dict(z.object({ - thresholdRatio: z.number(), - retainTokens: z.number().step(1), - })), + thresholdRatio: z.number().default(0.8), + retainTokens: z.number().step(1), summarizationModel: z.string().default(''), maxTokens: z.number().step(1).min(1).default(8192), compactionRetries: z.number().step(1).min(0).default(1), auto: z.boolean().default(true), }) - /** Resolved and validated common configuration plus named partial overrides. */ + /** Resolved and validated compaction configuration. */ readonly config: ResolvedConfig - private readonly modelConfigs = new Map() - constructor(ctx: Context, config: BasicCompactConfig = {}) { super(ctx) this.config = resolveConfig(config, ctx.tokenMeter) @@ -107,9 +99,8 @@ export class BasicCompactService extends CompactService { /** * Check replayed pressure for the provisional pre-step envelope and compact - * a tool-balanced head until it falls below the effective model threshold. - * A genuinely model-less router-first step skips this provisional check; - * naming an unconfigured model throws the token meter's typed error. + * a tool-balanced head until it falls below the service-wide threshold. + * A genuinely model-less router-first step skips this provisional check. * @param agent - agent whose session and provisional model are measured. * @param fullSystemPrompt - current assembled system prompt override. * @param sessionPrefix - current request-only prefix override. @@ -124,10 +115,9 @@ export class BasicCompactService extends CompactService { ): Promise { const model = effectiveModel(agent) if (model === undefined || model.length === 0) return null - const meter = this.ctx.tokenMeter.resolve(model) - const policy = this._modelConfig(meter) + const meter = this.ctx.tokenMeter const requestHeader = provisionalHeader(model, agent.session, fullSystemPrompt, sessionPrefix) - const threshold = Math.floor(policy.contextWindow * policy.thresholdRatio) + const threshold = Math.floor(meter.contextWindow * this.config.thresholdRatio) let measurement = meter.measure(agent.session, requestHeader) if (measurement.totalTokens < threshold) return null @@ -139,7 +129,7 @@ export class BasicCompactService extends CompactService { `compaction: pressure revision ${measurement.logRevision} does not match surface revision ${surface.logRevision}`, ) } - const range = selectCompactableRange(agent.session, surface, policy.retainTokens) + const range = selectCompactableRange(agent.session, surface, this.config.retainTokens) if (range === null) { /* v8 ignore else -- concrete replacement preserves a compactable checkpoint; subclass hooks cannot mutate it. */ if (result === null) return null @@ -159,12 +149,12 @@ export class BasicCompactService extends CompactService { /** * Compact one inclusive positional surface range using the effective - * conversation model for all retention and shrink pricing. Reject an agent - * that does not own the exact target before any resolution or mutation. + * token meter for all retention and shrink pricing. Reject an agent that does + * not own the exact target before any mutation. * @param session - session whose surface is mutated; must equal `agent.session`. * @param start - inclusive first surface-node seq. * @param end - inclusive last surface-node seq. - * @param agent - owner of the target session, used by the summarizer and model resolver. + * @param agent - owner of the target session, used by the summarizer. * @param signal - optional summarization cancellation signal. * @returns the successful durable compaction result. */ @@ -178,27 +168,11 @@ export class BasicCompactService extends CompactService { if (session !== agent.session) { throw new Error('compactRegion: agent.session must be the exact target session') } - const model = effectiveModel(agent) - if (model === undefined || model.length === 0) { - throw new Error('compactRegion: no routed or configured conversation model is available for token pricing') - } - const meter = this.ctx.tokenMeter.resolve(model) - this._modelConfig(meter) return compactSurfaceRegion({ - meter, + meter: this.ctx.tokenMeter, summarize: (text, owner, abort) => this.summarize(text, owner, abort), }, session, start, end, agent, signal) } - - /** Resolve and memoize one lazy default/override model policy. */ - private _modelConfig(meter: ModelTokenMeter): ResolvedModelCompactConfig { - let modelConfig = this.modelConfigs.get(meter.model) - if (modelConfig === undefined) { - modelConfig = resolveModelConfig(this.config, meter) - this.modelConfigs.set(meter.model, modelConfig) - } - return modelConfig - } } export default BasicCompactService diff --git a/packages/compact/compact-basic/src/region.ts b/packages/compact/compact-basic/src/region.ts index 1bc9b7b0a7..83ed04a3eb 100644 --- a/packages/compact/compact-basic/src/region.ts +++ b/packages/compact/compact-basic/src/region.ts @@ -10,14 +10,14 @@ import { toolPairingBalancedBefore, } from '@deepseek-ai/dsh-compact' import type { CompactionResult } from '@deepseek-ai/dsh-compact' -import type { ModelTokenMeter, TokenSurfaceMeasurement } from '@deepseek-ai/dsh-token-meter' +import type { TokenMeterService, TokenSurfaceMeasurement } from '@deepseek-ai/dsh-token-meter' import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' import type { Agent } from '@deepseek-ai/dsh-agent' import { frameSummary } from './summarizer.ts' import type { SummaryResult } from './summarizer.ts' interface RegionDependencies { - readonly meter: ModelTokenMeter + readonly meter: TokenMeterService summarize(text: string, agent: Agent, signal?: AbortSignal): Promise } diff --git a/packages/compact/compact-basic/src/types.ts b/packages/compact/compact-basic/src/types.ts index 44ff06435d..b9f6c4742c 100644 --- a/packages/compact/compact-basic/src/types.ts +++ b/packages/compact/compact-basic/src/types.ts @@ -4,18 +4,12 @@ * @module @deepseek-ai/dsh-compact-basic/types */ -/** Optional pressure and retention policy for one metered model. */ -export interface ModelCompactConfig { - /** Compact at this fraction of the model's configured context window. Defaults to `0.8`. */ +/** Basic compaction configuration; every common field has a deployment default. */ +export interface BasicCompactConfig { + /** Compact at this fraction of the token meter's context window. Defaults to `0.8`. */ thresholdRatio?: number /** Recent surface tokens retained verbatim. Defaults to `floor(contextWindow * 0.16)`. */ retainTokens?: number -} - -/** Basic compaction configuration; every common field has a deployment default. */ -export interface BasicCompactConfig { - /** Field-wise pressure/retention overrides keyed by configured token-meter model name. */ - models?: Record /** Summary model; `''` resolves the latest routed model, then `AgentOptions.model`. Defaults to `''`. */ summarizationModel?: string /** Provider generation cap for summarization. Defaults to `8192`. */ @@ -26,19 +20,12 @@ export interface BasicCompactConfig { auto?: boolean } -/** Validated top-level defaults plus detached per-model partial overrides. */ +/** Validated and detached compaction configuration. */ export interface ResolvedConfig { - readonly models: Readonly>> + readonly thresholdRatio: number + readonly retainTokens: number readonly summarizationModel: string readonly maxTokens: number readonly compactionRetries: number readonly auto: boolean } - -/** Fully resolved pressure/retention policy for one effective model. */ -export interface ResolvedModelCompactConfig { - readonly model: string - readonly contextWindow: number - readonly thresholdRatio: number - readonly retainTokens: number -} diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 98b4b2f15b..86471d2630 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -1,31 +1,21 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import BasicCompactService, { - resolveConfig, - resolveModelConfig, -} from '@deepseek-ai/dsh-compact-basic' +import BasicCompactService, { resolveConfig } from '@deepseek-ai/dsh-compact-basic' import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic' import { selectCompactableRange } from '@deepseek-ai/dsh-compact-basic/src/region.ts' import type { CompactionResult } from '@deepseek-ai/dsh-compact' import LlmService, { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' import type { ContentBlock, GenerateOptions, Message, StreamChunk } from '@deepseek-ai/dsh-llm' import { Session, SessionId } from '@deepseek-ai/dsh-session' -import TokenMeterService, { - TOKEN_METER_MODEL_UNCONFIGURED, - TokenMeterError, -} from '@deepseek-ai/dsh-token-meter' +import TokenMeterService from '@deepseek-ai/dsh-token-meter' import type { Agent } from '@deepseek-ai/dsh-agent' const SIGNAL = new AbortController().signal const MODEL = 'test-model' -function createContext( - models: Record = { - [MODEL]: { contextWindow: 100, charsPerToken: 1_000 }, - }, -): Context { +function createContext(contextWindow = 1_000): Context { const ctx = new Context() - void new TokenMeterService(ctx, { models }) + void new TokenMeterService(ctx, { contextWindow }) return ctx } @@ -34,7 +24,7 @@ function agent(session: Session, model?: string): Agent { } /** Closed two-message turns followed by one open turn for durable compaction events. */ -function conversation(turns = 4, text = 'fixture'): Session { +function conversation(turns = 4, text = 'fixture '.repeat(40).trim()): Session { const session = new Session(SessionId(`conversation-${turns}`)) for (let turn = 1; turn <= turns; turn += 1) { session.append('turn/start', { turn, trigger: { kind: 'message', source: { kind: 'user' } } }) @@ -128,83 +118,64 @@ async function compactIfNeeded( } describe('compact configuration and defaults', () => { - it('uses low-friction common and per-profile defaults', () => { - const ctx = createContext({ - [MODEL]: { contextWindow: 100, charsPerToken: 1_000 }, - large: { contextWindow: 1_000, charsPerToken: 4 }, - }) + it('uses low-friction service-wide defaults', () => { + const ctx = createContext() const resolved = resolveConfig({}, ctx.tokenMeter) expect(resolved).toEqual({ - models: {}, + thresholdRatio: 0.8, + retainTokens: 160, summarizationModel: '', maxTokens: 8192, compactionRetries: 1, auto: true, }) - expect(resolveModelConfig(resolved, ctx.tokenMeter.resolve(MODEL))).toEqual({ - model: MODEL, - contextWindow: 100, - thresholdRatio: 0.8, - retainTokens: 16, - }) - expect(resolveModelConfig(resolved, ctx.tokenMeter.resolve('large')).retainTokens).toBe(160) expect(Object.isFrozen(resolved)).toBe(true) }) - it('merges threshold and retention overrides field-wise', () => { + it('resolves threshold and retention overrides independently', () => { const ctx = createContext() const thresholdOnly = resolveConfig({ - models: { [MODEL]: { thresholdRatio: 0.5 } }, - }, ctx.tokenMeter) - expect(resolveModelConfig(thresholdOnly, ctx.tokenMeter.resolve(MODEL))).toMatchObject({ thresholdRatio: 0.5, - retainTokens: 16, + }, ctx.tokenMeter) + expect(thresholdOnly).toMatchObject({ + thresholdRatio: 0.5, + retainTokens: 160, }) const retentionOnly = resolveConfig({ - models: { [MODEL]: { retainTokens: 7 } }, + retainTokens: 70, }, ctx.tokenMeter) - expect(resolveModelConfig(retentionOnly, ctx.tokenMeter.resolve(MODEL))).toMatchObject({ + expect(retentionOnly).toMatchObject({ thresholdRatio: 0.8, - retainTokens: 7, + retainTokens: 70, }) }) - it('validates common values and model policy invariants', () => { + it('validates common values and pressure-policy invariants', () => { const ctx = createContext() const bad = [ [{ maxTokens: 0 }, /maxTokens/], [{ compactionRetries: -1 }, /compactionRetries/], [{ auto: 'yes' }, /auto must be a boolean/], [{ summarizationModel: 1 }, /summarizationModel must be a string/], - [{ models: null }, /models must be an object/], - [{ models: { [MODEL]: null } }, /must be an object/], - [{ models: { [MODEL]: { thresholdRatio: 0 } } }, /number in \(0, 1\]/], - [{ models: { [MODEL]: { thresholdRatio: 1.1 } } }, /number in \(0, 1\]/], - [{ models: { [MODEL]: { retainTokens: -1 } } }, /non-negative integer/], - [{ models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 50 } } }, /less than threshold/], + [{ thresholdRatio: 0 }, /number in \(0, 1\]/], + [{ thresholdRatio: 1.1 }, /number in \(0, 1\]/], + [{ retainTokens: -1 }, /non-negative integer/], + [{ thresholdRatio: 0.5, retainTokens: 500 }, /less than threshold/], ] as Array<[unknown, RegExp]> for (const [config, pattern] of bad) { expect(() => resolveConfig(config as BasicCompactConfig, ctx.tokenMeter)).toThrow(pattern) } }) - - it('rejects an override for an unknown meter profile with the exact typed error', () => { - const ctx = createContext() - expect(() => resolveConfig({ models: { missing: { retainTokens: 1 } } }, ctx.tokenMeter)) - .toThrow(expect.objectContaining({ - code: TOKEN_METER_MODEL_UNCONFIGURED, - model: 'missing', - })) - }) }) describe('pressure measurement and retention', () => { const compactConfig: BasicCompactConfig = { auto: false, - models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + thresholdRatio: 0.5, + retainTokens: 180, } it('skips the provisional check only when no routed or fallback model exists', async () => { @@ -214,10 +185,10 @@ describe('pressure measurement and retention', () => { expect(compact.calls).toHaveLength(0) }) - it('throws for a named unconfigured model instead of swallowing it', async () => { + it('meters any routed model without profile resolution', async () => { const compact = service(compactConfig) - await expect(compactIfNeeded(compact, conversation(), 'missing')) - .rejects.toMatchObject({ code: TOKEN_METER_MODEL_UNCONFIGURED, model: 'missing' }) + await expect(compactIfNeeded(compact, conversation(), 'unlisted-model')) + .resolves.not.toBeNull() }) it('does nothing below threshold and compacts a priced head above threshold', async () => { @@ -234,38 +205,39 @@ describe('pressure measurement and retention', () => { it('counts the current prompt and request prefix without putting either on the surface', async () => { const compact = service({ auto: false, - models: { [MODEL]: { thresholdRatio: 0.7, retainTokens: 9 } }, + thresholdRatio: 0.7, + retainTokens: 50, }) - const session = conversation(2, 'x'.repeat(2_000)) + const session = conversation(2, 'x'.repeat(200)) expect(await compactIfNeeded(compact, session)).toBeNull() const prefix: Message[] = [{ role: 'user', - content: [{ type: 'text', text: 'p'.repeat(10_000) }], + content: [{ type: 'text', text: 'p'.repeat(1_000) }], }] - const result = await compactIfNeeded(compact, session, MODEL, 's'.repeat(5_000), prefix) + const result = await compactIfNeeded(compact, session, MODEL, 's'.repeat(1_000), prefix) expect(result).not.toBeNull() expect(prefix).toHaveLength(1) expect(session.events.some(event => event.type === 'context/message')).toBe(false) }) - it('uses the latest logged routed model instead of AgentOptions.model', async () => { - const ctx = createContext({ - actual: { contextWindow: 100, charsPerToken: 1_000 }, - fallback: { contextWindow: 10_000, charsPerToken: 1_000 }, - }) + it('uses the latest logged routed model in the provisional request envelope', async () => { + const ctx = createContext() const compact = service({ auto: false, - models: { actual: { thresholdRatio: 0.5, retainTokens: 18 } }, + thresholdRatio: 0.5, + retainTokens: 180, }, ctx) const session = conversation(4) session.append('request/header', { header: { config: { model: 'actual' } }, reason: 'initial', }) + const measure = vi.spyOn(ctx.tokenMeter, 'measure') const result = await compactIfNeeded(compact, session, 'fallback') expect(result).not.toBeNull() + expect(measure.mock.calls[0]?.[1]?.config.model).toBe('actual') }) it('declines when envelope pressure is high but the surface has no compactable range', async () => { @@ -279,7 +251,7 @@ describe('pressure measurement and retention', () => { it('detects scalar/surface revision disagreement', async () => { const ctx = createContext() - const meter = ctx.tokenMeter.resolve(MODEL) + const meter = ctx.tokenMeter const original = meter.measureSurface.bind(meter) vi.spyOn(meter, 'measureSurface').mockImplementation((session) => { const measurement = original(session) @@ -294,7 +266,8 @@ describe('pressure measurement and retention', () => { const compact = service({ auto: false, compactionRetries: 0, - models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + thresholdRatio: 0.3, + retainTokens: 180, }) compact.summary = Array.from({ length: 7 }, (_, index) => ({ type: 'text', @@ -308,8 +281,9 @@ describe('pressure measurement and retention', () => { it('rounds a retention cut head-ward to preserve tool-call/result pairing', async () => { const compact = service({ auto: false, - models: { [MODEL]: { thresholdRatio: 0.8, retainTokens: 8 } }, - }) + thresholdRatio: 0.8, + retainTokens: 80, + }, createContext(4_000)) const session = toolConversation() const result = await compactIfNeeded(compact, session) expect(result).not.toBeNull() @@ -327,7 +301,7 @@ describe('pressure measurement and retention', () => { it('rejects a priced surface that is not the current positional surface', () => { const ctx = createContext() const session = conversation(2) - const priced = ctx.tokenMeter.resolve(MODEL).measureSurface(session) + const priced = ctx.tokenMeter.measureSurface(session) expect(() => selectCompactableRange(session, { ...priced, nodes: priced.nodes.slice(1), @@ -355,7 +329,7 @@ describe('pressure measurement and retention', () => { }, { surfaceOp: 'append' }) session.append('step/end', { turn: 1, step: 1 }) - const priced = ctx.tokenMeter.resolve(MODEL).measureSurface(session) + const priced = ctx.tokenMeter.measureSurface(session) expect(selectCompactableRange(session, priced, 1)).toBeNull() }) }) @@ -497,7 +471,7 @@ describe('compaction region transaction', () => { it('rejects a meter snapshot that changed before summarization began', async () => { const ctx = createContext() - const meter = ctx.tokenMeter.resolve(MODEL) + const meter = ctx.tokenMeter const original = meter.measureSurface.bind(meter) vi.spyOn(meter, 'measureSurface').mockImplementationOnce((session) => { const measurement = original(session) @@ -569,7 +543,7 @@ describe('compaction region transaction', () => { it('rejects a non-shrinking framed summary under the conversation meter', async () => { const compact = service() - compact.summary = Array.from({ length: 20 }, (_, index) => ({ + compact.summary = Array.from({ length: 100 }, (_, index) => ({ type: 'text', text: `verbose ${index}`, })) @@ -585,7 +559,7 @@ describe('compaction region transaction', () => { expect(session.events.some(event => event.type === 'compact/summary')).toBe(false) }) - it('requires a conversation model for pricing', async () => { + it('lets a model-independent custom summarizer compact without a conversation model', async () => { const compact = service() const session = conversation(1) const nodes = session.surface.nodes @@ -594,7 +568,7 @@ describe('compaction region transaction', () => { nodes[0]!.seq, nodes[1]!.seq, agent(session), - )).rejects.toThrow(/no routed or configured conversation model/) + )).resolves.toMatchObject({ shadowedSeqs: [nodes[0]!.seq, nodes[1]!.seq] }) }) }) @@ -632,7 +606,7 @@ async function summarizerHarness( ): Promise<{ ctx: Context; adapter: ScriptedAdapter; compact: BasicCompactService }> { const ctx = new Context() await ctx.plugin(LlmService) - void new TokenMeterService(ctx, { models: { [model]: { contextWindow: 100 } } }) + void new TokenMeterService(ctx, { contextWindow: 1_000 }) const adapter = new ScriptedAdapter(blocks, finish) ctx.llm.registerAdapter([model], adapter) const compact = new BasicCompactService(ctx, config) @@ -724,7 +698,8 @@ describe('automatic listener and loader composition', () => { it('compacts above threshold and remains idle below it', async () => { const ctx = createContext() const compact = new TestCompactService(ctx, { - models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + thresholdRatio: 0.5, + retainTokens: 180, }) const pressured = conversation(4) await preStep(ctx, agent(pressured, MODEL)) @@ -741,7 +716,8 @@ describe('automatic listener and loader composition', () => { const warnings: string[] = [] ctx.logger.warn = ((message: string) => void warnings.push(message)) as typeof ctx.logger.warn const compact = new TestCompactService(ctx, { - models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + thresholdRatio: 0.5, + retainTokens: 180, }) compact.error = 'temporary failure' const session = conversation(4) @@ -751,20 +727,12 @@ describe('automatic listener and loader composition', () => { expect(session.events.some(event => event.type === 'compact/summary')).toBe(false) }) - it('propagates a named unknown-model configuration failure', async () => { - const ctx = createContext() - void new TestCompactService(ctx) - await expect(preStep(ctx, agent(conversation(4), 'missing'))).rejects.toMatchObject({ - code: TOKEN_METER_MODEL_UNCONFIGURED, - model: 'missing', - }) - }) - it('auto:false installs no listener', async () => { const ctx = createContext() void new TestCompactService(ctx, { auto: false, - models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + thresholdRatio: 0.5, + retainTokens: 180, }) const session = conversation(4) await preStep(ctx, agent(session, MODEL)) @@ -777,7 +745,7 @@ describe('automatic listener and loader composition', () => { const meterFiber = await ctx.plugin(TokenMeterService) const compactFiber = await ctx.plugin(BasicCompactService, { auto: false }) - expect(ctx.tokenMeter.resolve('deepseek-v4-flash').contextWindow).toBe(128_000) + expect(ctx.tokenMeter.contextWindow).toBe(128_000) expect(ctx.get('compact')).toBeInstanceOf(BasicCompactService) await compactFiber.dispose() expect(ctx.get('compact')).toBeUndefined() @@ -788,11 +756,10 @@ describe('automatic listener and loader composition', () => { it('removes its automatic listener with the plugin fiber', async () => { const ctx = new Context() await ctx.plugin(LlmService) - await ctx.plugin(TokenMeterService, { - models: { [MODEL]: { contextWindow: 100, charsPerToken: 1_000 } }, - }) + await ctx.plugin(TokenMeterService, { contextWindow: 1_000 }) const fiber = await ctx.plugin(TestCompactService, { - models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + thresholdRatio: 0.5, + retainTokens: 180, }) await fiber.dispose() @@ -801,17 +768,3 @@ describe('automatic listener and loader composition', () => { expect(session.events.some(event => event.type === 'compact/start')).toBe(false) }) }) - -describe('typed unknown-model boundary', () => { - it('uses TokenMeterError identity rather than message matching', () => { - const ctx = createContext() - let thrown: unknown - try { - ctx.tokenMeter.resolve('missing') - } catch (error: unknown) { - thrown = error - } - expect(thrown).toBeInstanceOf(TokenMeterError) - expect(thrown).toMatchObject({ code: TOKEN_METER_MODEL_UNCONFIGURED }) - }) -}) diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index cc1111c5f1..e02e788074 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -62,9 +62,7 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) - await ctx.plugin(TokenMeterService, { - models: { mock: { contextWindow: 64, charsPerToken: 1_000 } }, - }) + await ctx.plugin(TokenMeterService, { contextWindow: 400 }) ctx.llm.registerAdapter(['mock'], new StepwiseToolAdapter(toolSteps)) ctx.tools.register(defineTool({ name: 'work', @@ -74,11 +72,12 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr return [{ type: 'text', text: 'work result' }] }, })) - // Tiny window so a couple of tool steps cross the threshold and compaction - // fires within the runaway turn. + // Small window so several tool steps cross the threshold and compaction + // fires within the runaway turn after enough history can shrink. const compact = new ReproCompactService(ctx, { auto: true, - models: { mock: { thresholdRatio: 0.5, retainTokens: 20 } }, + thresholdRatio: 0.5, + retainTokens: 50, summarizationModel: '', maxTokens: 8192, compactionRetries: 1, diff --git a/packages/compact/compact-basic/tests/loader-composition.spec.ts b/packages/compact/compact-basic/tests/loader-composition.spec.ts index ff6320c05f..26ff37a8e6 100644 --- a/packages/compact/compact-basic/tests/loader-composition.spec.ts +++ b/packages/compact/compact-basic/tests/loader-composition.spec.ts @@ -57,10 +57,7 @@ describe('real Loader composition', () => { .filter(entry => entry.fiber === undefined && !entry.disabled) .map(entry => entry.options.name) expect(unloaded).toEqual([]) - expect(context.tokenMeter.resolve('deepseek-v4-flash')).toMatchObject({ - contextWindow: 128_000, - charsPerToken: 4, - }) + expect(context.tokenMeter.contextWindow).toBe(128_000) expect(context.get('compact')).toBeInstanceOf(BasicCompactService) }) }) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 25dafac885..6edd2b809e 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -224,9 +224,11 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ }, { key: 'tokenMeter', - summary: 'Concrete registry and replay owner for all configured model meters.', + summary: 'Replay owner for one service-wide estimator and isolated per-session folds.', methods: [ - 'resolve(model: string): ModelTokenMeter', + 'measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement', + 'measureSurface(session: Session): TokenSurfaceMeasurement', + 'estimateMessage(message: Message): number', ], }, { @@ -760,10 +762,6 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'MessageSourceMap', declaration: 'export interface MessageSourceMap {\n user: {\n kind: \'user\';\n };\n plugin: {\n kind: \'plugin\';\n plugin: string;\n };\n}', }, - { - name: 'ModelTokenMeter', - declaration: 'export interface ModelTokenMeter {\n readonly model: string;\n readonly contextWindow: number;\n readonly charsPerToken: number;\n measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement;\n measureSurface(session: Session): TokenSurfaceMeasurement;\n estimateMessage(message: Message): number;\n}', - }, { name: 'PresetOption', declaration: 'export interface PresetOption {\n value: string;\n name: string;\n description?: string;\n}', @@ -994,7 +992,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'TokenMeasurement', - declaration: 'export interface TokenMeasurement {\n readonly model: string;\n readonly logRevision: number;\n readonly baseline: TokenMeasurementBaseline;\n readonly surfaceDeltaTokens: number;\n readonly totalTokens: number;\n}', + declaration: 'export interface TokenMeasurement {\n readonly logRevision: number;\n readonly baseline: TokenMeasurementBaseline;\n readonly surfaceDeltaTokens: number;\n readonly totalTokens: number;\n}', }, { name: 'TokenMeasurementBaseline', @@ -1002,7 +1000,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'TokenSurfaceMeasurement', - declaration: 'export interface TokenSurfaceMeasurement {\n readonly model: string;\n readonly logRevision: number;\n readonly totalTokens: number;\n readonly nodes: readonly TokenSurfaceNode[];\n}', + declaration: 'export interface TokenSurfaceMeasurement {\n readonly logRevision: number;\n readonly totalTokens: number;\n readonly nodes: readonly TokenSurfaceNode[];\n}', }, { name: 'TokenSurfaceNode', diff --git a/packages/llm/README.md b/packages/llm/README.md index f4d9dd82cb..61368d81f0 100644 --- a/packages/llm/README.md +++ b/packages/llm/README.md @@ -5,7 +5,7 @@ The LLM seam and its provider adapters. The interface package (`llm`) owns the a | Package | Role | ctx key | |---|---|---| | `llm/` | Abstract LLM service + content-block vocabulary + chunk assembler | `ctx.llm` | -| `token-meter/` | Replay-aware, per-model request and surface token measurement | `ctx.tokenMeter` | +| `token-meter/` | Replay-aware request and surface token measurement | `ctx.tokenMeter` | | `llm-deepseek/` | DeepSeek API adapter (hand-rolled fetch/SSE) | (registers on `ctx.llm`) | | `llm-pi-ai/` | DeepSeek adapter via `@earendil-works/pi-ai` (design twin) | (registers on `ctx.llm`) | diff --git a/packages/llm/token-meter/README.md b/packages/llm/token-meter/README.md index e50ee84b3b..85f14aed35 100644 --- a/packages/llm/token-meter/README.md +++ b/packages/llm/token-meter/README.md @@ -1,29 +1,26 @@ # @deepseek-ai/dsh-token-meter -Replay-aware token measurement through `ctx.tokenMeter`. The service binds one stable meter to each configured model and advances isolated per-model/per-session folds from the durable session log. Compaction consumes it today; other pressure-sensitive plugins can reuse the same accounting without depending on `CompactService`. +Replay-aware token measurement through the singleton `ctx.tokenMeter` service. It advances one isolated fold per session from the durable log, so compaction and other pressure-sensitive plugins can share accounting without depending on `CompactService`. -## Profiles and configuration - -The built-in `deepseek-v4-flash` and `deepseek-v4-pro` profiles each use a 128,000-token context window and four characters per estimated token. `models` merges overrides field-by-field, so changing only density keeps the built-in window. A custom model requires `contextWindow`; its `charsPerToken` defaults to `4`. +## Configuration | Key | Default | Contract | |---|---:|---| -| `models..contextWindow` | `128000` | Positive integer provider capacity. | -| `models..charsPerToken` | `4` | Positive finite heuristic density. | +| `contextWindow` | `128000` | Positive integer service-wide context capacity. | -Resolving an unknown model throws `TokenMeterError` with code `TOKEN_METER_MODEL_UNCONFIGURED` and preserves the exact model name. Direct-construction profile validation uses `TOKEN_METER_INVALID_CONFIG`; Loader mounts first apply the package's Schemastery shape validation. There is no universal fallback window. +The estimator intentionally uses one fixed heuristic: four characters per token plus structural overhead for roles, blocks, and request-envelope fields. `contextWindow` is the only deployment setting. Direct construction validates it; Loader mounts first apply the package's Schemastery shape validation. ## Measurement contract -`ctx.tokenMeter.resolve(model)` returns a `ModelTokenMeter` with three operations: +`ctx.tokenMeter` directly exposes three operations: - `measure(session, requestHeader?)` returns scalar request pressure at one consumed-log revision. - `measureSurface(session)` returns current surface nodes and their per-node prices at the same kind of revision. -- `estimateMessage(message)` prices one detached message under that profile. +- `estimateMessage(message)` prices one message with the fixed heuristic. Measurements are detached and deeply immutable. A caller that needs a consistent scalar/surface decision compares their `logRevision` values instead of copying the full history on every read. -The fold tracks request headers and deltas, step boundaries, surface appends and replacements, successful assistant messages, provider usage, and assistant-chunk provenance. Provider usage is reused only when the handle's model and the canonical request envelope match the successful-call anchor. Otherwise the complete current envelope and surface are repriced under the requested model. Surface changes remain signed relative to a matching anchor, including negative deltas after shrinking replacements. +The fold tracks request headers and deltas, step boundaries, surface appends and replacements, successful assistant messages, provider usage, and assistant-chunk provenance. Provider usage is reused only when the latest successful call's canonical request envelope matches the measured envelope; a later success replaces the earlier anchor. Otherwise the complete current envelope and surface are estimated. Surface changes remain signed relative to a matching anchor, including negative deltas after shrinking replacements. Usage accounting sums disjoint input, cache-read, cache-write, and output buckets; reasoning is not added again. Every successful call records an assistant anchor, including content-less calls. An explicit empty provenance list means a known empty provider stream, while absent legacy provenance conservatively treats the durable assistant output as provider output. @@ -34,16 +31,12 @@ Usage accounting sums disjoint input, cache-read, cache-write, and output bucket - name: '@deepseek-ai/dsh-compact-basic' ``` -Both plugins have usable defaults for the bundled DeepSeek profiles. Custom deployments can override only the fields that differ: +Both plugins have usable defaults. A deployment with a different capacity configures the meter once: ```yaml - name: '@deepseek-ai/dsh-token-meter' config: - models: - deepseek-v4-flash: - charsPerToken: 2 - local-model: - contextWindow: 32768 + contextWindow: 32768 ``` ## Model Experience @@ -52,6 +45,6 @@ Indirectly, through consumers such as `dsh-compact-basic`; the service itself ad ## Known Limitations and Deferred Work -- **Heuristic density still needs maintenance** — message content without provider usage is priced by configured character density plus structural overhead, not an exact provider tokenizer. CJK-heavy or provider-specific formats may need profile overrides. -- **Provider usage is only reusable for an identical canonical envelope** — prompt, prefix, tools, or call-config changes deliberately fall back to full heuristic repricing. +- **The fixed heuristic is approximate** — content without reusable provider usage is priced by character count plus structural overhead, not an exact provider tokenizer or request serializer. +- **Provider usage is only reusable for an identical canonical envelope** — prompt, prefix, tools, model, or call-config changes deliberately fall back to full heuristic estimation. - **Legacy provenance is conservative** — assistant messages without `sourceEventSeqs` cannot distinguish provider output from listener rewrites, so the fold avoids claiming a known empty or exact chunk stream. diff --git a/packages/llm/token-meter/package.json b/packages/llm/token-meter/package.json index 30031b0b2e..13fa4e3cdc 100644 --- a/packages/llm/token-meter/package.json +++ b/packages/llm/token-meter/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-token-meter", - "description": "Replay-aware per-model token measurement service (ctx.tokenMeter) for the DeepSeek Harness", + "description": "Replay-aware token measurement service (ctx.tokenMeter) for the DeepSeek Harness", "version": "0.0.1", "private": true, "type": "module", diff --git a/packages/llm/token-meter/src/index.ts b/packages/llm/token-meter/src/index.ts index 19d700ac96..0b5b3b062d 100644 --- a/packages/llm/token-meter/src/index.ts +++ b/packages/llm/token-meter/src/index.ts @@ -1,59 +1,85 @@ /** - * Replay token-meter service with model-specific context capacity and pricing. + * Single replay-aware token-meter service for request and surface pressure. * * @module @deepseek-ai/dsh-token-meter */ import { Context, Service } from 'cordis' import z from 'schemastery' -import { HarnessError, deepFreeze } from '@deepseek-ai/dsh-llm' -import type { Session } from '@deepseek-ai/dsh-session' -import { ReplayModelTokenMeter } from './replay.ts' -import type { ModelTokenProfile } from './replay.ts' +import { BlockAssembler, deepFreeze } from '@deepseek-ai/dsh-llm' +import type { ContentBlock, Message, TokenUsage } from '@deepseek-ai/dsh-llm' +import type { EpochHeader, Session, SessionEvent, SurfaceEvent } from '@deepseek-ai/dsh-session' +import { applyHeaderDelta, canonicalHeader, headerEquals, isSurfaceEvent } from '@deepseek-ai/dsh-session' import type { - ModelTokenMeter, - ModelTokenMeterConfig, + TokenMeasurement, + TokenMeasurementBaseline, TokenMeterConfig, + TokenSurfaceMeasurement, + TokenSurfaceNode, } from './types.ts' export type * from './types.ts' -/** Exact error code for resolving a model without a configured profile. */ -export const TOKEN_METER_MODEL_UNCONFIGURED = 'TOKEN_METER_MODEL_UNCONFIGURED' +/** Default service-wide provider context capacity. */ +const DEFAULT_CONTEXT_WINDOW = 128_000 -/** Exact error code for invalid token-meter configuration. */ -export const TOKEN_METER_INVALID_CONFIG = 'TOKEN_METER_INVALID_CONFIG' +/** Fixed text-density estimate used until exact tokenization is needed. */ +const CHARS_PER_TOKEN = 4 -/** Closed machine-routable token-meter failure taxonomy. */ -export type TokenMeterErrorCode = - | typeof TOKEN_METER_MODEL_UNCONFIGURED - | typeof TOKEN_METER_INVALID_CONFIG +/** Per-block structural overhead for JSON framing and type tags. */ +const BLOCK_OVERHEAD = 4 -/** Built-in DeepSeek model profiles available with zero configuration. */ -const BUILTIN_TOKEN_PROFILES: Readonly>> = deepFreeze({ - 'deepseek-v4-flash': { - model: 'deepseek-v4-flash', - contextWindow: 128_000, - charsPerToken: 4, - }, - 'deepseek-v4-pro': { - model: 'deepseek-v4-pro', - contextWindow: 128_000, - charsPerToken: 4, - }, -}) +/** Role-field framing overhead added to every priced message. */ +const ROLE_OVERHEAD = 4 -/** Typed token-meter failure with the affected model preserved for callers. */ -export class TokenMeterError extends HarnessError { - declare readonly code: TokenMeterErrorCode - /** Exact model name involved in this error, when applicable. */ - readonly model: string | undefined +interface MeasurementAnchor { + readonly header: EpochHeader | undefined + readonly surfaceTokens: number + readonly baseline: Exclude +} - constructor(message: string, code: TokenMeterErrorCode, model?: string, options?: ErrorOptions) { - super(message, code, options) - this.name = 'TokenMeterError' - this.model = model +interface ReplayState { + consumedEvents: number + header: EpochHeader | undefined + surface: TokenSurfaceNode[] + surfaceTokens: number + stepStart: { turn: number; step: number; surfaceTokens: number } | undefined + anchor: MeasurementAnchor | undefined +} + +interface PreparedSurfaceMutation { + readonly tokens: number + commit(state: ReplayState): void +} + +/** Sum disjoint provider usage buckets without double-counting reasoning output. */ +function usageTokens(usage: TokenUsage): number { + return usage.inputTokens + + (usage.cacheReadTokens ?? 0) + + (usage.cacheWriteTokens ?? 0) + + usage.outputTokens +} + +/** Compare optional envelopes so a headerless estimate can track later surface deltas. */ +function optionalHeaderEquals( + left: EpochHeader | undefined, + right: EpochHeader | undefined, +): boolean { + if (left === undefined || right === undefined) return left === right + return headerEquals(left, right) +} + +/** Resolve and validate the one service-wide context capacity. */ +function resolveContextWindow(config: TokenMeterConfig): number { + const contextWindow = config.contextWindow === undefined + ? DEFAULT_CONTEXT_WINDOW + : config.contextWindow + if (!Number.isInteger(contextWindow) || contextWindow <= 0) { + throw new Error( + `TokenMeterConfig: contextWindow (${contextWindow}) must be a positive integer`, + ) } + return contextWindow } declare module 'cordis' { @@ -62,131 +88,327 @@ declare module 'cordis' { } } -/** Validate and detach all configured model profiles. */ -function resolveProfiles(config: TokenMeterConfig): readonly ModelTokenProfile[] { - const profiles = new Map() - for (const profile of Object.values(BUILTIN_TOKEN_PROFILES)) { - profiles.set(profile.model, { ...profile }) - } - - const configuredValue: unknown = config.models - const configuredModels = configuredValue === undefined ? {} : configuredValue - if (typeof configuredModels !== 'object' - || configuredModels === null - || Array.isArray(configuredModels)) { - throw new TokenMeterError( - 'TokenMeterConfig: models must be an object', - TOKEN_METER_INVALID_CONFIG, - ) - } - - for (const [model, override] of Object.entries(configuredModels as Record)) { - if (model.length === 0) { - throw new TokenMeterError( - 'TokenMeterConfig: model names must not be empty', - TOKEN_METER_INVALID_CONFIG, - model, - ) - } - assertProfileObject(model, override) - const builtIn = profiles.get(model) - const contextWindow = override.contextWindow ?? builtIn?.contextWindow - const charsPerToken = override.charsPerToken ?? builtIn?.charsPerToken ?? 4 - if (contextWindow === undefined) { - throw new TokenMeterError( - `TokenMeterConfig: custom model "${model}" requires contextWindow`, - TOKEN_METER_INVALID_CONFIG, - model, - ) - } - assertPositiveInteger(model, 'contextWindow', contextWindow) - assertPositiveFinite(model, 'charsPerToken', charsPerToken) - profiles.set(model, { model, contextWindow, charsPerToken }) - } - - for (const profile of profiles.values()) { - assertPositiveInteger(profile.model, 'contextWindow', profile.contextWindow) - assertPositiveFinite(profile.model, 'charsPerToken', profile.charsPerToken) - } - return deepFreeze([...profiles.values()].map(profile => ({ ...profile }))) -} - -function assertProfileObject(model: string, value: unknown): asserts value is ModelTokenMeterConfig { - if (typeof value !== 'object' || value === null || Array.isArray(value)) { - throw new TokenMeterError( - `TokenMeterConfig: profile "${model}" must be an object`, - TOKEN_METER_INVALID_CONFIG, - model, - ) - } -} - -function assertPositiveInteger(model: string, name: string, value: number): void { - if (!Number.isInteger(value) || value <= 0) { - throw new TokenMeterError( - `TokenMeterConfig: ${model}.${name} (${value}) must be a positive integer`, - TOKEN_METER_INVALID_CONFIG, - model, - ) - } -} - -function assertPositiveFinite(model: string, name: string, value: number): void { - if (typeof value !== 'number' || !Number.isFinite(value) || value <= 0) { - throw new TokenMeterError( - `TokenMeterConfig: ${model}.${name} (${value}) must be a positive finite number`, - TOKEN_METER_INVALID_CONFIG, - model, - ) - } -} - -/** Concrete registry and replay owner for all configured model meters. */ +/** Replay owner for one service-wide estimator and isolated per-session folds. */ export class TokenMeterService extends Service { static Config: z = z.object({ - models: z.dict(z.object({ - contextWindow: z.number(), - charsPerToken: z.number(), - })), + contextWindow: z.number().step(1).min(1).default(DEFAULT_CONTEXT_WINDOW), }) - private readonly meters = new Map() + /** Provider context-window capacity used by pressure consumers. */ + readonly contextWindow: number + + private readonly states = new WeakMap() constructor(ctx: Context, config: TokenMeterConfig = {}) { super(ctx, 'tokenMeter') - for (const profile of resolveProfiles(config)) { - this.meters.set(profile.model, new ReplayModelTokenMeter(profile)) - } + this.contextWindow = resolveContextWindow(config) // Readers catch up independently, while eager observation bounds ordinary - // read latency. A reader in an earlier listener consumes the new event; - // this listener then sees the same revision and performs no duplicate fold. + // read latency without creating state for sessions no consumer has read. ctx.on('session/event', (session) => { - this._observe(session) + if (this.states.has(session)) this._sync(session) }) } /** - * Resolve one stable model-bound replay handle. - * @param model - exact routed model name. - * @throws {@link TokenMeterError} with `TOKEN_METER_MODEL_UNCONFIGURED` when no profile exists. - * @returns the configured handle for this model. + * Measure current request pressure through the session's durable tail. + * + * Provider usage is reused only when the latest successful call's canonical + * request envelope matches `requestHeader`; otherwise the complete envelope + * and surface are heuristically repriced. + * + * @param session - session to replay through its current durable tail. + * @param requestHeader - optional effective request envelope replacing the latest logged header. + * @returns a detached deeply immutable pressure measurement. */ - resolve(model: string): ModelTokenMeter { - const meter = this.meters.get(model) - if (meter === undefined) { - throw new TokenMeterError( - `token meter has no profile for model "${model}"`, - TOKEN_METER_MODEL_UNCONFIGURED, - model, - ) + measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement { + const state = this._sync(session) + const header = requestHeader === undefined + ? state.header + : canonicalHeader(requestHeader) + const anchor = state.anchor + + let baseline: TokenMeasurementBaseline + let surfaceDeltaTokens: number + if (anchor !== undefined && optionalHeaderEquals(anchor.header, header)) { + baseline = anchor.baseline + surfaceDeltaTokens = state.surfaceTokens - anchor.surfaceTokens + } else if (header === undefined && state.surfaceTokens === 0) { + baseline = { kind: 'none', tokens: 0 } + surfaceDeltaTokens = 0 + } else { + baseline = { + kind: 'estimated', + tokens: this._estimateHeader(header) + state.surfaceTokens, + } + surfaceDeltaTokens = 0 } - return meter + + return deepFreeze(structuredClone({ + logRevision: state.consumedEvents, + baseline, + surfaceDeltaTokens, + totalTokens: Math.max(0, baseline.tokens + surfaceDeltaTokens), + })) } - /** Advance every configured model's isolated replay fold. */ - private _observe(session: Session): void { - for (const meter of this.meters.values()) meter.observeIfActive(session) + /** + * Price the current surface for retention and replacement decisions. + * @param session - session to replay through its current durable tail. + * @returns a detached deeply immutable positional surface measurement. + */ + measureSurface(session: Session): TokenSurfaceMeasurement { + const state = this._sync(session) + return deepFreeze(structuredClone({ + logRevision: state.consumedEvents, + totalTokens: state.surfaceTokens, + nodes: state.surface, + })) + } + + /** + * Heuristically price one model-visible message. + * @param message - message to price without mutation. + * @returns content and role-framing tokens under the fixed service heuristic. + */ + estimateMessage(message: Message): number { + return this._estimateContent(message.content) + ROLE_OVERHEAD + } + + /** Catch one session's fold up to the current durable tail. */ + private _sync(session: Session): ReplayState { + let state = this.states.get(session) + if (state === undefined) { + state = { + consumedEvents: 0, + header: undefined, + surface: [], + surfaceTokens: 0, + stepStart: undefined, + anchor: undefined, + } + this.states.set(session, state) + } + + while (state.consumedEvents < session.events.length) { + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- contiguous session seqs index the durable log + const event = session.events[state.consumedEvents]! + this._foldEvent(session, state, event) + state.consumedEvents += 1 + } + return state + } + + /** + * Validate and prepare every fallible part before mutating replay state. + * A malformed event remains unread on every retry instead of partially + * applying the same mutation more than once. + */ + private _foldEvent(session: Session, state: ReplayState, event: SessionEvent): void { + let nextHeader = state.header + let nextStepStart = state.stepStart + let nextAnchor = state.anchor + + switch (event.type) { + case 'request/header': + nextHeader = canonicalHeader(event.data.header) + break + case 'request/header-delta': + if (state.header === undefined) { + throw new Error(`token meter: request/header-delta at seq ${event.seq} has no preceding header`) + } + nextHeader = applyHeaderDelta(state.header, event.data) + break + case 'step/start': + if (state.stepStart !== undefined) { + throw new Error( + `token meter: step/start at seq ${event.seq} arrived before turn ${state.stepStart.turn}/step ${state.stepStart.step} ended`, + ) + } + nextStepStart = { ...event.data, surfaceTokens: state.surfaceTokens } + break + case 'step/end': + if (state.stepStart === undefined + || state.stepStart.turn !== event.data.turn + || state.stepStart.step !== event.data.step) { + throw new Error(`token meter: step/end at seq ${event.seq} has no matching step/start boundary`) + } + nextStepStart = undefined + break + default: + break + } + + const surface = isSurfaceEvent(event) + ? this._prepareSurfaceMutation(session, state, event) + : undefined + + if (event.type === 'assistant/message') { + const stepStart = state.stepStart + if (stepStart === undefined + || stepStart.turn !== event.data.turn + || stepStart.step !== event.data.step) { + throw new Error(`token meter: assistant/message at seq ${event.seq} has no matching step/start boundary`) + } + + // assistant/message is surface-mandatory at every append/seed boundary. + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + const eventTokens = surface!.tokens + if (event.data.usage !== undefined && nextHeader !== undefined) { + const providerAssistantTokens = this._estimateProviderAssistant( + session, + event, + eventTokens, + ) + nextAnchor = { + header: nextHeader, + surfaceTokens: stepStart.surfaceTokens + providerAssistantTokens, + baseline: { + kind: 'usage', + tokens: usageTokens(event.data.usage), + usage: event.data.usage, + }, + } + } else { + const anchorSurfaceTokens = stepStart.surfaceTokens + eventTokens + nextAnchor = { + header: nextHeader, + surfaceTokens: anchorSurfaceTokens, + baseline: { + kind: 'estimated', + tokens: this._estimateHeader(nextHeader) + anchorSurfaceTokens, + }, + } + } + } + + state.header = nextHeader + state.stepStart = nextStepStart + if (surface !== undefined) surface.commit(state) + state.anchor = nextAnchor + } + + /** Validate one surface operation and return its allocation-light commit. */ + private _prepareSurfaceMutation( + session: Session, + state: ReplayState, + event: SurfaceEvent, + ): PreparedSurfaceMutation { + const tokens = this._estimateSurfaceEvent(session, event) + const op = event.surfaceOp + if (op === 'append') { + return { + tokens, + commit(target) { + target.surface.push({ seq: event.seq, tokens }) + target.surfaceTokens += tokens + }, + } + } + + const startIdx = state.surface.findIndex(node => node.seq === op.start) + const endIdx = state.surface.findIndex(node => node.seq === op.end) + if (startIdx === -1 || endIdx === -1 || startIdx > endIdx) { + throw new Error( + `token meter: replace at seq ${event.seq} has invalid current range ${op.start}-${op.end}`, + ) + } + const removedTokens = state.surface + .slice(startIdx, endIdx + 1) + .reduce((total, node) => total + node.tokens, 0) + return { + tokens, + commit(target) { + target.surface.splice(startIdx, endIdx - startIdx + 1, { seq: event.seq, tokens }) + target.surfaceTokens += tokens - removedTokens + }, + } + } + + /** Price one current surface event exactly as it projects to a request. */ + private _estimateSurfaceEvent(session: Session, event: SurfaceEvent): number { + const message = session.deriveEventMessage(event) + return message === null ? 0 : this.estimateMessage(message) + } + + /** + * Reassemble provider output from exact chunk provenance for a usage anchor. + * Missing legacy provenance conservatively treats the durable output as the + * provider output; explicit empty provenance prices a known empty stream. + */ + private _estimateProviderAssistant( + session: Session, + event: SessionEvent<'assistant/message'>, + durableEventTokens: number, + ): number { + const sourceSeqs = event.sourceEventSeqs + if (sourceSeqs === undefined) return durableEventTokens + + const assembler = new BlockAssembler() + const seen = new Set() + for (const seq of sourceSeqs) { + if (seq >= event.seq) { + throw new Error(`token meter: assistant/message at seq ${event.seq} source seq ${seq} is not earlier`) + } + if (seen.has(seq)) { + throw new Error(`token meter: assistant/message at seq ${event.seq} repeats source seq ${seq}`) + } + seen.add(seq) + // Session construction validates contiguous seqs, and the explicit + // earlier-than-assistant check above therefore guarantees existence. + const source = session.events[seq] + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + const sourceEvent = source! + if (sourceEvent.type !== 'assistant/chunk') { + throw new Error(`token meter: assistant/message at seq ${event.seq} source seq ${seq} is not assistant/chunk`) + } + if (sourceEvent.data.turn !== event.data.turn || sourceEvent.data.step !== event.data.step) { + throw new Error(`token meter: assistant/message at seq ${event.seq} source seq ${seq} belongs to another step`) + } + assembler.push(sourceEvent.data.chunk) + } + const providerMessage = assembler.message() + return providerMessage.content.length === 0 ? 0 : this.estimateMessage(providerMessage) + } + + /** Price content blocks recursively under the fixed density heuristic. */ + private _estimateContent(blocks: readonly ContentBlock[]): number { + let tokens = 0 + for (const block of blocks) { + switch (block.type) { + case 'text': + case 'reasoning': + tokens += Math.ceil(block.text.length / CHARS_PER_TOKEN) + BLOCK_OVERHEAD + break + case 'tool-call': + tokens += Math.ceil(block.name.length / CHARS_PER_TOKEN) + + Math.ceil(block.arguments.length / CHARS_PER_TOKEN) + + BLOCK_OVERHEAD + break + case 'tool-result': + tokens += this._estimateContent(block.content) + BLOCK_OVERHEAD + break + default: + // ContentBlockMap is merge-extensible; unknown blocks retain a + // conservative structural JSON price under the fixed heuristic. + tokens += BLOCK_OVERHEAD + Math.ceil(JSON.stringify(block).length / CHARS_PER_TOKEN) + } + } + return tokens + } + + /** Price the canonical non-surface request envelope. */ + private _estimateHeader(header: EpochHeader | undefined): number { + if (header === undefined) return 0 + let tokens = 0 + for (const message of header.messagePrefix ?? []) tokens += this.estimateMessage(message) + if (header.system !== undefined) { + tokens += Math.ceil(header.system.length / CHARS_PER_TOKEN) + ROLE_OVERHEAD + } + if (header.tools !== undefined && header.tools.length > 0) { + tokens += Math.ceil(JSON.stringify(header.tools).length / CHARS_PER_TOKEN) + BLOCK_OVERHEAD + } + return tokens } } diff --git a/packages/llm/token-meter/src/replay.ts b/packages/llm/token-meter/src/replay.ts deleted file mode 100644 index 8b4af52dc5..0000000000 --- a/packages/llm/token-meter/src/replay.ts +++ /dev/null @@ -1,367 +0,0 @@ -/** - * Model-bound transactional replay of request headers, surface mutations, and - * successful-call token anchors. - * - * @module @deepseek-ai/dsh-token-meter/replay - */ - -import { BlockAssembler, deepFreeze } from '@deepseek-ai/dsh-llm' -import type { ContentBlock, Message, TokenUsage } from '@deepseek-ai/dsh-llm' -import type { EpochHeader, Session, SessionEvent, SurfaceEvent } from '@deepseek-ai/dsh-session' -import { applyHeaderDelta, canonicalHeader, headerEquals, isSurfaceEvent } from '@deepseek-ai/dsh-session' -import type { - ModelTokenMeter, - TokenMeasurement, - TokenMeasurementBaseline, - TokenSurfaceMeasurement, - TokenSurfaceNode, -} from './types.ts' - -/** Internal validated pricing profile. */ -export interface ModelTokenProfile { - readonly model: string - readonly contextWindow: number - readonly charsPerToken: number -} - -/** Per-block structural overhead for JSON framing and type tags. */ -const BLOCK_OVERHEAD = 4 - -/** Role-field framing overhead added to every priced message. */ -const ROLE_OVERHEAD = 4 - -interface UsageAnchor { - readonly header: EpochHeader - readonly surfaceTokens: number - readonly baseline: Exclude -} - -interface ReplayState { - consumedEvents: number - header: EpochHeader | undefined - surface: TokenSurfaceNode[] - surfaceTokens: number - stepStart: { turn: number; step: number; surfaceTokens: number } | undefined - anchor: UsageAnchor | undefined -} - -interface PreparedSurfaceMutation { - readonly tokens: number - commit(state: ReplayState): void -} - -/** Sum disjoint provider usage buckets without double-counting reasoning output. */ -function usageTokens(usage: TokenUsage): number { - return usage.inputTokens - + (usage.cacheReadTokens ?? 0) - + (usage.cacheWriteTokens ?? 0) - + usage.outputTokens -} - -/** One configured model's replay fold, weakly isolated by session identity. */ -export class ReplayModelTokenMeter implements ModelTokenMeter { - readonly model: string - readonly contextWindow: number - readonly charsPerToken: number - - private readonly states = new WeakMap() - - constructor(profile: ModelTokenProfile) { - this.model = profile.model - this.contextWindow = profile.contextWindow - this.charsPerToken = profile.charsPerToken - } - - /** - * Advance an already-read model/session fold without creating unused state. - * @param session - session whose durable tail advanced. - */ - observeIfActive(session: Session): void { - if (this.states.has(session)) this._sync(session) - } - - /** @inheritdoc */ - estimateMessage(message: Message): number { - return this._estimateContent(message.content) + ROLE_OVERHEAD - } - - /** @inheritdoc */ - measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement { - const state = this._sync(session) - const header = requestHeader === undefined - ? state.header - : canonicalHeader(requestHeader) - const anchor = state.anchor - - let baseline: TokenMeasurementBaseline - let surfaceDeltaTokens: number - if (anchor !== undefined && header !== undefined && headerEquals(anchor.header, header)) { - baseline = anchor.baseline - surfaceDeltaTokens = state.surfaceTokens - anchor.surfaceTokens - } else if (header === undefined && state.surfaceTokens === 0) { - baseline = { kind: 'none', tokens: 0 } - surfaceDeltaTokens = 0 - } else { - baseline = { - kind: 'estimated', - tokens: this._estimateHeader(header) + state.surfaceTokens, - } - surfaceDeltaTokens = 0 - } - - return deepFreeze(structuredClone({ - model: this.model, - logRevision: state.consumedEvents, - baseline, - surfaceDeltaTokens, - totalTokens: Math.max(0, baseline.tokens + surfaceDeltaTokens), - })) - } - - /** @inheritdoc */ - measureSurface(session: Session): TokenSurfaceMeasurement { - const state = this._sync(session) - return deepFreeze(structuredClone({ - model: this.model, - logRevision: state.consumedEvents, - totalTokens: state.surfaceTokens, - nodes: state.surface, - })) - } - - /** Catch one session's fold up to the current durable tail. */ - private _sync(session: Session): ReplayState { - let state = this.states.get(session) - if (state === undefined) { - state = { - consumedEvents: 0, - header: undefined, - surface: [], - surfaceTokens: 0, - stepStart: undefined, - anchor: undefined, - } - this.states.set(session, state) - } - - while (state.consumedEvents < session.events.length) { - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- contiguous session seqs index the durable log - const event = session.events[state.consumedEvents]! - this._foldEvent(session, state, event) - state.consumedEvents += 1 - } - return state - } - - /** - * Validate and prepare every fallible part before mutating replay state. - * A malformed event therefore remains the next unread event on every retry - * instead of applying a partial surface mutation twice. - */ - private _foldEvent(session: Session, state: ReplayState, event: SessionEvent): void { - let nextHeader = state.header - let nextStepStart = state.stepStart - let nextAnchor = state.anchor - - switch (event.type) { - case 'request/header': - nextHeader = canonicalHeader(event.data.header) - break - case 'request/header-delta': - if (state.header === undefined) { - throw new Error(`token meter: request/header-delta at seq ${event.seq} has no preceding header`) - } - nextHeader = applyHeaderDelta(state.header, event.data) - break - case 'step/start': - if (state.stepStart !== undefined) { - throw new Error( - `token meter: step/start at seq ${event.seq} arrived before turn ${state.stepStart.turn}/step ${state.stepStart.step} ended`, - ) - } - nextStepStart = { ...event.data, surfaceTokens: state.surfaceTokens } - break - case 'step/end': - if (state.stepStart === undefined - || state.stepStart.turn !== event.data.turn - || state.stepStart.step !== event.data.step) { - throw new Error(`token meter: step/end at seq ${event.seq} has no matching step/start boundary`) - } - nextStepStart = undefined - break - default: - break - } - - const surface = isSurfaceEvent(event) - ? this._prepareSurfaceMutation(session, state, event) - : undefined - - if (event.type === 'assistant/message' && nextHeader?.config.model === this.model) { - const stepStart = state.stepStart - if (stepStart === undefined - || stepStart.turn !== event.data.turn - || stepStart.step !== event.data.step) { - throw new Error(`token meter: assistant/message at seq ${event.seq} has no matching step/start boundary`) - } - - // assistant/message is surface-mandatory at every append/seed boundary. - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const eventTokens = surface!.tokens - if (event.data.usage !== undefined) { - const providerAssistantTokens = this._estimateProviderAssistant( - session, - event, - eventTokens, - ) - nextAnchor = { - header: nextHeader, - surfaceTokens: stepStart.surfaceTokens + providerAssistantTokens, - baseline: { - kind: 'usage', - tokens: usageTokens(event.data.usage), - usage: event.data.usage, - }, - } - } else { - const anchorSurfaceTokens = stepStart.surfaceTokens + eventTokens - nextAnchor = { - header: nextHeader, - surfaceTokens: anchorSurfaceTokens, - baseline: { - kind: 'estimated', - tokens: this._estimateHeader(nextHeader) + anchorSurfaceTokens, - }, - } - } - } - - state.header = nextHeader - state.stepStart = nextStepStart - if (surface !== undefined) surface.commit(state) - state.anchor = nextAnchor - } - - /** Validate one surface operation and return its allocation-light commit. */ - private _prepareSurfaceMutation( - session: Session, - state: ReplayState, - event: SurfaceEvent, - ): PreparedSurfaceMutation { - const tokens = this._estimateSurfaceEvent(session, event) - const op = event.surfaceOp - if (op === 'append') { - return { - tokens, - commit(target) { - target.surface.push({ seq: event.seq, tokens }) - target.surfaceTokens += tokens - }, - } - } - - const startIdx = state.surface.findIndex(node => node.seq === op.start) - const endIdx = state.surface.findIndex(node => node.seq === op.end) - if (startIdx === -1 || endIdx === -1 || startIdx > endIdx) { - throw new Error( - `token meter: replace at seq ${event.seq} has invalid current range ${op.start}-${op.end}`, - ) - } - const removedTokens = state.surface - .slice(startIdx, endIdx + 1) - .reduce((total, node) => total + node.tokens, 0) - return { - tokens, - commit(target) { - target.surface.splice(startIdx, endIdx - startIdx + 1, { seq: event.seq, tokens }) - target.surfaceTokens += tokens - removedTokens - }, - } - } - - /** Price one current surface event exactly as it projects to a request. */ - private _estimateSurfaceEvent(session: Session, event: SurfaceEvent): number { - const message = session.deriveEventMessage(event) - return message === null ? 0 : this.estimateMessage(message) - } - - /** - * Reassemble provider output from exact chunk provenance for a usage anchor. - * Missing legacy provenance conservatively treats the durable output as the - * provider output; explicit empty provenance prices a known empty stream. - */ - private _estimateProviderAssistant( - session: Session, - event: SessionEvent<'assistant/message'>, - durableEventTokens: number, - ): number { - const sourceSeqs = event.sourceEventSeqs - if (sourceSeqs === undefined) return durableEventTokens - - const assembler = new BlockAssembler() - const seen = new Set() - for (const seq of sourceSeqs) { - if (seq >= event.seq) { - throw new Error(`token meter: assistant/message at seq ${event.seq} source seq ${seq} is not earlier`) - } - if (seen.has(seq)) { - throw new Error(`token meter: assistant/message at seq ${event.seq} repeats source seq ${seq}`) - } - seen.add(seq) - // Session construction validates contiguous seqs, and the explicit - // earlier-than-assistant check above therefore guarantees existence. - const source = session.events[seq] - // eslint-disable-next-line @typescript-eslint/no-non-null-assertion - const sourceEvent = source! - if (sourceEvent.type !== 'assistant/chunk') { - throw new Error(`token meter: assistant/message at seq ${event.seq} source seq ${seq} is not assistant/chunk`) - } - if (sourceEvent.data.turn !== event.data.turn || sourceEvent.data.step !== event.data.step) { - throw new Error(`token meter: assistant/message at seq ${event.seq} source seq ${seq} belongs to another step`) - } - assembler.push(sourceEvent.data.chunk) - } - const providerMessage = assembler.message() - return providerMessage.content.length === 0 ? 0 : this.estimateMessage(providerMessage) - } - - /** Price content blocks recursively under this model's density profile. */ - private _estimateContent(blocks: readonly ContentBlock[]): number { - let tokens = 0 - for (const block of blocks) { - switch (block.type) { - case 'text': - case 'reasoning': - tokens += Math.ceil(block.text.length / this.charsPerToken) + BLOCK_OVERHEAD - break - case 'tool-call': - tokens += Math.ceil(block.name.length / this.charsPerToken) - + Math.ceil(block.arguments.length / this.charsPerToken) - + BLOCK_OVERHEAD - break - case 'tool-result': - tokens += this._estimateContent(block.content) + BLOCK_OVERHEAD - break - default: - // ContentBlockMap is merge-extensible; unknown blocks retain a - // conservative structural JSON price under the selected profile. - tokens += BLOCK_OVERHEAD + Math.ceil(JSON.stringify(block).length / this.charsPerToken) - } - } - return tokens - } - - /** Price the canonical non-surface request envelope. */ - private _estimateHeader(header: EpochHeader | undefined): number { - if (header === undefined) return 0 - let tokens = 0 - for (const message of header.messagePrefix ?? []) tokens += this.estimateMessage(message) - if (header.system !== undefined) { - tokens += Math.ceil(header.system.length / this.charsPerToken) + ROLE_OVERHEAD - } - if (header.tools !== undefined && header.tools.length > 0) { - tokens += Math.ceil(JSON.stringify(header.tools).length / this.charsPerToken) + BLOCK_OVERHEAD - } - return tokens - } -} diff --git a/packages/llm/token-meter/src/types.ts b/packages/llm/token-meter/src/types.ts index e9b7e812c1..1f2c2f68f2 100644 --- a/packages/llm/token-meter/src/types.ts +++ b/packages/llm/token-meter/src/types.ts @@ -4,21 +4,12 @@ * @module @deepseek-ai/dsh-token-meter/types */ -import type { Message, TokenUsage } from '@deepseek-ai/dsh-llm' -import type { EpochHeader, Session } from '@deepseek-ai/dsh-session' - -/** Optional pricing fields for one configured model. */ -export interface ModelTokenMeterConfig { - /** Provider context-window capacity in tokens. Required for a custom model. */ - contextWindow?: number - /** Heuristic text density in characters per token. Defaults to `4`. */ - charsPerToken?: number -} +import type { TokenUsage } from '@deepseek-ai/dsh-llm' /** Token-meter plugin configuration. */ export interface TokenMeterConfig { - /** Built-in field overrides and custom model profiles, keyed by routed model name. */ - models?: Record + /** Service-wide context-window capacity in tokens. Defaults to `128000`. */ + contextWindow?: number } /** The baseline from which a signed surface delta produces current pressure. */ @@ -29,8 +20,6 @@ export type TokenMeasurementBaseline = /** Detached immutable scalar pressure at one consumed session-log revision. */ export interface TokenMeasurement { - /** Model profile used for every heuristic component. */ - readonly model: string /** Number of durable events consumed; equal to the next unread event seq. */ readonly logRevision: number /** Provider or heuristic anchor used for this measurement. */ @@ -51,8 +40,6 @@ export interface TokenSurfaceNode { /** Detached immutable priced surface at one consumed session-log revision. */ export interface TokenSurfaceMeasurement { - /** Model profile used to price every node. */ - readonly model: string /** Number of durable events consumed; equal to the next unread event seq. */ readonly logRevision: number /** Total heuristic tokens across the current surface. */ @@ -60,42 +47,3 @@ export interface TokenSurfaceMeasurement { /** Current surface nodes in positional head-to-tail order. */ readonly nodes: readonly TokenSurfaceNode[] } - -/** A model-bound replay meter returned by {@link TokenMeterService.resolve}. */ -export interface ModelTokenMeter { - /** Routed model name bound to this handle. */ - readonly model: string - /** Provider context-window capacity in tokens. */ - readonly contextWindow: number - /** Heuristic text density in characters per token. */ - readonly charsPerToken: number - - /** - * Measure current request pressure through the session's durable tail. - * - * Provider usage is reused only when its routed model and canonical request - * envelope match `requestHeader`; otherwise the complete envelope and - * surface are heuristically repriced for this handle's model. - * - * @param session - session to replay through its current durable tail. - * @param requestHeader - optional effective request envelope replacing the latest logged header. - * @returns a detached deeply immutable pressure measurement. - */ - measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement - - /** - * Price the current surface for retention and replacement decisions. - * - * @param session - session to replay through its current durable tail. - * @returns a detached deeply immutable positional surface measurement. - */ - measureSurface(session: Session): TokenSurfaceMeasurement - - /** - * Heuristically price one model-visible message. - * - * @param message - message to price without mutation. - * @returns content and role-framing tokens under this model profile. - */ - estimateMessage(message: Message): number -} diff --git a/packages/llm/token-meter/tests/token-meter.spec.ts b/packages/llm/token-meter/tests/token-meter.spec.ts index 1012d5c15e..a91bd392e1 100644 --- a/packages/llm/token-meter/tests/token-meter.spec.ts +++ b/packages/llm/token-meter/tests/token-meter.spec.ts @@ -4,12 +4,8 @@ import { CallId } from '@deepseek-ai/dsh-llm' import type { ContentBlock, Message, TokenUsage } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId, canonicalHeader } from '@deepseek-ai/dsh-session' import type { EpochHeader } from '@deepseek-ai/dsh-session' -import TokenMeterService, { - TOKEN_METER_INVALID_CONFIG, - TOKEN_METER_MODEL_UNCONFIGURED, - TokenMeterError, -} from '@deepseek-ai/dsh-token-meter' -import type { ModelTokenMeter, TokenMeterConfig } from '@deepseek-ai/dsh-token-meter' +import TokenMeterService from '@deepseek-ai/dsh-token-meter' +import type { TokenMeterConfig } from '@deepseek-ai/dsh-token-meter' function header(model: string, extras: Omit = {}): EpochHeader { return canonicalHeader({ config: { model }, ...extras }) @@ -76,69 +72,23 @@ function meter(config: TokenMeterConfig = {}): TokenMeterService { } describe('TokenMeterService configuration and registration', () => { - it('provides immutable zero-config DeepSeek profiles', () => { + it('provides one zero-config context window', () => { const service = meter() - expect(service.resolve('deepseek-v4-flash')).toMatchObject({ - model: 'deepseek-v4-flash', - contextWindow: 128_000, - charsPerToken: 4, - }) - expect(service.resolve('deepseek-v4-pro')).toMatchObject({ - model: 'deepseek-v4-pro', - contextWindow: 128_000, - charsPerToken: 4, - }) + expect(service.contextWindow).toBe(128_000) }) - it('merges built-in overrides field-wise and defaults custom density', () => { - const service = meter({ - models: { - 'deepseek-v4-flash': { charsPerToken: 2 }, - custom: { contextWindow: 32_000 }, - }, - }) - expect(service.resolve('deepseek-v4-flash')).toMatchObject({ contextWindow: 128_000, charsPerToken: 2 }) - expect(service.resolve('deepseek-v4-pro')).toMatchObject({ contextWindow: 128_000, charsPerToken: 4 }) - expect(service.resolve('custom')).toMatchObject({ contextWindow: 32_000, charsPerToken: 4 }) - }) - - it('throws a typed exact-code error for unknown models', () => { - const service = meter() - let thrown: unknown - try { - service.resolve('unconfigured-model') - } catch (error: unknown) { - thrown = error - } - expect(thrown).toBeInstanceOf(TokenMeterError) - expect(thrown).toMatchObject({ - code: TOKEN_METER_MODEL_UNCONFIGURED, - model: 'unconfigured-model', - }) - expect((thrown as Error).message).toContain('unconfigured-model') + it('accepts one service-wide context-window override', () => { + expect(meter({ contextWindow: 32_000 }).contextWindow).toBe(32_000) }) it.each([ - [{ models: null }, /models must be an object/], - [{ models: [] }, /models must be an object/], - [{ models: { custom: {} } }, /requires contextWindow/], - [{ models: { '': { contextWindow: 1 } } }, /must not be empty/], - [{ models: { custom: { contextWindow: 0 } } }, /positive integer/], - [{ models: { custom: { contextWindow: 1.5 } } }, /positive integer/], - [{ models: { custom: { contextWindow: 1, charsPerToken: 0 } } }, /positive finite/], - [{ models: { custom: { contextWindow: 1, charsPerToken: Number.NaN } } }, /positive finite/], - [{ models: { custom: null } }, /must be an object/], - [{ models: { custom: [] } }, /must be an object/], - ] as unknown as Array<[TokenMeterConfig, RegExp]>)('rejects invalid profile config %#', (config, pattern) => { - let thrown: unknown - try { - meter(config) - } catch (error: unknown) { - thrown = error - } - expect(thrown).toBeInstanceOf(TokenMeterError) - expect(thrown).toMatchObject({ code: TOKEN_METER_INVALID_CONFIG }) - expect((thrown as Error).message).toMatch(pattern) + { contextWindow: 0 }, + { contextWindow: -1 }, + { contextWindow: 1.5 }, + { contextWindow: Number.NaN }, + { contextWindow: null }, + ] as unknown as TokenMeterConfig[])('rejects invalid context capacity %#', (config) => { + expect(() => meter(config)).toThrow(/contextWindow .* positive integer/) }) it('registers and unregisters ctx.tokenMeter with its plugin fiber', async () => { @@ -151,9 +101,9 @@ describe('TokenMeterService configuration and registration', () => { }) }) -describe('ModelTokenMeter pricing', () => { - it('prices every built-in content shape and merge-extended blocks', () => { - const handle = meter({ models: { custom: { contextWindow: 100, charsPerToken: 2 } } }).resolve('custom') +describe('TokenMeterService pricing', () => { + it('prices every built-in content shape and merge-extended blocks with one fixed heuristic', () => { + const service = meter({ contextWindow: 100 }) const blocks: ContentBlock[] = [ { type: 'text', text: 'abcd' }, { type: 'reasoning', text: 'ab' }, @@ -166,17 +116,16 @@ describe('ModelTokenMeter pricing', () => { }, { type: 'future-block', payload: 'abcd' } as unknown as ContentBlock, ] - const estimated = handle.estimateMessage({ role: 'assistant', content: blocks }) + const estimated = service.estimateMessage({ role: 'assistant', content: blocks }) expect(estimated).toBeGreaterThan(30) - expect(handle.estimateMessage(textMessage('abcd'))).toBe(10) + expect(service.estimateMessage(textMessage('abcd'))).toBe(9) }) it('returns a detached deeply immutable empty measurement', () => { - const handle = meter().resolve('deepseek-v4-flash') + const service = meter() const session = new Session(SessionId('empty')) - const result = handle.measure(session) + const result = service.measure(session) expect(result).toEqual({ - model: 'deepseek-v4-flash', logRevision: 0, baseline: { kind: 'none', tokens: 0 }, surfaceDeltaTokens: 0, @@ -190,14 +139,14 @@ describe('ModelTokenMeter pricing', () => { }) it('keeps earlier scalar and surface snapshots detached from later replay', () => { - const handle = meter().resolve('deepseek-v4-flash') + const service = meter() const session = new Session(SessionId('detached')) session.append('user/message', { content: [{ type: 'text', text: 'first' }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - const scalar = handle.measure(session) - const surface = handle.measureSurface(session) + const scalar = service.measure(session) + const surface = service.measureSurface(session) const scalarCopy = structuredClone(scalar) const surfaceCopy = structuredClone(surface) @@ -205,8 +154,8 @@ describe('ModelTokenMeter pricing', () => { content: [{ type: 'text', text: 'second' }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - expect(handle.measure(session).logRevision).toBe(2) - expect(handle.measureSurface(session).nodes).toHaveLength(2) + expect(service.measure(session).logRevision).toBe(2) + expect(service.measureSurface(session).nodes).toHaveLength(2) expect(scalar).toEqual(scalarCopy) expect(surface).toEqual(surfaceCopy) expect(scalar.logRevision).toBe(1) @@ -214,7 +163,7 @@ describe('ModelTokenMeter pricing', () => { }) it('prices header, prefix, tools, and surface when no reusable usage exists', () => { - const handle = meter().resolve('deepseek-v4-flash') + const service = meter() const session = new Session(SessionId('heuristic')) session.append('user/message', { content: [{ type: 'text', text: 'question' }], @@ -225,9 +174,9 @@ describe('ModelTokenMeter pricing', () => { messagePrefix: [textMessage('prefix')], tools: [{ name: 'read', description: 'read', parameters: { type: 'object' } }], })) - const result = handle.measure(session) + const result = service.measure(session) expect(result.baseline.kind).toBe('estimated') - expect(result.totalTokens).toBeGreaterThan(handle.measureSurface(session).totalTokens) + expect(result.totalTokens).toBeGreaterThan(service.measureSurface(session).totalTokens) expect(result.logRevision).toBe(session.events.length) }) }) @@ -242,7 +191,7 @@ describe('replay anchors and surface folds', () => { } it('uses disjoint provider usage and signed durable-output rewrites', () => { - const handle = meter().resolve('deepseek-v4-flash') + const service = meter() const session = new Session(SessionId('usage')) session.append('user/message', { content: [{ type: 'text', text: 'before' }], @@ -253,7 +202,7 @@ describe('replay anchors and surface folds', () => { durableText: 'a much longer rewritten durable assistant answer', usage: USAGE, }) - const result = handle.measure(session) + const result = service.measure(session) expect(result.baseline).toMatchObject({ kind: 'usage', tokens: 34, usage: USAGE }) expect(result.surfaceDeltaTokens).toBeGreaterThan(0) expect(result.totalTokens).toBe(34 + result.surfaceDeltaTokens) @@ -263,20 +212,20 @@ describe('replay anchors and surface folds', () => { }) it('uses an estimated anchor when provider usage is absent', () => { - const handle = meter().resolve('deepseek-v4-flash') + const service = meter() const session = new Session(SessionId('missing-usage')) appendSuccessfulCall(session, header('deepseek-v4-flash', { system: 's' }), { providerText: 'provider', durableText: 'rewritten', }) - const anchored = handle.measure(session) + const anchored = service.measure(session) expect(anchored.baseline.kind).toBe('estimated') expect(anchored.surfaceDeltaTokens).toBe(0) session.append('user/message', { content: [{ type: 'text', text: 'later' }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - const advanced = handle.measure(session) + const advanced = service.measure(session) expect(advanced.surfaceDeltaTokens).toBeGreaterThan(0) }) @@ -295,24 +244,17 @@ describe('replay anchors and surface folds', () => { usage: USAGE, provenance: 'absent', }) - const handle = meter().resolve('deepseek-v4-flash') - expect(handle.measure(explicit).surfaceDeltaTokens).toBeGreaterThan(0) - expect(handle.measure(legacy).surfaceDeltaTokens).toBe(0) + const service = meter() + expect(service.measure(explicit).surfaceDeltaTokens).toBeGreaterThan(0) + expect(service.measure(legacy).surfaceDeltaTokens).toBe(0) }) - it('preserves one model anchor across another model success and reuses it after switching back', () => { - const service = meter({ - models: { - alpha: { contextWindow: 1000 }, - beta: { contextWindow: 1000, charsPerToken: 2 }, - }, - }) - const alpha = service.resolve('alpha') - const beta = service.resolve('beta') + it('keeps only the latest successful request anchor across model switches', () => { + const service = meter({ contextWindow: 1_000 }) const session = new Session(SessionId('switch')) const alphaHeader = header('alpha', { system: 'same envelope' }) appendSuccessfulCall(session, alphaHeader, { usage: USAGE, providerText: 'alpha' }) - expect(alpha.measure(session).baseline.kind).toBe('usage') + expect(service.measure(session).baseline).toMatchObject({ kind: 'usage', tokens: 34 }) appendSuccessfulCall(session, header('beta'), { turn: 1, @@ -320,34 +262,33 @@ describe('replay anchors and surface folds', () => { usage: { inputTokens: 100, outputTokens: 50 }, providerText: 'beta response', }) - expect(alpha.measure(session).baseline.kind).toBe('estimated') - expect(beta.measure(session).baseline).toMatchObject({ kind: 'usage', tokens: 150 }) + expect(service.measure(session).baseline).toMatchObject({ kind: 'usage', tokens: 150 }) appendHeader(session, alphaHeader) - const switchedBack = alpha.measure(session) - expect(switchedBack.baseline).toMatchObject({ kind: 'usage', tokens: 34 }) - expect(switchedBack.surfaceDeltaTokens).toBeGreaterThan(0) + const switchedBack = service.measure(session) + expect(switchedBack.baseline.kind).toBe('estimated') + expect(switchedBack.surfaceDeltaTokens).toBe(0) }) it('invalidates usage for any canonical envelope change or explicit override', () => { - const handle = meter().resolve('deepseek-v4-flash') + const service = meter() const session = new Session(SessionId('envelope')) const anchoredHeader = header('deepseek-v4-flash', { system: 'one' }) appendSuccessfulCall(session, anchoredHeader, { usage: USAGE }) - expect(handle.measure(session, { ...anchoredHeader, tools: [] }).baseline.kind).toBe('usage') - expect(handle.measure(session, header('deepseek-v4-flash', { system: 'two' })).baseline.kind) + expect(service.measure(session, { ...anchoredHeader, tools: [] }).baseline.kind).toBe('usage') + expect(service.measure(session, header('deepseek-v4-flash', { system: 'two' })).baseline.kind) .toBe('estimated') - expect(handle.measure(session, header('deepseek-v4-pro', { system: 'one' })).baseline.kind) + expect(service.measure(session, header('deepseek-v4-pro', { system: 'one' })).baseline.kind) .toBe('estimated') - expect(handle.measure(session, { + expect(service.measure(session, { ...anchoredHeader, config: { ...anchoredHeader.config, temperature: 0.2 }, }).baseline.kind).toBe('estimated') - expect(handle.measure(session, { + expect(service.measure(session, { ...anchoredHeader, messagePrefix: [textMessage('prefix')], }).baseline.kind).toBe('estimated') - expect(handle.measure(session, { + expect(service.measure(session, { ...anchoredHeader, tools: [{ name: 'read', description: 'read', parameters: { type: 'object' } }], }).baseline.kind).toBe('estimated') @@ -357,7 +298,7 @@ describe('replay anchors and surface folds', () => { const session = new Session(SessionId('header-delta')) appendHeader(session, header('deepseek-v4-flash')) session.append('request/header-delta', { config: { model: 'deepseek-v4-pro' } }) - const result = meter().resolve('deepseek-v4-flash').measure(session) + const result = meter().measure(session) expect(result.baseline.kind).toBe('estimated') expect(result.logRevision).toBe(2) }) @@ -374,9 +315,8 @@ describe('replay anchors and surface folds', () => { source: { kind: 'user' }, }, { surfaceOp: 'append' }) const seeded = new Session(SessionId('surface-seeded'), original.events) - const handle = service.resolve('deepseek-v4-flash') - const before = handle.measureSurface(seeded) - const beforeScalar = handle.measure(seeded) + const before = service.measureSurface(seeded) + const beforeScalar = service.measure(seeded) expect(before.nodes).toHaveLength(2) expect(beforeScalar.surfaceDeltaTokens).toBeGreaterThan(0) @@ -385,8 +325,8 @@ describe('replay anchors and surface folds', () => { content: [{ type: 'text', text: 'replacement' }], source: { kind: 'plugin', plugin: 'test' }, }, { surfaceOp: { op: 'replace', start: first, end: first }, sourceEventSeqs: [first] }) - const after = handle.measureSurface(seeded) - const afterScalar = handle.measure(seeded) + const after = service.measureSurface(seeded) + const afterScalar = service.measure(seeded) expect(after.nodes).toHaveLength(2) expect(after.nodes[0]!.seq).toBe(seeded.events.length - 1) expect(after.logRevision).toBe(seeded.events.length) @@ -405,7 +345,7 @@ describe('replay anchors and surface folds', () => { durableText: '', provenance: 'empty', }) - const surface = meter().resolve('deepseek-v4-flash').measureSurface(session) + const surface = meter().measureSurface(session) const assistant = session.events.find(event => event.type === 'assistant/message')! expect(surface.nodes).toEqual([{ seq: assistant.seq, tokens: 0 }]) expect(surface.totalTokens).toBe(0) @@ -413,18 +353,18 @@ describe('replay anchors and surface folds', () => { }) describe('malformed replay and listener lifecycle', () => { - function expectRepeatedFailure(handle: ModelTokenMeter, session: Session, pattern: RegExp): void { - expect(() => handle.measure(session)).toThrow(pattern) - expect(() => handle.measure(session)).toThrow(pattern) + function expectRepeatedFailure(service: TokenMeterService, session: Session, pattern: RegExp): void { + expect(() => service.measure(session)).toThrow(pattern) + expect(() => service.measure(session)).toThrow(pattern) } it('rejects a header delta before any snapshot transactionally', () => { const session = new Session(SessionId('bad-delta')) session.append('request/header-delta', { config: { model: 'deepseek-v4-flash' } }) - expectRepeatedFailure(meter().resolve('deepseek-v4-flash'), session, /no preceding header/) + expectRepeatedFailure(meter(), session, /no preceding header/) }) - it('rejects a matching-model assistant without its step boundary transactionally', () => { + it('rejects an assistant without its step boundary transactionally', () => { const session = new Session(SessionId('bad-step')) appendHeader(session, header('deepseek-v4-flash')) session.append('assistant/message', { @@ -432,7 +372,7 @@ describe('malformed replay and listener lifecycle', () => { step: 1, content: [{ type: 'text', text: 'bad' }], }, { surfaceOp: 'append', sourceEventSeqs: [] }) - expectRepeatedFailure(meter().resolve('deepseek-v4-flash'), session, /no matching step\/start/) + expectRepeatedFailure(meter(), session, /no matching step\/start/) }) it('clears completed step boundaries and rejects overlapping or late step events', () => { @@ -440,7 +380,7 @@ describe('malformed replay and listener lifecycle', () => { overlapping.append('step/start', { turn: 1, step: 1 }) overlapping.append('step/start', { turn: 1, step: 2 }) expectRepeatedFailure( - meter().resolve('deepseek-v4-flash'), + meter(), overlapping, /arrived before turn 1\/step 1 ended/, ) @@ -455,7 +395,7 @@ describe('malformed replay and listener lifecycle', () => { content: [], }, { surfaceOp: 'append', sourceEventSeqs: [] }) expectRepeatedFailure( - meter().resolve('deepseek-v4-flash'), + meter(), late, /no matching step\/start/, ) @@ -464,7 +404,7 @@ describe('malformed replay and listener lifecycle', () => { mismatchedEnd.append('step/start', { turn: 1, step: 1 }) mismatchedEnd.append('step/end', { turn: 1, step: 2 }) expectRepeatedFailure( - meter().resolve('deepseek-v4-flash'), + meter(), mismatchedEnd, /step\/end .* no matching step\/start/, ) @@ -509,7 +449,7 @@ describe('malformed replay and listener lifecycle', () => { content: [{ type: 'text', text: 'bad' }], usage: { inputTokens: 1, outputTokens: 1 }, }, { surfaceOp: 'append', sourceEventSeqs }) - expect(() => meter().resolve('deepseek-v4-flash').measure(session)).toThrow(testCase.pattern) + expect(() => meter().measure(session)).toThrow(testCase.pattern) } }) @@ -528,7 +468,7 @@ describe('malformed replay and listener lifecycle', () => { content: [], usage: { inputTokens: 1, outputTokens: 0 }, }, { surfaceOp: 'append', sourceEventSeqs: [source, source] }) - expect(() => meter().resolve('deepseek-v4-flash').measure(duplicate)).toThrow(/repeats source seq/) + expect(() => meter().measure(duplicate)).toThrow(/repeats source seq/) const future = new Session(SessionId('future-source')) future.append('step/start', { turn: 1, step: 1 }) @@ -539,7 +479,7 @@ describe('malformed replay and listener lifecycle', () => { content: [], usage: { inputTokens: 1, outputTokens: 0 }, }, { surfaceOp: 'append', sourceEventSeqs: [99] }) - expect(() => meter().resolve('deepseek-v4-flash').measure(future)).toThrow(/is not earlier/) + expect(() => meter().measure(future)).toThrow(/is not earlier/) }) it('does not partially apply a malformed assistant replacement', () => { @@ -556,7 +496,7 @@ describe('malformed replay and listener lifecycle', () => { content: [{ type: 'text', text: 'replacement' }], }, { surfaceOp: { op: 'replace', start: head, end: head }, sourceEventSeqs: [head] }) expectRepeatedFailure( - meter().resolve('deepseek-v4-flash'), + meter(), session, /no matching step\/start/, ) @@ -572,32 +512,32 @@ describe('malformed replay and listener lifecycle', () => { content: [{ type: 'text', text: 'bad' }], source: { kind: 'user' }, }, { surfaceOp: { op: 'replace', start: 99, end: 99 }, sourceEventSeqs: [0] }) - expectRepeatedFailure(meter().resolve('deepseek-v4-flash'), session, /invalid current range/) + expectRepeatedFailure(meter(), session, /invalid current range/) }) it('handles earlier-reader catch-up, eager observation, and service reload', async () => { const ctx = new Context() await ctx.plugin(SessionStore) - let handle: ModelTokenMeter | undefined + let activeMeter: TokenMeterService | undefined const revisions: number[] = [] ctx.on('session/event', (session) => { - if (handle !== undefined) revisions.push(handle.measure(session).logRevision) + if (activeMeter !== undefined) revisions.push(activeMeter.measure(session).logRevision) }) const firstFiber = await ctx.plugin(TokenMeterService) - handle = ctx.tokenMeter.resolve('deepseek-v4-flash') + activeMeter = ctx.tokenMeter const session = ctx.sessions.create(SessionId('listener-order')) - handle.measure(session) + activeMeter.measure(session) session.append('user/message', { content: [{ type: 'text', text: 'one' }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) expect(revisions).toEqual([1]) - expect(handle.measure(session).logRevision).toBe(1) + expect(activeMeter.measure(session).logRevision).toBe(1) await firstFiber.dispose() const secondFiber = await ctx.plugin(TokenMeterService) - handle = ctx.tokenMeter.resolve('deepseek-v4-flash') - expect(handle.measure(session).logRevision).toBe(1) + activeMeter = ctx.tokenMeter + expect(activeMeter.measure(session).logRevision).toBe(1) await secondFiber.dispose() }) }) diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 1152bb8270..994edaa8bb 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -92,7 +92,7 @@ const SERVICE_ROLES: ServiceRole[] = [ title: 'Replay token measurement', mode: 'core', consumers: ['compact-basic'], - note: 'Owns isolated per-model/session replay folds; pressure consumers share immutable revisioned measurements.', + note: 'Owns isolated per-session replay folds; pressure consumers share immutable revisioned measurements.', }, { key: 'sessions', From 19a56ec542f30c07f4bb5ec419a91de80c107948 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 13:23:20 +0800 Subject: [PATCH 202/359] fix(token-meter): reject stale config (round 2) --- docs/cordis-catalog/services.md | 2 +- .../2026-06-18-compaction-capability-seam.md | 2 +- packages/compact/compact-basic/README.md | 2 +- packages/compact/compact-basic/src/config.ts | 23 +++++ .../compact-basic/tests/compact-basic.spec.ts | 2 + .../tests/loader-composition.spec.ts | 91 +++++++++++++------ packages/llm/token-meter/README.md | 2 +- packages/llm/token-meter/src/index.ts | 15 +++ .../llm/token-meter/tests/token-meter.spec.ts | 5 + 9 files changed, 110 insertions(+), 34 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 5805ae130d..d57f0ed9c5 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -273,7 +273,7 @@ estimateMessage(message: Message): number Types: [Message](../core-data-structures/core.md) -Source: [`packages/llm/token-meter/src/index.ts:92`](../../packages/llm/token-meter/src/index.ts) +Source: [`packages/llm/token-meter/src/index.ts:107`](../../packages/llm/token-meter/src/index.ts) ## `ctx.tools` — `ToolRegistry` diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index 77f836e8e3..341e5f2866 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -28,7 +28,7 @@ This is not a coupling smell — it is the contract's domain. The "only cordis" ### Abstract `compactIfNeeded` / `compactRegion`, algorithm in the backend -An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the standalone service lets multiple consumers share one model/session replay fold. +An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the singleton service lets multiple consumers share one per-session replay fold. `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` takes required pressure inputs and cancellation. The session comes from the agent. `compactRegion(session, start, end, agent, signal?)` keeps an optional signal for manual callers and requires `session === agent.session`; implementations reject mismatch before model resolution, lock acquisition, summarization, or log mutation. The pre-step integration resolves a provisional model from the latest logged request header, then `AgentOptions.model`; a model-less router-only first step skips pressure because `agent/request` can route later. The default summarizer resolves its model from explicit config, the latest logged routed model, then agent options. diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index b166636a5f..d537848bd2 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -20,7 +20,7 @@ This backend owns the compaction policy: ## Config (`BasicCompactConfig`) -Every setting is optional. The pressure and retention policy applies to the token meter's single context window. +Every setting is optional. The pressure and retention policy applies to the token meter's single context window. Unrecognized top-level keys are rejected. | Key | Required | Meaning | |---|---|---| diff --git a/packages/compact/compact-basic/src/config.ts b/packages/compact/compact-basic/src/config.ts index da2cd7bea7..377bd21523 100644 --- a/packages/compact/compact-basic/src/config.ts +++ b/packages/compact/compact-basic/src/config.ts @@ -14,6 +14,28 @@ const DEFAULT_THRESHOLD_RATIO = 0.8 /** Default verbatim-tail fraction of the token meter's context window. */ const DEFAULT_RETAIN_RATIO = 0.16 +/** Complete public configuration key set. */ +const BASIC_COMPACT_CONFIG_KEYS: ReadonlySet = new Set([ + 'thresholdRatio', + 'retainTokens', + 'summarizationModel', + 'maxTokens', + 'compactionRetries', + 'auto', +]) + +/** Reject stale or misspelled keys before defaults can hide them. */ +function validateConfigKeys(config: BasicCompactConfig): void { + for (const key of Object.keys(config)) { + if (!BASIC_COMPACT_CONFIG_KEYS.has(key)) { + throw new Error( + `BasicCompactConfig: unknown key "${key}" ` + + '(allowed: thresholdRatio, retainTokens, summarizationModel, maxTokens, compactionRetries, auto)', + ) + } + } +} + /** * Resolve defaults and validate the service-wide compaction policy. * @param config - raw compact-basic configuration. @@ -24,6 +46,7 @@ export function resolveConfig( config: BasicCompactConfig = {}, tokenMeter: TokenMeterService, ): ResolvedConfig { + validateConfigKeys(config) const thresholdRatio = config.thresholdRatio ?? DEFAULT_THRESHOLD_RATIO const retainTokens = config.retainTokens ?? Math.floor(tokenMeter.contextWindow * DEFAULT_RETAIN_RATIO) diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 86471d2630..ffc60ef024 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -163,6 +163,8 @@ describe('compact configuration and defaults', () => { [{ thresholdRatio: 1.1 }, /number in \(0, 1\]/], [{ retainTokens: -1 }, /non-negative integer/], [{ thresholdRatio: 0.5, retainTokens: 500 }, /less than threshold/], + [{ models: { [MODEL]: { retainTokens: 10 } } }, /BasicCompactConfig: unknown key "models"/], + [{ thresholdRato: 0.5 }, /BasicCompactConfig: unknown key "thresholdRato"/], ] as Array<[unknown, RegExp]> for (const [config, pattern] of bad) { diff --git a/packages/compact/compact-basic/tests/loader-composition.spec.ts b/packages/compact/compact-basic/tests/loader-composition.spec.ts index 26ff37a8e6..b13e8f8b67 100644 --- a/packages/compact/compact-basic/tests/loader-composition.spec.ts +++ b/packages/compact/compact-basic/tests/loader-composition.spec.ts @@ -20,44 +20,75 @@ afterEach(async () => { root = undefined }) +async function loadYaml(lines: readonly string[]): Promise { + root = await mkdtemp(join(tmpdir(), 'dsh-token-meter-loader-')) + const configPath = join(root, 'cordis.yml') + await writeFile(configPath, [...lines, ''].join('\n')) + + context = new Context() + context.baseUrl = pathToFileURL(root).href + '/' + await context.plugin(Loader) + context.loader.builtins.include = Include + const modules = new Map([ + ['@deepseek-ai/dsh-llm', LlmService], + ['@deepseek-ai/dsh-token-meter', TokenMeterService], + ['@deepseek-ai/dsh-compact-basic', BasicCompactService], + ]) + context.loader.internal = { + version: 'v2', + async import(specifier: string) { + if (!modules.has(specifier)) throw new Error(`unexpected Loader import: ${specifier}`) + return modules.get(specifier) + }, + } as unknown as NonNullable + await context.loader.create({ + name: 'cordis:include', + config: { path: pathToFileURL(configPath).href }, + }) + await context.loader.await() + return context +} + describe('real Loader composition', () => { - it('loads the zero-config token-meter then compact-basic YAML pair', async () => { - root = await mkdtemp(join(tmpdir(), 'dsh-token-meter-loader-')) - const configPath = join(root, 'cordis.yml') - await writeFile(configPath, [ + it('loads the flat token-meter and compact-basic YAML shape', async () => { + const loaded = await loadYaml([ "- name: '@deepseek-ai/dsh-llm'", "- name: '@deepseek-ai/dsh-token-meter'", + ' config:', + ' contextWindow: 4096', "- name: '@deepseek-ai/dsh-compact-basic'", - '', - ].join('\n')) - - context = new Context() - context.baseUrl = pathToFileURL(root).href + '/' - await context.plugin(Loader) - context.loader.builtins.include = Include - const modules = new Map([ - ['@deepseek-ai/dsh-llm', LlmService], - ['@deepseek-ai/dsh-token-meter', TokenMeterService], - ['@deepseek-ai/dsh-compact-basic', BasicCompactService], + ' config:', + ' thresholdRatio: 0.5', + ' retainTokens: 512', + ' auto: false', ]) - context.loader.internal = { - version: 'v2', - async import(specifier: string) { - if (!modules.has(specifier)) throw new Error(`unexpected Loader import: ${specifier}`) - return modules.get(specifier) - }, - } as unknown as NonNullable - await context.loader.create({ - name: 'cordis:include', - config: { path: pathToFileURL(configPath).href }, - }) - await context.loader.await() - const unloaded = [...context.loader.entries()] + const unloaded = [...loaded.loader.entries()] .filter(entry => entry.fiber === undefined && !entry.disabled) .map(entry => entry.options.name) expect(unloaded).toEqual([]) - expect(context.tokenMeter.contextWindow).toBe(128_000) - expect(context.get('compact')).toBeInstanceOf(BasicCompactService) + expect(loaded.tokenMeter.contextWindow).toBe(4096) + expect(loaded.get('compact')).toBeInstanceOf(BasicCompactService) + expect((loaded.compact as BasicCompactService).config).toMatchObject({ + thresholdRatio: 0.5, + retainTokens: 512, + auto: false, + }) + }) + + it('rejects stale token-meter config after Schemastery normalization', async () => { + context = new Context() + await expect(context.plugin(TokenMeterService, { + models: { legacy: { contextWindow: 4096 } }, + } as never)).rejects.toThrow(/TokenMeterConfig: unknown key "models"/) + }) + + it('rejects stale compact-basic config after Schemastery normalization', async () => { + context = new Context() + await context.plugin(LlmService) + await context.plugin(TokenMeterService) + await expect(context.plugin(BasicCompactService, { + models: { legacy: { thresholdRatio: 0.5 } }, + } as never)).rejects.toThrow(/BasicCompactConfig: unknown key "models"/) }) }) diff --git a/packages/llm/token-meter/README.md b/packages/llm/token-meter/README.md index 85f14aed35..3beaff1506 100644 --- a/packages/llm/token-meter/README.md +++ b/packages/llm/token-meter/README.md @@ -8,7 +8,7 @@ Replay-aware token measurement through the singleton `ctx.tokenMeter` service. I |---|---:|---| | `contextWindow` | `128000` | Positive integer service-wide context capacity. | -The estimator intentionally uses one fixed heuristic: four characters per token plus structural overhead for roles, blocks, and request-envelope fields. `contextWindow` is the only deployment setting. Direct construction validates it; Loader mounts first apply the package's Schemastery shape validation. +The estimator intentionally uses one fixed heuristic: four characters per token plus structural overhead for roles, blocks, and request-envelope fields. `contextWindow` is the only deployment setting. Direct construction validates it; Loader mounts first apply the package's Schemastery shape validation. Unrecognized top-level keys are rejected. ## Measurement contract diff --git a/packages/llm/token-meter/src/index.ts b/packages/llm/token-meter/src/index.ts index 0b5b3b062d..aa88831033 100644 --- a/packages/llm/token-meter/src/index.ts +++ b/packages/llm/token-meter/src/index.ts @@ -23,6 +23,9 @@ export type * from './types.ts' /** Default service-wide provider context capacity. */ const DEFAULT_CONTEXT_WINDOW = 128_000 +/** Complete public configuration key set. */ +const TOKEN_METER_CONFIG_KEYS: ReadonlySet = new Set(['contextWindow']) + /** Fixed text-density estimate used until exact tokenization is needed. */ const CHARS_PER_TOKEN = 4 @@ -69,8 +72,20 @@ function optionalHeaderEquals( return headerEquals(left, right) } +/** Reject stale or misspelled keys before defaults can hide them. */ +function validateConfigKeys(config: TokenMeterConfig): void { + for (const key of Object.keys(config)) { + if (!TOKEN_METER_CONFIG_KEYS.has(key)) { + throw new Error( + `TokenMeterConfig: unknown key "${key}" (allowed: contextWindow)`, + ) + } + } +} + /** Resolve and validate the one service-wide context capacity. */ function resolveContextWindow(config: TokenMeterConfig): number { + validateConfigKeys(config) const contextWindow = config.contextWindow === undefined ? DEFAULT_CONTEXT_WINDOW : config.contextWindow diff --git a/packages/llm/token-meter/tests/token-meter.spec.ts b/packages/llm/token-meter/tests/token-meter.spec.ts index a91bd392e1..648eef01f5 100644 --- a/packages/llm/token-meter/tests/token-meter.spec.ts +++ b/packages/llm/token-meter/tests/token-meter.spec.ts @@ -81,6 +81,11 @@ describe('TokenMeterService configuration and registration', () => { expect(meter({ contextWindow: 32_000 }).contextWindow).toBe(32_000) }) + it.each(['models', 'contextWidow'])('rejects unknown top-level config key %s', (key) => { + expect(() => meter({ [key]: {} })) + .toThrow(`TokenMeterConfig: unknown key "${key}"`) + }) + it.each([ { contextWindow: 0 }, { contextWindow: -1 }, From 91da66e7150f54a9cfaa3c9d9a7b19406b37d33f Mon Sep 17 00:00:00 2001 From: Dudu-0223 Date: Thu, 16 Jul 2026 14:36:16 +0800 Subject: [PATCH 203/359] refactor(agent-loop): simplify parallel tool-call cap config --- docs/config-catalog.md | 30 ++--- docs/cordis-catalog/services.md | 2 +- docs/core-data-structures/core.md | 2 +- ...2026-07-10-parallel-tool-call-execution.md | 119 ++++++++---------- packages/core/agent-core/README.md | 2 +- packages/core/agent-core/src/index.ts | 4 +- .../core/agent-core/tests/agent-core.spec.ts | 5 +- packages/core/agent-loop/README.md | 4 +- packages/core/agent-loop/src/agent.ts | 10 +- packages/core/agent-loop/src/constants.ts | 8 +- packages/core/agent-loop/src/index.ts | 88 ++++--------- packages/core/agent-loop/src/loop.ts | 17 ++- packages/core/agent-loop/src/tool-calls.ts | 28 +---- packages/core/agent-loop/tests/agent.spec.ts | 22 +++- .../tests/contract-regressions.spec.ts | 6 +- .../core/agent-loop/tests/tool-calls.spec.ts | 91 ++++++-------- packages/ui/acp/README.md | 1 - packages/ui/acp/src/index.ts | 12 +- packages/ui/acp/tests/stream-update.spec.ts | 2 - packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/src/index.ts | 7 +- .../ui/stdio-agent/tests/stdio-agent.spec.ts | 4 +- 22 files changed, 182 insertions(+), 284 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index dbee6b350f..abe03d6461 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -18,8 +18,6 @@ Requires: `agents` · `sessions` · `sessionPersistence` · `tools` · `userInte export interface AcpConfig { /** Model name for created agents (must have a registered adapter). */ model?: string - /** Positive-integer concurrent tool-call cap for each created agent; `1` is serial. */ - maxParallelToolCalls?: number /** Runtime-only transport override for tests; production uses stdio. */ stream?: Stream } @@ -77,8 +75,8 @@ export interface Config { /** The agent-loop `agents` list (see dsh-agent-loop's `Config`). */ agents?: AgentLoopConfig['agents'] /** - * The factory-wide default concurrent tool-call cap applied to every agent - * this bundle creates (see dsh-agent-loop's `Config.maxParallelToolCalls`). + * Concurrent tool-call cap shared by every agent this bundle's loop creates + * (see dsh-agent-loop's `Config.maxParallelToolCalls`). */ maxParallelToolCalls?: AgentLoopConfig['maxParallelToolCalls'] /** The deployment persona (see dsh-system-prompt's `Config`). */ @@ -111,16 +109,12 @@ Source: [`packages/core/agent-core/src/index.ts:46`](../packages/core/agent-core Requires: `agents` · `sessions` · `llm` · `tools` · `systemPrompt` ```ts config-catalog -/** Plugin configuration for declarative startup agents. */ +/** Agent-loop plugin configuration. */ export interface Config { /** - * Default concurrent tool-call cap applied to every agent this factory - * creates (declarative startup agents and factory callers such as the ACP, - * stdio, and SDK front doors that go through `create`/`createAgent`/`resume`). - * A positive integer; a per-agent `maxParallelToolCalls` overrides it, and an - * agent with neither falls back to {@link DEFAULT_MAX_PARALLEL_TOOL_CALLS}. - * This is the single `cordis.yml` knob that reaches agents whose front door - * does not expose its own cap field. + * Concurrent parallel-safe tool-call cap shared by every agent this factory + * creates. A positive integer; `1` preserves fully serial execution and an + * omitted value defaults to {@link DEFAULT_MAX_PARALLEL_TOOL_CALLS}. */ maxParallelToolCalls?: number /** Agents created or resumed at plugin startup. */ @@ -129,11 +123,6 @@ export interface Config { id: AgentId /** Optional workspace for a fresh session. */ cwd?: string - /** - * Maximum parallel-safe tool calls to run concurrently within one assistant - * step. Must be a positive integer; `1` preserves serial execution. - */ - maxParallelToolCalls?: number /** Persisted session to resume instead of creating a fresh session. */ resumeSessionId?: SessionId })[] @@ -142,7 +131,7 @@ export interface Config { Depends on: [`AgentId`](../packages/core/agent/src/index.ts) · [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:346`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:334`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` @@ -647,9 +636,8 @@ export interface Config { /** Model name for the `main` agent (must have a registered adapter). */ model: string /** - * Maximum tool calls the `main` agent runs concurrently within one assistant - * step (a positive integer; the agent loop defaults it when omitted). `1` - * preserves fully serial execution. + * Concurrent parallel-safe tool-call cap for the bundled agent loop. A + * positive integer; the loop defaults it when omitted and `1` is serial. */ maxParallelToolCalls?: number /** Deployment persona (the system-prompt plugin's `persona` config). */ diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 830184e804..12a41b2aed 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:374`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:353`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 42c11a84f0..9a9a1706fc 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -347,7 +347,7 @@ interface Agent { } ``` -`AgentStatus` is `'idle' | 'running' | 'disposed'`, and `AgentId` is branded. `AgentOptions` is merge-extensible and currently includes `model?` and `maxParallelToolCalls?` (the loop's per-agent concurrent tool-call cap; the owning field, defaulted by `AgentLoop.Config` and, absent that, by `DEFAULT_MAX_PARALLEL_TOOL_CALLS`). Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default. +`AgentStatus` is `'idle' | 'running' | 'disposed'`, and `AgentId` is branded. `AgentOptions` is merge-extensible and currently includes `model?`. Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default. The [event taxonomy](../architecture.md#event) owns the `agent/*` lifecycle, checkpoint, and waterfall contracts. Turn and step boundaries are durable session events rather than agent emits. diff --git a/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md b/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md index 23e0f0d22e..74a8ef6c61 100644 --- a/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md +++ b/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md @@ -4,109 +4,100 @@ Status: implemented ## Problem -The loop accepts an assistant message containing multiple `tool-call` blocks. Serial execution makes independent reads, web requests, and subagent delegations pay the sum of their wall-clock latency even though the model and adapters already represent sibling tool calls in one response. +An assistant message may contain several sibling `tool-call` blocks. Running them serially adds the latency of independent reads, web requests, and subagent runs even though the model has already requested them together. -Concurrency cannot live in the model-facing JSON schema. `ctx.tools.schemas()` exposes only `name`, `description`, and `parameters`; scheduling is a host contract. The loop needs an internal per-call safety decision and must use it without hardcoding tool names. +Concurrency is a host scheduling concern, not model-facing tool metadata. The loop needs to decide which calls may overlap without hardcoding tool names or exposing scheduler policy in the JSON schema. -The hard constraint is replay. The session log remains the source of truth: the assistant message contains the model's calls in order, each started call has a `tool/call` audit event before its body runs, each model-facing result is a `tool/result`, and derived history sees results in the original call order. Live ACP and stdio surfaces may show several pending calls before the first result; that progress interleaving is not part of the model-history guarantee. +The session log remains authoritative: every started call has an audit event, every started call receives a result, and model history observes results in the original call order regardless of completion order. ## Decision -`ToolDefinition` carries an optional host-only classifier: +Each tool may provide an optional `isConcurrencySafe(args)` classifier. It is synchronous and pure: it examines only the current call's parsed arguments and performs no I/O or mutation. Only an explicit `true` opts in; a missing classifier, invalid arguments, a thrown classifier, or any other return value makes the call exclusive. The canonical type contract lives in the [tool data structures](../../../core-data-structures/tools.md). + +The classifier is deliberately unary. Returning `true` is the tool's promise that this call may overlap with any sibling call that also returns `true`; the scheduler does not compare calls or prove that their resource accesses are compatible. + +Arguments still support input-sensitive classification. A tool may classify a read-only operation as parallel and a mutating operation as exclusive. The interface cannot express relational rules such as "these writes are safe only when their paths differ," so a call whose safety depends on a sibling remains exclusive. + +`defineTool()` validates arguments before invoking a typed classifier. Invalid arguments classify as exclusive and produce the ordinary argument error only if the call executes. `ctx.tools.executionMode(exec)` resolves the live tool definition and returns the tagged `parallel` or `exclusive` mode; unknown tools fail closed to exclusive. + +A tagged mode, rather than a public boolean scheduler API, leaves room for a future resource-aware mode without changing the classifier contract. + +## Scheduling and ordering + +The loop waits for the complete assistant message, parses every call once, creates a distinct `ToolExecution` for each call, and scans them in model order. Consecutive parallel calls form one group; every exclusive call forms a singleton group and an ordering barrier. Groups execute sequentially. + +For example: ```text -export interface ToolDefinition extends ToolSchema { - execute(args: unknown, exec: ToolExecution): Promise - isConcurrencySafe?(args: unknown): boolean -} +[parallel read(A), parallel read(B), exclusive write(A), parallel read(C)] + +→ [read(A), read(B)] +→ [write(A)] +→ [read(C)] ``` -`isConcurrencySafe` is synchronous, pure classification metadata. It may inspect parsed call arguments; `defineTool()` schema-validates those arguments before the typed callback runs, while hand-rolled definitions receive the raw parsed value. The callback performs no I/O and receives no live `Agent` or mutable `ToolExecution`. `defineTool()` validates arguments softly for `isConcurrencySafe`, matching the display-only `presentCall`/`presentResult` pattern: invalid args return `false`, and the ordinary `ToolArgsError` is produced only if the tool executes. +`read(A)` and `read(B)` may overlap. `write(A)` starts after both finish, and `read(C)` starts after the write finishes. -The registry exposes the scheduling decision as a plain method: +Every group uses a rolling pool bounded by `maxParallelToolCalls`: the loop starts calls in model order up to the cap and starts another whenever one settles. An exclusive group is a pool of one. A cap of `1` preserves serial execution. -```text -export type ToolExecutionMode = - | { kind: 'parallel' } - | { kind: 'exclusive' } -``` +Only dispatch and the tool body overlap. `tools/pre-execute` and `tools/post-execute` run in model order because middleware may maintain ordering-sensitive state. `tools/execute` wrappers run around concurrent dispatches and therefore must be reentrant across distinct executions. -```text -class ToolRegistry { - executionMode(exec: ToolExecutionInput): ToolExecutionMode -} -``` +Each started call appends `tool/call` immediately before its pre-execute gate. Completed dispatches occupy model-order slots, and a commit cursor appends `tool/result` and collects `additionalContext` only when the next slot is ready. Live surfaces may show several pending calls, but results and post-tool context remain model-ordered. -`ctx.tools.executionMode(exec)` looks up the registered tool and calls `tool.isConcurrencySafe?.(exec.arguments)`. Unknown tools, missing declarations, malformed typed args, and thrown safety checks all resolve to `{ kind: 'exclusive' }`. The method is not a Cordis waterfall; it is the future insertion point if hook, MCP, or provider policy needs to downgrade a tool's baseline decision. The object-tagged union leaves room for future resource grouping, for example `{ kind: 'exclusive', group: 'session:...' }`. +An abort before a group starts records no calls from that group. An abort during a group stops replenishment, waits for already-started calls, commits their results in order, drops their buffered additional context, and then ends the step through the existing abort path. Calls that never start have no audit event. -A parallel-safe declaration is a contract. The tool body must not mutate the parent agent's session or other parent-owned async state during `execute`; parent-session writes such as `exec.agent.session.append(...)`, `agent.inject(...)`, or other tool-owned parent events belong to exclusive tools unless the mutation moves behind the loop's ordered result path. The only parent-step outputs a parallel-safe call may produce are its returned content, `meta`, structured error, and `additionalContext` carried through the ordered post-execute path. The narrow exception is a synchronous, side-effect-only recorder whose updates are commutative or fail closed for concurrent calls by the same session. `fs/observed` is the worked example: `read` emits it synchronously after a successful read, `dsh-fs-policy` records `WeakMap` state synchronously, and write/edit remain exclusive barriers that re-check versions before mutating; a stale observation can only make the provider CAS reject with `FS_STALE_VERSION`. +Code Mode remains outside this scheduler because the model emits one native `run_code` call. `run_code` and its internal dispatch queue remain serial; native sibling calls in `mode: 'both'` use the normal scheduler. -## Scheduling +## Safety contract -The loop waits for the model stream to finish and logs one authoritative `assistant/message` before scheduling tools. Streaming tool execution is out of scope. +A tool that returns `true` promises that its body is safe to run at the same time as other parallel calls. It must not directly mutate the parent session or other parent-owned state; it returns its outputs to the loop, which commits them in model order. -For each assistant step, `packages/core/agent-loop/src/tool-calls.ts` parses each call's raw JSON arguments exactly once, creates one distinct `ToolExecution` object per call, asks `ctx.tools.executionMode(exec)`, and partitions calls into ordered groups. A group is either one exclusive call or a run of consecutive parallel calls; grouping classifies each call exactly once. `loop.ts` calls the helper so the turn/step lifecycle remains readable. +Any shared state touched during execution must be concurrency-safe. This includes tool wrappers and providers: they may serialize internally or enforce their own capacity, but they must support concurrent dispatch without corrupting state. -Parallelism is per agent. `AgentOptions.maxParallelToolCalls` is a positive integer, defaults to `DEFAULT_MAX_PARALLEL_TOOL_CALLS` (`10`), and reaches an agent three ways in precedence order: the per-agent option, the factory-wide `AgentLoop.Config.maxParallelToolCalls` applied to every agent the loop creates (declarative startup agents and factory callers such as the ACP, stdio, and SDK front doors), then the built-in default. The factory default is the single `cordis.yml` knob for agents whose front door exposes no cap field of its own. Setting the value to `1` preserves serial execution for that agent. The TypeScript `AgentOptions` vocabulary and both `AgentLoop.Config` fields validate the cap, so invalid `cordis.yml` values fail during config validation. +## Configuration and declarations -Every group runs through the same rolling pool: start calls in model order up to `maxParallelToolCalls`, and whenever one call settles, start the next unstarted call until the group is exhausted. An exclusive group is a pool of one — a barrier — so the loop needs no separate serial path. A group larger than the cap is not truncated; the cap limits simultaneous in-flight calls only. +`maxParallelToolCalls` is a positive AgentLoop deployment cap shared by every agent the factory creates. It defaults to `10`; `1` preserves serial execution. Exact fields and defaults live in the generated [configuration catalog](../../../config-catalog.md). -Only the dispatch/body stage runs concurrently. Generic middleware that can shape ordering-sensitive state remains ordered: `tools/pre-execute` and `tools/post-execute` run in model call order. `@deepseek-ai/dsh-tools` exposes the symbol-keyed internal `TOOL_REGISTRY_SCHEDULER` view so `dsh-agent-loop` can split prepare, dispatch, and finalize without adding named staged service methods to `ctx.tools`; ordinary callers still use the one-call `execute(exec)` API. `tools/execute` around-dispatch listeners run with the dispatch they wrap, so wrappers must be reentrant across distinct `ToolExecution` objects. The shipped timeout policy is per-call: every call owns its mutable `exec` and deadline. +The shipped declarations are conservative. Web search, web fetch, filesystem read, and subagent calls opt in. Filesystem writes and edits, bash tools, workflow, user interaction, todo mutation, Code Mode, and Cordis mutation tools remain exclusive. Bash stays exclusive until its owning package supplies a proven input-sensitive classifier. -Each started call appends its own `tool/call` immediately before its pre-execute gate and body can run. `tool/call` events remain in model order relative to started calls, but their log positions may interleave with sibling results: a later call's `tool/call` can appear before or after an earlier call's `tool/result` as the rolling pool replenishes. That is safe because `tool/call` is log-only; derived model history reads the assistant's `tool-call` blocks and the ordered `tool/result` events, pairing by `callId`. Settled dispatches are stored in model-order slots, and a commit cursor appends `tool/result` only while the next slot is ready. `additionalContext` is collected from those same slots and injected in model call order after normal completion of every started tool result in the step. +Filesystem read relies on a narrow recorder exception: its synchronous observation updates may settle out of order, but write and edit re-check the observed version before mutation, so stale state only produces `FS_STALE_VERSION`. -If the parent signal is already aborted before a group starts, the group is not started and no `tool/call` audit records are appended for it. If the signal aborts while a parallel group is running, the pool stops replenishing, waits for only the already-started calls to settle, records their results in order, drops buffered `additionalContext`, and then raises the abort error so the existing `runTurn` catch path owns `turn/end` reason selection. This keeps every started call paired while avoiding audit records for calls that never began. +The subagent declaration requires providers to accept concurrent `start()` calls for independent runs. A provider may queue, enforce its own capacity, or return a typed failure instead of requiring the parent loop to serialize every subagent call. -Code Mode remains outside native scheduling. In `mode: 'code'`, the wire exposes only `run_code`, so the model emits one native tool call and the loop-level scheduler has nothing to parallelize. `run_code` stays exclusive, and its in-program dispatch queue remains serialized. In `mode: 'both'`, native sibling tool calls can form parallel groups normally, while calls made inside one `run_code` execution still follow Code Mode's own queue. +## Verification -## Tool declarations +Unit coverage pins fail-closed classification, typed argument validation, grouping, barriers, the rolling cap, distinct execution objects, middleware order, ordered results and context, and abort draining. First-party tests pin each parallel declaration. -The shipped declarations are conservative: - -- `web_search`, `web_fetch`, filesystem `read`, and `subagent` return `true`. -- Filesystem `write`, filesystem `edit`, `todo_write`, `bash`, `bash_output`, `bash_kill`, `workflow`, `ask_user_question`, and Cordis mutation tools stay exclusive by omitting `isConcurrencySafe`. -- Bash stays exclusive until a bash-owned read-only classifier exists; the loop never infers shell safety. - -Subagent providers do not get an extra opt-in field. `SubagentProvider.start()` is part of the provider contract and must be safe to call concurrently for independent runs. A provider backed by a limited resource may queue internally, apply its own capacity limit, or return a typed failure for the affected run, but it must not require the parent agent loop to serialize every `subagent` tool call. Built-in spawn, fork, and ACP runs own a child session or process; fork seeds only the parent's completed-turn prefix, so concurrent forks inside the parent's open step all see the same stable prefix. - -Exclusive tools naturally form ordering barriers. A step such as `[read A, write A, read A]` becomes three ordered groups because `write` is exclusive, so the scheduler does not introduce a read/write race inside one assistant step. - -The subagent tool remains synchronous. Multiple subagent tool calls in one assistant message can run concurrently, but each tool result is still the child final answer. Background spawning plus later collection would be a separate tool vocabulary. - -## Testing - -Unit tests cover the classifier (`ToolDefinition.isConcurrencySafe`, `defineTool()` soft validation, `ToolRegistry.executionMode`, and schema projection), the loop scheduler (grouping, exclusive barriers, rolling-pool replenishment, `maxParallelToolCalls: 1`, distinct `ToolExecution` objects, ordered pre/post middleware, ordered `tool/result`, concrete `tool/call`/`tool/result` interleaving, ordered `additionalContext`, and abort/drop-context cases), and first-party safe declarations for filesystem read, web tools, and subagent. - -Snapshot coverage pins the transcript-facing ACP behavior for a multi-call step: several pending tool-call updates may precede model-ordered result updates. Code Mode tests and docs pin that `run_code` remains exclusive and that in-program dispatch stays serialized. No real-API e2e is required for this decision because scheduling is deterministic loop behavior with mocked tools and replayable snapshots, not provider-specific behavior. +Snapshot coverage pins the visible multi-call transcript: pending calls may overlap while completed results remain model-ordered. Code Mode coverage pins its serial boundary. No provider-backed e2e is required because scheduling is deterministic loop behavior. ## Alternatives considered -**Keep serial execution.** This keeps the loop simple and avoids new abort ordering cases, but it leaves obvious latency on the table for independent reads, web calls, and subagent delegations. The model and adapters already represent multiple tool calls in one assistant message, so serial execution is a host limitation rather than a protocol limitation. +**Keep serial execution.** This avoids new ordering and abort cases but retains unnecessary latency for independent sibling calls. -**Codex-style tool-level `supportsParallelToolCalls`.** A tool-level boolean is smaller, but it cannot express that the same tool is safe for some inputs and unsafe for others. Bash is the key example: a read-only command classifier can make `pwd` or `ls` parallel-safe without making `rm` or a long-lived background-task operation parallel-safe. +**Use one tool-level boolean.** A fixed `supportsParallelToolCalls` flag is smaller but cannot distinguish a tool's read-only and mutating operations. The argument-sensitive classifier preserves that distinction. -**Parallelize the complete `ctx.tools.execute()` pipeline.** This preserves the existing one-call API in the loop, but it also runs `tools/pre-execute` and `tools/post-execute` concurrently. The shipped repeat-tool guard and hook bridges can carry ordering-sensitive state, so the shipped design keeps pre/post ordered and overlaps only dispatch/body work. +**Use stateful classification.** Giving the classifier a live agent, registry, or I/O access makes the decision depend on when it runs and creates a gap between classification and dispatch. Mutable authorization and stale-state checks remain execution-time responsibilities. -**Expose a public staged API such as `prepare` / `dispatch` / `finalize`.** That names too much implementation surface before another consumer exists. The loop needs staged behavior, but `ToolRegistry` factors it through a symbol-keyed internal view while keeping `execute(exec)` as the public one-call API for ordinary callers. +**Use sibling-aware or resource-aware classification.** The scheduler could compare calls pairwise or let each call declare resource read/write claims. This can parallelize non-conflicting writes, but it requires shared resource identity and conflict semantics across unrelated tools. The unary contract instead gives up that concurrency and fails closed when safety is relational. -**Add a `tools/execution-mode` waterfall.** A Cordis seam would let hook bridges, provider policies, or MCP server metadata downgrade a tool's declaration. It is not needed for the conservative declaration set: raw and undeclared tools default exclusive, pre/post middleware stays ordered, and a non-reentrant around-dispatch wrapper can serialize internally. The `executionMode(exec)` method remains the insertion point if a real deployment needs policy-driven downgrades. +**Parallelize the complete tool pipeline.** This keeps the loop on the public one-call API but runs pre- and post-execute middleware concurrently. Existing guards and hook bridges may carry ordered state, so only dispatch overlaps. -**Start tools while the model is still streaming.** Claude Code has a streaming executor path, but this repo's log reconstruction and surface-pairing contracts make that a larger design. This decision waits for the assistant message to be assembled, so the log records one authoritative assistant message before scheduling tools. +**Expose staged methods or a scheduling waterfall.** Public `prepare` / `dispatch` / `finalize` methods or a `tools/execution-mode` event add extension surface before another consumer needs it. The loop uses an internal scheduler view, while `executionMode(exec)` remains the insertion point for a future policy seam. -**Use fixed windows inside one parallel group.** Fixed windows would start `maxParallelToolCalls` calls, wait for all of them to settle, then start the next window. The rolling pool wins because slot-based result storage and a model-order commit cursor preserve the transcript contract without sacrificing avoidable latency. +**Start calls while the model streams.** This may reduce latency further but changes assistant-message authority, replay, and call/result pairing. The scheduler starts only after the assistant message is complete. -**Expose concurrency in the model-facing schema.** The model does not need a scheduler flag to request multiple calls; it already can emit multiple `tool-call` blocks. Sending host-only concurrency metadata would bloat requests and mix execution policy into the schema whose job is only argument shape and tool-choice guidance. +**Use fixed-size windows.** Waiting for every call in one window before starting the next leaves capacity idle behind a slow call. The rolling pool preserves the cap without that delay. + +**Expose concurrency metadata to the model.** The model can already emit sibling calls. Host scheduling metadata would enlarge requests without improving tool choice. ## Consequences -Parallel execution can expose latent shared-state bugs in tools that declare themselves safe too broadly. The default is exclusive, the shipped declarations are conservative, and input-sensitive tools such as bash stay exclusive until their owning package proves a narrower classifier. +The design is fail-closed and simple for tool authors, but it cannot exploit concurrency whose safety depends on comparing siblings. A tool that opts in too broadly can expose latent shared-state races. -Tool registration changes are a scheduling boundary. A call classified against one tool definition can become unsafe if an earlier exclusive tool replaces that definition before dispatch, so registry-mutating tools stay exclusive and scheduler changes that cross such barriers must either reclassify against the live registry view or bind dispatch to the classified definition. +Parallel calls may begin in cases where serial execution would have aborted before reaching them. The scheduler therefore records only started calls, drains them on abort, and never starts replacements after cancellation. -An around-dispatch plugin can also violate the contract even when the tool itself is safe. The scheduler limits that risk to `tools/execute`; shipped wrappers are per-call, and third-party wrappers with shared mutable state must serialize internally. +Ordered commits may hold a fast result behind a slow earlier sibling. This preserves replay and model-history order while live surfaces still show pending progress. -Parallel groups change abort timing: a sibling call may have started in a case where the serial loop would not have reached it yet. The pool makes this explicit by logging only started calls, stopping replenishment on abort, draining those calls to results, and preventing later calls from starting. +Concurrent subagents and external calls can compete for quota or process capacity. Providers own their capacity controls; the loop cap only limits calls from one agent step. -Concurrent subagents can compete for model quota, filesystem state, or external process resources. The provider contract requires concurrent `start()` safety, not unlimited capacity, and tool guidance still tells the model to parallelize only independent tasks with non-overlapping write scopes. - -The result-order rule can delay a fast result behind a slow sibling in the same group. That preserves the model transcript and replay contract. ACP and stdio still expose immediate pending-call progress, but completion updates stay model-ordered. +Tool registration is a scheduling boundary. The scheduler currently plans all groups before dispatch, so an earlier registry mutation can make a later classification stale. Binding dispatch to the classified definition or reclassifying after exclusive barriers remains a named correctness gap. diff --git a/packages/core/agent-core/README.md b/packages/core/agent-core/README.md index 594c4a8c82..ea9d94b011 100644 --- a/packages/core/agent-core/README.md +++ b/packages/core/agent-core/README.md @@ -43,7 +43,7 @@ import type { Config } from '@deepseek-ai/dsh-agent-core' // intersects the owner schemas, so validation and defaulting can never drift from the owners. ``` -The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `maxParallelToolCalls` to `agent-loop` as the factory-wide default concurrent tool-call cap for every agent it creates; `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure. +The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `maxParallelToolCalls` to `agent-loop` as the shared concurrent tool-call cap for every agent it creates; `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure. ## Why a code bundle, not a shared YAML include diff --git a/packages/core/agent-core/src/index.ts b/packages/core/agent-core/src/index.ts index fcb4e87f1e..7e4da95921 100644 --- a/packages/core/agent-core/src/index.ts +++ b/packages/core/agent-core/src/index.ts @@ -47,8 +47,8 @@ export interface Config { /** The agent-loop `agents` list (see dsh-agent-loop's `Config`). */ agents?: AgentLoopConfig['agents'] /** - * The factory-wide default concurrent tool-call cap applied to every agent - * this bundle creates (see dsh-agent-loop's `Config.maxParallelToolCalls`). + * Concurrent tool-call cap shared by every agent this bundle's loop creates + * (see dsh-agent-loop's `Config.maxParallelToolCalls`). */ maxParallelToolCalls?: AgentLoopConfig['maxParallelToolCalls'] /** The deployment persona (see dsh-system-prompt's `Config`). */ diff --git a/packages/core/agent-core/tests/agent-core.spec.ts b/packages/core/agent-core/tests/agent-core.spec.ts index fe240da8ed..4657bb2a40 100644 --- a/packages/core/agent-core/tests/agent-core.spec.ts +++ b/packages/core/agent-core/tests/agent-core.spec.ts @@ -117,13 +117,12 @@ describe('dsh-agent-core bundle', () => { await ctx.fiber.dispose() }) - it('forwards the factory-wide maxParallelToolCalls default to agents without a per-agent cap', async () => { + it('forwards the global maxParallelToolCalls config to agent-loop', async () => { const ctx = await mount({ agents: [{ id: AgentId('main'), model: 'mock' }], maxParallelToolCalls: 3, }) - const main = ctx.get('agents')?.get(AgentId('main')) - expect(main?.options.maxParallelToolCalls).toBe(3) + expect(ctx.get('agentLoop')?.config.maxParallelToolCalls).toBe(3) await ctx.fiber.dispose() }) diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index e35089b409..1460203cd7 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -29,17 +29,17 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo ```ts interface Config { + maxParallelToolCalls?: number // shared by every agent; default 10; 1 is serial agents: Array<{ id: string // required model?: string - maxParallelToolCalls?: number // positive integer; default 10; 1 is serial resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session }> } ``` -Configured agents start automatically. `cwd` applies only to fresh sessions; `resumeSessionId` retains persisted metadata. `maxParallelToolCalls` bounds the rolling pool for parallel-safe calls and defaults to `10`. They use the deployment persona. Programmatic setup can shadow it per agent. This plugin supplies the per-agent `model` and `cwd` prompt variables; harness identity and deployment persona belong to `dsh-system-prompt`. +Configured agents start automatically. `cwd` applies only to fresh sessions; `resumeSessionId` retains persisted metadata. `maxParallelToolCalls` bounds every agent's rolling pool for parallel-safe calls and defaults to `10`. They use the deployment persona, which programmatic setup can shadow per agent. This plugin supplies the per-agent `model` and `cwd` prompt variables; harness identity and deployment persona belong to `dsh-system-prompt`. ### Exported concrete class diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index a2288c65b7..72834db998 100644 --- a/packages/core/agent-loop/src/agent.ts +++ b/packages/core/agent-loop/src/agent.ts @@ -54,15 +54,16 @@ export interface PreparedReactLoopAgent { * @param id - the concrete agent identity. * @param options - loop options for the agent. * @param session - the prepared session the agent will own. + * @param maxParallelToolCalls - resolved scheduler cap shared by this factory's agents. * @returns the agent and closures bound only to that exact instance. */ export function prepareReactLoopAgent( - ctx: Context, id: AgentId, options: AgentOptions, session: Session, + ctx: Context, id: AgentId, options: AgentOptions, session: Session, maxParallelToolCalls: number, ): PreparedReactLoopAgent { if (claimedDriverSessions.has(session)) { throw new Error(`session "${session.id}" already has a concrete agent driver`) } - const agent = new ReactLoopAgent(ctx, id, options, session) + const agent = new ReactLoopAgent(ctx, id, options, session, maxParallelToolCalls) claimedDriverSessions.add(session) const dispose = () => agent[stopDriver]() return { @@ -143,6 +144,8 @@ export class ReactLoopAgent implements Agent { * the `disposed` transition fires and leave the promise hanging. */ private idleWaiters: (() => void)[] = [] + /** Immutable scheduler cap resolved by the owning AgentLoop factory. */ + private readonly maxParallelToolCalls: number /** * Durability checkpoints started by idle {@link inject} calls. `inject()` is * synchronous, so it cannot await them itself; the driver disposer drains @@ -155,7 +158,9 @@ export class ReactLoopAgent implements Agent { public readonly id: AgentId, public readonly options: AgentOptions, public readonly session: Session, + maxParallelToolCalls: number, ) { + this.maxParallelToolCalls = maxParallelToolCalls const { promise, resolve } = Promise.withResolvers() this.disposed = promise this.resolveDisposed = resolve @@ -329,6 +334,7 @@ export class ReactLoopAgent implements Agent { this.driverStarted = true this.done = runLoop(this.loopCtx, this, { inbox: this.#inbox, + maxParallelToolCalls: this.maxParallelToolCalls, setStatus: (status) => { this.setStatus(status) }, setAbort: controller => void (this.currentAbort = controller), disposed: this.disposed, diff --git a/packages/core/agent-loop/src/constants.ts b/packages/core/agent-loop/src/constants.ts index de18e0411e..72ba7051c2 100644 --- a/packages/core/agent-loop/src/constants.ts +++ b/packages/core/agent-loop/src/constants.ts @@ -7,9 +7,9 @@ */ /** - * Default cap on simultaneously in-flight tool calls within one assistant step, - * when {@link AgentOptions.maxParallelToolCalls} is unset. Matches the - * rolling-pool size Claude Code uses; a group larger than the cap is not - * truncated — the cap limits concurrency, not the group. + * Default cap on simultaneously in-flight tool calls within one assistant step + * when the agent-loop config omits one. Matches the rolling-pool size Claude + * Code uses; a larger group is not truncated — the cap limits concurrency, not + * the group. */ export const DEFAULT_MAX_PARALLEL_TOOL_CALLS = 10 diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 86df80cd8e..3c9c807e15 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -32,6 +32,7 @@ import { ReactLoopAgent, } from './agent.ts' import type { PreparedReactLoopAgent } from './agent.ts' +import { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from './constants.ts' export { ReactLoopAgent } from './agent.ts' @@ -73,12 +74,13 @@ function signalAbortError(id: AgentId, signal: AbortSignal): Error { return new Error(`agent "${id}" creation aborted`, { cause: signal.reason }) } -/** Validate merge-extended options the loop owns before a session is published. */ -function validateAgentOptions(options: AgentOptions): void { - const { maxParallelToolCalls } = options - if (maxParallelToolCalls !== undefined && (!Number.isInteger(maxParallelToolCalls) || maxParallelToolCalls < 1)) { +/** Resolve the deployment-wide scheduler cap at the owning config boundary. */ +function resolveMaxParallelToolCalls(value: number | undefined): number { + const maxParallelToolCalls = value ?? DEFAULT_MAX_PARALLEL_TOOL_CALLS + if (!Number.isInteger(maxParallelToolCalls) || maxParallelToolCalls < 1) { throw new Error('maxParallelToolCalls must be a positive integer') } + return maxParallelToolCalls } /** @@ -171,13 +173,13 @@ class AgentCreationTransaction { } /** Construct the driver and scope, then install their complete ordered lifecycle. */ - prepare(options: AgentOptions, session: Session): ReactLoopAgent { + prepare(options: AgentOptions, session: Session, maxParallelToolCalls: number): ReactLoopAgent { this.assertActive() const gate = Promise.withResolvers() this.preparing = gate.promise try { this.session = session - const driver = prepareReactLoopAgent(this.loopCtx, this.id, options, session) + const driver = prepareReactLoopAgent(this.loopCtx, this.id, options, session, maxParallelToolCalls) this.driver = driver const agent = driver.agent const scope = createScope(this.loopCtx, agent) @@ -326,32 +328,14 @@ declare module 'cordis' { } } -declare module '@deepseek-ai/dsh-agent' { - interface AgentOptions { - /** - * Maximum tool calls this agent runs concurrently within one assistant step - * (a positive integer; defaults to {@link DEFAULT_MAX_PARALLEL_TOOL_CALLS}). - * The loop's rolling pool starts up to this many parallel-safe calls at once - * and replenishes as each settles; `1` preserves the fully serial path. - * A merge-extensible field — the loop owns it (it neither the agent nor the - * subagent seam sets it), read in `runStep` when scheduling a parallel group. - */ - maxParallelToolCalls?: number - } -} +export { DEFAULT_MAX_PARALLEL_TOOL_CALLS } -export { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from './constants.ts' - -/** Plugin configuration for declarative startup agents. */ +/** Agent-loop plugin configuration. */ export interface Config { /** - * Default concurrent tool-call cap applied to every agent this factory - * creates (declarative startup agents and factory callers such as the ACP, - * stdio, and SDK front doors that go through `create`/`createAgent`/`resume`). - * A positive integer; a per-agent `maxParallelToolCalls` overrides it, and an - * agent with neither falls back to {@link DEFAULT_MAX_PARALLEL_TOOL_CALLS}. - * This is the single `cordis.yml` knob that reaches agents whose front door - * does not expose its own cap field. + * Concurrent parallel-safe tool-call cap shared by every agent this factory + * creates. A positive integer; `1` preserves fully serial execution and an + * omitted value defaults to {@link DEFAULT_MAX_PARALLEL_TOOL_CALLS}. */ maxParallelToolCalls?: number /** Agents created or resumed at plugin startup. */ @@ -360,11 +344,6 @@ export interface Config { id: AgentId /** Optional workspace for a fresh session. */ cwd?: string - /** - * Maximum parallel-safe tool calls to run concurrently within one assistant - * step. Must be a positive integer; `1` preserves serial execution. - */ - maxParallelToolCalls?: number /** Persisted session to resume instead of creating a fresh session. */ resumeSessionId?: SessionId })[] @@ -376,26 +355,25 @@ export class AgentLoop extends Service implements AgentFactory { /** Runtime schema for declarative agents. */ static Config = z.object({ - // The factory-wide default cap; a per-agent value overrides it. A positive - // integer, validated here so a bad cordis.yml value fails at load. - maxParallelToolCalls: z.number().step(1).min(1), + // The deployment-wide cap is defaulted and validated at plugin load. + maxParallelToolCalls: z.number().step(1).min(1).default(DEFAULT_MAX_PARALLEL_TOOL_CALLS), agents: z.array(z.object({ id: z.string().required(), model: z.string(), cwd: z.string(), resumeSessionId: z.string(), - // A positive integer; a bad value (0, negative, fractional) fails config - // validation here rather than being silently dropped from cordis.yml. - maxParallelToolCalls: z.number().step(1).min(1), })).default([]), }) as unknown as z private readonly ownership: FactoryOwnership + /** Resolved immutable scheduler cap shared by every driver from this factory. */ + private readonly maxParallelToolCalls: number /** Plain holder prevents Cordis from re-tracing the factory's dependency context through a caller shadow. */ private readonly runtime: { ctx: Context } constructor(ctx: Context, public config: Config) { super(ctx, 'agentLoop') + this.maxParallelToolCalls = resolveMaxParallelToolCalls(config.maxParallelToolCalls) this.ownership = new FactoryOwnership(ctx.fiber) this.runtime = { ctx } ctx.effect(() => () => this.ownership.dispose(), 'agentLoop.transactions()') @@ -423,22 +401,6 @@ export class AgentLoop extends Service implements AgentFactory { } } - /** - * Merge the factory-wide default cap into one agent's options. A per-agent - * `maxParallelToolCalls` wins; otherwise the `Config.maxParallelToolCalls` - * default applies, reaching factory callers (ACP/stdio/SDK front doors) whose - * own config does not set a cap. Absent both, the loop falls back to - * {@link DEFAULT_MAX_PARALLEL_TOOL_CALLS} at schedule time. - * @param options - the caller-supplied agent options. - * @returns options with the default cap applied when the caller omitted one. - */ - private withFactoryDefaults(options: AgentOptions): AgentOptions { - if (options.maxParallelToolCalls !== undefined || this.config.maxParallelToolCalls === undefined) { - return options - } - return { ...options, maxParallelToolCalls: this.config.maxParallelToolCalls } - } - /** * Create an agent on a fresh per-run session, owned by the accessing fiber. * Constructor-driven config calls use the loop fiber itself. @@ -448,14 +410,12 @@ export class AgentLoop extends Service implements AgentFactory { * @returns the published running agent. */ create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent { - const resolved = this.withFactoryDefaults(options) - validateAgentOptions(resolved) const loopCtx = this.runtime.ctx const transaction = new AgentCreationTransaction(loopCtx, this.ctx, this.ownership, id) try { const sessionId = SessionId(`${id}-session-${randomUUID()}`) const session = loopCtx.sessions.prepare(sessionId, { meta }) - const agent = transaction.prepare(resolved, session) + const agent = transaction.prepare(options, session, this.maxParallelToolCalls) transaction.publish('startup') return agent } catch (error: unknown) { @@ -473,8 +433,7 @@ export class AgentLoop extends Service implements AgentFactory { * @returns the published handle. */ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise { - const agentOptions = this.withFactoryDefaults(options.agentOptions ?? {}) - validateAgentOptions(agentOptions) + const agentOptions = options.agentOptions ?? {} const transaction = new AgentCreationTransaction( this.runtime.ctx, ownerCtx, @@ -487,7 +446,7 @@ export class AgentLoop extends Service implements AgentFactory { ...options.seed === undefined ? {} : { seed: options.seed }, ...options.meta === undefined ? {} : { meta: options.meta }, }) - const agent = transaction.prepare(agentOptions, session) + const agent = transaction.prepare(agentOptions, session, this.maxParallelToolCalls) await transaction.waitFor(options.setup?.(agent.ctx)) transaction.assertActive() return transaction.publish('startup') @@ -519,8 +478,7 @@ export class AgentLoop extends Service implements AgentFactory { persistence: SessionPersistence, options: ResumeAgentOptions, ): Promise { - const agentOptions = this.withFactoryDefaults(options.agentOptions ?? {}) - validateAgentOptions(agentOptions) + const agentOptions = options.agentOptions ?? {} const transaction = new AgentCreationTransaction( this.runtime.ctx, ownerCtx, @@ -540,7 +498,7 @@ export class AgentLoop extends Service implements AgentFactory { ...loaded.meta.seedLength === undefined ? {} : { seedLength: loaded.meta.seedLength }, }, }) - const agent = transaction.prepare(agentOptions, session) + const agent = transaction.prepare(agentOptions, session, this.maxParallelToolCalls) await transaction.waitFor(options.setup?.(agent.ctx)) transaction.assertActive() return transaction.publish('resume') diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 7efbceef5e..a04f653b65 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -17,7 +17,7 @@ import type { TransmissionLog } from './request-log.ts' import { renderPrompt } from '@deepseek-ai/dsh-system-prompt' import type { PromptAssembly } from '@deepseek-ai/dsh-system-prompt' import type {} from '@deepseek-ai/dsh-tools' -import { executeToolCalls, resolveMaxParallelToolCalls } from './tool-calls.ts' +import { executeToolCalls } from './tool-calls.ts' import type { ReactLoopAgent } from './agent.ts' import type { Inbox } from './inbox.ts' @@ -73,6 +73,8 @@ function stepFinishReason(finish: FinishReason): TurnEndReason | undefined { export interface LoopHandle { /** Native-private agent inbox handed to the driver only at internal startup. */ readonly inbox: Inbox + /** Immutable concurrent tool-call cap resolved by the owning factory. */ + readonly maxParallelToolCalls: number setStatus(status: 'idle' | 'running'): void setAbort(controller: AbortController | undefined): void /** Resolves when the agent is disposed — unblocks the idle wait. */ @@ -326,7 +328,8 @@ async function runTurn( let stepOutcome: { hadToolCalls: boolean; finish: FinishReason } | { error: Error } try { stepOutcome = await runStep( - ctx, events, agent, turn, step, assembly, fullSystemPrompt, boundaryMessages, transmission, abort.signal) + ctx, events, agent, turn, step, assembly, fullSystemPrompt, boundaryMessages, + transmission, abort.signal, handle.maxParallelToolCalls) } catch (error: unknown) { stepOutcome = { error: toError(error) } } finally { @@ -470,6 +473,7 @@ async function runStep( boundaryMessages: Message[], transmission: TransmissionLog, signal: AbortSignal, + maxParallelToolCalls: number, ): Promise<{ hadToolCalls: boolean; finish: FinishReason }> { const { session, options } = agent @@ -545,12 +549,7 @@ async function runStep( let message: Message = assembler.message() message = await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message)) - // Validate the live cap before logging model-visible tool calls so bad mutable - // options cannot leave unanswered calls in the transcript. const toolCalls = message.content.filter(block => block.type === 'tool-call') - const maxParallel = toolCalls.length > 0 - ? resolveMaxParallelToolCalls(agent.options.maxParallelToolCalls) - : undefined // Empty messages exist only to carry usage; omit empty provenance. if (message.content.length > 0 || assembler.usage) { @@ -563,8 +562,8 @@ async function runStep( // The scheduler overlaps only dispatch/body for parallel-safe calls; policy, // results, and additional context remain in model order. - const pendingContext = maxParallel !== undefined - ? await executeToolCalls(ctx, agent, turn, step, toolCalls, signal, maxParallel) + const pendingContext = toolCalls.length > 0 + ? await executeToolCalls(ctx, agent, turn, step, toolCalls, signal, maxParallelToolCalls) : [] // Append context after the complete result batch to preserve call/result adjacency. diff --git a/packages/core/agent-loop/src/tool-calls.ts b/packages/core/agent-loop/src/tool-calls.ts index d117823a43..52328a080a 100644 --- a/packages/core/agent-loop/src/tool-calls.ts +++ b/packages/core/agent-loop/src/tool-calls.ts @@ -4,8 +4,8 @@ * arguments once, classifies it via `ctx.tools.executionMode`, partitions the * calls into ordered groups (one exclusive call, or a run of consecutive * parallel-safe calls), and runs every group through the same rolling pool - * bounded by the agent's `maxParallelToolCalls` — an exclusive group is a pool - * of one. + * bounded by the agent-loop's `maxParallelToolCalls` config — an exclusive + * group is a pool of one. * * The session log stays the source of truth and is reconstructable regardless * of dispatch timing: each STARTED call appends its own `tool/call` before its @@ -25,7 +25,6 @@ import type { HookContext } from '@deepseek-ai/dsh-agent' import type { Session } from '@deepseek-ai/dsh-session' import { TOOL_REGISTRY_SCHEDULER, type ToolExecution, type ToolExecutionInput, type ToolExecutionResult } from '@deepseek-ai/dsh-tools' import type { ReactLoopAgent } from './agent.ts' -import { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from './constants.ts' /** One tool call after argument parsing, ready to schedule. */ interface PlannedCall { @@ -107,20 +106,6 @@ export async function executeToolCalls( return pendingContext } -/** - * Resolve and validate the per-step parallel dispatch cap before the assistant - * tool-call message is logged, so invalid mutable options fail without leaving - * dangling model-visible tool calls in the session transcript. - * - * @param maxParallelToolCalls - the live agent option value. - * @returns the positive integer cap to use for this step. - */ -export function resolveMaxParallelToolCalls(maxParallelToolCalls: number | undefined): number { - const maxParallel = maxParallelToolCalls ?? DEFAULT_MAX_PARALLEL_TOOL_CALLS - assertMaxParallelToolCalls(maxParallel) - return maxParallel -} - /** Parse a model-produced raw arguments string, falling back to the raw string on invalid JSON (empty ⇒ `{}`). */ function parseArguments(raw: string): unknown { try { @@ -157,13 +142,6 @@ function groupByMode(ctx: Context, planned: PlannedCall[]): PlannedCall[][] { return groups } -/** Validate the live per-agent cap at the point it controls dispatch. */ -function assertMaxParallelToolCalls(maxParallel: number): void { - if (!Number.isInteger(maxParallel) || maxParallel < 1) { - throw new Error('maxParallelToolCalls must be a positive integer') - } -} - /** * The rolling-pool path for one ordered group. A singleton exclusive group runs * as a pool of one (a barrier); a parallel-safe run starts calls in model order @@ -189,8 +167,6 @@ async function runGroup( ): Promise { /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) - assertMaxParallelToolCalls(maxParallel) - const slots: (Slot | undefined)[] = group.map(() => undefined) // callSeqs[i] is the `tool/call` event seq for started slot i (its provenance // for the matching tool/result). A slot is only committed after it is started, diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 581b6fa207..2f3f23bcd2 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -6,7 +6,7 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS, ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { bindReactLoopAgentContext, prepareReactLoopAgent } from '../src/agent.ts' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -53,10 +53,14 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('exclusive-driver')) - const prepared = prepareReactLoopAgent(ctx, AgentId('first-driver'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent( + ctx, AgentId('first-driver'), { model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, + ) expect(() => prepared.agent.ctx).toThrow('context is not bound') - expect(() => prepareReactLoopAgent(ctx, AgentId('second-driver'), { model: 'mock' }, session)) + expect(() => prepareReactLoopAgent( + ctx, AgentId('second-driver'), { model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, + )) .toThrow('already has a concrete agent driver') await prepared.dispose() @@ -254,7 +258,9 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('test')) - const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent( + ctx, AgentId('bare'), { model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, + ) const { agent } = prepared prepared.markPublished() @@ -272,7 +278,9 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('pre-start-dispose')) - const prepared = prepareReactLoopAgent(ctx, AgentId('pre-start-dispose'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent( + ctx, AgentId('pre-start-dispose'), { model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, + ) await prepared.dispose() expect(prepared.agent.status).toBe('disposed') @@ -369,7 +377,9 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter(['hang']) ctx.llm.registerAdapter(['mock'], adapter) const session = ctx.sessions.create(SessionId('bare')) - const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent( + ctx, AgentId('bare'), { model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, + ) const { agent } = prepared prepared.markPublished() const dispose = prepared.startDriver() diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 8130d4b893..00c5c45c09 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -5,7 +5,7 @@ import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId, type ContinuationDecision } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS, ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { prepareReactLoopAgent } from '../src/agent.ts' import * as Invariants from '@deepseek-ai/dsh-invariants' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -528,7 +528,9 @@ describe('turn numbering continues across seeded sessions', () => { ctx2.llm.registerAdapter(['mock'], second) const seeded = ctx2.sessions.create(SessionId('forked'), { seed: [...agent.session.events] }) - const prepared = prepareReactLoopAgent(ctx2, AgentId('forked-agent'), { model: 'mock' }, seeded) + const prepared = prepareReactLoopAgent( + ctx2, AgentId('forked-agent'), { model: 'mock' }, seeded, DEFAULT_MAX_PARALLEL_TOOL_CALLS, + ) const forked = prepared.agent prepared.markPublished() ctx2.effect(() => prepared.startDriver()) diff --git a/packages/core/agent-loop/tests/tool-calls.spec.ts b/packages/core/agent-loop/tests/tool-calls.spec.ts index a270ad6da1..8ca6170b03 100644 --- a/packages/core/agent-loop/tests/tool-calls.spec.ts +++ b/packages/core/agent-loop/tests/tool-calls.spec.ts @@ -12,7 +12,7 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import { CallId, StreamChunk } from '@deepseek-ai/dsh-llm' -import SessionStore, { SessionEvent, SessionId } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import LlmService from '@deepseek-ai/dsh-llm' import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools' @@ -20,14 +20,17 @@ import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' -async function harness(adapter: MockAdapter) { +async function harness(adapter: MockAdapter, maxParallelToolCalls?: number) { const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(SessionStore) await ctx.plugin(SystemPrompt, { persona: '' }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentLoop, { agents: [] }) + await ctx.plugin(AgentLoop, { + agents: [], + ...maxParallelToolCalls === undefined ? {} : { maxParallelToolCalls }, + }) ctx.llm.registerAdapter(['mock'], adapter) return ctx } @@ -190,38 +193,28 @@ describe('tool-call scheduler: model-order results despite out-of-order settleme }) describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => { - it('rejects invalid programmatic maxParallelToolCalls values before creating agents', async () => { - const ctx = await harness(new MockAdapter([])) - - expect(() => ctx.agentLoop.create(AgentId('bad-zero'), { model: 'mock', maxParallelToolCalls: 0 })) - .toThrow('maxParallelToolCalls must be a positive integer') - await expect(ctx.agents.create({ - agentId: AgentId('bad-fractional'), - sessionId: SessionId('bad-fractional-session'), - agentOptions: { model: 'mock', maxParallelToolCalls: 1.5 }, - })).rejects.toThrow('maxParallelToolCalls must be a positive integer') + it('rejects invalid global maxParallelToolCalls config at plugin load', async () => { + await expect(harness(new MockAdapter([]), 0)).rejects.toThrow() + await expect(harness(new MockAdapter([]), 1.5)).rejects.toThrow() }) - it('fails loud if maxParallelToolCalls is mutated invalid after agent creation', async () => { - const adapter = new MockAdapter([ - multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]), - textResponse('must not run after unanswered tool calls'), - ]) - const ctx = await harness(adapter) - const gated = gatedParallelTool('p') - ctx.tools.register(gated.tool) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock', maxParallelToolCalls: 2 }) - ;(agent.options as { maxParallelToolCalls: number }).maxParallelToolCalls = 0 + it('defensively rejects invalid caps when direct construction bypasses the config schema', () => { + expect(() => new AgentLoop(new Context(), { agents: [], maxParallelToolCalls: 0 })) + .toThrow('maxParallelToolCalls must be a positive integer') + expect(() => new AgentLoop(new Context(), { agents: [], maxParallelToolCalls: 1.5 })) + .toThrow('maxParallelToolCalls must be a positive integer') + }) - agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, agent) + it('defaults the cap when direct construction bypasses the config schema', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt, { persona: '' }) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) - expect(gated.started).toEqual([]) - expect(adapter.requests).toHaveLength(1) - expect(events(agent).some(e => e.type === 'assistant/message')).toBe(false) - expect(events(agent).filter(e => e.type === 'tool/call' || e.type === 'tool/result')).toEqual([]) - const turnEnd = events(agent).findLast(e => e.type === 'turn/end') - expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind).toBe('error') + expect(() => new AgentLoop(ctx, { agents: [] })).not.toThrow() + await ctx.fiber.dispose() }) it('starts at most the cap, replenishing as calls settle', async () => { @@ -229,10 +222,10 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => multiCall([1, 2, 3, 4].map(n => ({ id: `c${n}`, name: 'p', args: { id: String(n) } }))), textResponse('done'), ]) - const ctx = await harness(adapter) + const ctx = await harness(adapter, 2) const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock', maxParallelToolCalls: 2 }) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) // Only 2 start initially (the cap). @@ -261,10 +254,10 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]), textResponse('done'), ]) - const ctx = await harness(adapter) + const ctx = await harness(adapter, 1) const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock', maxParallelToolCalls: 1 }) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 1) await new Promise(r => setTimeout(r, 5)) @@ -275,7 +268,7 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => await waitForIdle(ctx, agent) }) - it('applies the factory-wide Config default to agents that set no per-agent cap', async () => { + it('applies the global Config cap to every agent created by the factory', async () => { const adapter = new MockAdapter([ multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]), textResponse('done'), @@ -286,14 +279,12 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => await ctx.plugin(SystemPrompt, { persona: '' }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - // Factory default of 1 (no per-agent cap set below) must serialize. + // The global cap of 1 must serialize every agent from this factory. await ctx.plugin(AgentLoop, { agents: [], maxParallelToolCalls: 1 }) ctx.llm.registerAdapter(['mock'], adapter) const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - expect(agent.options.maxParallelToolCalls).toBe(1) - agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 1) await new Promise(r => setTimeout(r, 5)) @@ -304,18 +295,6 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => await waitForIdle(ctx, agent) }) - it('lets a per-agent cap override the factory-wide Config default', async () => { - const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt, { persona: '' }) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentLoop, { agents: [], maxParallelToolCalls: 1 }) - ctx.llm.registerAdapter(['mock'], new MockAdapter([])) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock', maxParallelToolCalls: 4 }) - expect(agent.options.maxParallelToolCalls).toBe(4) - }) }) describe('tool-call scheduler: ordered middleware and additionalContext', () => { @@ -349,7 +328,7 @@ describe('tool-call scheduler: ordered middleware and additionalContext', () => multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]), textResponse('done'), ]) - const ctx = await harness(adapter) + const ctx = await harness(adapter, 2) const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) ctx.on('tools/post-execute', async (exec, _result): Promise => @@ -467,14 +446,14 @@ describe('tool-call scheduler: abort handling', () => { multiCall([1, 2, 3, 4].map(n => ({ id: `c${n}`, name: 'p', args: { id: String(n) } }))), textResponse('should never be requested'), ]) - const ctx = await harness(adapter) + const ctx = await harness(adapter, 2) const gated = gatedParallelTool('p') ctx.tools.register(gated.tool) ctx.on('tools/post-execute', async (exec, _result, next): Promise => ({ ...await next(), additionalContext: { content: [{ type: 'text', text: `ctx-${exec.callId}` }], source: { kind: 'plugin', plugin: 'p' } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock', maxParallelToolCalls: 2 }) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 2) @@ -500,7 +479,7 @@ describe('tool-call scheduler: abort handling', () => { ]), textResponse('should never be requested'), ]) - const ctx = await harness(adapter) + const ctx = await harness(adapter, 2) const gated = gatedParallelTool('p') const exclusive: string[] = [] ctx.tools.register(gated.tool) @@ -510,7 +489,7 @@ describe('tool-call scheduler: abort handling', () => { parameters: { id: { type: 'string', required: true } }, async execute(args) { exclusive.push(args.id); return [{ type: 'text', text: 'x' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock', maxParallelToolCalls: 2 }) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await until(() => gated.started.length === 2) diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index d157a5158b..dd705e8d8d 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -15,7 +15,6 @@ The plugin injects `agents`, `sessions`, `sessionPersistence`, `tools`, and `use | Key | Default | Meaning | |---|---|---| | `model` | — | Model name for created agents (must have a registered adapter). | -| `maxParallelToolCalls` | (agent-loop default) | Positive integer cap on tool calls each created agent runs concurrently within one assistant step; `1` is fully serial. | (No persona key: `dsh-system-prompt`'s own `persona` config supplies the global default section, so ACP-created agents render it without the bridge carrying prompt text. An agent-scoped same-name section may still shadow that default.) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index ca6e31d008..c464ffd22b 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -203,17 +203,12 @@ function stringArrayContent( export interface AcpConfig { /** Model name for created agents (must have a registered adapter). */ model?: string - /** Positive-integer concurrent tool-call cap for each created agent; `1` is serial. */ - maxParallelToolCalls?: number /** Runtime-only transport override for tests; production uses stdio. */ stream?: Stream } export const Config: Schema = Schema.object({ model: Schema.string(), - // A positive integer; a bad value (0, negative, fractional) fails config - // validation here rather than being silently dropped from cordis.yml. - maxParallelToolCalls: Schema.number().step(1).min(1), }) /** Per-session bridge state keyed by ACP session id. */ @@ -856,13 +851,12 @@ export function apply(ctx: Context, config: AcpConfig): void { * Build per-agent options from the plugin config, omitting absent fields * (exactOptionalPropertyTypes: never assign `undefined` to an optional key). * Exported for unit coverage of both the present and absent branches. - * @param config - the plugin config carrying the optional model name and parallel cap. - * @returns the per-agent options, with each field present only when configured. + * @param config - the plugin config carrying the optional model name. + * @returns the per-agent options, with `model` present only when configured. */ -export function agentOptions(config: AcpConfig): { model?: string; maxParallelToolCalls?: number } { +export function agentOptions(config: AcpConfig): { model?: string } { return { ...config.model !== undefined ? { model: config.model } : {}, - ...config.maxParallelToolCalls !== undefined ? { maxParallelToolCalls: config.maxParallelToolCalls } : {}, } } diff --git a/packages/ui/acp/tests/stream-update.spec.ts b/packages/ui/acp/tests/stream-update.spec.ts index 1112cc3808..2afa49e1d4 100644 --- a/packages/ui/acp/tests/stream-update.spec.ts +++ b/packages/ui/acp/tests/stream-update.spec.ts @@ -794,7 +794,5 @@ describe('agentOptions', () => { it('includes only the fields present in config', () => { expect(agentOptions({})).toEqual({}) expect(agentOptions({ model: 'm' })).toEqual({ model: 'm' }) - expect(agentOptions({ maxParallelToolCalls: 3 })).toEqual({ maxParallelToolCalls: 3 }) - expect(agentOptions({ model: 'm', maxParallelToolCalls: 1 })).toEqual({ model: 'm', maxParallelToolCalls: 1 }) }) }) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 853abd52e2..5c37043b42 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -26,7 +26,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | Key | Default | Routed to | |---|---|---| | `model` | (required) | the pre-created `main` agent's model | -| `maxParallelToolCalls` | agent-loop default | positive-integer concurrent tool-call cap for the `main` agent; `1` is serial | +| `maxParallelToolCalls` | agent-loop default | positive-integer concurrent tool-call cap shared by the bundled loop's agents; `1` is serial | | `persona` | — | the deployment persona template (may reference `{{model}}`/`{{cwd}}`), routed to `dsh-system-prompt` | | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | | `tools` | `{ mode: 'native' }` | tool-registry presentation config (`native` / `code` / `both`), routed through `dsh-agent-core` | diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 65b38a0fd4..c3d6192a4b 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -37,9 +37,8 @@ export interface Config { /** Model name for the `main` agent (must have a registered adapter). */ model: string /** - * Maximum tool calls the `main` agent runs concurrently within one assistant - * step (a positive integer; the agent loop defaults it when omitted). `1` - * preserves fully serial execution. + * Concurrent parallel-safe tool-call cap for the bundled agent loop. A + * positive integer; the loop defaults it when omitted and `1` is serial. */ maxParallelToolCalls?: number /** Deployment persona (the system-prompt plugin's `persona` config). */ @@ -94,11 +93,11 @@ export function apply(ctx: Context, config: Config): void { ...config.persona !== undefined ? { persona: config.persona } : {}, ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {}, ...config.tools !== undefined ? { tools: config.tools } : {}, + ...config.maxParallelToolCalls !== undefined ? { maxParallelToolCalls: config.maxParallelToolCalls } : {}, agents: [{ id: AgentId('main'), model: config.model, cwd: process.cwd(), - ...config.maxParallelToolCalls !== undefined ? { maxParallelToolCalls: config.maxParallelToolCalls } : {}, ...config.resumeSessionId !== undefined ? { resumeSessionId: SessionId(config.resumeSessionId) } : {}, }], ...config.skills !== undefined ? { skills: config.skills } : {}, diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 54853b7ca1..b5438caf77 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -126,14 +126,14 @@ describe('dsh-stdio-agent app', () => { await ctx.fiber.dispose() }) - it('forwards maxParallelToolCalls onto the pre-created agent when set', async () => { + it('forwards maxParallelToolCalls to the bundled agent loop', async () => { const ctx = await mount({ model: 'mock', maxParallelToolCalls: 3, persistenceRoot: '/tmp/dsh-stdio-agent-spec-parallel', skills: await isolatedSkillsConfig(), }) - expect(ctx.get('agents')?.get(AgentId('main'))?.options.maxParallelToolCalls).toBe(3) + expect(ctx.get('agentLoop')?.config.maxParallelToolCalls).toBe(3) await ctx.fiber.dispose() }) From 6d96b3e4a85ca2c14ae68d6f234dbb8def456fe0 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 14:38:24 +0800 Subject: [PATCH 204/359] refactor(token-meter): merge measurement snapshots (round 1) --- docs/cordis-catalog/services.md | 3 +- docs/core-data-structures/token-meter.md | 21 ++--- ...07-15-replay-token-meter-service.i18n.yaml | 4 +- .../2026-07-15-replay-token-meter-service.md | 11 ++- ...026-07-15-replay-token-meter-service.zh.md | 11 ++- packages/compact/compact-basic/src/index.ts | 8 +- packages/compact/compact-basic/src/region.ts | 16 ++-- .../compact-basic/tests/compact-basic.spec.ts | 22 +++-- .../cordis/tool-cordis/src/api-catalog.ts | 7 +- packages/llm/token-meter/README.md | 8 +- packages/llm/token-meter/src/index.ts | 23 ++--- packages/llm/token-meter/src/types.ts | 16 ++-- .../llm/token-meter/tests/token-meter.spec.ts | 83 ++++++++++++++----- scripts/type-equiv.manifest.json | 1 - 14 files changed, 119 insertions(+), 115 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index d57f0ed9c5..7bccc15778 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -267,13 +267,12 @@ Replay owner for one service-wide estimator and isolated per-session folds. ```ts cordis-catalog measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement -measureSurface(session: Session): TokenSurfaceMeasurement estimateMessage(message: Message): number ``` Types: [Message](../core-data-structures/core.md) -Source: [`packages/llm/token-meter/src/index.ts:107`](../../packages/llm/token-meter/src/index.ts) +Source: [`packages/llm/token-meter/src/index.ts:106`](../../packages/llm/token-meter/src/index.ts) ## `ctx.tools` — `ToolRegistry` diff --git a/docs/core-data-structures/token-meter.md b/docs/core-data-structures/token-meter.md index eee01c27b8..a6e70f56f6 100644 --- a/docs/core-data-structures/token-meter.md +++ b/docs/core-data-structures/token-meter.md @@ -1,6 +1,6 @@ # Token Meter -`@deepseek-ai/dsh-token-meter` exposes detached replay measurements for request pressure and positional surface pricing. Scalar and surface snapshots carry the number of durable events consumed as `logRevision`; consumers compare revisions before making a joint decision. +`@deepseek-ai/dsh-token-meter` exposes one detached replay snapshot for request pressure and positional surface pricing. `logRevision` is the number of durable events consumed for every field in the measurement. Source: [`packages/llm/token-meter/src/types.ts`](../../packages/llm/token-meter/src/types.ts) @@ -16,10 +16,14 @@ interface TokenMeasurement { readonly surfaceDeltaTokens: number /** Non-negative current request-and-response pressure. */ readonly totalTokens: number + /** Total heuristic tokens across the current surface. */ + readonly surfaceTokens: number + /** Current surface nodes in positional head-to-tail order. */ + readonly nodes: readonly TokenSurfaceNode[] } ``` -`baseline.kind === 'usage'` means the latest successful provider call has the same canonical request envelope. `estimated` means the service priced the complete envelope and surface with its fixed heuristic. A later successful request replaces the earlier anchor; signed `surfaceDeltaTokens` preserves growth and shrinkage relative to a matching anchor. +`baseline.kind === 'usage'` means the latest successful provider call has the same canonical request envelope. `estimated` means the service priced the complete envelope and surface with its fixed heuristic. A later successful request replaces the earlier anchor; signed `surfaceDeltaTokens` preserves growth and shrinkage relative to a matching anchor. `totalTokens` remains request-and-response pressure, while `surfaceTokens` is the surface-only heuristic total and equals the sum of the node prices. ## `TokenSurfaceNode` @@ -32,17 +36,4 @@ interface TokenSurfaceNode { } ``` -## `TokenSurfaceMeasurement` - -```ts type-equiv -interface TokenSurfaceMeasurement { - /** Number of durable events consumed; equal to the next unread event seq. */ - readonly logRevision: number - /** Total heuristic tokens across the current surface. */ - readonly totalTokens: number - /** Current surface nodes in positional head-to-tail order. */ - readonly nodes: readonly TokenSurfaceNode[] -} -``` - Surface order is authoritative; replacement nodes can have higher durable seqs than later positional nodes. The snapshot is immutable and does not grow when the underlying replay fold advances. diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml index afd99ac686..cb5affaaf7 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-replay-token-meter-service.md: 981e789a51bbe7e2b09d47a76d71ac79fe14c999 -2026-07-15-replay-token-meter-service.zh.md: 85565b6f3db77ab81712f9c128e570c7a16bae8d +2026-07-15-replay-token-meter-service.md: 5a3ffe61bef73eeffd3441291d3ae997f0e092fd +2026-07-15-replay-token-meter-service.zh.md: e6a2e1163ac0803cd87b917f9d2a14ad2372c2f0 diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md index 981e789a51..5a3ffe61be 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md @@ -14,7 +14,7 @@ Provider usage is not a complete answer. It describes one successful call under ### One concrete LLM-family service -`@deepseek-ai/dsh-token-meter` is one concrete package under `packages/llm/` and registers `ctx.tokenMeter`. It is not split into an interface and backend before a second implementation exists. `TokenMeterService` itself exposes `contextWindow`, `measure(session, requestHeader?)`, `measureSurface(session)`, and `estimateMessage(message)`; consumers call the singleton service directly. +`@deepseek-ai/dsh-token-meter` is one concrete package under `packages/llm/` and registers `ctx.tokenMeter`. It is not split into an interface and backend before a second implementation exists. `TokenMeterService` itself exposes `contextWindow`, `measure(session, requestHeader?)`, and `estimateMessage(message)`; consumers call the singleton service directly. The service has one `contextWindow`, defaulting to 128,000 tokens and configurable as a positive integer. Estimation uses a fixed four-characters-per-token heuristic plus structural overhead. There are no model profiles, density settings, tokenizer backends, or language-specific strategies. @@ -22,7 +22,7 @@ The service has one `contextWindow`, defaulting to 128,000 tokens and configurab Each session owns one isolated incremental fold. Active folds advance from `session/event`; every read catches up through the durable tail, so listener ordering, seeded sessions, and service reload do not change the answer. The fold tracks canonical request headers and deltas, step boundaries, surface appends and replacements, assistant usage, and assistant-chunk provenance. A malformed next event fails transactionally and remains unread rather than partially mutating state. -`measure(session, requestHeader?)` returns scalar pressure. `measureSurface(session)` returns positional per-node prices for retention and replacement decisions. `estimateMessage(message)` applies the fixed heuristic without session state. Results are detached, deeply immutable snapshots carrying `logRevision`; a consumer compares scalar and surface revisions before making one decision. +`measure(session, requestHeader?)` synchronizes the fold once and returns scalar pressure together with positional per-node prices. `totalTokens` remains request-and-response pressure; `surfaceTokens` is the surface-only heuristic total and equals the sum of `nodes[].tokens`. A `requestHeader` override changes pressure pricing only, while the surface fields always describe the current session. `estimateMessage(message)` applies the fixed heuristic without session state. Each result is one detached, deeply immutable snapshot carrying one `logRevision`. Every measurement clones the current nodes and is therefore O(surface). Provider usage is reused only when the measured canonical request envelope equals the latest successful-call anchor. Any model, system, prefix, tool, or call-config change causes complete heuristic repricing. Surface changes remain a signed delta from a matching anchor, including negative values after a shrinking replacement. A later successful request replaces the earlier anchor, including across model switches. @@ -32,20 +32,22 @@ Usage sums the disjoint input, cache-read, cache-write, and output buckets. Reas `dsh-compact-basic` requires `ctx.tokenMeter`; `CompactService` gains no token methods or types. The backend is factored into configuration, automatic triggering, region transaction, and summarizer modules, while `summarize()` remains its sole subclass hook. The singleton service consistently prices pressure, retention, shadowed content, provenance, and non-shrinking-summary rejection. +Automatic compaction uses one unified measurement for each threshold-and-retention decision. The region transaction measures after appending its durable `compact/start` lock and again after asynchronous summarization; any intervening durable append changes `logRevision` and prevents replacement. + Compact policy has service-wide defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, summarization model `''`, maximum summary output `8192`, one extra compaction attempt, and automatic triggering enabled. Top-level `thresholdRatio` and `retainTokens` override the pressure policy; retention must remain below the resulting threshold. Empty summarization model resolves the latest logged routed model, then `AgentOptions.model`. The pre-step trigger measures a provisional envelope: the current prompt and prefix override logged values, while the latest logged header supplies model, tools, and other call config. A model-less router-only agent skips that provisional check because `agent/request` can route later; any routed model name can use the singleton estimator. ## Testing -Unit coverage pins service configuration, fixed estimation, envelope invalidation, latest-anchor replacement across model switches, usage and missing-usage paths, seeded append/replace replay, signed deltas, provenance modes, malformed boundaries, immutable snapshots, listener ordering, reload, compact defaults, routing fallback, retention, convergence, and transaction rollback. A real Loader/Include YAML fixture loads the exact zero-config token-meter and compact-basic package names in dependency order. +Unit coverage pins service configuration, fixed estimation, envelope invalidation, latest-anchor replacement across model switches, usage and missing-usage paths, seeded append/replace replay, signed deltas, provenance modes, malformed boundaries, unified snapshot detachment and deep immutability, surface-total equality, listener ordering, reload, compact defaults, routing fallback, one-call automatic decisions, retention, convergence, and log-revision rollback. A real Loader/Include YAML fixture loads the exact zero-config token-meter and compact-basic package names in dependency order. ## Alternatives considered - **Keep estimation inside `CompactService`** — rejected because measurement has consumers and replay semantics independent of compaction; it would also force every compactor to expose the same unrelated API. - **Split a token-meter interface from a heuristic backend immediately** — rejected because only one implementation exists. One concrete service preserves the future seam without speculative packages or configuration. - **Keep model-keyed windows and density profiles** — rejected because the deployment currently has one context policy and one estimator. Model registries, unknown-model failures, and configurable density add branches without a second behavior to select. -- **Copy complete history into each scalar result** — rejected because below-threshold reads are common. Immutable revisioned scalars and a separate surface snapshot preserve consistency without an O(history) copy. +- **Keep separate scalar and surface measurements** — rejected because callers would need two reads and revision matching for one decision. A scalar-only read could avoid cloning nodes below threshold, but the split API introduces a caller-side race window; the unified snapshot accepts O(surface) cloning in exchange for coherence. - **Treat provider usage as portable between envelopes** — rejected because model, tools, prefixes, and call config are request facts. Mismatch reprices the whole current request. ## Consequences @@ -53,5 +55,6 @@ Unit coverage pins service configuration, fixed estimation, envelope invalidatio - Token pressure has one replay-aware owner that compaction and future plugins can share. - The default makes the bundled composition usable with two zero-config plugin entries; deployments override one context capacity when needed. - Fixed heuristic pricing remains an estimate of provider behavior and is not an exact tokenizer or request serializer. +- Every measurement clones the current positional surface and therefore costs O(surface), including pressure checks that finish below threshold. - Measurements fail loudly on malformed durable boundaries. This turns corrupted replay into a named integration failure instead of silently drifting pressure. - The pre-step compact integration can skip a router-only first check and can miss tool or routing changes applied later in request middleware. diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md index 85565b6f3d..e6a2e1163a 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md @@ -14,7 +14,7 @@ Status: implemented ### 一个具体的 LLM 家族服务 -`@deepseek-ai/dsh-token-meter` 是 `packages/llm/` 下的单个具体包，并注册 `ctx.tokenMeter`。在第二种实现出现之前，它不会被拆成接口与后端。`TokenMeterService` 本身公开 `contextWindow`、`measure(session, requestHeader?)`、`measureSurface(session)` 与 `estimateMessage(message)`；消费方直接调用这个单例服务。 +`@deepseek-ai/dsh-token-meter` 是 `packages/llm/` 下的单个具体包，并注册 `ctx.tokenMeter`。在第二种实现出现之前，它不会被拆成接口与后端。`TokenMeterService` 本身公开 `contextWindow`、`measure(session, requestHeader?)` 与 `estimateMessage(message)`；消费方直接调用这个单例服务。 服务只有一个 `contextWindow`，默认值为 128,000 token，并允许配置为正整数。估算采用固定的每 token 四个字符启发式规则，并加上结构开销。服务不提供模型 profile、密度设置、分词器后端或语言专用策略。 @@ -22,7 +22,7 @@ Status: implemented 每个会话都有一个隔离的增量折叠。活跃折叠通过 `session/event` 前进；每次读取都会追到持久日志尾部，因此监听器顺序、种子会话与服务重载不会改变答案。折叠跟踪规范请求头及其增量、步骤边界、表层追加与替换、assistant usage，以及 assistant 分片来源。下一个畸形事件会以事务方式失败并保持未读，不会让状态只修改一半。 -`measure(session, requestHeader?)` 返回标量压力。`measureSurface(session)` 返回用于保留与替换决策的逐位置节点价格。`estimateMessage(message)` 不依赖会话状态，直接应用固定启发式规则。结果是分离且深度不可变的快照，并携带 `logRevision`；消费方在一次联合决策前比较标量与表层修订号。 +`measure(session, requestHeader?)` 只同步一次折叠，并在返回标量压力的同时给出逐位置节点价格。`totalTokens` 仍表示请求与响应压力；`surfaceTokens` 是仅针对表层的启发式总量，并等于 `nodes[].tokens` 之和。`requestHeader` 覆盖只改变压力定价，表层字段始终描述当前会话。`estimateMessage(message)` 不依赖会话状态，直接应用固定启发式规则。每个结果都是一个分离且深度不可变的快照，只携带一个 `logRevision`。每次计量都会复制当前节点，因此成本为 O(surface)。 只有当待计量的规范请求信封等于最近一次成功调用的锚点时，服务才复用提供方 usage。模型、系统提示词、前缀、工具或调用配置任一变化都会触发完整的启发式重新定价。表层变化相对匹配锚点保留有符号增量，包括缩小替换后的负值。后续成功请求会替换先前锚点，模型切换时也一样。 @@ -32,20 +32,22 @@ Usage 会对互不重叠的输入、缓存读取、缓存写入与输出 bucket `dsh-compact-basic` 要求 `ctx.tokenMeter`；`CompactService` 不增加 token 方法或类型。后端拆分为配置、自动触发、区域事务与摘要器模块，而 `summarize()` 仍是唯一的子类 hook。单例服务一致用于压力、保留、被遮蔽内容、来源以及非缩小摘要拒绝的定价。 +自动压缩的每次阈值与保留联合决策只使用一次统一计量。区域事务先追加持久 `compact/start` 锁，再执行一次计量，并在异步摘要完成后再次计量；期间任何持久追加都会改变 `logRevision`，从而阻止替换。 + 压缩策略采用服务级默认值：阈值比例 `0.8`、保留尾部 `floor(contextWindow × 0.16)`、摘要模型 `''`、摘要最大输出 `8192`、一次额外压缩尝试，以及启用自动触发。顶层 `thresholdRatio` 与 `retainTokens` 覆盖压力策略；保留值必须小于最终阈值。空摘要模型先解析最近记录的实际路由模型，再使用 `AgentOptions.model`。 pre-step 触发器计量临时请求信封：当前提示词与前缀覆盖日志值，最近记录的请求头提供模型、工具及其他调用配置。没有模型的纯路由 agent（智能体）会跳过该临时检查，因为 `agent/request` 仍可稍后路由；任意路由模型名都可使用这个单例估算器。 ## 测试 -单元覆盖固定服务配置、固定估算、信封失效、模型切换时替换最新锚点、有无 usage 的路径、种子追加/替换回放、有符号增量、来源模式、畸形边界、不可变快照、监听器顺序、重载、压缩默认值、路由回退、保留、收敛与事务回滚。真实 Loader/Include YAML fixture 按依赖顺序加载精确的零配置 token-meter 与 compact-basic 包名称。 +单元覆盖固定服务配置、固定估算、信封失效、模型切换时替换最新锚点、有无 usage 的路径、种子追加/替换回放、有符号增量、来源模式、畸形边界、统一快照的分离性与深度不可变性、表层总量相等性、监听器顺序、重载、压缩默认值、路由回退、自动决策单次调用、保留、收敛与日志修订回滚。真实 Loader/Include YAML fixture 按依赖顺序加载精确的零配置 token-meter 与 compact-basic 包名称。 ## 考虑过的替代方案 - **把估算保留在 `CompactService` 内**——不予采纳，因为计量拥有独立于压缩的消费方与回放语义；它还会强迫每个压缩器暴露同一套无关 API。 - **立即把 token meter 拆成接口与启发式后端**——不予采纳，因为目前只有一种实现。单个具体服务保留未来接缝，同时避免推测性的包与配置。 - **保留模型键控的窗口与密度 profile**——不予采纳，因为当前部署只有一种上下文策略与一个估算器。模型注册表、未知模型错误和可配置密度只增加分支，却没有第二种行为可供选择。 -- **在每个标量结果中复制完整历史**——不予采纳，因为低于阈值的读取很常见。不可变且带修订号的标量与独立表层快照，在不进行 O(history) 复制的情况下保持一致性。 +- **保留独立的标量与表层计量**——不予采纳，因为消费方必须为一次决策执行两次读取并匹配修订号。仅读取标量可以避免在低于阈值时复制节点，但拆分 API 会在消费方引入竞态窗口；统一快照接受 O(surface) 复制成本，以换取结果一致性。 - **在不同信封之间移用提供方 usage**——不予采纳，因为模型、工具、前缀与调用配置都是请求事实。不匹配时会重新定价完整当前请求。 ## 后果 @@ -53,5 +55,6 @@ pre-step 触发器计量临时请求信封：当前提示词与前缀覆盖日 - Token 压力拥有一个可供压缩与未来插件共享的回放感知所有者。 - 默认值让内置组合只需两个零配置插件条目即可使用；部署需要时只覆盖一个上下文容量。 - 固定启发式定价仍然只是提供方行为的估计，并不是精确分词器或请求序列化器。 +- 每次计量都会复制当前的位置表层，因此成本为 O(surface)，低于阈值即可结束的压力检查也不例外。 - 遇到畸形持久边界时，计量会明确失败。这会把损坏的回放转化为具名集成错误，而不是让压力静默漂移。 - pre-step 压缩集成可能跳过纯路由的首次检查，也可能错过请求中间件稍后应用的工具或路由变化。 diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index 16387c5e09..285ad5163e 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -123,13 +123,7 @@ export class BasicCompactService extends CompactService { let result: CompactionResult | null = null for (let attempt = 0; attempt <= this.config.compactionRetries; attempt += 1) { - const surface = meter.measureSurface(agent.session) - if (surface.logRevision !== measurement.logRevision) { - throw new Error( - `compaction: pressure revision ${measurement.logRevision} does not match surface revision ${surface.logRevision}`, - ) - } - const range = selectCompactableRange(agent.session, surface, this.config.retainTokens) + const range = selectCompactableRange(agent.session, measurement, this.config.retainTokens) if (range === null) { /* v8 ignore else -- concrete replacement preserves a compactable checkpoint; subclass hooks cannot mutate it. */ if (result === null) return null diff --git a/packages/compact/compact-basic/src/region.ts b/packages/compact/compact-basic/src/region.ts index 83ed04a3eb..60bec61048 100644 --- a/packages/compact/compact-basic/src/region.ts +++ b/packages/compact/compact-basic/src/region.ts @@ -10,7 +10,7 @@ import { toolPairingBalancedBefore, } from '@deepseek-ai/dsh-compact' import type { CompactionResult } from '@deepseek-ai/dsh-compact' -import type { TokenMeterService, TokenSurfaceMeasurement } from '@deepseek-ai/dsh-token-meter' +import type { TokenMeasurement, TokenMeterService } from '@deepseek-ai/dsh-token-meter' import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' import type { Agent } from '@deepseek-ai/dsh-agent' import { frameSummary } from './summarizer.ts' @@ -25,16 +25,16 @@ interface RegionDependencies { * Resolve the next head-anchored range while retaining a priced recent tail * and never splitting an assistant tool-call/result pair. * @param session - session supplying authoritative current surface positions. - * @param pricedSurface - same-revision surface measurement from the conversation meter. + * @param measurement - unified pressure and surface measurement from the conversation meter. * @param retainTokens - minimum recent tail budget retained verbatim. * @returns the inclusive positional seq range to compact, or `null`. */ export function selectCompactableRange( session: Session, - pricedSurface: TokenSurfaceMeasurement, + measurement: TokenMeasurement, retainTokens: number, ): { start: number; end: number } | null { - const pricedNodes = pricedSurface.nodes + const pricedNodes = measurement.nodes if (pricedNodes.length === 0) return null const surfaceNodes = session.surface.nodes @@ -115,8 +115,8 @@ export async function compactSurfaceRegion( try { // Capture after the lock event so any later durable append, including a // log-only one, invalidates the async selection before replacement. - const lockedSurface = dependencies.meter.measureSurface(session) - const selected = lockedSurface.nodes.slice(startIdx, endIdx + 1) + const lockedMeasurement = dependencies.meter.measure(session) + const selected = lockedMeasurement.nodes.slice(startIdx, endIdx + 1) if (selected.length !== shadowedSeqs.length || selected.some((node, index) => node.seq !== shadowedSeqs[index])) { throw new Error('compaction: selected surface changed before summarization began') @@ -125,8 +125,8 @@ export async function compactSurfaceRegion( const text = renderTranscript(session.events, shadowedSeqs) const { summary, model, maxTokens } = await dependencies.summarize(text, agent, signal) - const currentSurface = dependencies.meter.measureSurface(session) - if (currentSurface.logRevision !== lockedSurface.logRevision) { + const currentMeasurement = dependencies.meter.measure(session) + if (currentMeasurement.logRevision !== lockedMeasurement.logRevision) { throw new Error('compaction: session log changed during summarization') } const framedSummary = frameSummary(summary) diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index ffc60ef024..486955b187 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -251,17 +251,15 @@ describe('pressure measurement and retention', () => { expect(await compactIfNeeded(compact, retained, MODEL, 'x'.repeat(100_000))).toBeNull() }) - it('detects scalar/surface revision disagreement', async () => { + it('uses one unified measurement for each pressure-and-retention decision', async () => { const ctx = createContext() - const meter = ctx.tokenMeter - const original = meter.measureSurface.bind(meter) - vi.spyOn(meter, 'measureSurface').mockImplementation((session) => { - const measurement = original(session) - return { ...measurement, logRevision: measurement.logRevision - 1 } - }) const compact = service(compactConfig, ctx) + const measure = vi.spyOn(ctx.tokenMeter, 'measure') + const stop = new Error('stop after first decision') + vi.spyOn(compact, 'compactRegion').mockRejectedValueOnce(stop) - await expect(compactIfNeeded(compact, conversation(4))).rejects.toThrow(/revision/) + await expect(compactIfNeeded(compact, conversation(4))).rejects.toBe(stop) + expect(measure).toHaveBeenCalledTimes(1) }) it('bounds retries when a shrinking checkpoint remains above threshold', async () => { @@ -303,7 +301,7 @@ describe('pressure measurement and retention', () => { it('rejects a priced surface that is not the current positional surface', () => { const ctx = createContext() const session = conversation(2) - const priced = ctx.tokenMeter.measureSurface(session) + const priced = ctx.tokenMeter.measure(session) expect(() => selectCompactableRange(session, { ...priced, nodes: priced.nodes.slice(1), @@ -331,7 +329,7 @@ describe('pressure measurement and retention', () => { }, { surfaceOp: 'append' }) session.append('step/end', { turn: 1, step: 1 }) - const priced = ctx.tokenMeter.measureSurface(session) + const priced = ctx.tokenMeter.measure(session) expect(selectCompactableRange(session, priced, 1)).toBeNull() }) }) @@ -474,8 +472,8 @@ describe('compaction region transaction', () => { it('rejects a meter snapshot that changed before summarization began', async () => { const ctx = createContext() const meter = ctx.tokenMeter - const original = meter.measureSurface.bind(meter) - vi.spyOn(meter, 'measureSurface').mockImplementationOnce((session) => { + const original = meter.measure.bind(meter) + vi.spyOn(meter, 'measure').mockImplementationOnce((session) => { const measurement = original(session) return { ...measurement, nodes: measurement.nodes.slice(1) } }) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 6edd2b809e..07ee50b95f 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -227,7 +227,6 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ summary: 'Replay owner for one service-wide estimator and isolated per-session folds.', methods: [ 'measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement', - 'measureSurface(session: Session): TokenSurfaceMeasurement', 'estimateMessage(message: Message): number', ], }, @@ -992,16 +991,12 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'TokenMeasurement', - declaration: 'export interface TokenMeasurement {\n readonly logRevision: number;\n readonly baseline: TokenMeasurementBaseline;\n readonly surfaceDeltaTokens: number;\n readonly totalTokens: number;\n}', + declaration: 'export interface TokenMeasurement {\n readonly logRevision: number;\n readonly baseline: TokenMeasurementBaseline;\n readonly surfaceDeltaTokens: number;\n readonly totalTokens: number;\n readonly surfaceTokens: number;\n readonly nodes: readonly TokenSurfaceNode[];\n}', }, { name: 'TokenMeasurementBaseline', declaration: 'export type TokenMeasurementBaseline = {\n readonly kind: \'none\';\n readonly tokens: 0;\n} | {\n readonly kind: \'estimated\';\n readonly tokens: number;\n} | {\n readonly kind: \'usage\';\n readonly tokens: number;\n readonly usage: Readonly;\n};', }, - { - name: 'TokenSurfaceMeasurement', - declaration: 'export interface TokenSurfaceMeasurement {\n readonly logRevision: number;\n readonly totalTokens: number;\n readonly nodes: readonly TokenSurfaceNode[];\n}', - }, { name: 'TokenSurfaceNode', declaration: 'export interface TokenSurfaceNode {\n readonly seq: number;\n readonly tokens: number;\n}', diff --git a/packages/llm/token-meter/README.md b/packages/llm/token-meter/README.md index 3beaff1506..4b2a03833e 100644 --- a/packages/llm/token-meter/README.md +++ b/packages/llm/token-meter/README.md @@ -12,13 +12,12 @@ The estimator intentionally uses one fixed heuristic: four characters per token ## Measurement contract -`ctx.tokenMeter` directly exposes three operations: +`ctx.tokenMeter` directly exposes two operations: -- `measure(session, requestHeader?)` returns scalar request pressure at one consumed-log revision. -- `measureSurface(session)` returns current surface nodes and their per-node prices at the same kind of revision. +- `measure(session, requestHeader?)` returns request pressure and the current priced surface at one consumed-log revision. - `estimateMessage(message)` prices one message with the fixed heuristic. -Measurements are detached and deeply immutable. A caller that needs a consistent scalar/surface decision compares their `logRevision` values instead of copying the full history on every read. +`measure()` synchronizes once and returns one detached, deeply immutable snapshot. `totalTokens` is request-and-response pressure, while `surfaceTokens` is the surface-only heuristic total and equals the sum of `nodes[].tokens`. A `requestHeader` override affects pressure fields only; the surface fields still describe the current session. Every call clones the positional nodes, so measurement is O(surface). The fold tracks request headers and deltas, step boundaries, surface appends and replacements, successful assistant messages, provider usage, and assistant-chunk provenance. Provider usage is reused only when the latest successful call's canonical request envelope matches the measured envelope; a later success replaces the earlier anchor. Otherwise the complete current envelope and surface are estimated. Surface changes remain signed relative to a matching anchor, including negative deltas after shrinking replacements. @@ -46,5 +45,6 @@ Indirectly, through consumers such as `dsh-compact-basic`; the service itself ad ## Known Limitations and Deferred Work - **The fixed heuristic is approximate** — content without reusable provider usage is priced by character count plus structural overhead, not an exact provider tokenizer or request serializer. +- **Every measurement clones the current surface** — coherent immutable snapshots make reads O(surface), including below-threshold pressure checks. - **Provider usage is only reusable for an identical canonical envelope** — prompt, prefix, tools, model, or call-config changes deliberately fall back to full heuristic estimation. - **Legacy provenance is conservative** — assistant messages without `sourceEventSeqs` cannot distinguish provider output from listener rewrites, so the fold avoids claiming a known empty or exact chunk stream. diff --git a/packages/llm/token-meter/src/index.ts b/packages/llm/token-meter/src/index.ts index aa88831033..3c446f4778 100644 --- a/packages/llm/token-meter/src/index.ts +++ b/packages/llm/token-meter/src/index.ts @@ -14,7 +14,6 @@ import type { TokenMeasurement, TokenMeasurementBaseline, TokenMeterConfig, - TokenSurfaceMeasurement, TokenSurfaceNode, } from './types.ts' @@ -126,15 +125,19 @@ export class TokenMeterService extends Service { } /** - * Measure current request pressure through the session's durable tail. + * Measure current request pressure and surface through the durable tail. * * Provider usage is reused only when the latest successful call's canonical * request envelope matches `requestHeader`; otherwise the complete envelope * and surface are heuristically repriced. * + * `requestHeader` affects request pressure only; surface fields always + * describe the current session surface. Every call clones those positional + * nodes, so measurement is O(surface). + * * @param session - session to replay through its current durable tail. * @param requestHeader - optional effective request envelope replacing the latest logged header. - * @returns a detached deeply immutable pressure measurement. + * @returns a detached deeply immutable pressure and surface measurement. */ measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement { const state = this._sync(session) @@ -164,19 +167,7 @@ export class TokenMeterService extends Service { baseline, surfaceDeltaTokens, totalTokens: Math.max(0, baseline.tokens + surfaceDeltaTokens), - })) - } - - /** - * Price the current surface for retention and replacement decisions. - * @param session - session to replay through its current durable tail. - * @returns a detached deeply immutable positional surface measurement. - */ - measureSurface(session: Session): TokenSurfaceMeasurement { - const state = this._sync(session) - return deepFreeze(structuredClone({ - logRevision: state.consumedEvents, - totalTokens: state.surfaceTokens, + surfaceTokens: state.surfaceTokens, nodes: state.surface, })) } diff --git a/packages/llm/token-meter/src/types.ts b/packages/llm/token-meter/src/types.ts index 1f2c2f68f2..7fb35af997 100644 --- a/packages/llm/token-meter/src/types.ts +++ b/packages/llm/token-meter/src/types.ts @@ -18,7 +18,7 @@ export type TokenMeasurementBaseline = | { readonly kind: 'estimated'; readonly tokens: number } | { readonly kind: 'usage'; readonly tokens: number; readonly usage: Readonly } -/** Detached immutable scalar pressure at one consumed session-log revision. */ +/** Detached immutable request-pressure and surface snapshot at one consumed log revision. */ export interface TokenMeasurement { /** Number of durable events consumed; equal to the next unread event seq. */ readonly logRevision: number @@ -28,6 +28,10 @@ export interface TokenMeasurement { readonly surfaceDeltaTokens: number /** Non-negative current request-and-response pressure. */ readonly totalTokens: number + /** Total heuristic tokens across the current surface. */ + readonly surfaceTokens: number + /** Current surface nodes in positional head-to-tail order. */ + readonly nodes: readonly TokenSurfaceNode[] } /** One token-priced node in the current ordered session surface. */ @@ -37,13 +41,3 @@ export interface TokenSurfaceNode { /** Heuristic tokens for the exact message projected by this node. */ readonly tokens: number } - -/** Detached immutable priced surface at one consumed session-log revision. */ -export interface TokenSurfaceMeasurement { - /** Number of durable events consumed; equal to the next unread event seq. */ - readonly logRevision: number - /** Total heuristic tokens across the current surface. */ - readonly totalTokens: number - /** Current surface nodes in positional head-to-tail order. */ - readonly nodes: readonly TokenSurfaceNode[] -} diff --git a/packages/llm/token-meter/tests/token-meter.spec.ts b/packages/llm/token-meter/tests/token-meter.spec.ts index 648eef01f5..18f78afad2 100644 --- a/packages/llm/token-meter/tests/token-meter.spec.ts +++ b/packages/llm/token-meter/tests/token-meter.spec.ts @@ -5,7 +5,7 @@ import type { ContentBlock, Message, TokenUsage } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId, canonicalHeader } from '@deepseek-ai/dsh-session' import type { EpochHeader } from '@deepseek-ai/dsh-session' import TokenMeterService from '@deepseek-ai/dsh-token-meter' -import type { TokenMeterConfig } from '@deepseek-ai/dsh-token-meter' +import type { TokenMeasurement, TokenMeterConfig } from '@deepseek-ai/dsh-token-meter' function header(model: string, extras: Omit = {}): EpochHeader { return canonicalHeader({ config: { model }, ...extras }) @@ -71,6 +71,11 @@ function meter(config: TokenMeterConfig = {}): TokenMeterService { return new TokenMeterService(new Context(), config) } +function expectSurfaceTotal(measurement: TokenMeasurement): void { + expect(measurement.nodes.reduce((total, node) => total + node.tokens, 0)) + .toBe(measurement.surfaceTokens) +} + describe('TokenMeterService configuration and registration', () => { it('provides one zero-config context window', () => { const service = meter() @@ -135,36 +140,48 @@ describe('TokenMeterService pricing', () => { baseline: { kind: 'none', tokens: 0 }, surfaceDeltaTokens: 0, totalTokens: 0, + surfaceTokens: 0, + nodes: [], }) expect(Object.isFrozen(result)).toBe(true) expect(Object.isFrozen(result.baseline)).toBe(true) + expect(Object.isFrozen(result.nodes)).toBe(true) + expectSurfaceTotal(result) expect(() => { ;(result as { totalTokens: number }).totalTokens = 1 }).toThrow(TypeError) }) - it('keeps earlier scalar and surface snapshots detached from later replay', () => { + it('keeps an earlier unified snapshot detached from later replay', () => { const service = meter() const session = new Session(SessionId('detached')) session.append('user/message', { content: [{ type: 'text', text: 'first' }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - const scalar = service.measure(session) - const surface = service.measureSurface(session) - const scalarCopy = structuredClone(scalar) - const surfaceCopy = structuredClone(surface) + const snapshot = service.measure(session) + const snapshotCopy = structuredClone(snapshot) + expect(Object.isFrozen(snapshot.nodes)).toBe(true) + expect(Object.isFrozen(snapshot.nodes[0])).toBe(true) + expectSurfaceTotal(snapshot) + expect(() => { + ;(snapshot.nodes as Array<{ seq: number; tokens: number }>).push({ seq: 99, tokens: 1 }) + }).toThrow(TypeError) + expect(() => { + ;(snapshot.nodes[0] as { seq: number; tokens: number }).tokens = 1 + }).toThrow(TypeError) session.append('user/message', { content: [{ type: 'text', text: 'second' }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - expect(service.measure(session).logRevision).toBe(2) - expect(service.measureSurface(session).nodes).toHaveLength(2) - expect(scalar).toEqual(scalarCopy) - expect(surface).toEqual(surfaceCopy) - expect(scalar.logRevision).toBe(1) - expect(surface.nodes).toHaveLength(1) + const advanced = service.measure(session) + expect(advanced.logRevision).toBe(2) + expect(advanced.nodes).toHaveLength(2) + expectSurfaceTotal(advanced) + expect(snapshot).toEqual(snapshotCopy) + expect(snapshot.logRevision).toBe(1) + expect(snapshot.nodes).toHaveLength(1) }) it('prices header, prefix, tools, and surface when no reusable usage exists', () => { @@ -181,8 +198,27 @@ describe('TokenMeterService pricing', () => { })) const result = service.measure(session) expect(result.baseline.kind).toBe('estimated') - expect(result.totalTokens).toBeGreaterThan(service.measureSurface(session).totalTokens) + expect(result.totalTokens).toBeGreaterThan(result.surfaceTokens) expect(result.logRevision).toBe(session.events.length) + expectSurfaceTotal(result) + }) + + it('keeps request-header overrides out of the returned surface', () => { + const service = meter() + const session = new Session(SessionId('override-surface')) + session.append('user/message', { + content: [{ type: 'text', text: 'question' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + + const logged = service.measure(session) + const overridden = service.measure(session, header('another-model', { + system: 'large override '.repeat(100), + })) + expect(overridden.totalTokens).toBeGreaterThan(logged.totalTokens) + expect(overridden.surfaceTokens).toBe(logged.surfaceTokens) + expect(overridden.nodes).toEqual(logged.nodes) + expectSurfaceTotal(overridden) }) }) @@ -320,27 +356,27 @@ describe('replay anchors and surface folds', () => { source: { kind: 'user' }, }, { surfaceOp: 'append' }) const seeded = new Session(SessionId('surface-seeded'), original.events) - const before = service.measureSurface(seeded) - const beforeScalar = service.measure(seeded) + const before = service.measure(seeded) expect(before.nodes).toHaveLength(2) - expect(beforeScalar.surfaceDeltaTokens).toBeGreaterThan(0) + expect(before.surfaceDeltaTokens).toBeGreaterThan(0) + expectSurfaceTotal(before) const first = seeded.surface.nodes[0]!.seq seeded.append('user/message', { content: [{ type: 'text', text: 'replacement' }], source: { kind: 'plugin', plugin: 'test' }, }, { surfaceOp: { op: 'replace', start: first, end: first }, sourceEventSeqs: [first] }) - const after = service.measureSurface(seeded) - const afterScalar = service.measure(seeded) + const after = service.measure(seeded) expect(after.nodes).toHaveLength(2) expect(after.nodes[0]!.seq).toBe(seeded.events.length - 1) expect(after.logRevision).toBe(seeded.events.length) expect(Object.isFrozen(after.nodes)).toBe(true) expect(Object.isFrozen(after.nodes[0])).toBe(true) - expect(afterScalar.surfaceDeltaTokens).toBeLessThan(0) + expect(after.surfaceDeltaTokens).toBeLessThan(0) + expectSurfaceTotal(after) expect(before.nodes).toHaveLength(2) expect(before.logRevision).toBe(original.events.length) - expect(beforeScalar.surfaceDeltaTokens).toBeGreaterThan(0) + expect(before.surfaceDeltaTokens).toBeGreaterThan(0) }) it('prices an empty assistant surface anchor as zero', () => { @@ -350,10 +386,11 @@ describe('replay anchors and surface folds', () => { durableText: '', provenance: 'empty', }) - const surface = meter().measureSurface(session) + const measurement = meter().measure(session) const assistant = session.events.find(event => event.type === 'assistant/message')! - expect(surface.nodes).toEqual([{ seq: assistant.seq, tokens: 0 }]) - expect(surface.totalTokens).toBe(0) + expect(measurement.nodes).toEqual([{ seq: assistant.seq, tokens: 0 }]) + expect(measurement.surfaceTokens).toBe(0) + expectSurfaceTotal(measurement) }) }) diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index e8cb4b8b8b..4a6fd2b88e 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -32,7 +32,6 @@ { "doc": "docs/core-data-structures/token-meter.md", "symbol": "TokenMeasurement", "source": "packages/llm/token-meter/src/types.ts" }, { "doc": "docs/core-data-structures/token-meter.md", "symbol": "TokenSurfaceNode", "source": "packages/llm/token-meter/src/types.ts" }, - { "doc": "docs/core-data-structures/token-meter.md", "symbol": "TokenSurfaceMeasurement", "source": "packages/llm/token-meter/src/types.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "SessionEventMap", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "EpochHeader", "source": "packages/core/session/src/types.ts" }, From d027ea0d1003b22f36c389bf126c7dd47a598981 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 15:10:45 +0800 Subject: [PATCH 205/359] refactor(compact-basic): inline automatic listeners into the service Fold automatic.ts into BasicCompactService as a private _registerAutomaticCompaction method, removing the AutomaticCompactor structural interface the standalone module needed to avoid an import cycle. Listener behavior is unchanged; compactIfNeeded stays dynamically dispatched so subclass overrides are honored at event time. --- .../compact/compact-basic/src/automatic.ts | 85 ------------------- packages/compact/compact-basic/src/index.ts | 68 ++++++++++++++- 2 files changed, 66 insertions(+), 87 deletions(-) delete mode 100644 packages/compact/compact-basic/src/automatic.ts diff --git a/packages/compact/compact-basic/src/automatic.ts b/packages/compact/compact-basic/src/automatic.ts deleted file mode 100644 index e837e076cc..0000000000 --- a/packages/compact/compact-basic/src/automatic.ts +++ /dev/null @@ -1,85 +0,0 @@ -/** - * Automatic post-step pressure and context-overflow recovery listeners. - * - * @module @deepseek-ai/dsh-compact-basic/automatic - */ - -import type { Context } from 'cordis' -import type { CompactionResult, CompactionTrigger } from '@deepseek-ai/dsh-compact' -import { CONTEXT_WINDOW_EXCEEDED_CODE } from '@deepseek-ai/dsh-llm' -import { - TOKEN_METER_MODEL_UNCONFIGURED, - TokenMeterError, -} from '@deepseek-ai/dsh-token-meter' -import type { Agent } from '@deepseek-ai/dsh-agent' - -interface AutomaticCompactor { - readonly config: { readonly maxOverflowRetries: number } - compactIfNeeded( - agent: Agent, - trigger: CompactionTrigger, - signal: AbortSignal, - ): Promise -} - -/** - * Register the implementation-owned automatic compaction listener. - * @param ctx - context owning the listener effect and logger. - * @param service - compactor whose public methods remain dynamically dispatched. - */ -export function registerAutomaticCompaction( - ctx: Context, - service: AutomaticCompactor, -): void { - const logResult = (result: CompactionResult, trigger: string): void => { - ctx.logger.info( - `compaction (${trigger}): shadowed ${result.shadowedSeqs.length} surface nodes ` - + `(seqs ${result.shadowedRange.start}-${result.shadowedRange.end}, ` - + `~${result.shadowedTokenCount} tokens)`, - ) - } - - ctx.on('agent/post-step', async ( - agent: Agent, - _turn: number, - _step: number, - signal: AbortSignal, - ) => { - if (signal.aborted) return - try { - const result = await service.compactIfNeeded(agent, 'pressure', signal) - if (result !== null) logResult(result, 'post-step pressure') - } catch (error: unknown) { - // A named routed model without a meter profile is configuration failure, - // not an optional operational compaction miss. - if (error instanceof TokenMeterError - && error.code === TOKEN_METER_MODEL_UNCONFIGURED) throw error - const message = error instanceof Error ? error.message : String(error) - ctx.logger.warn(`post-step compaction failed: ${message}; continuing the turn`) - } - }) - - ctx.on('agent/request-error', async (agent, _turn, _step, error, retryAttempt, signal, next) => { - if (error.code !== CONTEXT_WINDOW_EXCEEDED_CODE - || retryAttempt >= service.config.maxOverflowRetries - || signal.aborted) return next() - - let generation: number - let result: CompactionResult | null - try { - generation = agent.session.surface.replaceGeneration - result = await service.compactIfNeeded(agent, 'context-overflow', signal) - } catch (recoveryError: unknown) { - const message = recoveryError instanceof Error ? recoveryError.message : String(recoveryError) - ctx.logger.warn( - `context-overflow compaction failed: ${message}; preserving the original request error`, - ) - return next() - } - // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while compaction is awaited. - if (signal.aborted || result === null - || agent.session.surface.replaceGeneration <= generation) return next() - logResult(result, 'context overflow recovery') - return { action: 'retry' } - }) -} diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index d420851166..64f8586bac 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -9,10 +9,14 @@ import z from 'schemastery' import { CompactService } from '@deepseek-ai/dsh-compact' import type { CompactionResult, CompactionTrigger } from '@deepseek-ai/dsh-compact' import type { Session } from '@deepseek-ai/dsh-session' +import { CONTEXT_WINDOW_EXCEEDED_CODE } from '@deepseek-ai/dsh-llm' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { + TOKEN_METER_MODEL_UNCONFIGURED, + TokenMeterError, +} from '@deepseek-ai/dsh-token-meter' import type { ModelTokenMeter } from '@deepseek-ai/dsh-token-meter' import type { Agent } from '@deepseek-ai/dsh-agent' -import { registerAutomaticCompaction } from './automatic.ts' import { resolveConfig, resolveModelConfig } from './config.ts' import { compactSurfaceRegion, selectCompactableRange } from './region.ts' import { summarizeWithLlm } from './summarizer.ts' @@ -72,7 +76,67 @@ export class BasicCompactService extends CompactService { constructor(ctx: Context, config: BasicCompactConfig = {}) { super(ctx) this.config = resolveConfig(config, ctx.tokenMeter) - if (this.config.auto) registerAutomaticCompaction(ctx, this) + if (this.config.auto) this._registerAutomaticCompaction() + } + + /** + * Register the automatic post-step pressure and context-overflow recovery + * listeners. `compactIfNeeded` stays dynamically dispatched so subclass + * overrides are honored at event time. + */ + private _registerAutomaticCompaction(): void { + const { ctx } = this + const logResult = (result: CompactionResult, trigger: string): void => { + ctx.logger.info( + `compaction (${trigger}): shadowed ${result.shadowedSeqs.length} surface nodes ` + + `(seqs ${result.shadowedRange.start}-${result.shadowedRange.end}, ` + + `~${result.shadowedTokenCount} tokens)`, + ) + } + + ctx.on('agent/post-step', async ( + agent: Agent, + _turn: number, + _step: number, + signal: AbortSignal, + ) => { + if (signal.aborted) return + try { + const result = await this.compactIfNeeded(agent, 'pressure', signal) + if (result !== null) logResult(result, 'post-step pressure') + } catch (error: unknown) { + // A named routed model without a meter profile is configuration failure, + // not an optional operational compaction miss. + if (error instanceof TokenMeterError + && error.code === TOKEN_METER_MODEL_UNCONFIGURED) throw error + const message = error instanceof Error ? error.message : String(error) + ctx.logger.warn(`post-step compaction failed: ${message}; continuing the turn`) + } + }) + + ctx.on('agent/request-error', async (agent, _turn, _step, error, retryAttempt, signal, next) => { + if (error.code !== CONTEXT_WINDOW_EXCEEDED_CODE + || retryAttempt >= this.config.maxOverflowRetries + || signal.aborted) return next() + + let generation: number + let result: CompactionResult | null + try { + generation = agent.session.surface.replaceGeneration + result = await this.compactIfNeeded(agent, 'context-overflow', signal) + } catch (recoveryError: unknown) { + const message = recoveryError instanceof Error ? recoveryError.message : String(recoveryError) + ctx.logger.warn( + `context-overflow compaction failed: ${message}; preserving the original request error`, + ) + return next() + } + // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while compaction is awaited. + if (signal.aborted || result === null + || agent.session.surface.replaceGeneration <= generation) return next() + logResult(result, 'context overflow recovery') + return { action: 'retry' } + }) } /** From 06e0450b8d8aae6f107818f4a29667c641af44c9 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 15:26:30 +0800 Subject: [PATCH 206/359] fix(token-meter): keep pressure anchors conservative --- docs/core-data-structures/token-meter.md | 2 +- packages/llm/token-meter/README.md | 2 +- packages/llm/token-meter/src/index.ts | 20 ++++++++----- .../llm/token-meter/tests/token-meter.spec.ts | 30 +++++++++++++++++++ 4 files changed, 44 insertions(+), 10 deletions(-) diff --git a/docs/core-data-structures/token-meter.md b/docs/core-data-structures/token-meter.md index a6e70f56f6..e082ea08a9 100644 --- a/docs/core-data-structures/token-meter.md +++ b/docs/core-data-structures/token-meter.md @@ -23,7 +23,7 @@ interface TokenMeasurement { } ``` -`baseline.kind === 'usage'` means the latest successful provider call has the same canonical request envelope. `estimated` means the service priced the complete envelope and surface with its fixed heuristic. A later successful request replaces the earlier anchor; signed `surfaceDeltaTokens` preserves growth and shrinkage relative to a matching anchor. `totalTokens` remains request-and-response pressure, while `surfaceTokens` is the surface-only heuristic total and equals the sum of the node prices. +`baseline.kind === 'usage'` means the latest successful provider call has the same canonical request envelope and its total is no lower than that call's full heuristic anchor. `estimated` means no reusable conservative usage anchor exists, so the service priced the complete envelope and surface with its fixed heuristic. A later successful request replaces the earlier anchor; signed `surfaceDeltaTokens` preserves growth and shrinkage relative to a matching anchor. `totalTokens` remains request-and-response pressure, while `surfaceTokens` is the surface-only heuristic total and equals the sum of the node prices. ## `TokenSurfaceNode` diff --git a/packages/llm/token-meter/README.md b/packages/llm/token-meter/README.md index 4b2a03833e..d879112897 100644 --- a/packages/llm/token-meter/README.md +++ b/packages/llm/token-meter/README.md @@ -19,7 +19,7 @@ The estimator intentionally uses one fixed heuristic: four characters per token `measure()` synchronizes once and returns one detached, deeply immutable snapshot. `totalTokens` is request-and-response pressure, while `surfaceTokens` is the surface-only heuristic total and equals the sum of `nodes[].tokens`. A `requestHeader` override affects pressure fields only; the surface fields still describe the current session. Every call clones the positional nodes, so measurement is O(surface). -The fold tracks request headers and deltas, step boundaries, surface appends and replacements, successful assistant messages, provider usage, and assistant-chunk provenance. Provider usage is reused only when the latest successful call's canonical request envelope matches the measured envelope; a later success replaces the earlier anchor. Otherwise the complete current envelope and surface are estimated. Surface changes remain signed relative to a matching anchor, including negative deltas after shrinking replacements. +The fold tracks request headers and deltas, step boundaries, surface appends and replacements, successful assistant messages, provider usage, and assistant-chunk provenance. Provider usage is reused only when the latest successful call's canonical request envelope matches the measured envelope and its total is no lower than that call's full heuristic anchor; a later success replaces the earlier anchor. Otherwise the complete current envelope and surface are estimated. Surface changes remain signed relative to a matching anchor, including negative deltas after shrinking replacements. Usage accounting sums disjoint input, cache-read, cache-write, and output buckets; reasoning is not added again. Every successful call records an assistant anchor, including content-less calls. An explicit empty provenance list means a known empty provider stream, while absent legacy provenance conservatively treats the durable assistant output as provider output. diff --git a/packages/llm/token-meter/src/index.ts b/packages/llm/token-meter/src/index.ts index 3c446f4778..0a3bf4180a 100644 --- a/packages/llm/token-meter/src/index.ts +++ b/packages/llm/token-meter/src/index.ts @@ -128,8 +128,9 @@ export class TokenMeterService extends Service { * Measure current request pressure and surface through the durable tail. * * Provider usage is reused only when the latest successful call's canonical - * request envelope matches `requestHeader`; otherwise the complete envelope - * and surface are heuristically repriced. + * request envelope matches `requestHeader` and its total is no lower than + * that call's full heuristic anchor; otherwise the complete envelope and + * surface are heuristically repriced. * * `requestHeader` affects request pressure only; surface fields always * describe the current session surface. Every call clones those positional @@ -266,14 +267,17 @@ export class TokenMeterService extends Service { event, eventTokens, ) + const anchorSurfaceTokens = stepStart.surfaceTokens + providerAssistantTokens + const providerTokens = usageTokens(event.data.usage) + const estimatedAnchorTokens = this._estimateHeader(nextHeader) + anchorSurfaceTokens nextAnchor = { header: nextHeader, - surfaceTokens: stepStart.surfaceTokens + providerAssistantTokens, - baseline: { - kind: 'usage', - tokens: usageTokens(event.data.usage), - usage: event.data.usage, - }, + surfaceTokens: anchorSurfaceTokens, + // Signed heuristic deltas remain conservative only from an anchor + // that is at least as large as the matching full heuristic price. + baseline: providerTokens >= estimatedAnchorTokens + ? { kind: 'usage', tokens: providerTokens, usage: event.data.usage } + : { kind: 'estimated', tokens: estimatedAnchorTokens }, } } else { const anchorSurfaceTokens = stepStart.surfaceTokens + eventTokens diff --git a/packages/llm/token-meter/tests/token-meter.spec.ts b/packages/llm/token-meter/tests/token-meter.spec.ts index 18f78afad2..f5d6afc4b3 100644 --- a/packages/llm/token-meter/tests/token-meter.spec.ts +++ b/packages/llm/token-meter/tests/token-meter.spec.ts @@ -252,6 +252,36 @@ describe('replay anchors and surface folds', () => { }).toThrow(TypeError) }) + it('selects a heuristic anchor when provider usage would undercut its scale', () => { + const service = meter() + const session = new Session(SessionId('low-usage-anchor')) + const system = 'system context' + const requestHeader = header('deepseek-v4-flash', { system }) + appendSuccessfulCall(session, requestHeader, { + providerText: 'abcd'.repeat(512), + usage: { inputTokens: 20, outputTokens: 7 }, + }) + + const anchored = service.measure(session) + expect(anchored.baseline.kind).toBe('estimated') + const assistant = anchored.nodes[0]!.seq + session.append('user/message', { + content: [{ type: 'text', text: 'short' }], + source: { kind: 'plugin', plugin: 'test' }, + }, { + surfaceOp: { op: 'replace', start: assistant, end: assistant }, + sourceEventSeqs: [assistant], + }) + + const shrunken = service.measure(session) + expect(27 + shrunken.surfaceDeltaTokens).toBeLessThan(0) + expect(shrunken.totalTokens).toBeGreaterThan(0) + expect(shrunken.totalTokens).toBe(service.measure( + session, + header('different-model', { system }), + ).totalTokens) + }) + it('uses an estimated anchor when provider usage is absent', () => { const service = meter() const session = new Session(SessionId('missing-usage')) From bbf66b3a5ba9e2126d92dc5eaeecd8b84b4e8552 Mon Sep 17 00:00:00 2001 From: Dudu-0223 Date: Thu, 16 Jul 2026 15:27:36 +0800 Subject: [PATCH 207/359] docs(tools): trim concurrency classifier contract --- docs/config-catalog.md | 2 +- docs/cordis-catalog/services.md | 2 +- packages/core/tools/src/index.ts | 30 +++++++++--------------------- 3 files changed, 11 insertions(+), 23 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 5df265f59c..9c1b5dd4c2 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1086,7 +1086,7 @@ export interface Config { export type ToolPresentationMode = 'native' | 'code' | 'both' ``` -Source: [`packages/core/tools/src/index.ts:388`](../packages/core/tools/src/index.ts) +Source: [`packages/core/tools/src/index.ts:376`](../packages/core/tools/src/index.ts) ## `@deepseek-ai/dsh-user-approval` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index ea287e4c0f..be4cdf73a8 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -277,7 +277,7 @@ async execute(exec: ToolExecutionInput): Promise Types: [ToolDefinition](../core-data-structures/tools.md) · [ToolExecutionInput](../core-data-structures/tools.md) · [ToolExecutionMode](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) -Source: [`packages/core/tools/src/index.ts:444`](../../packages/core/tools/src/index.ts) +Source: [`packages/core/tools/src/index.ts:432`](../../packages/core/tools/src/index.ts) ## `ctx.userInteraction` — `UserInteractionService` diff --git a/packages/core/tools/src/index.ts b/packages/core/tools/src/index.ts index 3af6e80918..ff74debb81 100644 --- a/packages/core/tools/src/index.ts +++ b/packages/core/tools/src/index.ts @@ -132,28 +132,16 @@ export interface ToolDefinition extends ToolSchema { */ timeoutMs?: number /** - * Optional synchronous, pure classification: may this call run concurrently - * with other tool calls in the same assistant step? The agent-loop scheduler - * calls it (via {@link ToolRegistry.executionMode}) to decide whether the call - * joins a parallel group or forms an exclusive barrier; a missing declaration, - * a thrown check, or any non-`true` return is treated as exclusive. Like - * `timeoutMs` it is host-only scheduler metadata — NEVER sent to the model, - * since `schemas()` whitelists only name/description/parameters. + * Pure, synchronous host-only classifier for overlap with sibling tool calls. + * Only `true` opts in; omission, exceptions, and invalid `defineTool` + * arguments are treated as exclusive. * - * It may inspect the parsed `args` (`unknown` — a hand-rolled definition - * receives the raw parsed value; `defineTool` schema-validates first and - * returns `false` on invalid args). The check performs no I/O and receives no - * live `Agent` or mutable `ToolExecution`. - * - * Declaring `true` is a contract: during `execute` the tool body must NOT - * mutate the parent agent's session or other parent-owned async state (no - * `exec.agent.session.append(...)`, no `agent.inject(...)`); its only parent- - * step outputs are the returned content, `meta`, structured error, and - * `additionalContext` on the loop's ordered post-execute path. A synchronous, - * side-effect-only recorder whose updates are commutative or fail closed for - * concurrent same-session calls is the one exception (`fs/observed` is the - * worked example). Full contract and rationale: the parallel-tool-call RFC - * (docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md). + * Opted-in executions must not mutate parent-owned state, and shared state + * they touch must be concurrency-safe. See the + * [parallel-tool-call RFC](../../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md) + * for the full safety contract and recorder exception. + * @param args - Parsed tool arguments. + * @returns Whether this call may join a parallel group. */ isConcurrencySafe?(args: unknown): boolean /** From 17fe9e5b1e2447629541afbef908ad65ee08bd1a Mon Sep 17 00:00:00 2001 From: Dudu-0223 Date: Thu, 16 Jul 2026 15:52:35 +0800 Subject: [PATCH 208/359] fix(agent-loop): tighten parallel tool-call safety --- docs/agent-lifecycle.md | 15 ++++++++++----- docs/architecture.md | 7 +++---- docs/config-catalog.md | 10 ++++++++-- .../2026-07-10-parallel-tool-call-execution.md | 8 +++----- docs/tool-catalog.md | 2 +- .../advanced-toolchain/system-prompt.golden.md | 4 ++-- .../advanced-toolchain/tool-schemas.golden.json | 4 ++-- .../both-mode-turn/system-prompt.golden.md | 4 ++-- .../both-mode-turn/tool-schemas.golden.json | 4 ++-- .../code-mode-turn/system-prompt.golden.md | 4 ++-- .../snapshots/escalation-approved/session.jsonl | 4 ++-- .../snapshots/escalation-rejected/session.jsonl | 4 ++-- .../snapshots/hook-cc-pretool-ask/session.jsonl | 4 ++-- .../permission-switching/tool-schemas.golden.json | 4 ++-- .../snapshots/skill-load/tool-schemas.golden.json | 4 ++-- .../snapshots/text-turn/tool-schemas.golden.json | 4 ++-- .../workspace-edit/tool-schemas.golden.json | 4 ++-- packages/examples/acp-demo/README.md | 1 + packages/examples/acp-demo/src/index.ts | 12 +++++++++++- .../examples/acp-demo/tests/acp-agent.spec.ts | 11 +++++++++++ packages/subagent/README.md | 2 -- packages/subagent/subagent/src/types.ts | 7 ------- packages/subagent/tool-subagent/README.md | 2 +- packages/subagent/tool-subagent/src/index.ts | 9 ++------- .../tool-subagent/tests/tool-subagent.spec.ts | 6 +++--- scripts/gen-doc-graphs.ts | 15 ++++++++++----- 26 files changed, 88 insertions(+), 67 deletions(-) diff --git a/docs/agent-lifecycle.md b/docs/agent-lifecycle.md index 60dfc6ed58..7de8e02bf1 100644 --- a/docs/agent-lifecycle.md +++ b/docs/agent-lifecycle.md @@ -35,12 +35,17 @@ sequenceDiagram Driver->>Hooks: agent/step-result waterfall Driver->>Session: assistant/message Driver->>Tools: group calls by executionMode - loop started tool calls (bounded pool) - Driver->>Session: tool/call pending audit - Driver->>Tools: ordered pre / pooled dispatch / ordered post - Tools-->>Session: tool-owned events when applicable + loop bounded rolling pool until group drains + opt capacity available for an unstarted call + Driver->>Session: tool/call pending audit + Driver->>Tools: ordered pre / pooled dispatch + Tools-->>Session: tool-owned events when applicable + end + opt next model-order result is ready + Driver->>Tools: ordered post + Driver->>Session: tool/result + end end - Driver->>Session: tool/result in model order Driver->>Session: step/end Driver->>Hooks: agent/turn-continuation waterfall Driver->>Hooks: agent/turn-stop serial terminal checkpoint diff --git a/docs/architecture.md b/docs/architecture.md index 3f1ec18764..82b60d3879 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -84,10 +84,9 @@ forever: 'assistant/message' schedule tool calls by ctx.tools.executionMode (exclusive = barrier; consecutive parallel-safe = one rolling-pool group, <= maxParallelToolCalls in flight): - each started call: - 'tool/call' - tools/pre-execute -> monotonic guards -> tools/execute -> tools/post-execute -> tools/result - 'tool/result' committed in model order (slot-buffered) + while the bounded pool has work: + capacity available -> 'tool/call' -> tools/pre-execute -> monotonic guards -> tools/execute + next model-order slot ready -> tools/post-execute -> 'tool/result' append post-tool context (model order) and steering 'step/end' agent/turn-continuation diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 9c1b5dd4c2..a8ca75de0a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -37,11 +37,17 @@ Source: [`packages/ui/acp/src/index.ts:203`](../packages/ui/acp/src/index.ts) * deployment persona (forwarded to the system-prompt plugin); `toolOrder` is * the explicit model-facing tool order (forwarded to the system-prompt plugin); * `tools` is the tool registry's config (its presentation `mode`, forwarded - * through agent-spine-demo); `persistenceRoot` is the JSONL backend's directory. + * through agent-spine-demo); `maxParallelToolCalls` configures the bundled + * agent loop; `persistenceRoot` is the JSONL backend's directory. */ export interface Config { /** Model name for ACP-created agents (must have a registered adapter). */ model: string + /** + * Concurrent parallel-safe tool-call cap for the bundled agent loop. A + * positive integer; the loop defaults it when omitted and `1` is serial. + */ + maxParallelToolCalls?: number /** Deployment persona (the system-prompt plugin's `persona` config). */ persona?: string /** Explicit model-facing tool order (the system-prompt plugin's `toolOrder` config; see dsh-system-prompt). */ @@ -61,7 +67,7 @@ export interface Config { Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/examples/acp-demo/src/index.ts:31`](../packages/examples/acp-demo/src/index.ts) +Source: [`packages/examples/acp-demo/src/index.ts:32`](../packages/examples/acp-demo/src/index.ts) ## `@deepseek-ai/dsh-agent-loop` diff --git a/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md b/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md index 9f123cb3f4..9326fda865 100644 --- a/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md +++ b/docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md @@ -4,7 +4,7 @@ Status: implemented ## Problem -An assistant message may contain several sibling `tool-call` blocks. Running them serially adds the latency of independent reads, web requests, and subagent runs even though the model has already requested them together. +An assistant message may contain several sibling `tool-call` blocks. Running them serially adds the latency of independent reads and web requests even though the model has already requested them together. Concurrency is a host scheduling concern, not model-facing tool metadata. The loop needs to decide which calls may overlap without hardcoding tool names or exposing scheduler policy in the JSON schema. @@ -58,12 +58,10 @@ Any shared state touched during execution must be concurrency-safe. This include `maxParallelToolCalls` is a positive AgentLoop deployment cap shared by every agent the factory creates. It defaults to `10`; `1` preserves serial execution. Exact fields and defaults live in the generated [configuration catalog](../../../config-catalog.md). -The shipped declarations are conservative. Web search, web fetch, filesystem read, and foreground subagent calls opt in. Background subagent starts remain exclusive because they register parent-owned task state. Filesystem writes and edits, bash tools, workflow, user interaction, todo mutation, Code Mode, and Cordis mutation tools also remain exclusive. Bash stays exclusive until its owning package supplies a proven input-sensitive classifier. +The shipped declarations are conservative. Web search, web fetch, and filesystem read opt in. Filesystem writes and edits, bash tools, subagent delegation, workflow, user interaction, todo mutation, Code Mode, and Cordis mutation tools remain exclusive. A subagent may share its parent's workspace or external resources, and the unary classifier cannot prove that sibling delegations have disjoint effects. Bash stays exclusive until its owning package supplies a proven input-sensitive classifier. Filesystem read relies on a narrow recorder exception: its synchronous observation updates may settle out of order, but write and edit re-check the observed version before mutation, so stale state only produces `FS_STALE_VERSION`. -The subagent declaration requires providers to accept concurrent `start()` calls for independent runs. A provider may queue, enforce its own capacity, or return a typed failure instead of requiring the parent loop to serialize every subagent call. - ## Verification Unit coverage pins fail-closed classification, typed argument validation, grouping, barriers, the rolling cap, distinct execution objects, middleware order, ordered results and context, and abort draining. First-party tests pin each parallel declaration. @@ -98,6 +96,6 @@ Parallel calls may begin in cases where serial execution would have aborted befo Ordered commits may hold a fast result behind a slow earlier sibling. This preserves replay and model-history order while live surfaces still show pending progress. -Concurrent subagents and external calls can compete for quota or process capacity. Providers own their capacity controls; the loop cap only limits calls from one agent step. +Concurrent external calls can compete for quota or process capacity. Providers own their capacity controls; the loop cap only limits calls from one agent step. Tool registration is a scheduling boundary. The scheduler currently plans all groups before dispatch, so an earlier registry mutation can make a later classification stale. Binding dispatch to the classified definition or reclassifying after exclusive barriers remains a named correctness gap. diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index c13274a7d9..121bfd09f7 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -357,7 +357,7 @@ Source: [`packages/skill/tool-skill/src/index.ts`](../packages/skill/tool-skill/ ### `subagent` -Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. +Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. ```json { diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index 30d34948c5..33bfa25590 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -64,7 +64,7 @@ declare const tools: { /** The exact skill name from the available skills list. */ name: string; }): Promise; - /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ + /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ subagent(args: { /** A short (3-5 word) description of the delegated task, for display. */ description: string; @@ -73,7 +73,7 @@ declare const tools: { /** Run as a background task and return its id; collect with task_output or stop with task_kill. */ run_in_background?: boolean; }): Promise; - /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ + /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ subagent_fork(args: { /** A short (3-5 word) description of the delegated task, for display. */ description: string; diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.golden.json index 61970ba85c..daf4e93ee8 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.golden.json +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.golden.json @@ -132,7 +132,7 @@ }, { "name": "subagent", - "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", + "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", "parameters": { "type": "object", "properties": { @@ -157,7 +157,7 @@ }, { "name": "subagent_fork", - "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", + "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", "parameters": { "type": "object", "properties": { diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index 07ce7afd14..36aa94c53c 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -49,7 +49,7 @@ declare const tools: { /** The exact skill name from the available skills list. */ name: string; }): Promise; - /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ + /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ subagent(args: { /** A short (3-5 word) description of the delegated task, for display. */ description: string; @@ -58,7 +58,7 @@ declare const tools: { /** Run as a background task and return its id; collect with task_output or stop with task_kill. */ run_in_background?: boolean; }): Promise; - /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ + /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ subagent_fork(args: { /** A short (3-5 word) description of the delegated task, for display. */ description: string; diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.golden.json index 817f2a3294..52e7974409 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.golden.json +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.golden.json @@ -79,7 +79,7 @@ }, { "name": "subagent", - "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", + "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", "parameters": { "type": "object", "properties": { @@ -104,7 +104,7 @@ }, { "name": "subagent_fork", - "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", + "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", "parameters": { "type": "object", "properties": { diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index 07ce7afd14..36aa94c53c 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -49,7 +49,7 @@ declare const tools: { /** The exact skill name from the available skills list. */ name: string; }): Promise; - /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ + /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ subagent(args: { /** A short (3-5 word) description of the delegated task, for display. */ description: string; @@ -58,7 +58,7 @@ declare const tools: { /** Run as a background task and return its id; collect with task_output or stop with task_kill. */ run_in_background?: boolean; }): Promise; - /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ + /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */ subagent_fork(args: { /** A short (3-5 word) description of the delegated task, for display. */ description: string; diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl index f7ef68e20f..a5c592b685 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl @@ -131,8 +131,8 @@ {"type":"assistant/chunk","seq":129,"time":1783962245385,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":130,"time":1783962245385,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a command with sandbox_permissions set to danger-full-access, no prior run needed, justified as instructed."},{"type":"tool-call","id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"usage":{"inputTokens":1501,"outputTokens":174,"cacheReadTokens":0,"reasoningTokens":28}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} {"type":"tool/call","seq":131,"time":1783962245385,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} -{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"53b0ac7f-9728-4c59-8c0d-fb007ce2cb60","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} -{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"53b0ac7f-9728-4c59-8c0d-fb007ce2cb60","outcome":"allowed-once"}} +{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"a54fc428-a072-486e-97f5-913970766bae","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"a54fc428-a072-486e-97f5-913970766bae","outcome":"allowed-once"}} {"type":"tool/result","seq":134,"time":1783962245399,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[131],"surfaceOp":"append"} {"type":"step/end","seq":135,"time":1783962245400,"data":{"turn":1,"step":1}} {"type":"step/start","seq":136,"time":1783962245400,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl index 4a7f6bc9fb..66f49c8350 100644 --- a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl @@ -155,8 +155,8 @@ {"type":"assistant/chunk","seq":153,"time":1783962246274,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":154,"time":1783962246274,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command with `sandbox_permissions` set to `danger-full-access` and a specific justification. They explicitly said NOT to run it without sandbox_permissions first. Let me do exactly that."},{"type":"tool-call","id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"usage":{"inputTokens":1509,"outputTokens":198,"cacheReadTokens":0,"reasoningTokens":48}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153],"surfaceOp":"append"} {"type":"tool/call","seq":155,"time":1783962246274,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} -{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"33b44536-0658-49f2-83ba-9a9cb9048cbd","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} -{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"33b44536-0658-49f2-83ba-9a9cb9048cbd","outcome":"rejected"}} +{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"8efbb6f0-1774-4c18-95ff-a8502ca2937a","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"8efbb6f0-1774-4c18-95ff-a8502ca2937a","outcome":"rejected"}} {"type":"tool/result","seq":158,"time":1783962246275,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"danger-full-access\""}],"isError":true},"sourceEventSeqs":[155],"surfaceOp":"append"} {"type":"step/end","seq":159,"time":1783962246276,"data":{"turn":1,"step":1}} {"type":"step/start","seq":160,"time":1783962246276,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl index cda99ed9ac..1fa40f9ace 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl @@ -55,8 +55,8 @@ {"type":"tool/call","seq":53,"time":1783352172557,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}} {"type":"hook/invoked","seq":54,"time":1783352172558,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":55,"time":1783352172573,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"ask","exitCode":0,"durationMs":14.113374999999905}} -{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"2e0af4ba-d9e7-4165-a2f9-313355f5c731","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} -{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"2e0af4ba-d9e7-4165-a2f9-313355f5c731","outcome":"rejected"}} +{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"47149e48-ec0b-4b29-9096-a27f94991e1e","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} +{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"47149e48-ec0b-4b29-9096-a27f94991e1e","outcome":"rejected"}} {"type":"tool/result","seq":58,"time":1783962235814,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","content":[{"type":"text","text":"Error: the user rejected tool \"bash\""}],"isError":true},"sourceEventSeqs":[53],"surfaceOp":"append"} {"type":"step/end","seq":59,"time":1783962235814,"data":{"turn":1,"step":1}} {"type":"step/start","seq":60,"time":1783962235814,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.golden.json index 127a1f962c..4b07d8edef 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.golden.json +++ b/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.golden.json @@ -63,7 +63,7 @@ }, { "name": "subagent", - "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", + "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", "parameters": { "type": "object", "properties": { @@ -88,7 +88,7 @@ }, { "name": "subagent_fork", - "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", + "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", "parameters": { "type": "object", "properties": { diff --git a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.golden.json index 127a1f962c..4b07d8edef 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.golden.json +++ b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.golden.json @@ -63,7 +63,7 @@ }, { "name": "subagent", - "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", + "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", "parameters": { "type": "object", "properties": { @@ -88,7 +88,7 @@ }, { "name": "subagent_fork", - "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", + "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", "parameters": { "type": "object", "properties": { diff --git a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.golden.json index 127a1f962c..4b07d8edef 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.golden.json +++ b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.golden.json @@ -63,7 +63,7 @@ }, { "name": "subagent", - "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", + "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", "parameters": { "type": "object", "properties": { @@ -88,7 +88,7 @@ }, { "name": "subagent_fork", - "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", + "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", "parameters": { "type": "object", "properties": { diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.golden.json index c74ab8b318..da5e23216c 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.golden.json +++ b/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.golden.json @@ -117,7 +117,7 @@ }, { "name": "subagent", - "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", + "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", "parameters": { "type": "object", "properties": { @@ -142,7 +142,7 @@ }, { "name": "subagent_fork", - "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. You may issue several subagent calls in one message to run independent tasks concurrently when their work scopes do not overlap. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", + "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.", "parameters": { "type": "object", "properties": { diff --git a/packages/examples/acp-demo/README.md b/packages/examples/acp-demo/README.md index c778ab6c2e..122a1b284b 100644 --- a/packages/examples/acp-demo/README.md +++ b/packages/examples/acp-demo/README.md @@ -26,6 +26,7 @@ Because the package wires no logger entry, an ACP leaf has **nothing to get wron | Key | Default | Routed to | |---|---|---| | `model` | (required) | the per-session agent template the bridge creates agents from | +| `maxParallelToolCalls` | agent-loop default | positive-integer concurrent tool-call cap shared by the bundled loop's agents; `1` is serial | | `persona` | — | the deployment persona template (may reference `{{model}}`/`{{cwd}}`), routed to `dsh-system-prompt` | | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | | `tools` | `{ mode: 'native' }` | tool-registry presentation config (`native` / `code` / `both`), routed through `dsh-agent-spine-demo` | diff --git a/packages/examples/acp-demo/src/index.ts b/packages/examples/acp-demo/src/index.ts index 917cb128a6..619aaf0ebb 100644 --- a/packages/examples/acp-demo/src/index.ts +++ b/packages/examples/acp-demo/src/index.ts @@ -26,11 +26,17 @@ export const name = 'acp-demo' * deployment persona (forwarded to the system-prompt plugin); `toolOrder` is * the explicit model-facing tool order (forwarded to the system-prompt plugin); * `tools` is the tool registry's config (its presentation `mode`, forwarded - * through agent-spine-demo); `persistenceRoot` is the JSONL backend's directory. + * through agent-spine-demo); `maxParallelToolCalls` configures the bundled + * agent loop; `persistenceRoot` is the JSONL backend's directory. */ export interface Config { /** Model name for ACP-created agents (must have a registered adapter). */ model: string + /** + * Concurrent parallel-safe tool-call cap for the bundled agent loop. A + * positive integer; the loop defaults it when omitted and `1` is serial. + */ + maxParallelToolCalls?: number /** Deployment persona (the system-prompt plugin's `persona` config). */ persona?: string /** Explicit model-facing tool order (the system-prompt plugin's `toolOrder` config; see dsh-system-prompt). */ @@ -52,6 +58,9 @@ export interface Config { /* jscpd:ignore-start */ export const Config: z = z.object({ model: z.string().required(), + // A positive integer; a bad value (0, negative, fractional) fails config + // validation here rather than being silently dropped from cordis.yml. + maxParallelToolCalls: z.number().step(1).min(1), persona: z.string(), // The array default is forced to undefined: ABSENT means "lexicographic // order" (the owning dsh-system-prompt schema does the same), while @@ -79,6 +88,7 @@ export function apply(ctx: Context, config: Config): void { ...config.persona !== undefined ? { persona: config.persona } : {}, ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {}, ...config.tools !== undefined ? { tools: config.tools } : {}, + ...config.maxParallelToolCalls !== undefined ? { maxParallelToolCalls: config.maxParallelToolCalls } : {}, ...config.skills !== undefined ? { skills: config.skills } : {}, ...config.toolBash !== undefined ? { toolBash: config.toolBash } : {}, ...config.toolTasks !== undefined ? { toolTasks: config.toolTasks } : {}, diff --git a/packages/examples/acp-demo/tests/acp-agent.spec.ts b/packages/examples/acp-demo/tests/acp-agent.spec.ts index 285e4756d0..1a6bd0483a 100644 --- a/packages/examples/acp-demo/tests/acp-agent.spec.ts +++ b/packages/examples/acp-demo/tests/acp-agent.spec.ts @@ -113,6 +113,17 @@ describe('dsh-acp-demo composition', () => { await ctx.fiber.dispose() }) + it('forwards maxParallelToolCalls to the bundled agent loop', async () => { + const ctx = await mount({ + model: 'mock', + maxParallelToolCalls: 3, + persistenceRoot: '/tmp/dsh-acp-demo-test-parallel', + skills: await isolatedSkillsConfig(), + }) + expect(ctx.get('agentLoop')?.config.maxParallelToolCalls).toBe(3) + await ctx.fiber.dispose() + }) + it('forwards bundled tool config into agent-core', async () => { const ctx = await mount({ model: 'mock', diff --git a/packages/subagent/README.md b/packages/subagent/README.md index 4ee59eab46..62de4ffb08 100644 --- a/packages/subagent/README.md +++ b/packages/subagent/README.md @@ -14,6 +14,4 @@ The subagent seam: an agent delegating work to a child agent. Like the [bash](.. The interface lives at `subagent/subagent/`. The in-process `subagent-spawn` / `subagent-fork` backends share the `subagent-inprocess` driver (a library with no provider of its own — both depend on it, neither on the other), the out-of-process `subagent-acp` backend builds on the `subagent-subprocess` library (the credential env scrub, the dispose ladder, isolated config dirs) and ships alongside them here; the test-only `dsh-subagent-mock` (in [support](../support/README.md)) is separate. All **product** packages except the mock. -`SubagentProvider.start()` must be safe to call concurrently for independent runs: foreground `subagent` calls are parallel-safe, so one parent step may issue several at once. Background starts remain exclusive while registering parent-owned task state. Each backend reads the parent synchronously at start (a snapshot, never mutated or re-read during the run) — `fork` seeds each child from the parent's completed-turn prefix, which the open in-flight turn cannot change, so concurrent forks inside one open step all see the same stable prefix. A resource-limited provider may queue or cap internally, but must not require the loop to serialize every foreground call. - The proposal and design rationale: [docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md](../../docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md). diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 4fed9816ea..05bb40d575 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -186,13 +186,6 @@ export interface SubagentProvider { * honorable when present. If setup fails or `request.signal` aborts before * fulfillment, the provider owns and cleans all partial resources before this * promise rejects. Ownership transfers to the caller only on fulfillment. - * - * MUST be safe to call concurrently for independent runs: foreground - * `subagent` calls are parallel-safe, so a parent step may issue several at once, - * each invoking `start()` before an earlier run settles. An implementation - * snapshots the parent at start and must not require the parent loop to - * serialize every foreground `subagent` call; a resource-limited provider queues or - * rejects internally. */ start(request: SubagentStartRequest): Promise } diff --git a/packages/subagent/tool-subagent/README.md b/packages/subagent/tool-subagent/README.md index 7e0aa298ad..637ddeded2 100644 --- a/packages/subagent/tool-subagent/README.md +++ b/packages/subagent/tool-subagent/README.md @@ -26,7 +26,7 @@ With `run_in_background: true`, the tool registers the parent-owned task before ## Concurrency -Foreground calls opt into concurrent scheduling because each owns an independent child run and returns only its final answer. Background starts remain exclusive because they register parent-owned task state. Providers must accept concurrent `start()` calls for independent runs; they may queue internally, enforce capacity, or return a typed failure. See the [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md). +Foreground and background calls are exclusive. Children may share the parent's workspace or external resources, and the unary scheduler classifier cannot prove that sibling delegations have disjoint effects. See the [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md). ## Model Experience diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index 8455537d42..cee354bdfe 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -174,8 +174,7 @@ export function providerWording(inheritsConversation: boolean): { description: s + 'completed turns so far (it does not see the current in-flight turn), returning only its final ' + 'result. Use this when the subtask builds on this conversation\'s context — a follow-up analysis, ' + 'a review, a continuation — without consuming this conversation\'s context for the work itself. ' - + 'You receive only its final answer, not its intermediate steps. You may issue several subagent ' - + 'calls in one message to run independent tasks concurrently when their work scopes do not overlap.', + + 'You receive only its final answer, not its intermediate steps.', promptDescription: 'The task for the subagent. It already sees this conversation\'s completed turns, so build on them ' + 'freely and state only what is new.', @@ -187,8 +186,7 @@ export function providerWording(inheritsConversation: boolean): { description: s + 'and return its final result. Use this to offload focused, independent work — research, a scoped ' + 'implementation, an analysis — so it does not consume this conversation\'s context. The subagent ' + 'runs to completion and you receive only its final answer, not its intermediate steps. Give it a ' - + 'complete, standalone prompt: it does not see this conversation. You may issue several subagent ' - + 'calls in one message to run independent tasks concurrently when their work scopes do not overlap.', + + 'complete, standalone prompt: it does not see this conversation.', promptDescription: 'The complete, self-contained task for the subagent. It does not share this ' + 'conversation\'s context, so include everything it needs.', @@ -254,9 +252,6 @@ export function apply(ctx: Context, config: Config): void { }, } : {}, }, - // A foreground call owns only its child run; background mode first - // registers parent-owned task state and therefore remains exclusive. - isConcurrencySafe: args => args.run_in_background !== true, async execute(args, exec): Promise { const parent = exec.agent if (!parent) { diff --git a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts index a057ec6e4d..90f84bfceb 100644 --- a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts +++ b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts @@ -96,13 +96,13 @@ describe('dsh-tool-subagent', () => { expect(foreground.isError).toBe(false) }) - it('classifies foreground calls as parallel and background starts as exclusive', async () => { + it('keeps foreground and background calls exclusive', async () => { const ctx = await setup({ provider: 'mock' }) expect(ctx.tools.executionMode({ - callId: CallId('subagent-safe'), + callId: CallId('subagent-foreground'), name: 'subagent', arguments: { description: 'do work', prompt: 'Reply OK' }, - })).toEqual({ kind: 'parallel' }) + })).toEqual({ kind: 'exclusive' }) expect(ctx.tools.executionMode({ callId: CallId('subagent-background'), name: 'subagent', diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 29183eff5d..feaafdac9e 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -823,12 +823,17 @@ function renderLifecycle(): string { ` Driver->>Hooks: ${mermaidCode('agent/step-result')} waterfall`, ` Driver->>Session: ${mermaidCode('assistant/message')}`, ' Driver->>Tools: group calls by executionMode', - ' loop started tool calls (bounded pool)', - ` Driver->>Session: ${mermaidCode('tool/call')} pending audit`, - ' Driver->>Tools: ordered pre / pooled dispatch / ordered post', - ' Tools-->>Session: tool-owned events when applicable', + ' loop bounded rolling pool until group drains', + ' opt capacity available for an unstarted call', + ` Driver->>Session: ${mermaidCode('tool/call')} pending audit`, + ' Driver->>Tools: ordered pre / pooled dispatch', + ' Tools-->>Session: tool-owned events when applicable', + ' end', + ' opt next model-order result is ready', + ' Driver->>Tools: ordered post', + ` Driver->>Session: ${mermaidCode('tool/result')}`, + ' end', ' end', - ` Driver->>Session: ${mermaidCode('tool/result')} in model order`, ` Driver->>Session: ${mermaidCode('step/end')}`, ` Driver->>Hooks: ${mermaidCode('agent/turn-continuation')} waterfall`, ` Driver->>Hooks: ${mermaidCode('agent/turn-stop')} serial terminal checkpoint`, From 8d35092e267102827a3153d0f113f838571e7b34 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 16:12:27 +0800 Subject: [PATCH 209/359] fix(examples): isolate headless agent example --- README.i18n.yaml | 4 +- README.md | 2 +- README.zh.md | 2 +- docs/cookbook/extension-cookbook.i18n.yaml | 4 +- docs/cookbook/extension-cookbook.md | 2 +- docs/cookbook/extension-cookbook.zh.md | 2 +- docs/graph-atlas.md | 1 + docs/testing.md | 4 +- examples/README.md | 10 +- examples/acp-agent/README.md | 2 +- .../advanced-headless.cordis.snapshot.yml | 32 ------ examples/coding-agent/README.md | 18 +--- examples/coding-agent/cli.cordis.yml | 24 ----- .../tests/fixtures/cli.cordis.yml | 24 ----- examples/headless-agent/README.md | 24 +++++ .../advanced.cordis.snapshot.yml | 12 +++ examples/headless-agent/advanced.cordis.yml | 22 +++++ examples/headless-agent/composition.md | 70 +++++++++++++ examples/headless-agent/cordis.yml | 97 +++++++++++++++++++ examples/headless-agent/package.json | 7 ++ .../tests/fixtures/cli-mock-llm.ts | 2 +- .../tests/fixtures/cli.cordis.yml | 17 ++++ .../tests/headless.snapshot.ts | 2 +- .../tests/keyless-smoke.e2e.ts} | 6 +- .../tests/real-model.e2e.ts} | 8 +- .../snapshots/advanced-toolchain/input.json | 7 ++ .../advanced-toolchain/session.1.jsonl | 13 +++ .../advanced-toolchain/session.2.jsonl | 13 +++ .../advanced-toolchain/session.jsonl | 64 ++++++++++++ .../stream-json.golden.jsonl | 20 ++-- knip.json | 3 +- package.json | 2 +- packages/examples/cli-demo/README.md | 6 +- packages/examples/cli-demo/package.json | 2 +- packages/support/llm-replay/README.md | 2 +- packages/support/loader-smoke/README.md | 2 +- scripts/gen-doc-graphs.ts | 10 ++ vitest.snapshot.config.ts | 8 +- 38 files changed, 410 insertions(+), 140 deletions(-) delete mode 100644 examples/acp-agent/advanced-headless.cordis.snapshot.yml delete mode 100644 examples/coding-agent/cli.cordis.yml delete mode 100644 examples/coding-agent/tests/fixtures/cli.cordis.yml create mode 100644 examples/headless-agent/README.md create mode 100644 examples/headless-agent/advanced.cordis.snapshot.yml create mode 100644 examples/headless-agent/advanced.cordis.yml create mode 100644 examples/headless-agent/composition.md create mode 100644 examples/headless-agent/cordis.yml create mode 100644 examples/headless-agent/package.json rename examples/{coding-agent => headless-agent}/tests/fixtures/cli-mock-llm.ts (95%) create mode 100644 examples/headless-agent/tests/fixtures/cli.cordis.yml rename examples/{acp-agent => headless-agent}/tests/headless.snapshot.ts (98%) rename examples/{coding-agent/tests/cli-keyless-smoke.e2e.ts => headless-agent/tests/keyless-smoke.e2e.ts} (93%) rename examples/{coding-agent/tests/cli.e2e.ts => headless-agent/tests/real-model.e2e.ts} (83%) create mode 100644 examples/headless-agent/tests/snapshots/advanced-toolchain/input.json create mode 100644 examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl create mode 100644 examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl create mode 100644 examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl rename examples/{acp-agent => headless-agent}/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl (92%) diff --git a/README.i18n.yaml b/README.i18n.yaml index 15992ac276..5fa4727e00 100644 --- a/README.i18n.yaml +++ b/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -README.md: 4d2d2c20a27aff67d42a4555f4e0ce410dd5d6d7 -README.zh.md: 0fb307653f978143b851ef4822d93714910043af +README.md: f3b602b070f32101ebab5e11d95e4d49f7ad77a2 +README.zh.md: 0e77269c121f7e95e71bc50855f6df8da9807651 diff --git a/README.md b/README.md index 4d2d2c20a2..f3b602b070 100644 --- a/README.md +++ b/README.md @@ -12,7 +12,7 @@ This monorepo is built on the [Cordis](https://github.com/cordiverse/cordis) fra pnpm install pnpm run test # vitest pnpm run demo:repl # REPL agent demo (needs DEEPSEEK_API_KEY) -pnpm run demo:headless -- "task" # one-shot agent demo (needs DEEPSEEK_API_KEY) +pnpm run demo:headless -- "task" # headless-agent demo (needs DEEPSEEK_API_KEY) pnpm run demo:acp # ACP server agent demo (needs DEEPSEEK_API_KEY) ``` diff --git a/README.zh.md b/README.zh.md index 0fb307653f..0e77269c12 100644 --- a/README.zh.md +++ b/README.zh.md @@ -12,7 +12,7 @@ pnpm install pnpm run test # vitest pnpm run demo:repl # REPL agent demo (needs DEEPSEEK_API_KEY) -pnpm run demo:headless -- "task" # one-shot agent demo (needs DEEPSEEK_API_KEY) +pnpm run demo:headless -- "task" # headless-agent demo (needs DEEPSEEK_API_KEY) pnpm run demo:acp # ACP server agent demo (needs DEEPSEEK_API_KEY) ``` diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index 207ea114e0..ce6b8a5316 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -extension-cookbook.md: 3474bc116b43f9be57b52e947f9cf99730f7e796 -extension-cookbook.zh.md: 1a605b20fe4e171a948ac2a046193a2f4d884e44 +extension-cookbook.md: 9d583a484fca89810bf1e7062fe9aab5b2a2da5e +extension-cookbook.zh.md: afb6edee56be5aeec22957acb903a6ac3a869856 diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index 3474bc116b..9d583a484f 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -87,7 +87,7 @@ export function apply(ctx: Context) { ## Runnable wirings -Three complete examples load their plugin trees from `cordis.yml`: [`examples/echo-agent`](../../examples/echo-agent) (mock model + echo tool — the all-mock skeleton check, `pnpm run demo:echo`), [`examples/coding-agent`](../../examples/coding-agent) (DeepSeek V4 + the bash tool suite behind a terminal REPL UI, `pnpm run demo:repl`), and [`examples/acp-agent`](../../examples/acp-agent) (an agent exposed as an ACP server over JSON-RPC stdio — the client-driver shape, `pnpm run demo:acp`). Each leaf is just its swappable backends plus an app-package entry: the stdio demos load [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo), the ACP demo loads [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo), and both app packages share the spine via the [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle. +Five complete examples load their plugin trees from `cordis.yml`: [`examples/echo-agent`](../../examples/echo-agent) (mock model + echo tool — the all-mock skeleton check, `pnpm run demo:echo`), [`examples/coding-agent`](../../examples/coding-agent) (DeepSeek V4 + coding tools behind a terminal REPL, `pnpm run demo:repl`), [`examples/headless-agent`](../../examples/headless-agent) (the same capability class behind a one-shot positional task and DSH-native output, `pnpm run demo:headless -- "task"`), [`examples/cordis-agent`](../../examples/cordis-agent) (the self-referential runtime-inspection demo, `pnpm run demo:cordis`), and [`examples/acp-agent`](../../examples/acp-agent) (an agent exposed as an ACP server over JSON-RPC stdio — the client-driver shape, `pnpm run demo:acp`). Each leaf is its swappable backends plus one app-package entry: the stdio demos load [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo), the headless demo loads [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo), the ACP demo loads [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo), and all three app packages share the spine through [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo). ## The feature → mechanism map diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index 1a605b20fe..afb6edee56 100644 --- a/docs/cookbook/extension-cookbook.zh.md +++ b/docs/cookbook/extension-cookbook.zh.md @@ -87,7 +87,7 @@ export function apply(ctx: Context) { ## 可运行的组装示例 -三个完整示例从 `cordis.yml` 加载各自的插件树：[`examples/echo-agent`](../../examples/echo-agent)（mock 模型 + echo 工具——全 mock 骨架检查，`pnpm run demo:echo`）、[`examples/coding-agent`](../../examples/coding-agent)（DeepSeek V4 + bash 工具套件，配合终端 REPL UI，`pnpm run demo:repl`）、[`examples/acp-agent`](../../examples/acp-agent)（通过 JSON-RPC stdio 暴露为 ACP 服务器的 agent——客户端驱动形态，`pnpm run demo:acp`）。每个叶子只是其可替换后端加一个 app 包入口：stdio 演示加载 [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo)，ACP 演示加载 [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo)，两个 app 包通过 [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle 共享主干。 +五个完整示例从 `cordis.yml` 加载各自的插件树：[`examples/echo-agent`](../../examples/echo-agent)（mock 模型 + echo 工具——全 mock 骨架检查，`pnpm run demo:echo`）、[`examples/coding-agent`](../../examples/coding-agent)（DeepSeek V4 + coding 工具，配合终端 REPL，`pnpm run demo:repl`）、[`examples/headless-agent`](../../examples/headless-agent)（同类能力通过单次位置任务和 DSH 原生输出运行，`pnpm run demo:headless -- "task"`）、[`examples/cordis-agent`](../../examples/cordis-agent)（自引用的运行时检查演示，`pnpm run demo:cordis`）、[`examples/acp-agent`](../../examples/acp-agent)（通过 JSON-RPC stdio 暴露为 ACP 服务器的 agent——客户端驱动形态，`pnpm run demo:acp`）。每个叶子由其可替换后端加一个 app 包入口组成：stdio 演示加载 [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo)，headless 演示加载 [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo)，ACP 演示加载 [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo)，三个 app 包都通过 [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) 共享主干。 ## 功能→机制映射 diff --git a/docs/graph-atlas.md b/docs/graph-atlas.md index 60de01ef81..6645fb5ef9 100644 --- a/docs/graph-atlas.md +++ b/docs/graph-atlas.md @@ -14,6 +14,7 @@ The process decision behind this index is recorded in [the documentation graph R | [capability seams and core services](capability-seams.md) | `hybrid generated` | | [echo-agent app composition](../examples/echo-agent/composition.md) | `hybrid generated` | | [coding-agent app composition](../examples/coding-agent/composition.md) | `hybrid generated` | +| [headless-agent app composition](../examples/headless-agent/composition.md) | `hybrid generated` | | [cordis-agent app composition](../examples/cordis-agent/composition.md) | `hybrid generated` | | [acp-agent app composition](../examples/acp-agent/composition.md) | `hybrid generated` | | [event producer/consumer matrix](event-producer-consumer.md) | `hybrid generated` | diff --git a/docs/testing.md b/docs/testing.md index 8d318ebd60..cf7343f8d9 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -7,7 +7,7 @@ How this repo tests, tier by tier, and the rules that keep a green suite meaning - **Unit** (`pnpm run test`): vitest over `packages|examples/*/tests/**/*.spec.ts`, colocated with what they test. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Prefer edge cases, error paths, event ordering, concurrency races, and permanent contract regressions (see `packages/core/agent-loop/tests/contract-regressions.spec.ts`). - **Coverage gate** (`pnpm run test:coverage`): the gating run, per-file 100% on `packages/*/*/src`. An uncovered line is often dead code the gate is correctly flagging for deletion, not a missing test to bolt on. Line coverage is necessary, never sufficient — it proves lines ran, not that the feature works as shipped. - **Real-API e2e** (`pnpm run test:e2e`): with-key tests against live provider APIs — the DeepSeek model plus provider-specific smokes that gate on their own keys (`EXA_API_KEY`, `PERPLEXITY_API_KEY`, …); each suite self-skips without its key so keyless CI stays green ([real-API e2e RFC](rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md)). -- **Snapshot** (`pnpm run test:snapshot`): real example subprocesses replay recorded model sessions keylessly and compare normalized stdout plus re-persisted logs ([snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)). The primary suite pins ACP JSON-RPC; the headless projection reuses `advanced-toolchain` for `stream-json`. Use `pnpm run test:snapshot:record` when the model transcript changes and `pnpm run test:snapshot:refresh` when only replay outputs change; review the golden diff. One scenario per header class pins system-prompt/tool-schema content; other fixtures tokenize it ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). +- **Snapshot** (`pnpm run test:snapshot`): real example subprocesses replay recorded model sessions keylessly and compare normalized stdout plus re-persisted logs ([snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)). `examples/acp-agent` pins ACP JSON-RPC, while `examples/headless-agent` independently pins its `stream-json` event surface. Use `pnpm run test:snapshot:record` when an ACP model transcript changes and `pnpm run test:snapshot:refresh` when replay outputs change; review the golden diff. One ACP scenario per header class pins system-prompt/tool-schema content; other ACP fixtures tokenize it ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). ## The with-key policy: inference is cheap here @@ -30,4 +30,4 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword ## When a snapshot test is required -A change affecting an editor transcript, headless event stream, or agent UX adds or updates the owning `examples//tests/snapshots/` scenario, or explains its omission in the PR. `examples/acp-agent` hosts the primary [`dsh-acp-snapshot`](../packages/support/acp-snapshot/README.md) table and the headless `stream-json` projection. Plans for new capability seams, lifecycle shapes, or transcript surfaces identify every test tier and any required harness work before implementation. +A change affecting an editor transcript, headless event stream, or agent UX adds or updates the owning `examples//tests/snapshots/` scenario, or explains its omission in the PR. `examples/acp-agent` owns the [`dsh-acp-snapshot`](../packages/support/acp-snapshot/README.md) table; `examples/headless-agent` owns the `stream-json` snapshot and its replay fixtures. Plans for new capability seams, lifecycle shapes, or transcript surfaces identify every test tier and any required harness work before implementation. diff --git a/examples/README.md b/examples/README.md index 399769992f..2ee6d3eee9 100644 --- a/examples/README.md +++ b/examples/README.md @@ -17,10 +17,16 @@ Run with: `pnpm run demo:echo`. When prompted, type "echo " to trigge A REPL agent demo: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite, `subagent` delegation, and the `todo_write` task tracker on the same `@deepseek-ai/dsh-stdio-demo` app. The UI is a terminal readline REPL. -Run interactively with `pnpm run demo:repl`, or run one headless task with `pnpm run demo:headless -- "task"` (both need `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. +Run with `pnpm run demo:repl` (needs `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. Run the Code Mode overlay with `pnpm run demo:code-mode`, or pass `acp` for the ACP example. See the [Code Mode example](coding-agent/README.md#code-mode) for its composition and a sample task. +## headless-agent + +A non-interactive agent demo that accepts one positional task, runs one complete model/tool turn on the `@deepseek-ai/dsh-cli-demo` app, persists a fresh session, prints `text`, `json`, or `stream-json`, and exits. + +Run with: `pnpm run demo:headless -- "task"` (needs `DEEPSEEK_API_KEY`). See [headless-agent/README.md](headless-agent/README.md) for the wire contract, mutation and token risks, and the headless-owned snapshot suite. + ## cordis-agent The **self-referential** demo: the coding spine plus [`@deepseek-ai/dsh-tool-cordis`](../packages/cordis/tool-cordis), whose three tools (`cordis_inspect` / `cordis_mount` / `cordis_unmount`) let the agent inspect the live cordis runtime it runs inside, mount model-written plugins into it (an event listener, a brand-new tool for itself, or a service another mount injects), and dispose them again — all dynamic mounts grouped under one `cordis-dynamic` fiber subtree. The `ctx.fs`/`ctx.web` services ride along provider-only, as the capabilities those plugins build on. @@ -29,7 +35,7 @@ Run with: `pnpm run demo:cordis` (needs `DEEPSEEK_API_KEY`). See [cordis-agent/R ## acp-agent -An agent demo exposed as an **Agent Client Protocol (ACP)** server over JSON-RPC stdio, via the [`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo) app — drive it from Zed or any other ACP client. Also the home of the keyless snapshot tests. +An agent demo exposed as an **Agent Client Protocol (ACP)** server over JSON-RPC stdio, via the [`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo) app — drive it from Zed or any other ACP client. It owns the ACP keyless snapshot suite. Run with: `pnpm run demo:acp` (needs `DEEPSEEK_API_KEY`); `pnpm run demo:code-mode acp` boots the same server in Code Mode via the `code-mode.cordis.yml` overlay. See [acp-agent/README.md](acp-agent/README.md) for the Zed setup and the snapshot-test design. diff --git a/examples/acp-agent/README.md b/examples/acp-agent/README.md index 427b924d45..000f693941 100644 --- a/examples/acp-agent/README.md +++ b/examples/acp-agent/README.md @@ -33,7 +33,7 @@ The editor sets each session's `cwd` to the project it opens, and bash uses that ## Snapshot tests (record-once / replay-deterministic) -This example hosts the ACP snapshot suite and the headless `stream-json` snapshot. Both replay through `dsh-llm-replay`, which reconstructs model streams from `assistant/chunk` events in each scenario's session JSONL. The headless snapshot reuses `advanced-toolchain` to pin the one-shot stream plus its re-persisted parent and child logs; child activity appears in the stream only through parent tool events. Recording runs the real ACP agent and harvests its logs; refresh keeps the committed transcript as mock input and rewrites current replay outputs. `replay.override.json` covers throw and hang cases that chunks cannot express, and an optional `workspace/` seeds files. The [snapshot RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) owns the ACP harness design. +This example hosts the ACP snapshot suite. It replays through `dsh-llm-replay`, which reconstructs model streams from `assistant/chunk` events in each scenario's session JSONL. Recording runs the real ACP agent and harvests its logs; refresh keeps the committed transcript as mock input and rewrites current replay outputs. `replay.override.json` covers throw and hang cases that chunks cannot express, and an optional `workspace/` seeds files. The [snapshot RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) owns the ACP harness design. ## Permissions and sandboxing diff --git a/examples/acp-agent/advanced-headless.cordis.snapshot.yml b/examples/acp-agent/advanced-headless.cordis.snapshot.yml deleted file mode 100644 index 5047635ddb..0000000000 --- a/examples/acp-agent/advanced-headless.cordis.snapshot.yml +++ /dev/null @@ -1,32 +0,0 @@ -# Replay the advanced toolchain through the headless one-shot front door. It -# receives this replay config explicitly; unlike the ACP bin, it does not swap -# a live config for a sibling snapshot overlay. -- id: base - name: '@cordisjs/plugin-include' - config: - path: ./cordis.yml - patches: - - id: llm-deepseek - name: '@deepseek-ai/dsh-llm-deepseek' - disabled: true - - id: acp-agent - name: '@deepseek-ai/dsh-acp-demo' - disabled: true - - insert: - - id: cli-agent - name: '@deepseek-ai/dsh-cli-demo' - config: - model: deepseek-v4-flash - persistenceRoot: './.sessions' - tools: - mode: both - persona: | - You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. - - Verify your work by running the code or tests. Keep answers brief and factual. - - id: code-runtime - name: '@deepseek-ai/dsh-code-runtime-worker' - - id: tool-cordis - name: '@deepseek-ai/dsh-tool-cordis' - - id: llm-replay - name: '@deepseek-ai/dsh-llm-replay' diff --git a/examples/coding-agent/README.md b/examples/coding-agent/README.md index cf47fb2a85..8dfff33f8b 100644 --- a/examples/coding-agent/README.md +++ b/examples/coding-agent/README.md @@ -1,6 +1,6 @@ # coding-agent -Coding-agent demo wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + workflows + `todo_write` + JSONL persistence. `cordis.yml` runs the terminal readline REPL; `cli.cordis.yml` keeps the same coding capabilities behind a headless one-shot CLI. +Coding-agent REPL wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + workflows + `todo_write` + JSONL persistence. ## Run it @@ -21,20 +21,6 @@ Type a coding task. The agent works through the `read`/`write`/`edit` filesystem … ``` -### One-shot CLI - -Run one task through all model and tool steps, flush its fresh session, print the final result, and exit: - -```sh -pnpm run demo:headless -- "fix the failing test in this workspace" -pnpm run demo:headless --output-format json -- "summarize the current implementation" -pnpm run demo:headless --output-format stream-json -- "run the focused tests" -``` - -The root command supplies `cli.cordis.yml`, which disables HMR and the REPL app and inserts [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo). Exactly one quoted positional task is required; there is no `-p` flag. `text` prints the last text-bearing assistant message, `json` prints one DSH-native result record, and `stream-json` emits the parent `main` session's canonical task-turn events before that record. Non-completed turns retain partial output but exit nonzero; argument and boot failures leave stdout empty. - -This is non-interactive automation with the same local bash, filesystem, skill, subagent, workflow, and todo capabilities as the REPL. It can mutate the launch workspace and spend provider tokens. No prompt, approval, resume, further turn, or stdin context is available in v1; see the [CLI package contract](../../packages/examples/cli-demo/README.md). - ### Resuming a prior session Each run starts a fresh session by default (its event log lands under `./.sessions/`). To **continue** a previous conversation, set `RESUME_SESSION_ID` to that session's id — the `main` agent then rehydrates the persisted log instead of starting fresh, so the model sees the earlier turns as history: @@ -83,4 +69,4 @@ This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads - `tests/compaction.e2e.ts` — the compaction smoke: a real multi-step bash task runs with a deliberately tiny context window so the auto-compaction listener fires MID-SESSION. Verifies the WORLD — a `compact/start…end` pair landed in the real log, the surface shrank (a replace node shadowed older nodes), and the agent still produced a correct final answer after compaction. - `tests/todo-write.e2e.ts` — a real model drives the real `todo_write` tool and the test verifies the resulting `todo/write` session event. -These self-skip without `DEEPSEEK_API_KEY`. `tests/code-mode.e2e.ts` is the with-key Code Mode proof — a real model, a two-tool task, asserting the wire tool list was exactly `[run_code]`, the `tool/code-dispatch` events landed under the parent call, and the curated answer came back. `tests/cli.e2e.ts` runs the one-shot bin with a real model and verifies its temporary file externally. The keyless Loader smokes run in the default e2e gate: `tests/keyless-smoke.e2e.ts`, `tests/code-mode-keyless-smoke.e2e.ts`, and `tests/cli-keyless-smoke.e2e.ts`; the CLI smoke mocks only the LLM boundary and asserts a real bash round trip plus persisted stream output. +These self-skip without `DEEPSEEK_API_KEY`. `tests/code-mode.e2e.ts` is the with-key Code Mode proof — a real model, a two-tool task, asserting the wire tool list was exactly `[run_code]`, the `tool/code-dispatch` events landed under the parent call, and the curated answer came back. The keyless Loader smokes run in the default e2e gate: `tests/keyless-smoke.e2e.ts` and `tests/code-mode-keyless-smoke.e2e.ts`. diff --git a/examples/coding-agent/cli.cordis.yml b/examples/coding-agent/cli.cordis.yml deleted file mode 100644 index 5a58dfd889..0000000000 --- a/examples/coding-agent/cli.cordis.yml +++ /dev/null @@ -1,24 +0,0 @@ -# One-shot headless overlay: keep the coding capabilities from `cordis.yml`, -# replace its REPL app with the stdout-pure CLI app, and disable dev-only HMR. -- id: base - name: '@cordisjs/plugin-include' - config: - path: ./cordis.yml - patches: - - id: hmr - name: '@cordisjs/plugin-hmr' - disabled: true - - id: stdio-agent - name: '@deepseek-ai/dsh-stdio-demo' - disabled: true - - insert: - - id: cli-agent - name: '@deepseek-ai/dsh-cli-demo' - config: - model: deepseek-v4-flash - persistenceRoot: './.sessions' - persona: | - You are coding-agent, a coding assistant powered by the {{model}} model. - - Verify your work by running the code or tests. Keep answers brief and - factual. diff --git a/examples/coding-agent/tests/fixtures/cli.cordis.yml b/examples/coding-agent/tests/fixtures/cli.cordis.yml deleted file mode 100644 index bdec0154c4..0000000000 --- a/examples/coding-agent/tests/fixtures/cli.cordis.yml +++ /dev/null @@ -1,24 +0,0 @@ -- id: cli-mock-llm - name: './cli-mock-llm.ts' - -- id: base - name: '@cordisjs/plugin-include' - config: - path: ../../cordis.yml - patches: - - id: hmr - name: '@cordisjs/plugin-hmr' - disabled: true - - id: llm-deepseek - name: '@deepseek-ai/dsh-llm-deepseek' - disabled: true - - id: stdio-agent - name: '@deepseek-ai/dsh-stdio-demo' - disabled: true - - insert: - - id: cli-agent - name: '@deepseek-ai/dsh-cli-demo' - config: - model: cli-mock - persistenceRoot: './.sessions' - persona: 'Keyless CLI smoke.' diff --git a/examples/headless-agent/README.md b/examples/headless-agent/README.md new file mode 100644 index 0000000000..5c21855afe --- /dev/null +++ b/examples/headless-agent/README.md @@ -0,0 +1,24 @@ +# headless-agent + +Headless one-shot agent wiring: DeepSeek V4 + local bash and filesystem tools + subagent delegation + workflows + `todo_write` + JSONL persistence, with [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo) as the app front door. + +## Run it + +```sh +# repo root .env (gitignored) or exported env: +# DEEPSEEK_API_KEY=sk-… +# DEEPSEEK_BASE_URL=https://… # optional; defaults to the public API +pnpm run demo:headless -- "fix the failing test in this workspace" +pnpm run demo:headless --output-format json -- "summarize the implementation" +pnpm run demo:headless --output-format stream-json -- "run the focused tests" +``` + +Exactly one nonblank positional task is required; quote tasks containing spaces. There is no `-p` flag. `text` prints the last text-bearing assistant message, `json` prints one DSH-native result record, and `stream-json` emits the parent `main` session's canonical task-turn events before that record. Child sessions surface only through parent tool events and results. + +Each invocation creates and persists a fresh session, runs all model and tool steps in one turn, flushes, disposes, and exits. This is non-interactive automation: there is no prompt, approval, resume, second turn, or stdin context. The configured tools can mutate the launch workspace, run commands, spawn child agents, and consume provider tokens. + +## Advanced and snapshot wiring + +[`advanced.cordis.yml`](advanced.cordis.yml) adds Code Mode and the Cordis tools to the shipped leaf. [`advanced.cordis.snapshot.yml`](advanced.cordis.snapshot.yml) replaces only the live LLM with replay. The tests under [`tests/`](tests/) own the keyless real-Loader smoke, key-gated world-verified smoke, and the `stream-json` replay snapshot with its parent and child session fixtures. + +The package-level [CLI contract](../../packages/examples/cli-demo/README.md) documents output records, exit status, cancellation, persistence, and model/token effects. diff --git a/examples/headless-agent/advanced.cordis.snapshot.yml b/examples/headless-agent/advanced.cordis.snapshot.yml new file mode 100644 index 0000000000..48541a1054 --- /dev/null +++ b/examples/headless-agent/advanced.cordis.snapshot.yml @@ -0,0 +1,12 @@ +# Replay counterpart to advanced.cordis.yml; only the live model is replaced. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./advanced.cordis.yml + patches: + - id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + disabled: true + - insert: + - id: llm-replay + name: '@deepseek-ai/dsh-llm-replay' diff --git a/examples/headless-agent/advanced.cordis.yml b/examples/headless-agent/advanced.cordis.yml new file mode 100644 index 0000000000..646bd8a11c --- /dev/null +++ b/examples/headless-agent/advanced.cordis.yml @@ -0,0 +1,22 @@ +# Add Code Mode and Cordis tools to the headless spawn/workflow stack. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./cordis.yml + patches: + - id: cli-agent + name: '@deepseek-ai/dsh-cli-demo' + config: + model: deepseek-v4-flash + persistenceRoot: './.sessions' + tools: + mode: both + persona: | + You are headless-agent, a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. + + Verify your work by running the code or tests. Keep answers brief and factual. + - insert: + - id: code-runtime + name: '@deepseek-ai/dsh-code-runtime-worker' + - id: tool-cordis + name: '@deepseek-ai/dsh-tool-cordis' diff --git a/examples/headless-agent/composition.md b/examples/headless-agent/composition.md new file mode 100644 index 0000000000..9a734fa2f0 --- /dev/null +++ b/examples/headless-agent/composition.md @@ -0,0 +1,70 @@ + + +# Headless Agent App Composition + +The headless demo combines the real DeepSeek adapter and coding capabilities with the one-shot app package, format-pure stdout, and one fresh persisted main session. + +```mermaid +flowchart LR + cfg["examples/headless-agent
cordis.yml"] + plugin_headless_llm_deepseek["llm-deepseek
@deepseek-ai/dsh-llm-deepseek"] + cfg --> plugin_headless_llm_deepseek + plugin_headless_bash["bash
@deepseek-ai/dsh-bash-local"] + cfg --> plugin_headless_bash + plugin_headless_cli_agent["cli-agent
@deepseek-ai/dsh-cli-demo"] + cfg --> plugin_headless_cli_agent + plugin_headless_cli_agent --> bundle_agent_core["@deepseek-ai/dsh-agent-spine-demo"] + plugin_headless_cli_agent --> bundle_jsonl["@deepseek-ai/dsh-session-persistence-jsonl"] + plugin_headless_cli_agent --> frontdoor_cli["one-shot driver
format-pure stdout
pre-created main agent"] + bundle_agent_core --> spine_llm["ctx.llm"] + bundle_agent_core --> spine_sessions["ctx.sessions"] + bundle_agent_core --> spine_tools["ctx.tools + tool-bash"] + bundle_agent_core --> spine_loop["ctx.agents + ctx.agentLoop"] + plugin_headless_compact_basic["compact-basic
@deepseek-ai/dsh-compact-basic"] + cfg --> plugin_headless_compact_basic + plugin_headless_subagent["subagent
@deepseek-ai/dsh-subagent"] + cfg --> plugin_headless_subagent + plugin_headless_subagent_spawn["subagent-spawn
@deepseek-ai/dsh-subagent-spawn"] + cfg --> plugin_headless_subagent_spawn + plugin_headless_subagent_fork["subagent-fork
@deepseek-ai/dsh-subagent-fork"] + cfg --> plugin_headless_subagent_fork + plugin_headless_tool_subagent["tool-subagent
@deepseek-ai/dsh-tool-subagent"] + cfg --> plugin_headless_tool_subagent + plugin_headless_tool_subagent_fork["tool-subagent-fork
@deepseek-ai/dsh-tool-subagent"] + cfg --> plugin_headless_tool_subagent_fork + plugin_headless_workflow_workerthread["workflow-workerthread
@deepseek-ai/dsh-workflow-workerthread"] + cfg --> plugin_headless_workflow_workerthread + plugin_headless_tool_workflow["tool-workflow
@deepseek-ai/dsh-tool-workflow"] + cfg --> plugin_headless_tool_workflow + plugin_headless_tool_todo["tool-todo
@deepseek-ai/dsh-tool-todo"] + cfg --> plugin_headless_tool_todo + plugin_headless_fs_local["fs-local
@deepseek-ai/dsh-fs-local"] + cfg --> plugin_headless_fs_local + plugin_headless_fs_policy["fs-policy
@deepseek-ai/dsh-fs-policy"] + cfg --> plugin_headless_fs_policy + plugin_headless_tool_fs["tool-fs
@deepseek-ai/dsh-tool-fs"] + cfg --> plugin_headless_tool_fs +``` + +| Plugin id | Package / module | +| --- | --- | +| `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` | +| `bash` | `@deepseek-ai/dsh-bash-local` | +| `cli-agent` | `@deepseek-ai/dsh-cli-demo` | +| `compact-basic` | `@deepseek-ai/dsh-compact-basic` | +| `subagent` | `@deepseek-ai/dsh-subagent` | +| `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` | +| `subagent-fork` | `@deepseek-ai/dsh-subagent-fork` | +| `tool-subagent` | `@deepseek-ai/dsh-tool-subagent` | +| `tool-subagent-fork` | `@deepseek-ai/dsh-tool-subagent` | +| `workflow-workerthread` | `@deepseek-ai/dsh-workflow-workerthread` | +| `tool-workflow` | `@deepseek-ai/dsh-tool-workflow` | +| `tool-todo` | `@deepseek-ai/dsh-tool-todo` | +| `fs-local` | `@deepseek-ai/dsh-fs-local` | +| `fs-policy` | `@deepseek-ai/dsh-fs-policy` | +| `tool-fs` | `@deepseek-ai/dsh-tool-fs` | + +Source config: [`examples/headless-agent/cordis.yml`](cordis.yml). + +Maintenance mode: hybrid: the leaf plugin list is parsed from its `cordis.yml`; app package expansion is curated from package source. diff --git a/examples/headless-agent/cordis.yml b/examples/headless-agent/cordis.yml new file mode 100644 index 0000000000..3cf1d127a2 --- /dev/null +++ b/examples/headless-agent/cordis.yml @@ -0,0 +1,97 @@ +# One-shot coding agent with format-pure stdout. The app bin loads the +# gitignored root `.env`; this file reads `DEEPSEEK_API_KEY` and optional +# `DEEPSEEK_BASE_URL` through `!!js`. + +# The DeepSeek adapter. Swap to '@deepseek-ai/dsh-llm-pi-ai' for the pi-ai-backed +# twin (same config shape; `reasoning: high` replaces thinking/reasoningEffort). +- id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + config: + apiKey: !!js process.env.DEEPSEEK_API_KEY + baseURL: !!js process.env.DEEPSEEK_BASE_URL + models: + - deepseek-v4-pro + - deepseek-v4-flash + +# Local executor for the app bundle's bash tool. +- id: bash + name: '@deepseek-ai/dsh-bash-local' + config: + timeoutMs: 60000 + +# The app bundle pre-creates one fresh `main` agent per invocation. +- id: cli-agent + name: '@deepseek-ai/dsh-cli-demo' + config: + model: deepseek-v4-flash + persistenceRoot: './.sessions' + persona: | + You are headless-agent, a coding assistant powered by the {{model}} model. + + Verify your work by running the code or tests. Keep answers brief and + factual. + +# Summarize an older range when derived history approaches the context window. +- id: compact-basic + name: '@deepseek-ai/dsh-compact-basic' + config: + contextWindow: 128000 + thresholdRatio: 0.8 + retainTokens: 20480 + summarizationModel: '' + maxTokens: 8192 + compactionRetries: 1 + +# Expose fresh-child `spawn` and completed-prefix `fork` through independent +# in-process backends. +- id: subagent + name: '@deepseek-ai/dsh-subagent' + +- id: subagent-spawn + name: '@deepseek-ai/dsh-subagent-spawn' + config: + providerName: spawn + +- id: subagent-fork + name: '@deepseek-ai/dsh-subagent-fork' + config: + providerName: fork + +- id: tool-subagent + name: '@deepseek-ai/dsh-tool-subagent' + config: + provider: spawn + toolName: subagent + +- id: tool-subagent-fork + name: '@deepseek-ai/dsh-tool-subagent' + config: + provider: fork + toolName: subagent_fork + +# The worker-thread workflow engine fans a model-written JavaScript script's +# `agent()` calls out through the spawn backend. +- id: workflow-workerthread + name: '@deepseek-ai/dsh-workflow-workerthread' + config: + provider: spawn + +- id: tool-workflow + name: '@deepseek-ai/dsh-tool-workflow' + +# `todo_write` replaces the logged whole list. +- id: tool-todo + name: '@deepseek-ai/dsh-tool-todo' + +# Policy loads before the model-facing filesystem tools so writes and edits +# require an observed file. Relative paths resolve from the process cwd. +- id: fs-local + name: '@deepseek-ai/dsh-fs-local' + config: + cwd: !!js process.cwd() + +- id: fs-policy + name: '@deepseek-ai/dsh-fs-policy' + +- id: tool-fs + name: '@deepseek-ai/dsh-tool-fs' diff --git a/examples/headless-agent/package.json b/examples/headless-agent/package.json new file mode 100644 index 0000000000..c331af0f05 --- /dev/null +++ b/examples/headless-agent/package.json @@ -0,0 +1,7 @@ +{ + "name": "headless-agent-example", + "private": true, + "version": "0.0.1", + "type": "module", + "description": "Runnable demo: one complete headless coding-agent turn" +} diff --git a/examples/coding-agent/tests/fixtures/cli-mock-llm.ts b/examples/headless-agent/tests/fixtures/cli-mock-llm.ts similarity index 95% rename from examples/coding-agent/tests/fixtures/cli-mock-llm.ts rename to examples/headless-agent/tests/fixtures/cli-mock-llm.ts index 6447ba1e18..5238e67374 100644 --- a/examples/coding-agent/tests/fixtures/cli-mock-llm.ts +++ b/examples/headless-agent/tests/fixtures/cli-mock-llm.ts @@ -1,7 +1,7 @@ import type { Context } from 'cordis' import { CallId, LlmAdapter, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm' -/** Keyless coding smoke adapter: one real bash call followed by a final answer. */ +/** Keyless headless-agent adapter: one real bash call followed by a final answer. */ class CliMockAdapter extends LlmAdapter { async * stream(options: GenerateOptions): AsyncIterable { const toolResult = options.messages.at(-1)?.content.find(block => block.type === 'tool-result') diff --git a/examples/headless-agent/tests/fixtures/cli.cordis.yml b/examples/headless-agent/tests/fixtures/cli.cordis.yml new file mode 100644 index 0000000000..7e042789b2 --- /dev/null +++ b/examples/headless-agent/tests/fixtures/cli.cordis.yml @@ -0,0 +1,17 @@ +- id: cli-mock-llm + name: './cli-mock-llm.ts' + +- id: base + name: '@cordisjs/plugin-include' + config: + path: ../../cordis.yml + patches: + - id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + disabled: true + - id: cli-agent + name: '@deepseek-ai/dsh-cli-demo' + config: + model: cli-mock + persistenceRoot: './.sessions' + persona: 'Keyless headless-agent smoke.' diff --git a/examples/acp-agent/tests/headless.snapshot.ts b/examples/headless-agent/tests/headless.snapshot.ts similarity index 98% rename from examples/acp-agent/tests/headless.snapshot.ts rename to examples/headless-agent/tests/headless.snapshot.ts index a38931a8ef..ff27347246 100644 --- a/examples/acp-agent/tests/headless.snapshot.ts +++ b/examples/headless-agent/tests/headless.snapshot.ts @@ -14,7 +14,7 @@ const snapshotsDir = join(dirname(fileURLToPath(import.meta.url)), 'snapshots') const scenarioDir = join(snapshotsDir, 'advanced-toolchain') const sessionFixture = join(scenarioDir, 'session.jsonl') const streamGolden = join(scenarioDir, 'stream-json.golden.jsonl') -const configPath = fileURLToPath(new URL('../advanced-headless.cordis.snapshot.yml', import.meta.url)) +const configPath = fileURLToPath(new URL('../advanced.cordis.snapshot.yml', import.meta.url)) const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url)) const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) const refreshing = process.env.DSH_SNAPSHOT === 'refresh' diff --git a/examples/coding-agent/tests/cli-keyless-smoke.e2e.ts b/examples/headless-agent/tests/keyless-smoke.e2e.ts similarity index 93% rename from examples/coding-agent/tests/cli-keyless-smoke.e2e.ts rename to examples/headless-agent/tests/keyless-smoke.e2e.ts index c2d0f3f946..57b8660c03 100644 --- a/examples/coding-agent/tests/cli-keyless-smoke.e2e.ts +++ b/examples/headless-agent/tests/keyless-smoke.e2e.ts @@ -8,12 +8,12 @@ const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src const configPath = fileURLToPath(new URL('./fixtures/cli.cordis.yml', import.meta.url)) const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) -describe('coding-agent one-shot CLI keyless smoke', () => { +describe('headless-agent keyless smoke', () => { it('boots the real Loader tree, runs a real bash tool round trip, and persists the turn', async () => { let persisted = false const { stdout, stderr } = await runLoaderSmoke({ - label: 'coding-agent CLI', - tempDirPrefix: 'coding-cli-smoke-', + label: 'headless-agent', + tempDirPrefix: 'headless-agent-smoke-', binScript, configPath, binArgs: ['--config', configPath, '--output-format', 'stream-json', 'prove the tool path'], diff --git a/examples/coding-agent/tests/cli.e2e.ts b/examples/headless-agent/tests/real-model.e2e.ts similarity index 83% rename from examples/coding-agent/tests/cli.e2e.ts rename to examples/headless-agent/tests/real-model.e2e.ts index a05e19fc06..653f5ab624 100644 --- a/examples/coding-agent/tests/cli.e2e.ts +++ b/examples/headless-agent/tests/real-model.e2e.ts @@ -5,16 +5,16 @@ import { describe, expect, it } from 'vitest' import { runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke' const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url)) -const configPath = fileURLToPath(new URL('../cli.cordis.yml', import.meta.url)) +const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) const hasKey = Boolean(process.env.DEEPSEEK_API_KEY) -describe.skipIf(!hasKey)('coding-agent one-shot CLI with real model', () => { +describe.skipIf(!hasKey)('headless-agent with real model', () => { it('modifies a temporary workspace and verifies the file outside the agent', async () => { let verified = '' const { stdout } = await runLoaderSmoke({ - label: 'coding-agent CLI real model', - tempDirPrefix: 'coding-cli-real-', + label: 'headless-agent real model', + tempDirPrefix: 'headless-agent-real-', binScript, configPath, binArgs: [ diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/input.json b/examples/headless-agent/tests/snapshots/advanced-toolchain/input.json new file mode 100644 index 0000000000..41072a211a --- /dev/null +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/input.json @@ -0,0 +1,7 @@ +{ + "steps": [ + { "op": "initialize" }, + { "op": "newSession" }, + { "op": "prompt", "text": "Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_HEADLESS_OK." } + ] +} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl new file mode 100644 index 0000000000..95924ff6c6 --- /dev/null +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -0,0 +1,13 @@ +{"type":"session","version":0,"id":"22222222-2222-4222-8222-222222222222","createdAt":1783950001000,"cwd":"/tmp/advanced-headless","parentSession":"11111111-1111-4111-8111-111111111111"} +{"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} +{"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} +{"type":"assistant/chunk","seq":7,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":8,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":9,"time":1783957884564,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"step/end","seq":10,"time":1783957884564,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":11,"time":1783957884564,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl new file mode 100644 index 0000000000..5e4387ccb7 --- /dev/null +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -0,0 +1,13 @@ +{"type":"session","version":0,"id":"33333333-3333-4333-8333-333333333333","createdAt":1783950002000,"cwd":"/tmp/advanced-headless","parentSession":"11111111-1111-4111-8111-111111111111"} +{"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} +{"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} +{"type":"assistant/chunk","seq":7,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":8,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":9,"time":1783957884701,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"step/end","seq":10,"time":1783957884701,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":11,"time":1783957884701,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl new file mode 100644 index 0000000000..a1785105cd --- /dev/null +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -0,0 +1,64 @@ +{"type":"session","version":0,"id":"11111111-1111-4111-8111-111111111111","createdAt":1783950000000,"cwd":"/tmp/advanced-headless"} +{"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} +{"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} +{"type":"assistant/chunk","seq":7,"time":1783950000008,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":8,"time":1783950000009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":9,"time":1783957884487,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"tool/call","seq":10,"time":1783957884487,"data":{"turn":1,"step":1,"callId":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}} +{"type":"tool/result","seq":11,"time":1783957884488,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"} +{"type":"step/end","seq":12,"time":1783957884489,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":13,"time":1783957884489,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":14,"time":1783950000015,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":15,"time":1783950000016,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-code","name":"run_code","argumentsDelta":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}} +{"type":"assistant/chunk","seq":16,"time":1783950000017,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}}} +{"type":"assistant/chunk","seq":17,"time":1783950000018,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":18,"time":1783950000019,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":19,"time":1783957884490,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"} +{"type":"tool/call","seq":20,"time":1783957884490,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}} +{"type":"tool/code-dispatch","seq":21,"time":1783957884560,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"},"isError":false,"resultSummary":"## dynamic\n- dyn-1: snapshot-marker [active]"}} +{"type":"tool/result","seq":22,"time":1783957884561,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}],"isError":false,"meta":{"logs":[]}},"sourceEventSeqs":[20],"surfaceOp":"append"} +{"type":"step/end","seq":23,"time":1783957884561,"data":{"turn":1,"step":2}} +{"type":"step/start","seq":24,"time":1783957884562,"data":{"turn":1,"step":3}} +{"type":"assistant/chunk","seq":25,"time":1783950000026,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":26,"time":1783950000027,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-direct-child","name":"subagent","argumentsDelta":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}} +{"type":"assistant/chunk","seq":27,"time":1783950000028,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}} +{"type":"assistant/chunk","seq":28,"time":1783950000029,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":29,"time":1783950000030,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":30,"time":1783957884562,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"} +{"type":"tool/call","seq":31,"time":1783957884562,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}} +{"type":"tool/result","seq":32,"time":1783957884593,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"isError":false},"sourceEventSeqs":[31],"surfaceOp":"append"} +{"type":"step/end","seq":33,"time":1783957884593,"data":{"turn":1,"step":3}} +{"type":"step/start","seq":34,"time":1783957884594,"data":{"turn":1,"step":4}} +{"type":"assistant/chunk","seq":35,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":36,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-workflow","name":"workflow","argumentsDelta":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}}} +{"type":"assistant/chunk","seq":37,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}}}} +{"type":"assistant/chunk","seq":38,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":39,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":40,"time":1783957884594,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"} +{"type":"tool/call","seq":41,"time":1783957884594,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}} +{"type":"tool/result","seq":42,"time":1783957884717,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-headless-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[41],"surfaceOp":"append"} +{"type":"step/end","seq":43,"time":1783957884718,"data":{"turn":1,"step":4}} +{"type":"step/start","seq":44,"time":1783957884718,"data":{"turn":1,"step":5}} +{"type":"assistant/chunk","seq":45,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":46,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-unmount","name":"cordis_unmount","argumentsDelta":"{\"id\":\"dyn-1\"}"}}} +{"type":"assistant/chunk","seq":47,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}}} +{"type":"assistant/chunk","seq":48,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":49,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":50,"time":1783957884719,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"} +{"type":"tool/call","seq":51,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}} +{"type":"tool/result","seq":52,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"unmounted dyn-1 (plugin \"snapshot-marker\")"}],"isError":false},"sourceEventSeqs":[51],"surfaceOp":"append"} +{"type":"step/end","seq":53,"time":1783957884719,"data":{"turn":1,"step":5}} +{"type":"step/start","seq":54,"time":1783957884720,"data":{"turn":1,"step":6}} +{"type":"assistant/chunk","seq":55,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":56,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"text-delta","index":0,"text":"ADVANCED_HEADLESS_OK"}}} +{"type":"assistant/chunk","seq":57,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_HEADLESS_OK"}}}} +{"type":"assistant/chunk","seq":58,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":59,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":60,"time":1783957884720,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_HEADLESS_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"} +{"type":"step/end","seq":61,"time":1783957884721,"data":{"turn":1,"step":6}} +{"type":"turn/end","seq":62,"time":1783957884721,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl similarity index 92% rename from examples/acp-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl rename to examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl index ea5eca3765..35aad5fc89 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl @@ -1,5 +1,5 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} @@ -34,13 +34,13 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":33,"time":0,"data":{"turn":1,"step":3}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":34,"time":0,"data":{"turn":1,"step":4}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":35,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":36,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-workflow","name":"workflow","argumentsDelta":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":36,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-workflow","name":"workflow","argumentsDelta":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":38,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":40,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":41,"time":0,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":42,"time":0,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-acp-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[41],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":40,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":41,"time":0,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":42,"time":0,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-headless-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[41],"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":43,"time":0,"data":{"turn":1,"step":4}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":44,"time":0,"data":{"turn":1,"step":5}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":45,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} @@ -54,11 +54,11 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":53,"time":0,"data":{"turn":1,"step":5}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":54,"time":0,"data":{"turn":1,"step":6}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":55,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":56,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"text-delta","index":0,"text":"ADVANCED_ACP_OK"}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":57,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_ACP_OK"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":56,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"text-delta","index":0,"text":"ADVANCED_HEADLESS_OK"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":57,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_HEADLESS_OK"}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":58,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":59,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":60,"time":0,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_ACP_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":60,"time":0,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_HEADLESS_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":61,"time":0,"data":{"turn":1,"step":6}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":62,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}} -{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"ADVANCED_ACP_OK","reason":{"kind":"completed"},"usage":{"inputTokens":18,"outputTokens":18}} +{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"ADVANCED_HEADLESS_OK","reason":{"kind":"completed"},"usage":{"inputTokens":18,"outputTokens":18}} diff --git a/knip.json b/knip.json index 0d367d84a6..348500575c 100644 --- a/knip.json +++ b/knip.json @@ -9,7 +9,8 @@ "examples/echo-agent/src/*.ts", "examples/echo-agent/tests/**/*.e2e.ts", "examples/coding-agent/tests/**/*.e2e.ts", - "examples/coding-agent/tests/fixtures/*.ts", + "examples/headless-agent/tests/**/*.e2e.ts", + "examples/headless-agent/tests/fixtures/*.ts", "examples/cordis-agent/tests/**/*.e2e.ts", "examples/acp-agent/tests/**/*.e2e.ts", "examples/*/tests/**/*.snapshot.ts" diff --git a/package.json b/package.json index 2bf8506bf8..b3e13479f0 100644 --- a/package.json +++ b/package.json @@ -74,7 +74,7 @@ "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-cordis-config && pnpm run verify-node-next-types && pnpm run verify-runtime-closure", "demo:echo": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/echo-agent/cordis.yml", "demo:repl": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/coding-agent/cordis.yml", - "demo:headless": "node --expose-internals --import tsx packages/examples/cli-demo/src/bin.ts --config examples/coding-agent/cli.cordis.yml", + "demo:headless": "node --expose-internals --import tsx packages/examples/cli-demo/src/bin.ts --config examples/headless-agent/cordis.yml", "demo:code-mode": "node scripts/demo-code-mode.mjs", "demo:cordis": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/cordis-agent/cordis.yml", "demo:acp": "node --import tsx packages/examples/acp-demo/src/bin.ts --config examples/acp-agent/cordis.yml", diff --git a/packages/examples/cli-demo/README.md b/packages/examples/cli-demo/README.md index 38c38cf69c..5334a5bcd9 100644 --- a/packages/examples/cli-demo/README.md +++ b/packages/examples/cli-demo/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-cli-demo -Headless one-shot app and bin for running one coding-agent task without a readline or editor client. The app composes [`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md), JSONL persistence, and one fresh `main` agent; the bin submits one task, waits through all model and tool steps, emits the selected result, disposes to quiescence, and exits. +Headless one-shot app and bin for running one agent task without a readline or editor client. The app composes [`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md), JSONL persistence, and one fresh `main` agent; the bin submits one task, waits through all model and tool steps, emits the selected result, disposes to quiescence, and exits. The package mounts no console logger, readline UI, user-interaction service, or `ask_user_question` tool. Stdout is reserved for the selected output format; diagnostics use stderr. @@ -25,7 +25,7 @@ dsh-cli-demo [--config path] [--output-format text|json|stream-json] `--config` defaults to `./cordis.yml`; `--output-format` defaults to `text`. Exactly one nonblank positional task is required, so quote tasks containing spaces. `--help` prints usage without booting. There is no `-p` or `--print` flag. -The root coding demo supplies its overlay: +The root headless-agent example supplies its leaf: ```sh pnpm run demo:headless -- "inspect the failing test and fix it" @@ -45,7 +45,7 @@ The task turn is explicitly flushed before final output. Session logs remain und ## Operational safety -The coding overlay retains local bash, filesystem, skill, subagent, workflow, and todo capabilities. A task can therefore mutate the launch workspace, run commands, spawn child agents, and consume provider tokens. Run the CLI from the intended project directory, review the leaf's capability and sandbox configuration, and do not treat non-interactive execution as an approval boundary. +The headless-agent leaf supplies local bash, filesystem, skill, subagent, workflow, and todo capabilities. A task can therefore mutate the launch workspace, run commands, spawn child agents, and consume provider tokens. Run the CLI from the intended project directory, review the leaf's capability and sandbox configuration, and do not treat non-interactive execution as an approval boundary. ## Model Experience diff --git a/packages/examples/cli-demo/package.json b/packages/examples/cli-demo/package.json index 3268f9733f..5f6d5d04c2 100644 --- a/packages/examples/cli-demo/package.json +++ b/packages/examples/cli-demo/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-cli-demo", - "description": "Headless one-shot coding-agent app with text and DSH-native JSON output", + "description": "Headless one-shot agent app with text and DSH-native JSON output", "version": "0.0.1", "private": true, "type": "module", diff --git a/packages/support/llm-replay/README.md b/packages/support/llm-replay/README.md index 847064b160..704173cf52 100644 --- a/packages/support/llm-replay/README.md +++ b/packages/support/llm-replay/README.md @@ -2,7 +2,7 @@ A replay LLM plugin for keyless snapshot tests. It installs a single `llm/stream` waterfall listener that short-circuits the waterfall (never calls `next()`) and yields model streams reconstructed from a recorded **session JSONL** fixture — so a test can boot the real agent against a fixed model transcript with no API key. -Its consumer is the ACP snapshot harness in `examples/acp-agent`, which loads this plugin (via `cordis.snapshot.yml`) in place of a real LLM adapter. The package exists so its derive/parse/replay logic falls under the per-file 100% coverage gate on `packages/*/src` (the same logic, while it lived under `examples/`, was outside the gate). +Its consumers are the ACP snapshot harness in `examples/acp-agent` and the `stream-json` snapshot in `examples/headless-agent`; each loads this plugin in place of a real LLM adapter. The package exists so its derive/parse/replay logic falls under the per-file 100% coverage gate on `packages/*/src` (the same logic, while it lived under `examples/`, was outside the gate). ## How the fixture works diff --git a/packages/support/loader-smoke/README.md b/packages/support/loader-smoke/README.md index 4527be6430..7514babb8a 100644 --- a/packages/support/loader-smoke/README.md +++ b/packages/support/loader-smoke/README.md @@ -4,7 +4,7 @@ Shared subprocess harness for keyless example smokes that boot a real app bin an Successful runs return stdout and stderr only after a zero exit. Non-zero exits and deadlines reject with both captured streams. `LOADER_SMOKE_TEST_TIMEOUT_MS` leaves Vitest enough room for the process-owned diagnostic timeout to fire first. -This is support-tier test infrastructure, not product API. The consumers are the Loader-path smokes under `examples/{echo-agent,coding-agent,cordis-agent}`. +This is support-tier test infrastructure, not product API. The consumers are the Loader-path smokes under `examples/{echo-agent,coding-agent,headless-agent,cordis-agent}`. ## Model Experience diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 5996cd203e..505921ab40 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -409,6 +409,14 @@ const APP_EXAMPLES = [ config: 'examples/coding-agent/cordis.yml', summary: 'The coding REPL demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package.', }, + { + id: 'headless', + rel: 'examples/headless-agent/composition.md', + title: 'Headless Agent App Composition', + label: 'examples/headless-agent', + config: 'examples/headless-agent/cordis.yml', + summary: 'The headless demo combines the real DeepSeek adapter and coding capabilities with the one-shot app package, format-pure stdout, and one fresh persisted main session.', + }, { id: 'cordis', rel: 'examples/cordis-agent/composition.md', @@ -944,6 +952,7 @@ function renderIndex(docs: GraphDoc[]): string { 'docs/capability-seams.md': 'capability seams and core services', 'examples/echo-agent/composition.md': 'echo-agent app composition', 'examples/coding-agent/composition.md': 'coding-agent app composition', + 'examples/headless-agent/composition.md': 'headless-agent app composition', 'examples/cordis-agent/composition.md': 'cordis-agent app composition', 'examples/acp-agent/composition.md': 'acp-agent app composition', 'docs/event-producer-consumer.md': 'event producer/consumer matrix', @@ -955,6 +964,7 @@ function renderIndex(docs: GraphDoc[]): string { 'docs/capability-seams.md': 'hybrid generated', 'examples/echo-agent/composition.md': 'hybrid generated', 'examples/coding-agent/composition.md': 'hybrid generated', + 'examples/headless-agent/composition.md': 'hybrid generated', 'examples/cordis-agent/composition.md': 'hybrid generated', 'examples/acp-agent/composition.md': 'hybrid generated', 'docs/event-producer-consumer.md': 'hybrid generated', diff --git a/vitest.snapshot.config.ts b/vitest.snapshot.config.ts index dbc51eae41..772bbf3f72 100644 --- a/vitest.snapshot.config.ts +++ b/vitest.snapshot.config.ts @@ -1,10 +1,10 @@ import tsconfigPaths from 'vite-tsconfig-paths' import { defineConfig } from 'vitest/config' -// Replay is the keyless default: boot the real ACP subprocess from recorded model scripts and diff -// normalized transcript plus persisted-log goldens. `record` calls the real API and updates fixtures -// and goldens; `refresh` replays committed scripts and updates only current goldens. Replay/refresh -// never load `.env`; only record reads a key from the environment or gitignored root `.env`. +// Replay is the keyless default: boot real example subprocesses from recorded model scripts and diff +// normalized protocol/event output plus persisted-log goldens. ACP `record` calls the real API and +// updates fixtures and goldens; `refresh` replays committed scripts and updates current goldens. +// Replay/refresh never load `.env`; only record reads a key from the environment or root `.env`. if (process.env.DSH_SNAPSHOT === 'record') { try { process.loadEnvFile(new URL('.env', import.meta.url).pathname) From 7bcae0cd64c3cca52ba1ee3ed846138ef354d307 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Thu, 16 Jul 2026 16:29:46 +0800 Subject: [PATCH 210/359] feat(core): add agent execution context --- docs/architecture.md | 23 +- docs/capability-seams.md | 5 + docs/config-catalog.md | 7 +- docs/cordis-catalog/services.md | 16 +- docs/core-data-structures/core.md | 44 +++ docs/module-graph.md | 9 +- docs/rfc/INDEX.md | 2 +- ...26-07-15-agent-execution-context.i18n.yaml | 4 +- .../2026-07-15-agent-execution-context.md | 71 ++++ .../2026-07-15-agent-execution-context.zh.md | 71 ++++ .../2026-07-15-agent-execution-context.md | 207 ---------- .../2026-07-15-agent-execution-context.zh.md | 207 ---------- examples/coding-agent/tests/code-mode.e2e.ts | 2 + examples/coding-agent/tests/harness.ts | 2 + examples/cordis-agent/tests/harness.ts | 2 + packages/README.md | 2 +- packages/bash/tool-bash/package.json | 1 + .../bash/tool-bash/tests/integration.spec.ts | 2 + packages/compact/compact-basic/package.json | 1 + .../tests/compact-loop-repro.spec.ts | 2 + packages/context/time-context/package.json | 1 + .../time-context/tests/time-context.spec.ts | 2 + packages/cordis/tool-cordis/package.json | 1 + .../cordis/tool-cordis/src/api-catalog.ts | 13 + .../tool-cordis/tests/integration.spec.ts | 2 + packages/core/README.md | 5 +- packages/core/agent-execution/README.md | 23 ++ packages/core/agent-execution/package.json | 31 ++ packages/core/agent-execution/src/index.ts | 139 +++++++ packages/core/agent-execution/src/types.ts | 12 + .../tests/agent-execution.spec.ts | 136 +++++++ packages/core/agent-execution/tsconfig.json | 21 + packages/core/agent-loop/README.md | 6 +- packages/core/agent-loop/package.json | 2 + packages/core/agent-loop/src/agent.ts | 4 +- packages/core/agent-loop/src/index.ts | 3 +- .../agent-loop/tests/agent-execution.spec.ts | 374 ++++++++++++++++++ packages/core/agent-loop/tests/agent.spec.ts | 5 + packages/core/agent-loop/tests/cancel.spec.ts | 4 + .../tests/config-session-id.spec.ts | 7 + .../tests/contract-regressions.spec.ts | 9 + .../agent-loop/tests/coverage-edges.spec.ts | 2 + .../agent-loop/tests/interception.spec.ts | 2 + packages/core/agent-loop/tests/loop.spec.ts | 4 + .../core/agent-loop/tests/properties.spec.ts | 2 + .../agent-loop/tests/request-cache.e2e.ts | 2 + .../tests/request-reconstruction.spec.ts | 2 + packages/core/agent-loop/tests/resume.spec.ts | 9 + .../agent-loop/tests/scope-lifecycle.spec.ts | 2 + .../core/agent-loop/tests/tool-order.spec.ts | 2 + .../core/agent-loop/tests/turn-stop.spec.ts | 2 + packages/core/agent-loop/tsconfig.json | 3 + .../agent/tests/gen-cordis-catalog.spec.ts | 20 + packages/examples/README.md | 2 +- packages/examples/agent-spine-demo/README.md | 1 + .../examples/agent-spine-demo/package.json | 4 +- .../examples/agent-spine-demo/src/index.ts | 2 + .../examples/agent-spine-demo/tsconfig.json | 3 + packages/fs/tool-fs/package.json | 1 + packages/fs/tool-fs/tests/harness.ts | 2 + packages/guard/repeat-tool-guard/package.json | 1 + .../tests/repeat-tool-guard.spec.ts | 3 + packages/hooks/hooks-claude/package.json | 1 + .../hooks/hooks-claude/tests/bridge.spec.ts | 4 + .../hooks/hooks-claude/tests/coverage.spec.ts | 5 + packages/hooks/hooks-codex/package.json | 1 + .../hooks/hooks-codex/tests/bridge.spec.ts | 4 + .../hooks/hooks-codex/tests/coverage.spec.ts | 4 + .../sdk/helper/src/features/builtin/spine.ts | 4 + packages/subagent/subagent-fork/package.json | 1 + .../tests/multi-subagent.spec.ts | 2 + .../subagent-fork/tests/subagent-fork.spec.ts | 2 + .../subagent/subagent-inprocess/package.json | 1 + .../tests/structured.spec.ts | 2 + .../tests/subagent-inprocess.spec.ts | 2 + packages/subagent/subagent-spawn/package.json | 1 + .../subagent/subagent-spawn/tests/harness.ts | 2 + .../tests/subagent-spawn.spec.ts | 4 + packages/todo/tool-todo/package.json | 1 + .../todo/tool-todo/tests/integration.spec.ts | 2 + packages/ui/acp/package.json | 1 + packages/ui/acp/tests/harness.ts | 2 + .../workflow-workerthread/package.json | 1 + .../tests/integration.spec.ts | 2 + .../tests/workflow-workerthread.e2e.ts | 2 + pnpm-lock.yaml | 79 +++- python/sdk-runtime/package.json | 1 + scripts/gen-cordis-catalog.ts | 39 +- scripts/gen-doc-graphs.ts | 8 + scripts/type-equiv.manifest.json | 2 + .../verify-package-readme-model-experience.ts | 1 + tsconfig.build.json | 1 + tsconfig.json | 1 + 93 files changed, 1272 insertions(+), 462 deletions(-) rename docs/rfc/{proposed => implemented}/architecture/2026-07-15-agent-execution-context.i18n.yaml (64%) create mode 100644 docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md create mode 100644 docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md delete mode 100644 docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.md delete mode 100644 docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.zh.md create mode 100644 packages/core/agent-execution/README.md create mode 100644 packages/core/agent-execution/package.json create mode 100644 packages/core/agent-execution/src/index.ts create mode 100644 packages/core/agent-execution/src/types.ts create mode 100644 packages/core/agent-execution/tests/agent-execution.spec.ts create mode 100644 packages/core/agent-execution/tsconfig.json create mode 100644 packages/core/agent-loop/tests/agent-execution.spec.ts diff --git a/docs/architecture.md b/docs/architecture.md index 848980a45a..d4faf07f4b 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -4,7 +4,7 @@ The **DeepSeek Harness SDK** builds agent harnesses on Cordis. The principle is ## Overview -A harness is one [Cordis](cordis-primer.md) context. Packages contribute service keys, typed events, and disposable registrations: services expose stable calls (`ctx.llm`, `ctx.tools`, `ctx.sessions`), events provide interception and notifications (`agent/request`, `tools/pre-execute`, `session/event`), and registrations install prompt sections, tools, providers, adapters, or listeners. +A harness is one [Cordis](cordis-primer.md) context whose plugins contribute services, typed events, and disposable registrations. `packages/core/` groups the default agent flow; surrounding capabilities are equally first-class Cordis plugins. @@ -17,6 +17,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service | `ctx.systemPrompt` | `dsh-system-prompt` | ordered prompt sections, tool schemas, and prompt variables | | `ctx.tools` | `dsh-tools` | tool registry and [execution pipeline](tool-execution-pipeline.md) | | `ctx.agents` | `dsh-agent` | live agent registry, public `Agent` handle, `agent/*` events | +| `ctx.agentExecution` | `dsh-agent-execution` | process-local ambient Agent identity for asynchronous driver work | | `ctx.agentLoop` | `dsh-agent-loop` | shipped `ReactLoopAgent` driver | ### Capability Services @@ -43,9 +44,9 @@ Events form the service extension API; see the exhaustive [events catalog](cordi ### Event Domains -- **Session events** are durable, replayable facts. Turn and step boundaries, user input, assistant output, tool calls, tool results, steering, compaction records, and tool-owned durable facts append to the session log and flow through `session/event`. -- **Agent events** carry the live `Agent` handle for status, diagnostics, prompt admission, call-config shaping, result validation, and continuation policy. -- **Capability events** belong to the seam that owns the action. `tools/*`, `llm/*`, `system-prompt/*`, `fs/*`, and `subagent/*` let policy and adapters attach without importing the loop. +- **Session events** are durable facts: turn/step boundaries, model input/output, tool activity, steering, compaction, and tool-owned records append to the log and flow through `session/event`. +- **Agent events** carry the live `Agent` handle through request and lifecycle policy. +- **Capability events** belong to the owning seam; policy and adapters attach without importing the loop. ### Interception Semantics @@ -53,7 +54,7 @@ Waterfall events behave like around-middleware: a listener delegates by calling ## Default Loop Lifecycle -The shipped loop drains work, assembles requests, streams model answers, executes tools, applies continuation policy, and checkpoints state. Every pause is a service call or event available to plugins. +The shipped loop drains work, assembles and streams requests, executes tools, applies continuation policy, and checkpoints through plugin-visible services and events. A **session** is one agent's append-only event log. A **turn** drains one queued batch and runs until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. @@ -97,13 +98,13 @@ forever: The loop renders one prompt assembly per step. Plugins contribute ordered sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn instead of shipping a hole. `dsh-system-prompt` owns the harness identity and default deployment persona; an agent-scoped persona may shadow the default. The loop supplies `model` and `cwd`. See the [prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md). -Post-tool context lands after all tool results so tool-call/result adjacency stays stable. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved. +Post-tool context follows all results, preserving call/result adjacency. Steering drains between steps and otherwise requeues after a turn. A terminal `agent/turn-stop` remains authoritative through turn close and flush, discarding later steering but preserving queued prompts. ### Failure Boundaries -The turn is the containment boundary. A throwing listener, adapter error finish, or failed step ends the current turn with an error reason and reports live diagnostics through `agent/error`; it does not kill the driver loop. `cancel()` clears queued and steering work, aborts the active model/tool boundary when possible, and records the appropriate turn end. Disposal stops the loop, awaits quiescence, unregisters the agent, and lets service disposers drain. +The turn contains listener, adapter, and step failures: it records an error reason and emits `agent/error` without killing the driver. `cancel()` clears pending work, aborts active model/tool work when possible, and records the turn end. Disposal stops and drains the loop before unregistering the agent. -Every session event is turn-enclosed. Reloading a crashed session preserves the interrupted tail and closes it with a synthetic `interrupted` turn end. A failure after the durable turn has closed reports through `agent/error` only because no safe in-turn position remains. A turn ends with one `TurnEndReason` (`completed`, `aborted`, `error`, `disposed`, `max-tokens`, `rejected`, or `interrupted`); per-variant semantics are in [session.md § TurnEndReasonMap](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap). +Every session event is turn-enclosed. Reload closes an interrupted tail with a synthetic `interrupted` end; failures after durable turn close only emit `agent/error`. A turn has one `TurnEndReason`; [TurnEndReasonMap](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap) defines each variant. ### Agent Handles @@ -111,7 +112,11 @@ Every session event is turn-enclosed. Reloading a crashed session preserves the ### Agent Scope -Every live agent owns a scoped `agent.ctx`. Its registrations shadow same-named globals, receive only that agent's dispatches, and unwind with the agent; async effects such as background-task cleanup are awaited. `CreateAgentOptions.setup(agentCtx)` composes the scope before publication. The [semantic-gates RFC](rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md) defines typed resolvers that derive carrier checks from merged `Events` signatures and `scopeTarget`, eliminating the handwritten event table. See the [agent-scope RFC](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md); subagent composition controls are documented [separately](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md). +Every live agent owns a scoped `agent.ctx`; its registrations shadow globals, receive only that agent's dispatches, and unwind with awaited cleanup. `CreateAgentOptions.setup(agentCtx)` composes the scope before publication. See the [scope](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md), [typed carrier checks](rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md), and [subagent composition](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) decisions. + +### Agent Execution Context + +`AgentLoop` wraps each concrete driver in process-local `ctx.agentExecution`; child creation and setup stay outside its boundary, and explicit identities remain authoritative. See the [package contract](../packages/core/agent-execution/README.md) and [decision](rfc/implemented/architecture/2026-07-15-agent-execution-context.md). ## State diff --git a/docs/capability-seams.md b/docs/capability-seams.md index af4beab19e..cee9d6ed17 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -45,6 +45,8 @@ flowchart LR svc_skills["ctx.skills
Skill provider registry"] pkg_skill_local["skill-local"] svc_agents["ctx.agents
Agent registry"] + pkg_agent_execution["agent-execution"] + svc_agentExecution["ctx.agentExecution
Agent execution context"] svc_agentLoop["ctx.agentLoop
Concrete loop driver"] pkg_agent_spine_demo["agent-spine-demo"] pkg_bash["bash"] @@ -91,6 +93,7 @@ flowchart LR pkg_acp --> svc_approval pkg_acp --> svc_userInteraction pkg_agent --> svc_agents + pkg_agent_execution --> svc_agentExecution pkg_agent_loop --> svc_agentLoop pkg_approval --> svc_approval pkg_bash --> svc_bash @@ -133,6 +136,7 @@ flowchart LR pkg_web_search_perplexity --> svc_web pkg_workflow --> svc_workflows pkg_workflow_workerthread --> svc_workflows + svc_agentExecution --> pkg_agent_loop svc_agentLoop --> pkg_agent_spine_demo svc_agents --> pkg_acp svc_agents --> pkg_agent_loop @@ -198,6 +202,7 @@ flowchart LR | `ctx.userInteraction` | `seam` | [`user-interaction`](../packages/ui/user-interaction) | [`stdio-demo`](../packages/examples/stdio-demo), [`acp`](../packages/ui/acp) | [`tool-ask-user`](../packages/ui/tool-ask-user), [`stdio-demo`](../packages/examples/stdio-demo), [`acp`](../packages/ui/acp) | - | UI front doors provide the active human-answer provider; tool-ask-user pauses a tool call on the provider-neutral ask() promise. | | `ctx.skills` | `seam` | [`skill`](../packages/skill/skill) | [`skill-local`](../packages/skill/skill-local) | [`tool-skill`](../packages/skill/tool-skill) | - | Merges provider skill catalogs; tool-skill renders the session-prefix catalog and loads complete skill bodies. | | `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`stdio-demo`](../packages/examples/stdio-demo), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles and the create/resume factory seam. | +| `ctx.agentExecution` | `core` | [`agent-execution`](../packages/core/agent-execution) | - | [`agent-loop`](../packages/core/agent-loop) | - | Carries the exact initiating Agent across one process-local asynchronous driver chain; explicit identities remain authoritative at external boundaries. | | `ctx.agentLoop` | `bundle` | [`agent-loop`](../packages/core/agent-loop) | - | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | - | The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package. | | `ctx.bash` | `seam` | [`bash`](../packages/bash/bash) | [`bash-local`](../packages/bash/bash-local), [`bash-sandbox`](../packages/bash/bash-sandbox) | [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors replace bash-local without touching them. | | `ctx.sandbox` | `seam` | [`sandbox`](../packages/sandbox/sandbox) | [`sandbox-local`](../packages/sandbox/sandbox-local) | [`bash-sandbox`](../packages/bash/bash-sandbox) | - | Consumers hand over the exact argv they are about to spawn; same-world backends wrap it under a per-call policy and report enforcement. | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 91fe7c6497..06547594ec 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -65,7 +65,7 @@ Source: [`packages/examples/acp-demo/src/index.ts:31`](../packages/examples/acp- ## `@deepseek-ai/dsh-agent-loop` -Requires: `agents` · `sessions` · `llm` · `tools` · `systemPrompt` +Requires: `agents` · `agentExecution` · `sessions` · `llm` · `tools` · `systemPrompt` ```ts config-catalog /** Plugin configuration for declarative startup agents. */ @@ -84,7 +84,7 @@ export interface Config { Depends on: [`AgentId`](../packages/core/agent/src/index.ts) · [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:322`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:323`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-agent-spine-demo` @@ -134,7 +134,7 @@ export interface SkillConfig { Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`toolBash`](../packages/bash/tool-bash/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts) · [`toolTasks`](../packages/tasks/tool-tasks/src/index.ts) -Source: [`packages/examples/agent-spine-demo/src/index.ts:55`](../packages/examples/agent-spine-demo/src/index.ts) +Source: [`packages/examples/agent-spine-demo/src/index.ts:56`](../packages/examples/agent-spine-demo/src/index.ts) ## `@deepseek-ai/dsh-bash-local` @@ -1250,6 +1250,7 @@ Source: [`packages/workflow/workflow-workerthread/src/index.ts:32`](../packages/ These load from a `cordis.yml` entry with no `config:` block; they declare no config surface. - `@deepseek-ai/dsh-agent` ([`packages/core/agent/src/index.ts`](../packages/core/agent/src/index.ts)) +- `@deepseek-ai/dsh-agent-execution` ([`packages/core/agent-execution/src/index.ts`](../packages/core/agent-execution/src/index.ts)) - `@deepseek-ai/dsh-fs-policy` ([`packages/fs/fs-policy/src/index.ts`](../packages/fs/fs-policy/src/index.ts)) - `@deepseek-ai/dsh-invariants` — requires `sessions` ([`packages/support/invariants/src/index.ts`](../packages/support/invariants/src/index.ts)) - `@deepseek-ai/dsh-llm` ([`packages/llm/llm/src/index.ts`](../packages/llm/llm/src/index.ts)) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 18e00b7904..dc4976238f 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -9,6 +9,20 @@ This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verifie The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary this repo owns. The **inherited tier** at the end is the cordis-core + loader/hmr/timer `ctx` surface a plugin also sees — pinned vendor source, summarized tersely. +## `ctx.agentExecution` — `AgentExecutionService` (abstract seam) + +Ambient Agent identity within one process-local asynchronous chain. + +```ts cordis-catalog +current(): AgentExecution | undefined +require(): AgentExecution +run(execution: AgentExecution | undefined, operation: () => T): T +``` + +Types: [AgentExecution](../core-data-structures/core.md) + +Source: [`packages/core/agent-execution/src/index.ts:17`](../../packages/core/agent-execution/src/index.ts) + ## `ctx.agentLoop` — `AgentLoop` Concrete ReactLoopAgent factory and driver service. @@ -19,7 +33,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:335`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:336`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 340212d37a..133458f55b 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -351,6 +351,50 @@ interface Agent { The [event taxonomy](../architecture.md#event) owns the `agent/*` lifecycle, checkpoint, and waterfall contracts. Turn and step boundaries are durable session events rather than agent emits. +## Agent execution context + +`AgentExecution` is the process-local ambient frame established around a concrete driver's lifetime. It holds the exact Agent rather than duplicating Session or step state; ambient presence is neither liveness proof nor authorization. + +Source: [`packages/core/agent-execution/src/types.ts`](../../packages/core/agent-execution/src/types.ts) + +```ts type-equiv +interface AgentExecution { + readonly agent: Agent +} +``` + +The mandatory service reads, requires, establishes, or explicitly clears that frame. `run()` preserves the operation's exact synchronous value or Promise. + +Source: [`packages/core/agent-execution/src/index.ts`](../../packages/core/agent-execution/src/index.ts) + +```ts type-equiv +interface AgentExecutionService { + /** + * Read the active execution without requiring one. + * @returns the inherited execution, or `undefined` outside/inside a cleared boundary. + * @throws when this service instance has been disposed. + */ + current(): AgentExecution | undefined + + /** + * Read the active execution and fail when no boundary is active. + * @returns the inherited execution. + * @throws when no execution is active or this service instance has been disposed. + */ + require(): AgentExecution + + /** + * Run an operation inside an execution boundary. Passing `undefined` clears + * an inherited execution; the exact synchronous value or Promise is returned. + * @param execution - execution to inherit, or `undefined` for a clearing boundary. + * @param operation - synchronous or asynchronous operation to invoke. + * @returns the exact value returned by `operation`. + * @throws when this service is closing/disposed, or when `operation` throws. + */ + run(execution: AgentExecution | undefined, operation: () => T): T +} +``` + ## Interception decisions Each `agent/*` interception waterfall returns a small, seam-specific typed union — the unified Decision idiom (the tool seams' `PreToolDecision`/`PostToolDecision` in [tools.md](tools.md) follow the same shape). A CC/Codex hook bridge maps its `permissionDecision`/`decision`/`continue`/`additionalContext` fields onto these; a native plugin returns them directly. They share one envelope for model-facing context, `HookContext`, which is `inject()`ed as a `context/message` and so carries a REQUIRED `source` (a missing source would default to `{kind:'user'}` and mislabel plugin context as a user prompt). diff --git a/docs/module-graph.md b/docs/module-graph.md index 82763bdc55..3cd212c61d 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -18,6 +18,7 @@ flowchart TD end subgraph group_core["packages/core"] pkg_agent["agent"] + pkg_agent_execution["agent-execution"] pkg_agent_loop["agent-loop"] pkg_scope["scope"] pkg_session["session"] @@ -175,6 +176,7 @@ flowchart TD pkg_llm_replay --> pkg_session pkg_sandbox_local --> pkg_llm pkg_sandbox_local --> pkg_sandbox + pkg_agent_execution --> pkg_agent pkg_bash_local --> pkg_bash pkg_bash_local --> pkg_timeout pkg_compact_basic --> pkg_agent @@ -230,6 +232,7 @@ flowchart TD pkg_stdio --> pkg_session pkg_stdio --> pkg_user_interaction pkg_agent_loop --> pkg_agent + pkg_agent_loop --> pkg_agent_execution pkg_agent_loop --> pkg_llm pkg_agent_loop --> pkg_scope pkg_agent_loop --> pkg_session @@ -330,6 +333,7 @@ flowchart TD pkg_jsonrpc --> pkg_session pkg_jsonrpc --> pkg_subagent pkg_agent_spine_demo --> pkg_agent + pkg_agent_spine_demo --> pkg_agent_execution pkg_agent_spine_demo --> pkg_agent_loop pkg_agent_spine_demo --> pkg_invariants pkg_agent_spine_demo --> pkg_llm @@ -409,6 +413,7 @@ flowchart TD | [`session-persistence`](../packages/session-persistence/session-persistence) | `session-persistence` | [`session`](../packages/core/session) | | [`llm-replay`](../packages/support/llm-replay) | `support` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) | +| [`agent-execution`](../packages/core/agent-execution) | `core` | [`agent`](../packages/core/agent) | | [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash), [`timeout`](../packages/util/timeout) | | [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`hook-protocol`](../packages/hooks/hook-protocol) | `hooks` | [`bash`](../packages/bash/bash), [`session`](../packages/core/session) | @@ -425,7 +430,7 @@ flowchart TD | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) | | [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) | | [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | -| [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | +| [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`agent-execution`](../packages/core/agent-execution), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | @@ -447,7 +452,7 @@ flowchart TD | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) | | [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | -| [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools) | +| [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-execution`](../packages/core/agent-execution), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index 2660132fb2..bc355fa328 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -28,7 +28,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | Title | First proposed | |---|---| | [Runtime schemas for the event vocabulary (Zod vs the merge-extensible-map pattern)](proposed/architecture/2026-06-16-typed-event-schemas.md) | 2026-06-16 | -| [Agent execution context over AsyncLocalStorage](proposed/architecture/2026-07-15-agent-execution-context.md) | 2026-07-15 | | [SDK project editing architecture](proposed/architecture/2026-07-15-sdk-project-editing-architecture.md) | 2026-07-15 | ### Process @@ -150,6 +149,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [The agent is a registration scope](implemented/architecture/2026-07-08-agent-scope-contexts.md) | 2026-07-08 | | [Single-file executable SDK runtime distribution (single-exe)](implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) | 2026-07-10 | | [Agent-scope runtime design and correctness](implemented/architecture/2026-07-12-agent-scope-runtime-design.md) | 2026-07-12 | +| [Agent execution context over AsyncLocalStorage](implemented/architecture/2026-07-15-agent-execution-context.md) | 2026-07-15 | ### Process diff --git a/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.i18n.yaml similarity index 64% rename from docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.i18n.yaml rename to docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.i18n.yaml index 65be95551b..24dfc87f70 100644 --- a/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-agent-execution-context.md: 7bea10fb1268c91a7668f7d269f83ae1250c373c -2026-07-15-agent-execution-context.zh.md: 5a7b12974818a076434ff1a1b3b4ab819866b3d7 +2026-07-15-agent-execution-context.md: 9f41aee74dbd94fa5acf93bface57618c604ec17 +2026-07-15-agent-execution-context.zh.md: 4747a506b4fb8a0ff798043ec772a4e810f84d7f diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md new file mode 100644 index 0000000000..9f41aee74d --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md @@ -0,0 +1,71 @@ +# RFC: Agent execution context over AsyncLocalStorage + +Status: implemented + +English | [中文](2026-07-15-agent-execution-context.zh.md) + +## Problem + +The harness has two useful but different notions of context. A Cordis `Context` selects services, registration ownership, and lifetime; `agent.ctx` is the flat registration scope owned by one live Agent. Agent and Session identity instead describe the subject of an asynchronous operation. Changing a root `ctx.agent` to mean “whichever Agent is running” would conflate those meanings and fail when one process drives Agents concurrently. + +Deep process-local infrastructure still needs a trusted initiating Agent. Capability transports, tracing helpers, loggers, and gateway clients may sit below the explicit loop, tool, and request parameters. Threading `agent` through every private helper adds plumbing, while a process-global mutable slot is incorrect across `await`. Model-visible arguments are also unsuitable because a model must not choose a trusted Session or routing header. + +## Decision + +`@deepseek-ai/dsh-agent-execution` provides the mandatory `ctx.agentExecution` service using Node `AsyncLocalStorage`. The frame contains only the exact live Agent: + +```text +export interface AgentExecution { + readonly agent: Agent +} + +export interface AgentExecutionService { + current(): AgentExecution | undefined + require(): AgentExecution + run(execution: AgentExecution | undefined, operation: () => T): T +} +``` + +`current()` is optional, `require()` throws `no agent execution context is active`, and `run()` preserves the operation's exact synchronous value or Promise. `run(undefined, operation)` establishes a real clearing boundary for work that must not inherit an Agent. Session remains derived as `execution.agent.session`; turn, step, tool call, signal, model, cwd, sandbox, and authorization stay with their existing owners. + +`AgentLoop` injects the service and wraps each concrete driver's complete `runLoop` lifetime in `agentExecution.run({ agent }, ...)`. Concurrent drivers therefore receive independent stores, a child driver shadows its parent, and the parent store returns when the child boundary settles. Creation, persistence load, and unpublished `setup(agentCtx)` remain outside the child's boundary: creation initiated by a parent runs under the parent identity, while `agentCtx.agent` explicitly identifies the child. + +Ambient identity does not replace explicit contracts. `ToolExecution.agent`, `AssembleContext.agent`, `GenerateOptions.sessionId`, task ownership, parent/child requests, `ctx.agent`, `agentCtx.agent`, approval and hook subjects, cwd selection, cancellation, worker/process messages, persistence records, and wire identity remain explicit. A remote boundary materializes the identity it needs into its typed request because ALS is process-local. + +The provider uses an ordered composite effect. Teardown first rejects new boundaries, then removes the service and awaits injected dependents such as AgentLoop, then waits for active returned-Promise boundaries before calling `AsyncLocalStorage.disable()`. `current()` and `require()` remain usable through a retained in-flight service reference while that drain runs; after disposal, retained calls throw `agent execution service is disposed`. Root Context disposal may start sibling fiber teardown concurrently, so active-boundary counting is required in addition to Cordis dependency ordering. + +Asynchronous resources created inside `run()` inherit its store even when the returned operation does not await them. Agent-owned foreground work may inherit `{ agent }` but keeps the explicit cancellation and disposal contract of its execution seam. Unrelated timers, queues, and deployment infrastructure start under `run(undefined, operation)` and own an explicit stop. Queue, worker, process, and wire boundaries serialize identity rather than expecting ALS propagation. + +A host-aware transport may derive a deployment-owned header such as `X-Harness-Session-Id` from `ctx.agentExecution.require().agent.session.id`; the header is absent from model-visible schema and arguments. No production MCP or Web transport adopts such a header in this decision. A test-double transport proves the trusted boundary without assigning host routing policy to an existing provider-neutral seam. + +This decision extends the [Agent registration-scope contract](2026-07-08-agent-scope-contexts.md) and its [runtime design](2026-07-12-agent-scope-runtime-design.md); it does not change their static `agent.ctx` meaning. + +## Verification + +Service tests pin optional and required reads, synchronous and awaited propagation, overlapping and nested boundaries, explicit clearing, restoration after throw or rejection, exact return identity, drain ordering, and disposed-reference errors. AgentLoop integration tests run overlapping real drivers, nested parent/child creation, agentless direct tool execution, cancellation during provider/root teardown, service restart, and a captured Agent after disposal. + +The test-double capability transport derives `X-Harness-Session-Id` internally and asserts that neither its tool schema nor logged arguments contains an identity field. Composition tests and generated catalogs keep the provider present in the default bundle, SDK spine, Python runtime closure, and direct AgentLoop harnesses; a missing provider leaves AgentLoop inactive. + +## Alternatives considered + +**Pass Agent through every function.** Public, worker, process, persistence, and wire boundaries continue to do this, but requiring every process-local private helper to carry Agent adds plumbing without improving trust. ALS is confined to the asynchronous chain inside those explicit boundaries. + +**Make `ctx.agent` dynamic.** `ctx.agent` already means the static Agent associated with an Agent-scoped Cordis context. Changing the root meaning would mix registration and execution scopes and make concurrent behavior surprising. + +**Store a complete mutable runtime frame.** Agent, Session, inbox, cancellation, turn, step, tool execution, and persistence already have authoritative owners. Duplicating them would create stale snapshots and another lifecycle. The wrapper leaves room for a separately justified stale-safe label without flattening the store to a bare Agent. + +**Include a step `AbortSignal`, cwd, sandbox, or authorization.** Their lifetimes and authority do not match the driver boundary, and their existing seams already pass them explicitly. Adding a control capability requires a separate decision and nested lifecycle contract. + +**Use a process-global `currentAgent`.** Concurrent Agents and subagents overwrite one another across awaited continuations, so a mutable global is correct only under a serialization guarantee the harness does not make. + +**Derive identity from model-visible arguments.** Model or user input cannot be trusted to select Session, tenant, or sandbox routing. + +**Add routing identity to every capability seam.** That spreads hosting concerns through provider-neutral APIs. A host-aware implementation owns its transport header while public boundaries remain explicit. + +## Consequences + +Deep infrastructure gains one trusted process-local initiating Agent without widening existing tool and capability requests. Concurrent and nested drivers isolate automatically, AgentLoop stays inactive when the provider is absent, and HMR/root disposal reaches quiescence before ALS is disabled. + +The dependency is implicit in function signatures and carries a live capability object. Consumers must restrict it to cross-cutting infrastructure, treat ambient presence as neither liveness nor authorization, and retain explicit cancellation and ownership checks. ALS also has an always-on propagation cost and does not cross worker, process, HTTP, or durable queue boundaries. + +The frame deliberately omits turn, step, signal, cwd, sandbox, and authorization. A real consumer that cannot use existing explicit fields must justify any refinement separately; a stale copied field may at most mislabel telemetry, never grant control. diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md new file mode 100644 index 0000000000..4747a506b4 --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md @@ -0,0 +1,71 @@ +# RFC: 基于 AsyncLocalStorage 的 Agent 执行上下文 + +Status: implemented + +[English](2026-07-15-agent-execution-context.md) | 中文 + +## 问题 + +Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负责选择服务、注册归属和生命周期；`agent.ctx` 是一个存活 Agent 所拥有的扁平注册作用域。Agent 与会话身份描述的则是异步操作主体。若把根 `ctx.agent` 改成「当前正在运行的 Agent」，就会混淆这两种含义，并在单进程并发驱动多个 Agent 时失效。 + +进程内深层基础设施仍需要可信的发起 Agent。能力传输层、追踪辅助函数、日志器和网关客户端可能位于显式 loop、工具及请求参数的下层。在每个私有辅助函数中传递 `agent` 会增加管道代码，而进程级可变槽会在 `await` 之间发生并发错误。模型可见参数同样不合适，因为模型不能选择可信的会话或路由请求头。 + +## 决策 + +`@deepseek-ai/dsh-agent-execution` 使用 Node `AsyncLocalStorage` 提供必载的 `ctx.agentExecution` 服务。该帧只包含准确的存活 Agent： + +```text +export interface AgentExecution { + readonly agent: Agent +} + +export interface AgentExecutionService { + current(): AgentExecution | undefined + require(): AgentExecution + run(execution: AgentExecution | undefined, operation: () => T): T +} +``` + +`current()` 执行可选读取，`require()` 抛出 `no agent execution context is active`，`run()` 保留操作返回的准确同步值或 Promise。`run(undefined, operation)` 会建立真实的清空边界，供不得继承 Agent 的工作使用。会话仍通过 `execution.agent.session` 推导；轮次、步骤、工具调用、signal、模型、cwd、沙箱和授权继续由现有归属方管理。 + +`AgentLoop` 注入该服务，并用 `agentExecution.run({ agent }, ...)` 包裹每个具体驱动的完整 `runLoop` 生命周期。因此，并发驱动使用彼此独立的存储，子驱动会遮蔽父驱动，子边界结束后父存储得到恢复。创建、持久化加载和尚未发布的 `setup(agentCtx)` 位于子边界之外：由父 Agent 发起的创建使用父身份，而 `agentCtx.agent` 显式标识子 Agent。 + +隐式身份不会取代显式契约。`ToolExecution.agent`、`AssembleContext.agent`、`GenerateOptions.sessionId`、任务归属、父子请求、`ctx.agent`、`agentCtx.agent`、审批与 hook 主体、cwd 选择、取消、worker/进程消息、持久化记录及协议身份都保持显式传递。远程边界会把所需身份写入类型化请求，因为 ALS 只在进程内有效。 + +提供方使用有序复合 effect。teardown 会先拒绝新边界，再移除服务并等待 AgentLoop 等注入方排空，随后等待活动的返回 Promise 边界，最后调用 `AsyncLocalStorage.disable()`。排空期间，进行中代码可通过保留的服务引用继续调用 `current()` 和 `require()`；dispose 后，保留引用会抛出 `agent execution service is disposed`。根 Context dispose 可能并发启动同级 fiber 的 teardown，因此除 Cordis 依赖顺序外还必须统计活动边界。 + +在 `run()` 内创建的异步资源会继承其存储，即使返回的操作没有等待它们。Agent 所拥有的前台工作可以继承 `{ agent }`，但仍使用其执行 seam 的显式取消和 dispose 契约。无关的定时器、队列和部署基础设施在 `run(undefined, operation)` 下启动，并拥有显式停止操作。队列、worker、进程和协议边界必须序列化身份，不能期待 ALS 传播。 + +宿主感知的传输层可以从 `ctx.agentExecution.require().agent.session.id` 推导由部署方拥有的 `X-Harness-Session-Id` 等请求头；模型可见 schema 和参数中不包含该请求头。本决策不让现有生产 MCP 或 Web 传输层采用此请求头。测试替身传输层用于证明可信边界，而不会把宿主路由策略分配给现有的提供方无关 seam。 + +本决策扩展 [Agent 注册作用域契约](2026-07-08-agent-scope-contexts.md)及其[运行时设计](2026-07-12-agent-scope-runtime-design.md)，不会改变其中 `agent.ctx` 的静态含义。 + +## 验证 + +服务测试锁定可选与必需读取、同步与跨 `await` 传播、并发与嵌套边界、显式清空、throw 或 rejection 后的恢复、准确返回值身份、排空顺序及已 dispose 引用错误。AgentLoop 集成测试覆盖重叠的真实驱动、嵌套父子创建、无 Agent 的直接工具执行、提供方或根 Context teardown 期间的取消、服务重启，以及 Agent dispose 后保留的引用。 + +测试替身能力传输层在内部推导 `X-Harness-Session-Id`，并断言工具 schema 与记录的参数都不包含身份字段。组合测试和生成目录确保默认 bundle、SDK 主干、Python 运行时闭包及直接 AgentLoop harness 都装载提供方；缺少提供方时 AgentLoop 保持未激活。 + +## 考虑过的替代方案 + +**在每个函数中传递 Agent。** 公开、worker、进程、持久化和协议边界继续显式传递，但要求每个进程内私有辅助函数都携带 Agent 只会增加管道代码，不会提高可信度。ALS 仅限于这些显式边界内部的异步调用链。 + +**让 `ctx.agent` 变成动态值。** `ctx.agent` 已经表示与 Agent 作用域 Cordis 上下文静态关联的 Agent。改变根上下文的含义会混合注册作用域与执行作用域，并让并发行为变得意外。 + +**保存完整的可变运行时帧。** Agent、会话、inbox、取消、轮次、步骤、工具执行和持久化已经有各自的真源。重复保存会产生陈旧快照和另一套生命周期。包装对象为另行论证的陈旧安全标签保留扩展空间，而不会把存储简化成裸 Agent。 + +**包含步骤级 `AbortSignal`、cwd、沙箱或授权。** 它们的生命周期与权限不匹配驱动边界，而且现有 seam 已经显式传递这些值。新增控制能力需要独立决策和嵌套生命周期契约。 + +**使用进程级 `currentAgent`。** 并发 Agent 和 subagent 会在异步 continuation 间相互覆盖，因此可变全局值只在 Harness 不具备的串行保证下才正确。 + +**从模型可见参数推导身份。** 不能信任模型或用户输入来选择会话、租户或沙箱路由。 + +**给每个能力 seam 增加路由身份。** 这会把宿主关注点扩散到提供方无关 API。宿主感知实现拥有其传输请求头，而公开边界继续显式传递身份。 + +## 后果 + +深层基础设施可以获得一个可信的进程内发起 Agent，而无需加宽现有工具和能力请求。并发及嵌套驱动会自动隔离，缺少提供方时 AgentLoop 保持未激活，HMR 或根 Context dispose 会在禁用 ALS 前达到静止状态。 + +该依赖不会出现在函数签名中，并且携带一个存活能力对象。消费方必须将其限制在横切基础设施中，把隐式存在视为既不证明存活、也不授予权限，并保留显式取消和归属检查。ALS 还有常驻传播成本，也无法跨越 worker、进程、HTTP 或持久化队列边界。 + +该帧有意省略轮次、步骤、signal、cwd、沙箱和授权。若真实消费方无法使用现有显式字段，必须另行论证扩展；陈旧字段最多只能误标遥测数据，绝不能授予控制权。 diff --git a/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.md b/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.md deleted file mode 100644 index 7bea10fb12..0000000000 --- a/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.md +++ /dev/null @@ -1,207 +0,0 @@ -# RFC: Agent execution context over AsyncLocalStorage - -Status: proposed - -English | [中文](2026-07-15-agent-execution-context.zh.md) - -## Problem - -The harness has two useful but different notions of context: - -- A Cordis `Context` is a composition and lifetime object. The deployment context exposes shared services, while `agent.ctx` exposes the flat registration layer owned by one live Agent. -- Agent, Session, turn, step, and tool identity are execution subjects. The loop passes them explicitly through events, prompt assembly, LLM requests, and `ToolExecution`. - -These concepts must not be conflated. In particular, `agent.ctx.agent` is a static association on the Agent's scoped composition context. A plain root context deliberately returns `undefined`; it cannot be changed to mean "whichever Agent happens to be running now" because one Node process may run many Agents concurrently. - -This leaves a practical gap for deeply nested infrastructure. A capability transport, skill provider, tracing helper, logger, or gateway client may need to know which Agent initiated the current asynchronous operation. Passing `agent` through every intermediate helper is noisy, while deriving identity from a process-global mutable slot is incorrect as soon as two Agents overlap. Model-visible tool arguments are also the wrong carrier: the model must not be able to choose a trusted Session or sandbox-routing header. - -The gap becomes important when a single Harness runtime multiplexes Sessions for a multi-tenant hosting platform. Outbound capability requests must automatically carry the current Harness Session ID so the host can resolve the correct tenant and sandbox owner. Model-facing skills and tools should not know host-specific routing, but the selected capability implementation still needs a trusted current Agent at the transport boundary. - -## Proposal - -Add a narrow Agent execution-context facility backed by Node `AsyncLocalStorage`. It provides ambient access to the Agent associated with the current asynchronous execution chain without replacing Cordis contexts, explicit protocol fields, or durable Session state. - -The first version stores only the Agent: - -```text -export interface AgentExecution { - readonly agent: Agent -} - -export interface AgentExecutionService { - current(): AgentExecution | undefined - require(): AgentExecution - run(execution: AgentExecution | undefined, operation: () => T): T -} -``` - -`Session` is derived as `execution.agent.session`; it is not duplicated in the store. Turn, step, tool call, model, cwd, and sandbox identity remain outside the first version because they already have authoritative owners and no confirmed ambient consumer requires them yet. The single-field wrapper is deliberate: a later execution-frame refinement extends `AgentExecution` without changing `run()` callers, so implementations must not flatten the store to a bare `Agent`. - -`AgentExecution` deliberately retains the exact live `Agent`, not an id snapshot. This is the one capability admitted to the first-version store because it is the subject whose driver establishes the boundary and because existing scoped helpers operate on that exact object. Ambient presence is not proof of liveness or authorization: consumers must still honor the Agent lifecycle and the explicit capability contract before performing lifecycle-sensitive work. - -The API must always establish an ALS boundary, including when the supplied execution is `undefined`. This provides an explicit way to clear inherited context for unrelated detached work. A comparable implementation observed an uncleared ambient value crossing scheduled work into a later turn; the explicit undefined boundary prevents that class of leak. - -### Package and service placement - -Create `packages/core/agent-execution/` as `@deepseek-ai/dsh-agent-execution`. The package owns the Node-specific ALS implementation and augments Cordis with the mandatory `ctx.agentExecution` service. It belongs to `core/` because it is part of the stable Agent control spine that every concrete Agent loop and ambient-identity consumer programs against. - -The public key is `ctx.agentExecution`, settled here so every surface — service key, interface name, and package name — shares one word root. It names the Agent-owned asynchronous chain rather than one turn or tool call. `ctx.execution` is too broad; a runtime-flavored name would collide with `packages/code-runtime/` and with "Harness runtime" meaning the whole process; and changing `ctx.agent` is excluded because it already means the static Agent association of `agent.ctx`. - -The package exposes the service through Cordis rather than a mutable module-global slot: - -- the Agent Loop can inject the service explicitly; -- tests can mount an isolated service per Harness context; -- service disposal can disable its ALS instance after dependent Agent drivers quiesce; -- the dependency remains visible in Cordis configuration and generated catalogs. - -The service loads mandatorily with the standard agent composition bundle, and `dsh-agent-loop` declares it in `inject`: a composition that drives agents without it fails at load, per the fail-loud rule, rather than degrading to absent ambient identity at the first deep consumer. Configuration tests pin this policy. The facility relies only on stable Node `AsyncLocalStorage`, available without a polyfill across the supported `node ^22.19 || >=24` range. Node 24+ uses an `AsyncContextFrame`-backed implementation, while Node 22 uses the earlier implementation; this RFC accepts the always-on propagation cost for the invariant and makes no zero-overhead claim. - -Service teardown is ordered rather than transparent. The Agent Loop stops accepting new work, cancels and drains every driver, and only then may the service disable its ALS instance. HMR of the service rebuilds that dependent subtree; it does not preserve an in-flight turn across reload. A retained reference to a disposed service throws a stable disposed-service error from both `current()` and `require()` instead of silently returning `undefined`. - -### Lifecycle boundary - -Bind the execution context around each concrete Agent driver's `runLoop` lifetime: - -```text -agentExecution.run({ agent }, () => runLoop(ctx, agent, handle)) -``` - -This gives every operation initiated by that driver the same trusted Agent: - -- prompt interception and prompt assembly; -- LLM adapter calls; -- tool policy and tool bodies; -- capability providers and transports; -- synchronous and asynchronous helpers awaited by those operations. - -Concurrent drivers receive distinct ALS stores. A child Agent's own driver establishes a new boundary with the child, so child operations do not inherit the parent Agent merely because child creation started inside a parent tool call. When a nested boundary returns, ALS restores the parent automatically. - -Agent creation setup is deliberately outside this dynamic boundary. Setup already receives `agentCtx`, whose `agentCtx.agent` is the correct unpublished Agent. Publication and lifecycle ownership continue to use the existing explicit Agent and scoped carrier. One consequence is a defined contract, not an accident: when child creation starts inside a parent tool call, the child's setup and persistence load run under the PARENT's ambient identity, because the child's driver has not started. A transport reached during that window routes under the parent's Session — correct for trusted routing, since the parent initiated and owns the creation work. Setup code that needs the child's identity uses the explicit `agentCtx.agent`, never the ambient store. - -### Explicit subjects remain authoritative - -Ambient identity is a convenience for deep infrastructure, not a replacement for existing contracts: - -- `AgentEventDispatch` continues to carry the explicit Agent subject and scope. -- `AssembleContext.agent` remains explicit. -- `ToolExecution.agent` remains explicit and continues to select the scoped tool and policy view. -- `GenerateOptions.sessionId` remains explicit at the LLM boundary. -- Subagent requests and lifecycle events continue to carry explicit parent and child identity. -- Session events remain the durable truth for replay and resume. - -Code at a public service, process, worker, persistence, or wire boundary must materialize the identity it needs into that boundary's typed request. A remote process cannot access the parent's ALS store. - -### Trusted transport use - -A host-aware capability transport may read `ctx.agentExecution.require().agent.session.id` when constructing an outbound request and add a deployment-owned trusted header such as `X-Harness-Session-Id`. The header is not present in model-visible tool arguments and cannot be overridden by the model. Ambient presence alone does not authorize a request; the transport still runs inside its normal explicit capability and Agent-lifecycle contracts. - -The bash seam's existing `OwnerToken` is the nearest explicit-identity precedent and shows why it does not close this gap: `BashExecSpec.owner` is a background-task isolation key that `dsh-tool-bash` casts from the session id, foreground `run()` deliberately ignores it, and the filesystem seam has no counterpart — its provider methods carry no identity parameter at all. Extending every capability seam with a routing-identity parameter would push hosting concerns into seam vocabularies that are otherwise deployment-neutral; ambient identity lets the transport implementation own routing without widening any seam. - -The hosting platform remains responsible for resolving the Harness runtime Session ID to its product Session and sandbox owner. Harness does not learn the host's sandbox identifier, sandbox provider, or persistence model. - -Model-facing skill and tool plugins should not add hosting-specific headers themselves. They call a capability service; the selected provider owns remote execution and identity propagation. This preserves the separation between model behavior and backend routing. - -### Detached asynchronous work - -Node ALS is inherited by asynchronous resources created inside `run()`, even when callers do not await them. This is useful for an Agent-owned background operation, but it can also retain a stale turn's context in unrelated work. - -Identity inheritance does not replace cancellation ownership. Work started inside an Agent's boundary is either **foreground** — it inherits `{ agent }` and separately receives the explicit cancellation signal owned by its execution seam — or **detached** — it starts under `run(undefined, operation)` and owns its own lifecycle with an explicit stop. The caller must keep those choices aligned. The implementation must document and test these rules: - -- Work logically owned by the Agent is foreground: it may inherit `{ agent }`, receives cancellation through the existing explicit seam, and must honor the Agent's disposal contract. -- Long-lived deployment infrastructure, timers, and work queues unrelated to that Agent are detached: they must start under `run(undefined, operation)` and be stopped by their own owner, never implicitly by a turn ending. -- Code that enqueues data for later processing must serialize the required identity into the queue item; it must not expect ALS to cross the queue, process, or worker boundary. -- Consumers must not treat an ambient Agent reference as proof that the Agent is still live. Lifecycle-sensitive operations still check `agent.status`, an explicit signal, or the owning service's contract. - -`turn` and `step` remain outside the first version; they can join later as a separate immutable execution-frame refinement if a real cross-cutting consumer (tracing, logging) cannot use the existing explicit fields. The full `Agent` is the deliberate capability exception because it is the execution subject that establishes the boundary. Every additional field must be a stale-safe label whose stale copy can at worst mislabel a trace; another capability or control channel requires its own RFC. `AbortSignal` is excluded from the first version under that rule; see Alternatives considered. - -## Current Harness evidence - -The implementation Session should re-check these symbols on its target branch before editing because this handoff was prepared against a local source snapshot and the branch may have advanced. - -- `packages/core/agent/src/types.ts`: `Agent` already owns `session`, `status`, and `ctx`. Its `ctx` documentation defines a registration scope, not a dynamic request context. -- `packages/core/agent/src/index.ts`: Cordis `Context.agent` is installed as an Agent-scope DX association and defaults to `undefined` on a plain context. Do not change this semantic. -- `packages/core/agent-loop/src/agent.ts`: `ReactLoopAgent` already owns inbox, cancellation, per-step abort, status, and driver lifetime. Do not create a parallel mutable runtime-state object. -- `packages/core/agent-loop/src/loop.ts`: `runLoop(ctx, agent, handle)` has the exact lifetime boundary to wrap. It passes Agent, turn, step, and signal explicitly to narrower operations. -- `packages/core/tools/src/index.ts`: `ToolExecutionInput.agent` is explicit and selects scoped policy and tool resolution. It remains in the contract after ALS is added. -- `packages/core/agent/src/dispatch.ts`: `agentEvents()` deliberately fuses the Agent subject with its scoped carrier. Ambient context must not replace this correctness mechanism. -- `packages/core/README.md` and the existing core packages: they show that stable Agent control contracts belong in `core/`; `agent-execution` is mandatory control infrastructure rather than optional model-visible context enrichment. - -This proposal extends, rather than supersedes, [the Agent registration-scope decision](../../implemented/architecture/2026-07-08-agent-scope-contexts.md) and its [runtime design](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md). - -## Claude Code reference implementation - -| Claude Code | Harness translation | -|---|---| -| AppState store | Cordis deployment services and their owned live state | -| QueryEngine | `ReactLoopAgent` plus its loop-owned runtime state | -| ToolUseContext | Explicit Agent/tool/request parameters at capability seams | -| AgentContext ALS | Proposed narrow `AgentExecution` carrier | -| Transcript | Event-sourced `Session` and persistence backends | - -## Implementation handoff - -The implementation Session should perform the work in this order: - -1. Switch to the intended target branch and inspect the current versions of the files listed under "Current Harness evidence". Do not merge or copy changes from the branch on which this handoff was authored. -2. Add `packages/core/agent-execution/` with package metadata, README, exported types, the Cordis service, module augmentation, and focused tests. -3. Add the package to TypeScript project references, path candidates, runtime closure/configuration, and generated catalogs according to existing package gates. Prefer repository generators over hand-editing generated files. Also update the `core/` repository-layout line in root `AGENTS.md`, the package table in `packages/core/README.md`, and the package-group description in `packages/README.md`. -4. Make the Agent Loop declare and consume the service. Wrap each Agent driver's complete `runLoop` invocation in `{ agent }` without changing public Agent, event, tool, LLM, or Session signatures. -5. Add an integration test that overlaps two Agents in one process and observes the correct ambient Agent from inside asynchronous tool execution after at least one `await`. -6. Add nested-Agent coverage proving a child sees itself and the parent context is restored after the child boundary settles. -7. Add clearing and failure coverage: outside a boundary returns `undefined`, `require()` fails clearly, `run(undefined, ...)` masks an inherited Agent, and thrown/rejected operations do not contaminate later unrelated work. -8. Add a test-double capability transport to the integration suite. Keep the model-facing schema unchanged and assert that a trusted Session header is generated internally. Adapting a production remote backend is follow-up work outside this RFC. -9. Run typecheck, targeted tests, documentation gates, generated-catalog checks, and then the repository's normal CI/pre-push gate. - -Suggested focused test matrix: - -| Scenario | Required observation | -|---|---| -| Outside driver | `current()` is `undefined` | -| One Agent across awaits | Every continuation sees the same exact Agent | -| Two concurrent Agents | A never observes B and B never observes A | -| Nested child | Child sees child; parent is restored afterward | -| Child creation window | Setup inside a parent tool call sees the parent ambiently; `agentCtx.agent` is the child | -| Direct Agent-less tool call | Explicit tool behavior remains valid; ambient identity is absent | -| Cleared detached work | `run(undefined, ...)` hides the inherited Agent | -| Failure and cancellation | Context restores after throw, rejection, and abort | -| Agent disposal | Lifecycle-sensitive consumers reject work from a captured Agent after disposal | -| Service reload | Agent drivers drain before ALS disable; retained disposed-service calls throw the documented stable error | -| Capability transport boundary | Session identity is materialized into the typed request/header by the test-double transport | - -## Alternatives considered - -**Pass Agent through every function.** This remains the right choice at public and authority-bearing boundaries, but forcing it through every private helper creates plumbing that ambient execution context is designed to remove. The proposal keeps explicit subjects at seams and uses ALS only within one trusted asynchronous process. - -**Change `ctx.agent` to return the currently executing Agent.** Rejected because `ctx.agent` already denotes the static association of an Agent-scoped Cordis context. Making a root context dynamic would combine registration scope with execution scope, produce surprising behavior under concurrency, and break the implemented Agent-scope RFCs. - -**Store a complete mutable runtime object in ALS.** Rejected because Agent, Session, inbox, cancellation, turn/step state, tool execution, and durable log already have authoritative owners. Duplicating them creates stale snapshots, write-order questions, and another lifecycle to clean up. - -**Carry the step `AbortSignal` in the first-version ALS frame.** Rejected for this RFC. The signal is per-step while the proposed boundary is per-driver, so carrying it requires nested step and tool boundaries plus explicit rules for detached work, deadline ownership, and restoration. Existing execution seams already pass cancellation explicitly. A future RFC may revisit this only with a concrete cross-cutting consumer and tests that establish those nested lifecycle semantics. - -**Use one process-global mutable `currentAgent`.** Rejected because concurrent Agents and subagents overwrite one another across awaits. It is correct only under serialization, which multi-Agent execution explicitly does not guarantee. - -**Infer the Session from model-visible tool arguments.** Rejected because the model can alter those arguments. Sandbox routing and authorization require a trusted in-process identity, not user/model input. - -**Put a hosting platform's sandbox-owner identifier or provider data in Harness context.** Rejected because sandbox ownership is hosting-product state resolved outside Harness. Harness should carry only its own Session identity across the trusted transport boundary. - -## Acceptance criteria - -- One Node Harness process can execute at least two Agents concurrently, and asynchronous consumers always observe the exact initiating Agent. -- Outside Agent driver execution, ambient lookup returns `undefined` and `require()` throws a stable, actionable error. -- Nested Agent execution restores the parent context after the child settles. -- `agent.ctx`, `ctx.agent`, Agent events, prompt assembly, `ToolExecution.agent`, LLM `sessionId`, and Session persistence retain their existing semantics. -- No Agent, Session, turn, step, sandbox, or authorization identity becomes model-controlled. -- The implementation provides an explicit undefined boundary for unrelated detached work and tests it against context leakage without changing existing explicit cancellation contracts. -- The service loads with the standard agent bundle and `dsh-agent-loop` fails at load without it; a configuration test pins the policy. -- Disposal/HMR drains every dependent Agent driver before disabling ALS; retained calls on the disposed service fail with the documented stable error, and no active ALS state remains reachable through the disposed Cordis context. -- A test-double capability transport proves trusted Session ID propagation without adding a model-visible schema field. -- Package catalogs, dependency graphs, API docs, and relevant architecture docs are regenerated or updated, and the repository's documentation gates pass. - -## Risks - -- Ambient context hides a dependency from function signatures. Restricting it to deep cross-cutting infrastructure and retaining explicit public subjects limits that cost. -- ALS inheritance into detached promises and timers can retain semantically stale identity. An explicit undefined boundary, documentation, and regression tests are required rather than assumed cleanup. -- ALS does not cross worker threads, subprocesses, Redis, HTTP, or persisted queues. Every such boundary must serialize the required identity explicitly. -- The ambient store intentionally carries the full live Agent capability. A captured reference can outlive publication, so ambient presence alone never authorizes lifecycle-sensitive work and consumers must still honor Agent lifecycle and cancellation contracts. -- Mandatory loading adds a core runtime dependency to every agent composition; the RFC accepts that cost because an optional service would make ambient identity composition-dependent. Propagation cost remains measurable across supported Node versions and should be benchmarked separately. -- Adding turn, step, signal, cwd, or tool details prematurely would expand inheritance and staleness hazards. The first version deliberately accepts the limitation of Agent-only ambient identity; any additional capability or control field requires a separate RFC. diff --git a/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.zh.md b/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.zh.md deleted file mode 100644 index 5a7b129748..0000000000 --- a/docs/rfc/proposed/architecture/2026-07-15-agent-execution-context.zh.md +++ /dev/null @@ -1,207 +0,0 @@ -# RFC：基于 AsyncLocalStorage 的 agent（智能体）执行上下文 - -Status: proposed - -[English](2026-07-15-agent-execution-context.md) | 中文 - -## 问题 - -harness 中存在两种有用但含义不同的上下文： - -- Cordis `Context` 是依赖组合和生命周期对象。部署上下文暴露共享服务，`agent.ctx` 则暴露某个存活 Agent 所拥有的扁平注册层。 -- Agent、会话、轮次、步骤和工具身份是执行主体。agent loop（智能体循环）通过事件、提示词组装、LLM（大语言模型）请求和 `ToolExecution` 显式传递这些信息。 - -这两类概念不能混为一谈。尤其是，`agent.ctx.agent` 是 Agent 作用域组合上下文上的静态关联。普通根上下文会有意返回 `undefined`；不能把它改成“当前恰好正在运行的 Agent”，因为一个 Node 进程可能并发运行多个 Agent。 - -这给深层基础设施留下了一个实际缺口。能力传输层、skill（技能）提供方、追踪辅助函数、日志记录器或网关客户端，可能需要知道当前异步操作由哪个 Agent 发起。让每一层中间辅助函数都继续传递 `agent` 会产生大量样板代码，而从进程级可变全局槽推导身份，会在两个 Agent 并发后立即出错。模型可见的工具参数也不是合适的载体：模型不能选择可信的会话或沙箱路由请求头。 - -当单个 Harness 运行时为多租户宿主平台复用多个会话时，这个缺口会变得尤其重要。对外能力请求必须自动携带当前 Harness 会话 ID，以便宿主平台解析正确的租户和沙箱归属。模型侧的 skill 和工具不应理解宿主平台特有的路由，但所选能力实现仍需要在传输边界获得可信的当前 Agent。 - -## 提案 - -新增一套由 Node `AsyncLocalStorage` 支撑的窄粒度 Agent 执行上下文能力。它允许代码在当前异步执行链内访问关联的 Agent，但不会取代 Cordis 上下文、显式协议字段或持久化会话状态。 - -第一版只保存 Agent： - -```text -export interface AgentExecution { - readonly agent: Agent -} - -export interface AgentExecutionService { - current(): AgentExecution | undefined - require(): AgentExecution - run(execution: AgentExecution | undefined, operation: () => T): T -} -``` - -`Session` 通过 `execution.agent.session` 推导，不在存储中重复保存。轮次、步骤、工具调用、模型、cwd 和沙箱身份不进入第一版，因为它们已经有各自的真源，而且目前没有已确认的隐式上下文消费方需要这些信息。单字段包装是有意为之：后续的执行帧扩展可以在不改动 `run()` 调用方的前提下扩展 `AgentExecution`，因此实现不得把存储简化成裸 `Agent`。 - -`AgentExecution` 有意保留准确的存活 `Agent`，而不是 ID 快照。这是第一版存储中唯一获准的能力对象，因为它正是由驱动建立边界的执行主体，而且现有作用域辅助函数依赖这个准确对象。隐式存在不代表仍然存活或已经获得授权：消费方执行生命周期敏感工作前，仍须遵循 Agent 生命周期和显式能力契约。 - -API 必须始终建立 ALS 边界，即使传入的 execution 是 `undefined` 也不例外。这样可以显式清除无关分离任务继承到的上下文。一个同类实现曾观察到未清空的隐式值穿过已调度工作泄漏进后续轮次；显式 undefined 边界可以防止这类泄漏。 - -### 包与服务位置 - -在 `packages/core/agent-execution/` 新建 `@deepseek-ai/dsh-agent-execution`。该包拥有 Node 专用的 ALS 实现，并通过必载的 `ctx.agentExecution` 服务扩展 Cordis。它属于 `core/`，因为这是每个具体 Agent loop 和隐式身份消费方所依赖的稳定 Agent 控制主干。 - -公开键名在此定为 `ctx.agentExecution`，服务键、接口名和包名共用同一个词根。它表示某个 Agent 所拥有的异步调用链，而不是单个轮次、步骤或工具调用；名字也直接说明存储的内容。`ctx.execution` 含义过宽；带 runtime 字样的名字会与 `packages/code-runtime/` 以及指整个进程的 “Harness 运行时” 冲突；修改 `ctx.agent` 被排除，因为它已经表示 `agent.ctx` 与 Agent 之间的静态关联。 - -该包通过 Cordis 暴露服务，而不是使用可变模块全局槽： - -- Agent Loop 可以显式注入该服务； -- 测试可以为每个 Harness 上下文挂载隔离的服务； -- 服务 dispose（资源释放）时可以在依赖它的 Agent 驱动静止后禁用其 ALS 实例； -- 依赖关系在 Cordis 配置和生成目录中保持可见。 - -该服务随标准 agent 组合包强制加载，`dsh-agent-loop` 在 `inject` 中声明它：缺少该服务的 agent 组合按快速失败规则在加载时报错，而不是等到第一个深层消费方读取时才发现隐式身份缺失。配置测试锁定这一策略。该能力只依赖稳定的 Node `AsyncLocalStorage`，支持范围 `node ^22.19 || >=24` 全部可原生使用且无需 polyfill。Node 24 及以上使用基于 `AsyncContextFrame` 的实现，Node 22 使用此前的实现；本 RFC 为保证该不变量接受常驻传播成本，不作零开销承诺。 - -服务关闭是有顺序的，不提供透明的进行中延续。Agent Loop 必须先停止接受新驱动并取消或等待所有进行中的驱动收敛，随后 Cordis 才 dispose 服务并调用 `disable()`。HMR（热模块替换）会重建依赖该服务的子树，不承诺让进行中的轮次跨服务替换继续执行。如果旧调用方保留了已 dispose 的服务引用，`current()` 和 `require()` 都会抛出稳定的 “service disposed” 错误，而不是返回模糊的 `undefined`。 - -### 生命周期边界 - -在每个具体 Agent 驱动的 `runLoop` 整个生命周期外围绑定执行上下文： - -```text -agentExecution.run({ agent }, () => runLoop(ctx, agent, handle)) -``` - -这样，由该驱动发起的每项操作都能获得同一个可信 Agent： - -- 提示词拦截和提示词组装； -- LLM 适配器调用； -- 工具策略和工具主体； -- 能力提供方和传输层； -- 这些操作所等待的同步和异步辅助函数。 - -并发驱动会获得彼此独立的 ALS 存储。子 Agent 自己的驱动会用该子 Agent 建立新边界，因此即使子 Agent 是在父 Agent 的工具调用中创建的，其操作也不会错误继承父 Agent。嵌套边界返回后，ALS 会自动恢复父 Agent。 - -Agent 创建阶段有意置于这个动态边界之外。创建过程已经接收 `agentCtx`，其中 `agentCtx.agent` 就是正确的、尚未发布的 Agent。发布流程和生命周期归属继续使用现有的显式 Agent 与作用域载体。由此产生一条明确契约，而非偶然行为：当子 Agent 的创建发生在父 Agent 的工具调用内时，子 Agent 的创建流程和持久化加载运行在**父 Agent** 的隐式身份之下，因为子驱动尚未启动。这个窗口内触达的传输层按父会话路由——对可信路由而言这是正确的，因为创建工作由父 Agent 发起并归它所有。创建代码需要子身份时使用显式的 `agentCtx.agent`，绝不读隐式存储。 - -### 显式主体仍是真源 - -隐式身份只是深层基础设施的便利能力，不会取代现有契约： - -- `AgentEventDispatch` 继续携带显式 Agent 主体和作用域。 -- `AssembleContext.agent` 保持显式传递。 -- `ToolExecution.agent` 保持显式传递，并继续选择作用域内的工具和策略视图。 -- `GenerateOptions.sessionId` 在 LLM 边界上保持显式传递。 -- subagent 请求和生命周期事件继续携带显式的父子身份。 -- 会话事件仍然是回放和恢复的持久化真源。 - -代码跨越公开服务、进程、worker、持久化或协议边界时，必须把边界所需身份写入其类型化请求。远程进程无法访问父进程的 ALS 存储。 - -### 可信传输层用途 - -能力传输层可以在构造对外请求时读取 `ctx.agentExecution.require().agent.session.id`，并添加由部署方控制的可信身份，例如 `X-Harness-Session-Id` 请求头。该身份不出现在模型可见的参数中，模型也不能覆盖它。传输层仍须执行自身的能力和生命周期授权；隐式 Agent 只提供发起方身份，不授予调用权限。 - -bash seam 现有的 `OwnerToken` 是最接近的显式身份先例，它也说明了为什么显式方案补不上这个缺口：`BashExecSpec.owner` 是一个后台任务隔离键，由 `dsh-tool-bash` 从会话 id 转换而来，前台 `run()` 有意忽略它，而文件系统 seam 没有对应物——其提供方方法完全不携带身份参数。给每个能力 seam 都加一个路由身份参数，会把宿主平台的关注点塞进本应与部署无关的 seam 词汇；隐式身份让传输层实现自己拥有路由逻辑，而不必加宽任何 seam。 - -宿主平台继续负责把 Harness 运行时会话 ID 解析成产品会话和沙箱归属方。Harness 不需要理解宿主平台的沙箱标识、沙箱提供方或持久化模型。 - -模型侧 skill 和工具插件不应自行添加宿主平台特有的请求头。它们调用能力服务；所选提供方负责远程执行和身份传播。这样可以保持模型行为与后端路由之间的职责分离。 - -### 分离异步工作 - -Node ALS 会被 `run()` 内创建的异步资源继承，即使调用方没有等待它们。这对 Agent 所拥有的后台操作很有用，但也可能让无关任务保留陈旧轮次的上下文。 - -身份继承不取代取消归属。在 Agent 边界内启动的工作要么是**前台**的——继承 `{ agent }`，并通过其执行 seam 单独接收显式取消信号；要么是**分离**的——在 `run(undefined, operation)` 下启动，并拥有独立生命周期和显式停止操作。调用方必须让这两个选择保持一致。实现必须记录并测试以下规则： - -- 逻辑上归 Agent 所有的工作是前台工作：可以继承 `{ agent }`，通过现有显式 seam 接收取消，并且必须遵守该 Agent 的 dispose 契约。 -- 与该 Agent 无关的长生命周期部署基础设施、定时器和工作队列是分离工作：必须在 `run(undefined, operation)` 下启动，由自己的归属方停止，绝不因某个轮次结束而被隐式终止。 -- 把数据入队并留待后续处理的代码必须将所需身份序列化到队列项中；不能期待 ALS 跨越队列、进程或 worker 边界。 -- 消费方不能把隐式 Agent 引用视为 Agent 仍然存活的证明。生命周期敏感的操作仍须检查 `agent.status`、显式 signal 或归属服务的契约。 - -`turn` 和 `step` 不进入第一版；如果未来出现真实的横切消费方（追踪、日志）无法使用现有显式字段，可以再将它们作为独立的不可变执行帧扩展引入。完整 `Agent` 是刻意允许的能力例外，因为它就是建立边界的执行主体。每个额外字段都必须是陈旧安全的标签，其陈旧副本最坏只能误标一条追踪记录；其他能力或控制通道需要独立 RFC。第一版不携带 `AbortSignal`；见「考虑过的替代方案」。 - -## 当前 Harness 依据 - -由于这份交接基于本地源码快照编写，目标分支可能已经前进，后续实现会话应在编辑前重新检查这些符号。 - -- `packages/core/agent/src/types.ts`：`Agent` 已经拥有 `session`、`status` 和 `ctx`。其中 `ctx` 的文档将它定义为注册作用域，而不是动态请求上下文。 -- `packages/core/agent/src/index.ts`：Cordis `Context.agent` 作为 Agent 作用域的开发体验关联被安装，在普通上下文上默认返回 `undefined`。不要改变这一语义。 -- `packages/core/agent-loop/src/agent.ts`：`ReactLoopAgent` 已经拥有 inbox、取消逻辑、每步骤 abort、状态和驱动生命周期。不要再创建一套并行的可变运行时状态对象。 -- `packages/core/agent-loop/src/loop.ts`：`runLoop(ctx, agent, handle)` 正好是需要包裹的生命周期边界。它会将 Agent、轮次、步骤和 signal 显式传给更窄的操作。 -- `packages/core/tools/src/index.ts`：`ToolExecutionInput.agent` 是显式字段，并用于选择作用域内的策略和工具解析。增加 ALS 后，它仍然保留在契约中。 -- `packages/core/agent/src/dispatch.ts`：`agentEvents()` 有意把 Agent 主体与其作用域载体融合。隐式上下文不能取代这套正确性机制。 -- `packages/core/README.md` 和现有 core 包：它们表明稳定的 Agent 控制契约位于 `core/`；`agent-execution` 是必载控制基础设施，而不是模型可见的可选上下文增强。 - -本提案扩展而非取代[关于 Agent 注册作用域的既有决策](../../implemented/architecture/2026-07-08-agent-scope-contexts.md)及其[运行时设计](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md)。 - -## Claude Code 参考实现 - -| Claude Code | Harness 中的对应设计 | -|---|---| -| AppState store | Cordis 部署服务及其拥有的实时状态 | -| QueryEngine | `ReactLoopAgent` 及其 loop 所拥有的运行时状态 | -| ToolUseContext | 能力边界上的显式 Agent、工具和请求参数 | -| AgentContext ALS | 本提案的窄粒度 `AgentExecution` 载体 | -| Transcript | 事件溯源 `Session` 与持久化后端 | - -## 实现交接步骤 - -后续实现会话应按以下顺序开展工作： - -1. 切换到预期目标分支，检查“当前 Harness 依据”中列出文件的当前版本。不要合并或复制编写本交接文档所在分支的修改。 -2. 新增 `packages/core/agent-execution/`，包含包元数据、README、导出类型、Cordis 服务、模块扩展和聚焦测试。 -3. 按照现有包门禁，把该包加入 TypeScript 项目引用、路径候选、运行时闭包或配置以及生成目录。优先使用仓库生成器，不要手工编辑生成文件。同时更新根 `AGENTS.md` 中 repository layout 的 `core/` 行、`packages/core/README.md` 中的包表，以及 `packages/README.md` 中的包组说明。 -4. 让 Agent Loop 声明并消费该服务。在不改变公开 Agent、事件、工具、LLM 或会话签名的前提下，用 `{ agent }` 包裹每个 Agent 驱动的完整 `runLoop` 调用。 -5. 增加集成测试：让同一进程中的两个 Agent 重叠执行，并在至少一次 `await` 后从异步工具执行内部观察到正确的隐式 Agent。 -6. 增加嵌套 Agent 覆盖：证明子 Agent 能看到自己，且子边界结束后父上下文得到恢复。 -7. 增加清除和失败覆盖：边界外返回 `undefined`，`require()` 清晰失败，`run(undefined, ...)` 屏蔽继承的 Agent，抛出异常或 rejected 操作不会污染后续无关工作。 -8. 在集成测试中增加一个能力传输测试替身。保持模型侧 schema 不变，并断言可信会话请求头由内部生成。适配真实生产远程后端属于本 RFC 之外的后续工作。 -9. 运行类型检查、定向测试、文档门禁、生成目录检查，最后运行仓库常规 CI 或 pre-push 门禁。 - -建议的聚焦测试矩阵： - -| 场景 | 必须观察到的结果 | -|---|---| -| 驱动之外 | `current()` 为 `undefined` | -| 一个 Agent 跨越 await | 每个 continuation 都看到完全相同的 Agent | -| 两个并发 Agent | A 永远看不到 B，B 永远看不到 A | -| 嵌套子 Agent | 子 Agent 看到自己；随后恢复父 Agent | -| 子 Agent 创建窗口 | 父工具调用内的创建流程隐式看到父 Agent；`agentCtx.agent` 是子 Agent | -| 直接调用无 Agent 工具 | 显式工具行为仍然有效；隐式身份不存在 | -| 已清除的分离工作 | `run(undefined, ...)` 隐藏继承的 Agent | -| 失败和取消 | throw、rejection 和 abort 后上下文均得到恢复 | -| Agent dispose | 隐式引用不赋予 dispose 后的能力 | -| 服务重载 | Agent 驱动在 ALS disable 前收敛；保留的已 dispose 服务调用抛出文档约定的稳定错误 | -| 能力传输边界 | 会话身份由测试替身传输层写入类型化请求或请求头 | - -## 考虑过的替代方案 - -**让每个函数都传递 Agent。** 对公开边界和承载权限的边界而言，这仍然是正确选择；但如果要求每个私有辅助函数都传递 Agent，就会产生大量样板代码，而隐式执行上下文正适合消除这些代码。本提案在边界处保留显式主体，只在单个可信异步进程内部使用 ALS。 - -**修改 `ctx.agent`，让它返回当前正在执行的 Agent。** 拒绝此方案，因为 `ctx.agent` 已经表示 Agent 作用域 Cordis 上下文的静态关联。让根上下文变成动态语义，会把注册作用域和执行作用域混合起来，在并发时产生意外行为，并破坏已经实现的 Agent 作用域 RFC。 - -**在 ALS 中存储完整的可变运行时对象。** 拒绝此方案，因为 Agent、会话、inbox、取消状态、轮次或步骤状态、工具执行和持久化日志已经有各自的真源。重复保存会产生陈旧快照、写入顺序问题，以及另一套需要清理的生命周期。 - -**在第一版 ALS 帧中携带步骤级 `AbortSignal`。** 本 RFC 拒绝此方案。signal 的生命周期是每步骤，而提议的 ALS 边界是每驱动，因此携带它需要嵌套的步骤和工具边界，还要明确规定分离工作、deadline 归属和恢复语义。现有执行 seam 已经显式传递取消。未来只有在出现具体横切消费方，并通过测试建立这些嵌套生命周期语义后，才可由独立 RFC 重新评估。 - -**使用一个进程级可变 `currentAgent`。** 拒绝此方案，因为并发 Agent 和 subagent 会在 await 边界间相互覆盖。它只有在所有工作严格串行时才正确，而多 Agent 执行明确不保证这一点。 - -**从模型可见的工具参数推导会话。** 拒绝此方案，因为模型可以修改这些参数。沙箱路由和授权需要可信的进程内身份，而不是用户或模型输入。 - -**把宿主平台的沙箱归属标识或提供方数据放入 Harness 上下文。** 拒绝此方案，因为沙箱归属是由 Harness 外部解析的宿主产品状态。Harness 在可信传输边界上传递自己的会话身份即可。 - -## 验收标准 - -- 一个 Node Harness 进程至少能并发执行两个 Agent，异步消费方始终观察到准确的发起 Agent。 -- 在 Agent 驱动执行之外，隐式查询返回 `undefined`，且 `require()` 抛出稳定、可操作的错误。 -- 嵌套 Agent 执行结束后会恢复父上下文。 -- `agent.ctx`、`ctx.agent`、Agent 事件、提示词组装、`ToolExecution.agent`、LLM `sessionId` 和会话持久化保持现有语义。 -- Agent、会话、轮次、步骤、沙箱和授权身份都不能由模型控制。 -- 实现为无关分离任务提供显式 undefined 边界，并通过测试防止上下文泄漏，且不改变现有显式取消契约。 -- 该服务随标准 agent 组合包加载，缺少它时 `dsh-agent-loop` 在加载阶段失败；配置测试锁定这一策略。 -- dispose 或 HMR（热模块替换）会先让所有依赖的 Agent 驱动收敛，再禁用 ALS；已 dispose 服务上的保留调用会抛出文档约定的稳定错误，且已 dispose 的 Cordis 上下文不能继续访问活跃 ALS 状态。 -- 一个能力传输测试替身能证明可信会话 ID 得到传播，同时不新增模型可见的 schema 字段。 -- 包目录、依赖图、API 文档和相关架构文档得到重新生成或更新，仓库文档门禁通过。 - -## 风险 - -- 隐式上下文会从函数签名中隐藏依赖。将它限制在深层横切基础设施，并保留显式公开主体，可以控制这一成本。 -- ALS 对分离 promise 和定时器的继承可能保留语义上陈旧的身份。实现必须提供显式 undefined 边界、文档和回归测试，而不能假设清理会自然发生。 -- ALS 不会跨越 worker thread、子进程、Redis、HTTP 或持久化队列。每个此类边界都必须显式序列化所需身份。 -- 隐式存储有意携带完整的存活 Agent 能力。被捕获的引用可能比 Agent 的发布状态活得更久，因此隐式存在本身绝不授权生命周期敏感工作，消费方仍须遵循 Agent 生命周期和取消契约。 -- 强制加载给每个 agent 组合新增一个核心运行时依赖；本 RFC 接受这一成本，因为可选服务会让隐式身份依赖具体组合。支持范围内的 Node 版本仍存在可测量的传播成本，应另行基准测试。 -- 过早加入轮次、步骤、signal、cwd 或工具细节会扩大继承范围和陈旧状态风险。第一版有意接受只提供 Agent 隐式身份的限制；未来任何额外的能力或控制字段都需要独立 RFC。 diff --git a/examples/coding-agent/tests/code-mode.e2e.ts b/examples/coding-agent/tests/code-mode.e2e.ts index 3f6e109e3f..1994ae9c36 100644 --- a/examples/coding-agent/tests/code-mode.e2e.ts +++ b/examples/coding-agent/tests/code-mode.e2e.ts @@ -9,6 +9,7 @@ import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' @@ -44,6 +45,7 @@ async function codeModeHarness(cwd: string): Promise { await harness.plugin(SystemPrompt, { persona: PERSONA }) await harness.plugin(ToolRegistry, { mode: 'code' }) await harness.plugin(AgentRegistry) + await harness.plugin(AgentExecutionProvider) await harness.plugin(AgentLoop, { agents: [] }) await harness.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) await harness.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 }) diff --git a/examples/coding-agent/tests/harness.ts b/examples/coding-agent/tests/harness.ts index dd0bc42a1b..d8790a0443 100644 --- a/examples/coding-agent/tests/harness.ts +++ b/examples/coding-agent/tests/harness.ts @@ -5,6 +5,7 @@ import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' @@ -55,6 +56,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio await ctx.plugin(SystemPrompt, { persona: options.persona ?? '' }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 }) diff --git a/examples/cordis-agent/tests/harness.ts b/examples/cordis-agent/tests/harness.ts index 78e5b0bb93..5286957b8a 100644 --- a/examples/cordis-agent/tests/harness.ts +++ b/examples/cordis-agent/tests/harness.ts @@ -4,6 +4,7 @@ import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import * as ToolCordis from '@deepseek-ai/dsh-tool-cordis' @@ -28,6 +29,7 @@ export async function cordisHarness(): Promise { await ctx.plugin(SystemPrompt, { persona: PERSONA }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) await ctx.plugin(ToolCordis) diff --git a/packages/README.md b/packages/README.md index 8f1bf3dde2..55bfa5cc7b 100644 --- a/packages/README.md +++ b/packages/README.md @@ -8,7 +8,7 @@ Packages live at `packages///`; groups are containers, while names r | Group | Role | Release expectation | |---|---|---| -| [`core/`](core/README.md) | Product API spine: session, system-prompt, tools, agent, and the concrete loop | Product — stable surface | +| [`core/`](core/README.md) | Product API spine: session, system-prompt, tools, agent, agent-execution, and the concrete loop | Product — stable surface | | [`llm/`](llm/README.md) | LLM capability family: the abstract service + provider adapters | Product — stable surface | | [`bash/`](bash/README.md) | Bash capability family: the executor seam, a local impl, and the model-facing tool | Product — stable surface | | [`code-runtime/`](code-runtime/README.md) | Code-execution capability family: the abstract runtime seam for model-written programs + a worker-thread backend | Product — stable surface | diff --git a/packages/bash/tool-bash/package.json b/packages/bash/tool-bash/package.json index 035b16aeec..b0a1eaf779 100644 --- a/packages/bash/tool-bash/package.json +++ b/packages/bash/tool-bash/package.json @@ -37,6 +37,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-user-approval": "workspace:^", "@deepseek-ai/dsh-bash": "workspace:^", diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index 238176b8a6..c07e49c91d 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -6,6 +6,7 @@ import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import TaskService from '@deepseek-ai/dsh-tasks' import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks' @@ -26,6 +27,7 @@ async function harness(adapter: MockAdapter) { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(TaskService) await ctx.plugin(ToolTasks) diff --git a/packages/compact/compact-basic/package.json b/packages/compact/compact-basic/package.json index 32852a060f..55327227c9 100644 --- a/packages/compact/compact-basic/package.json +++ b/packages/compact/compact-basic/package.json @@ -30,6 +30,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-compact": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index dbf8a3b737..03870c7a6e 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -8,6 +8,7 @@ import { isToolPairingBalanced } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' @@ -66,6 +67,7 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], new StepwiseToolAdapter(toolSteps)) ctx.tools.register(defineTool({ diff --git a/packages/context/time-context/package.json b/packages/context/time-context/package.json index f319c7a5b1..ee7a60c839 100644 --- a/packages/context/time-context/package.json +++ b/packages/context/time-context/package.json @@ -31,6 +31,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", diff --git a/packages/context/time-context/tests/time-context.spec.ts b/packages/context/time-context/tests/time-context.spec.ts index 562b002b68..2b55dd509f 100644 --- a/packages/context/time-context/tests/time-context.spec.ts +++ b/packages/context/time-context/tests/time-context.spec.ts @@ -8,6 +8,7 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as timeContext from '@deepseek-ai/dsh-time-context' import type { Config } from '@deepseek-ai/dsh-time-context' @@ -94,6 +95,7 @@ async function loopHarness(adapter: ScriptedAdapter, config: Config = {}): Promi await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(timeContext, config) ctx.llm.registerAdapter(['mock'], adapter) diff --git a/packages/cordis/tool-cordis/package.json b/packages/cordis/tool-cordis/package.json index fd9c35e48e..7c5db05b23 100644 --- a/packages/cordis/tool-cordis/package.json +++ b/packages/cordis/tool-cordis/package.json @@ -31,6 +31,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 51b4a5155f..eb8a25d8b4 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -52,6 +52,15 @@ export interface TypeApiEntry { /** Every harness `ctx.` service, sorted by key. */ export const SERVICE_API: readonly ServiceApiEntry[] = [ + { + key: 'agentExecution', + summary: 'Ambient Agent identity within one process-local asynchronous chain.', + methods: [ + 'current(): AgentExecution | undefined', + 'require(): AgentExecution', + 'run(execution: AgentExecution | undefined, operation: () => T): T', + ], + }, { key: 'agentLoop', summary: 'Concrete ReactLoopAgent factory and driver service.', @@ -505,6 +514,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'Agent', declaration: 'export interface Agent {\n readonly id: AgentId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: SendOptions): void;\n cancel(reason?: string): void;\n whenIdle(): Promise;\n}', }, + { + name: 'AgentExecution', + declaration: 'export interface AgentExecution {\n readonly agent: Agent;\n}', + }, { name: 'AgentFactory', declaration: 'export interface AgentFactory {\n createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise;\n resume(ownerCtx: Context, options: ResumeAgentOptions): Promise;\n}', diff --git a/packages/cordis/tool-cordis/tests/integration.spec.ts b/packages/cordis/tool-cordis/tests/integration.spec.ts index 94331df7c0..920909c26e 100644 --- a/packages/cordis/tool-cordis/tests/integration.spec.ts +++ b/packages/cordis/tool-cordis/tests/integration.spec.ts @@ -5,6 +5,7 @@ import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as ToolCordis from '../src/index.ts' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -25,6 +26,7 @@ async function harness(adapter: MockAdapter): Promise { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(ToolCordis) ctx.llm.registerAdapter(['mock'], adapter) diff --git a/packages/core/README.md b/packages/core/README.md index 921591d85e..8223b7b0b0 100644 --- a/packages/core/README.md +++ b/packages/core/README.md @@ -9,10 +9,11 @@ The session log, system-prompt assembly, tool registry, agent vocabulary, and co | `system-prompt/` | Prompt-section + tool-schema assembly registry | `ctx.systemPrompt` | | `tools/` | Scoped tool registry + pre-policy, guards, around-dispatch, post-policy, and final-result observation | `ctx.tools` | | `agent/` | Agent interface, registry, `agent/*` event vocabulary | `ctx.agents` | +| `agent-execution/` | Process-local ambient Agent identity for asynchronous driver work | `ctx.agentExecution` | | `agent-loop/` | The concrete loop plugin: `ReactLoopAgent` + the loop driver | `ctx.agentLoop` | `scope/` is the one non-service package here: a dependency-free library (`createScope`/`scopeOf`/`scopeTarget`) the registries and the loop build per-agent scoping on — it sits below `session/` and `system-prompt/` in the module graph precisely so they can consume it without a cycle. -`agent-loop` is the one concrete implementation of the `agent` seam and lives here because it is the harness's default product loop; everything else in `core/` is interface/vocabulary. Plugins depend on the `agent` vocabulary, never on `agent-loop` directly, so the loop stays swappable. +`agent-execution` is mandatory control infrastructure shared by concrete loops and deep process-local consumers. `agent-loop` is the one concrete implementation of the `agent` seam and lives here because it is the harness's default product loop; other plugins depend on the `agent` vocabulary and execution service, never on `agent-loop` directly, so the loop stays swappable. -The default composition that wires this spine into a runnable agent lives in [`examples/agent-spine-demo`](../examples/agent-spine-demo/README.md): one bundle plugin that loads the control spine plus selected default capabilities (`timer` + `llm` + sessions + system-prompt + tools + agents + invariants + the local [skill family](../skill/README.md) + `tool-bash` + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. It sits in `examples/` — ready-to-run demo/reference bundles — not in `core/`: `core/` ships the swappable spine pieces, while a demo bundle picks one concrete composition of them and adds a front door. +The default composition that wires this spine into a runnable agent lives in [`examples/agent-spine-demo`](../examples/agent-spine-demo/README.md): one bundle plugin that loads the control spine plus selected default capabilities (`timer` + `llm` + sessions + system-prompt + tools + agents + agent-execution + invariants + the local [skill family](../skill/README.md) + `tool-bash` + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. It sits in `examples/` — ready-to-run demo/reference bundles — not in `core/`: `core/` ships the swappable spine pieces, while a demo bundle picks one concrete composition of them and adds a front door. diff --git a/packages/core/agent-execution/README.md b/packages/core/agent-execution/README.md new file mode 100644 index 0000000000..a389699863 --- /dev/null +++ b/packages/core/agent-execution/README.md @@ -0,0 +1,23 @@ +# dsh-agent-execution + +Process-local ambient Agent identity for asynchronous work initiated by a concrete agent driver. The default export, `AgentExecutionProvider`, installs the mandatory `ctx.agentExecution` service; [`dsh-agent-loop`](../agent-loop/README.md) establishes one boundary around each driver's complete lifetime. + +## Service: `AgentExecutionService` (ctx key: `agentExecution`) + +- `current()` returns the inherited `AgentExecution` or `undefined` outside a driver and inside an explicit clearing boundary. +- `require()` returns the inherited execution or throws `no agent execution context is active`. +- `run(execution, operation)` returns the exact synchronous value or Promise from `operation`. Passing `undefined` establishes a real boundary that hides an inherited Agent. + +The store contains only `{ readonly agent: Agent }`. A Session is available through `agent.session`; turn, step, signal, cwd, sandbox, authorization, and other capability state remain with their explicit owners. Ambient presence identifies the initiator but does not prove that the Agent is live or that an operation is authorized. + +## Lifetime and detached work + +Provider teardown rejects new `run()` boundaries, removes the service so injected dependents drain, waits for returned Promise boundaries, then disables its `AsyncLocalStorage`. In-flight code retaining the service can call `current()` and `require()` while it drains; after disposal, all three methods throw `agent execution service is disposed`. + +Async resources created inside `run()` inherit its Agent even when the operation does not await them. Agent-owned foreground work may inherit the boundary but keeps using the explicit cancellation and disposal contract of its execution seam. Unrelated timers, queues, and deployment infrastructure start under `run(undefined, operation)` and own an explicit stop. Queue, worker, process, and wire boundaries serialize any identity they need instead of relying on ALS propagation. + +## Known Limitations and Deferred Work + +- **Process-local only** — ALS does not cross workers, child processes, HTTP, durable queues, or restarts; each boundary materializes a typed identity explicitly. +- **Agent identity only** — turn, step, signal, cwd, sandbox, and authorization stay outside the frame until a concrete cross-cutting consumer justifies a separate design. +- **Ambient references may outlive liveness** — consumers still check `agent.status`, their explicit signal, and the owning capability contract before lifecycle-sensitive work. diff --git a/packages/core/agent-execution/package.json b/packages/core/agent-execution/package.json new file mode 100644 index 0000000000..e5ebbbf5f3 --- /dev/null +++ b/packages/core/agent-execution/package.json @@ -0,0 +1,31 @@ +{ + "name": "@deepseek-ai/dsh-agent-execution", + "description": "Agent-scoped asynchronous execution context for the DeepSeek Harness", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@deepseek-ai/dsh-agent": "^0.0.1", + "cordis": "^4.0.0-rc.7" + }, + "devDependencies": { + "@deepseek-ai/dsh-agent": "workspace:^", + "cordis": "^4.0.0-rc.7" + } +} diff --git a/packages/core/agent-execution/src/index.ts b/packages/core/agent-execution/src/index.ts new file mode 100644 index 0000000000..3aef4c1856 --- /dev/null +++ b/packages/core/agent-execution/src/index.ts @@ -0,0 +1,139 @@ +/** + * Process-local Agent execution context backed by Node AsyncLocalStorage. + * + * @module @deepseek-ai/dsh-agent-execution + */ + +import type { Context } from 'cordis' +import { AsyncLocalStorage } from 'node:async_hooks' +import type { AgentExecution } from './types.ts' + +export type { AgentExecution } from './types.ts' + +const NO_ACTIVE_EXECUTION = 'no agent execution context is active' +const DISPOSED_SERVICE = 'agent execution service is disposed' + +/** Ambient Agent identity within one process-local asynchronous chain. */ +export interface AgentExecutionService { + /** + * Read the active execution without requiring one. + * @returns the inherited execution, or `undefined` outside/inside a cleared boundary. + * @throws when this service instance has been disposed. + */ + current(): AgentExecution | undefined + + /** + * Read the active execution and fail when no boundary is active. + * @returns the inherited execution. + * @throws when no execution is active or this service instance has been disposed. + */ + require(): AgentExecution + + /** + * Run an operation inside an execution boundary. Passing `undefined` clears + * an inherited execution; the exact synchronous value or Promise is returned. + * @param execution - execution to inherit, or `undefined` for a clearing boundary. + * @param operation - synchronous or asynchronous operation to invoke. + * @returns the exact value returned by `operation`. + * @throws when this service is closing/disposed, or when `operation` throws. + */ + run(execution: AgentExecution | undefined, operation: () => T): T +} + +declare module 'cordis' { + interface Context { + agentExecution: AgentExecutionService + } +} + +/** One provider-owned ALS instance with quiescent shutdown. */ +class DefaultAgentExecutionService implements AgentExecutionService { + private readonly storage = new AsyncLocalStorage() + private state: 'active' | 'closing' | 'disposed' = 'active' + private activeRuns = 0 + private drainWaiter: PromiseWithResolvers | undefined + private disposalTask: Promise | undefined + + current(): AgentExecution | undefined { + this.assertReadable() + return this.storage.getStore() + } + + require(): AgentExecution { + const execution = this.current() + if (execution === undefined) throw new Error(NO_ACTIVE_EXECUTION) + return execution + } + + run(execution: AgentExecution | undefined, operation: () => T): T { + if (this.state !== 'active') throw new Error(DISPOSED_SERVICE) + this.activeRuns += 1 + let result: T + try { + result = this.storage.run(execution, operation) + } catch (error: unknown) { + this.releaseRun() + throw error + } + if (result instanceof Promise) { + void result.then( + () => { this.releaseRun() }, + () => { this.releaseRun() }, + ) + } else { + this.releaseRun() + } + return result + } + + /** Reject new boundaries while existing continuations remain readable. */ + close(): void { + if (this.state === 'active') this.state = 'closing' + } + + /** Wait for every returned Promise boundary, then invalidate retained references. */ + dispose(): Promise { + return (this.disposalTask ??= (async () => { + this.close() + if (this.activeRuns !== 0) { + this.drainWaiter ??= Promise.withResolvers() + await this.drainWaiter.promise + } + this.state = 'disposed' + this.storage.disable() + })()) + } + + private assertReadable(): void { + if (this.state === 'disposed') throw new Error(DISPOSED_SERVICE) + } + + private releaseRun(): void { + this.activeRuns -= 1 + if (this.activeRuns !== 0) return + this.drainWaiter?.resolve() + this.drainWaiter = undefined + } +} + +/** Cordis provider for the mandatory `ctx.agentExecution` service. */ +export class AgentExecutionProvider { + private readonly service = new DefaultAgentExecutionService() + + /** + * Install one isolated execution service and its ordered lifecycle. + * @param ctx - provider-owning Cordis context. + */ + constructor(ctx: Context) { + const service = this.service + ctx.effect(function* () { + // First yielded, disposed last: invalidate ALS only after dependents and active runs drain. + yield () => service.dispose() + yield ctx.provide('agentExecution', service) + // Last yielded, disposed first: prevent a teardown race from opening another boundary. + yield () => { service.close() } + }, 'agentExecution.lifecycle()') + } +} + +export default AgentExecutionProvider diff --git a/packages/core/agent-execution/src/types.ts b/packages/core/agent-execution/src/types.ts new file mode 100644 index 0000000000..ccafb4840a --- /dev/null +++ b/packages/core/agent-execution/src/types.ts @@ -0,0 +1,12 @@ +/** + * Public Agent execution-context types. + * + * @module @deepseek-ai/dsh-agent-execution/types + */ + +import type { Agent } from '@deepseek-ai/dsh-agent' + +/** The exact live Agent associated with one asynchronous execution chain. */ +export interface AgentExecution { + readonly agent: Agent +} diff --git a/packages/core/agent-execution/tests/agent-execution.spec.ts b/packages/core/agent-execution/tests/agent-execution.spec.ts new file mode 100644 index 0000000000..ccf17f6722 --- /dev/null +++ b/packages/core/agent-execution/tests/agent-execution.spec.ts @@ -0,0 +1,136 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' +import type { AgentExecution, AgentExecutionService } from '@deepseek-ai/dsh-agent-execution' + +function execution(id: string): AgentExecution { + return { agent: { id: AgentId(id) } as Agent } +} + +async function harness(): Promise<{ + ctx: Context + service: AgentExecutionService + dispose: () => Promise +}> { + const ctx = new Context() + const fiber = await ctx.plugin(AgentExecutionProvider) + return { + ctx, + service: ctx.agentExecution, + dispose: fiber.dispose, + } +} + +describe('AgentExecutionProvider', () => { + it('reports an absent boundary and requires an active execution', async () => { + const { service, dispose } = await harness() + expect(service.current()).toBeUndefined() + expect(() => service.require()).toThrow('no agent execution context is active') + await dispose() + }) + + it('preserves exact synchronous and Promise return identities across await', async () => { + const { service, dispose } = await harness() + const active = execution('identity') + const value = { result: true } + expect(service.run(active, () => { + expect(service.require()).toBe(active) + return value + })).toBe(value) + + const promise = service.run(active, async () => { + expect(service.require()).toBe(active) + await Promise.resolve() + expect(service.require()).toBe(active) + return value + }) + expect(service.run(active, () => promise)).toBe(promise) + await expect(promise).resolves.toBe(value) + expect(service.current()).toBeUndefined() + await dispose() + }) + + it('isolates overlapping executions', async () => { + const { service, dispose } = await harness() + const a = execution('a') + const b = execution('b') + const bothStarted = Promise.withResolvers() + const release = Promise.withResolvers() + let starts = 0 + const run = (active: AgentExecution): Promise => service.run(active, async () => { + expect(service.require()).toBe(active) + starts += 1 + if (starts === 2) bothStarted.resolve(true) + await release.promise + expect(service.require()).toBe(active) + }) + + const pending = [run(a), run(b)] + await bothStarted.promise + expect(service.current()).toBeUndefined() + release.resolve(true) + await Promise.all(pending) + await dispose() + }) + + it('restores nested and explicitly cleared boundaries', async () => { + const { service, dispose } = await harness() + const parent = execution('parent') + const child = execution('child') + + service.run(parent, () => { + expect(service.require()).toBe(parent) + service.run(child, () => { expect(service.require()).toBe(child) }) + expect(service.require()).toBe(parent) + service.run(undefined, () => { + expect(service.current()).toBeUndefined() + expect(() => service.require()).toThrow('no agent execution context is active') + }) + expect(service.require()).toBe(parent) + }) + expect(service.current()).toBeUndefined() + await dispose() + }) + + it('restores context after synchronous throws and rejected operations', async () => { + const { service, dispose } = await harness() + const parent = execution('parent') + const child = execution('child') + const syncError = new Error('sync failure') + const asyncError = new Error('async failure') + + service.run(parent, () => { + expect(() => service.run(child, () => { throw syncError })).toThrow(syncError) + expect(service.require()).toBe(parent) + }) + await expect(service.run(child, async () => { + await Promise.resolve() + throw asyncError + })).rejects.toBe(asyncError) + expect(service.current()).toBeUndefined() + await dispose() + }) + + it('stops new boundaries, drains active Promises, and invalidates retained references', async () => { + const { ctx, service, dispose } = await harness() + const active = execution('draining') + const release = Promise.withResolvers() + const pending = service.run(active, async () => { + await release.promise + expect(service.require()).toBe(active) + }) + let disposed = false + const disposal = dispose().then(() => { disposed = true }) + await Promise.resolve() + + expect(() => service.run(active, () => 1)).toThrow('agent execution service is disposed') + expect(disposed).toBe(false) + expect(ctx.get('agentExecution')).toBeUndefined() + release.resolve(true) + await pending + await disposal + expect(() => service.current()).toThrow('agent execution service is disposed') + expect(() => service.require()).toThrow('agent execution service is disposed') + }) +}) diff --git a/packages/core/agent-execution/tsconfig.json b/packages/core/agent-execution/tsconfig.json new file mode 100644 index 0000000000..a06784e926 --- /dev/null +++ b/packages/core/agent-execution/tsconfig.json @@ -0,0 +1,21 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../../vendor/cosmokit" + }, + { + "path": "../../../vendor/cordis" + }, + { + "path": "../../core/agent" + } + ] +} diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index a07aa5fa70..c961969edc 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -23,7 +23,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo ### Injected services -`agents`, `sessions`, `llm`, `tools`, `systemPrompt` — all five interface services. +`agents`, `agentExecution`, `sessions`, `llm`, `tools`, `systemPrompt` — all six interface services. The loop cannot activate without `agentExecution`; the default bundle loads its provider before the loop. ### Configuration (schemastery) @@ -48,7 +48,9 @@ Configured agents start automatically. `cwd` applies only to fresh sessions; `re ### Loop lifecycle (`loop.ts`) -The driver owns one agent for its lifetime. It records turn, step, request, stream, and tool boundaries in the session log; live extension events coordinate policy around those durable facts. The [architecture turn flow](../../../docs/architecture.md#turn-flow) and generated [event catalog](../../../docs/cordis-catalog/events.md) are the authoritative sequence and signatures. +The driver owns one agent for its lifetime and runs inside `ctx.agentExecution.run({ agent }, ...)`, so process-local asynchronous continuations can recover the initiating Agent. Creation, persistence load, and unpublished setup stay outside the child boundary; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. The [execution-context package](../agent-execution/README.md) owns propagation and detached-work rules. + +The loop records turn, step, request, stream, and tool boundaries in the session log; live extension events coordinate policy around those durable facts. The [architecture turn flow](../../../docs/architecture.md#turn-flow) and generated [event catalog](../../../docs/cordis-catalog/events.md) are the authoritative sequence and signatures. Plugin failure ends the current turn, not the loop. Cancellation clears pending work and aborts the current step without leaking to the next prompt. Terminal continuation stops remain authoritative through turn close and durability flush. diff --git a/packages/core/agent-loop/package.json b/packages/core/agent-loop/package.json index 7e2fb235a2..6a7fe2d937 100644 --- a/packages/core/agent-loop/package.json +++ b/packages/core/agent-loop/package.json @@ -22,6 +22,7 @@ "license": "BSD-3-Clause", "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", + "@deepseek-ai/dsh-agent-execution": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", @@ -35,6 +36,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-scope": "workspace:^", diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index a2288c65b7..7194d6c7e8 100644 --- a/packages/core/agent-loop/src/agent.ts +++ b/packages/core/agent-loop/src/agent.ts @@ -327,7 +327,7 @@ export class ReactLoopAgent implements Agent { [startDriver](): void { if (this._status === 'disposed') return this.driverStarted = true - this.done = runLoop(this.loopCtx, this, { + this.done = this.loopCtx.agentExecution.run({ agent: this }, () => runLoop(this.loopCtx, this, { inbox: this.#inbox, setStatus: (status) => { this.setStatus(status) }, setAbort: controller => void (this.currentAbort = controller), @@ -338,7 +338,7 @@ export class ReactLoopAgent implements Agent { clearCancel: () => { this.cancelRequested = false }, // Pre-step cancellation re-parks without emitting a status transition. settleIdle: () => { this.settleIdleWaiters() }, - }) + })) } /** diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 6cd66f622c..51dc0f311f 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -11,6 +11,7 @@ import z from 'schemastery' import { createScope } from '@deepseek-ai/dsh-scope' import type { Scope } from '@deepseek-ai/dsh-scope' import { agentEvents } from '@deepseek-ai/dsh-agent' +import type {} from '@deepseek-ai/dsh-agent-execution' import type { AgentFactory, AgentHandle, @@ -333,7 +334,7 @@ export interface Config { /** Concrete ReactLoopAgent factory and driver service. */ export class AgentLoop extends Service implements AgentFactory { - static inject = ['agents', 'sessions', 'llm', 'tools', 'systemPrompt'] + static inject = ['agents', 'agentExecution', 'sessions', 'llm', 'tools', 'systemPrompt'] /** Runtime schema for declarative agents. */ static Config = z.object({ diff --git a/packages/core/agent-loop/tests/agent-execution.spec.ts b/packages/core/agent-loop/tests/agent-execution.spec.ts new file mode 100644 index 0000000000..98cebcbc97 --- /dev/null +++ b/packages/core/agent-loop/tests/agent-execution.spec.ts @@ -0,0 +1,374 @@ +import { describe, expect, it } from 'vitest' +import { Context, FiberState, type Fiber } from 'cordis' +import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' +import type { AgentExecutionService } from '@deepseek-ai/dsh-agent-execution' +import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import LlmService, { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' +import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' +import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' + +interface Harness { + ctx: Context + providerFiber: Fiber + loopFiber: Fiber +} + +async function harness(adapter: LlmAdapter): Promise { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + const providerFiber = await ctx.plugin(AgentExecutionProvider) + const loopFiber = await ctx.plugin(AgentLoop, { agents: [] }) + ctx.llm.registerAdapter(['mock'], adapter) + return { ctx, providerFiber, loopFiber } +} + +function waitForIdle(ctx: Context, agent: ReactLoopAgent | Agent): Promise { + return new Promise((resolve) => { + const dispose = ctx.on('agent/status', (subject, status) => { + if (subject === agent && status === 'idle') { + dispose() + resolve() + } + }) + }) +} + +function send(agent: Agent, text: string): void { + agent.send([{ type: 'text', text }]) +} + +/** Adapter that holds both drivers at the same awaited continuation. */ +class OverlapAdapter extends LlmAdapter { + private readonly bothStarted = Promise.withResolvers() + private starts = 0 + readonly observations: { sessionId: SessionId | undefined; before: Agent; after: Agent }[] = [] + + constructor(private readonly ctx: Context) { + super() + } + + async * stream(options: GenerateOptions): AsyncIterable { + const before = this.ctx.agentExecution.require().agent + this.starts += 1 + if (this.starts === 2) this.bothStarted.resolve(true) + await this.bothStarted.promise + await Promise.resolve() + const after = this.ctx.agentExecution.require().agent + this.observations.push({ sessionId: options.sessionId, before, after }) + yield* textResponse('done') + } +} + +/** Test-only transport that materializes ambient identity at its request boundary. */ +class TestCapabilityTransport { + readonly requests: { path: string; headers: Record }[] = [] + + constructor(private readonly execution: AgentExecutionService) {} + + async request(path: string): Promise> { + await Promise.resolve() + const headers = { + 'X-Harness-Session-Id': this.execution.require().agent.session.id, + } + this.requests.push({ path, headers }) + return headers + } +} + +/** Adapter whose first call waits for cancellation and whose later calls complete. */ +class ReloadAdapter extends LlmAdapter { + readonly firstStarted = Promise.withResolvers() + firstAgentDuringAbort: Agent | undefined + laterAgent: Agent | undefined + calls = 0 + execution: AgentExecutionService | undefined + + async * stream(options: GenerateOptions): AsyncIterable { + const execution = this.execution + if (execution === undefined) throw new Error('execution service missing') + this.calls += 1 + if (this.calls === 1) { + this.firstStarted.resolve(true) + try { + await new Promise((_resolve, reject) => { + const abort = (): void => { reject(new Error('aborted')) } + if (options.signal?.aborted === true) abort() + else options.signal?.addEventListener('abort', abort, { once: true }) + }) + } catch (error: unknown) { + await Promise.resolve() + this.firstAgentDuringAbort = execution.require().agent + throw error + } + return + } + await Promise.resolve() + this.laterAgent = execution.require().agent + yield* textResponse('reloaded') + } +} + +describe('AgentLoop execution context', () => { + it('keeps overlapping driver continuations bound to their exact Agents', async () => { + const ctx = new Context() + const adapter = new OverlapAdapter(ctx) + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) + await ctx.plugin(AgentLoop, { agents: [] }) + ctx.llm.registerAdapter(['mock'], adapter) + + const a = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const b = ctx.agentLoop.create(AgentId('b'), { model: 'mock' }) + const idleA = waitForIdle(ctx, a) + const idleB = waitForIdle(ctx, b) + send(a, 'a') + send(b, 'b') + await Promise.all([idleA, idleB]) + + expect(adapter.observations).toHaveLength(2) + expect(adapter.observations).toEqual(expect.arrayContaining([ + { sessionId: a.session.id, before: a, after: a }, + { sessionId: b.session.id, before: b, after: b }, + ])) + expect(ctx.agentExecution.current()).toBeUndefined() + await ctx.fiber.dispose() + }) + + it('keeps child setup under the parent boundary, switches for the child driver, then restores the parent', async () => { + const adapter = new MockAdapter([ + toolCallResponse('spawn', 'spawn-child', {}), + toolCallResponse('observe', 'observe-child', {}), + textResponse('child done'), + textResponse('parent done'), + ]) + const { ctx } = await harness(adapter) + let parentDuringSetup: Agent | undefined + let explicitChild: Agent | undefined + let childDuringDriver: Agent | undefined + let parentAfterChild: Agent | undefined + let child: Agent | undefined + + ctx.tools.register(defineTool({ + name: 'spawn-child', + description: 'create one child agent', + parameters: {}, + execute: async (_args, exec) => { + if (exec.agent === undefined) throw new Error('parent agent missing') + const handle = await exec.agent.ctx.agents.create({ + agentId: AgentId('child'), + sessionId: SessionId('child-session'), + agentOptions: { model: 'mock' }, + setup: (agentCtx) => { + parentDuringSetup = ctx.agentExecution.require().agent + explicitChild = agentCtx.agent + agentCtx.tools.register(defineTool({ + name: 'observe-child', + description: 'observe child execution identity', + parameters: {}, + execute: async () => { + await Promise.resolve() + childDuringDriver = ctx.agentExecution.require().agent + return [{ type: 'text', text: 'observed' }] + }, + })) + }, + }) + child = handle.agent + send(handle.agent, 'run child') + await handle.agent.whenIdle() + parentAfterChild = ctx.agentExecution.require().agent + await handle.dispose() + return [{ type: 'text', text: 'child completed' }] + }, + })) + + const parentHandle = await ctx.agents.create({ + agentId: AgentId('parent'), + sessionId: SessionId('parent-session'), + agentOptions: { model: 'mock' }, + }) + const idle = waitForIdle(ctx, parentHandle.agent) + send(parentHandle.agent, 'spawn') + await idle + + expect(parentDuringSetup).toBe(parentHandle.agent) + expect(explicitChild).toBe(child) + expect(childDuringDriver).toBe(child) + expect(parentAfterChild).toBe(parentHandle.agent) + expect(ctx.agentExecution.current()).toBeUndefined() + await parentHandle.dispose() + await ctx.fiber.dispose() + }) + + it('keeps agentless direct tools ambient-free and builds trusted transport headers internally', async () => { + const adapter = new MockAdapter([ + toolCallResponse('capability', 'capability-request', { path: '/v1/capability' }), + textResponse('done'), + ]) + const { ctx } = await harness(adapter) + const transport = new TestCapabilityTransport(ctx.agentExecution) + let directAmbient: Agent | undefined + let captured: Agent | undefined + + ctx.tools.register(defineTool({ + name: 'agentless-probe', + description: 'observe an agentless call', + parameters: {}, + execute: async () => { + await Promise.resolve() + directAmbient = ctx.agentExecution.current()?.agent + return [{ type: 'text', text: 'ok' }] + }, + })) + ctx.tools.register(defineTool({ + name: 'capability-request', + description: 'call the test capability transport', + parameters: { path: { type: 'string' } }, + execute: async (args) => { + captured = ctx.agentExecution.require().agent + const path = (args as { path: string }).path + const headers = await transport.request(path) + return [{ type: 'text', text: JSON.stringify(headers) }] + }, + })) + + const direct = await ctx.tools.execute({ + callId: CallId('direct'), + name: 'agentless-probe', + arguments: {}, + }) + expect(direct.isError).toBe(false) + expect(directAmbient).toBeUndefined() + + const handle = await ctx.agents.create({ + agentId: AgentId('transport'), + sessionId: SessionId('transport-session'), + agentOptions: { model: 'mock' }, + }) + const idle = waitForIdle(ctx, handle.agent) + send(handle.agent, 'call transport') + await idle + + expect(transport.requests).toEqual([{ + path: '/v1/capability', + headers: { 'X-Harness-Session-Id': 'transport-session' }, + }]) + const schema = adapter.requests[0]?.tools?.find(tool => tool.name === 'capability-request') + expect(JSON.stringify(schema?.parameters)).not.toMatch(/session|harness/i) + const call = handle.agent.session.events.find(event => event.type === 'tool/call') + expect(call?.type === 'tool/call' ? call.data.arguments : undefined) + .toBe(JSON.stringify({ path: '/v1/capability' })) + expect(captured).toBe(handle.agent) + + await handle.dispose() + expect(captured?.status).toBe('disposed') + expect(ctx.agentExecution.current()).toBeUndefined() + await ctx.fiber.dispose() + }) + + it('keeps AgentLoop inactive until the mandatory provider appears', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + const loopFiber = ctx.plugin(AgentLoop, { agents: [] }) + await Promise.resolve() + expect(loopFiber.state).toBe(FiberState.PENDING) + + await ctx.plugin(AgentExecutionProvider) + await loopFiber + expect(loopFiber.state).toBe(FiberState.ACTIVE) + await ctx.fiber.dispose() + }) + + it('drains the old driver before disabling ALS during provider restart', async () => { + const ctx = new Context() + const adapter = new ReloadAdapter() + const { providerFiber, loopFiber } = await (async (): Promise => { + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + const mountedProvider = await ctx.plugin(AgentExecutionProvider) + const mountedLoop = await ctx.plugin(AgentLoop, { agents: [] }) + ctx.llm.registerAdapter(['mock'], adapter) + return { ctx, providerFiber: mountedProvider, loopFiber: mountedLoop } + })() + const oldService = ctx.agentExecution + adapter.execution = oldService + const oldHandle = await ctx.agents.create({ + agentId: AgentId('before-restart'), + sessionId: SessionId('before-restart-session'), + agentOptions: { model: 'mock' }, + }) + const oldAgent = oldHandle.agent + send(oldAgent, 'block') + await adapter.firstStarted.promise + + await providerFiber.restart() + await loopFiber.await() + expect(adapter.firstAgentDuringAbort?.id).toBe(oldAgent.id) + expect(adapter.firstAgentDuringAbort?.session).toBe(oldAgent.session) + expect(oldAgent.status).toBe('disposed') + expect(() => oldService.current()).toThrow('agent execution service is disposed') + expect(ctx.agentExecution).not.toBe(oldService) + adapter.execution = ctx.agentExecution + + const newHandle = await ctx.agents.create({ + agentId: AgentId('after-restart'), + sessionId: SessionId('after-restart-session'), + agentOptions: { model: 'mock' }, + }) + const newAgent = newHandle.agent + const idle = waitForIdle(ctx, newAgent) + send(newAgent, 'continue') + await idle + expect(adapter.laterAgent?.id).toBe(newAgent.id) + expect(adapter.laterAgent?.session).toBe(newAgent.session) + await ctx.fiber.dispose() + }) + + it('keeps ALS readable while root disposal drains sibling AgentLoop fibers', async () => { + const ctx = new Context() + const adapter = new ReloadAdapter() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) + await ctx.plugin(AgentLoop, { agents: [] }) + ctx.llm.registerAdapter(['mock'], adapter) + const service = ctx.agentExecution + adapter.execution = service + const handle = await ctx.agents.create({ + agentId: AgentId('root-dispose'), + sessionId: SessionId('root-dispose-session'), + agentOptions: { model: 'mock' }, + }) + const agent = handle.agent + send(agent, 'block') + await adapter.firstStarted.promise + + await ctx.fiber.dispose() + expect(adapter.firstAgentDuringAbort?.id).toBe(agent.id) + expect(adapter.firstAgentDuringAbort?.session).toBe(agent.session) + expect(agent.status).toBe('disposed') + expect(() => service.current()).toThrow('agent execution service is disposed') + }) +}) diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 581b6fa207..bcc31a6172 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -6,6 +6,7 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { bindReactLoopAgentContext, prepareReactLoopAgent } from '../src/agent.ts' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -17,6 +18,7 @@ async function harness(adapter: MockAdapter) { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx @@ -51,6 +53,7 @@ function send(agent: ReactLoopAgent, text: string) { describe('ReactLoopAgent', () => { it('rejects access before context binding and a second driver for one session', async () => { const ctx = new Context() + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('exclusive-driver')) const prepared = prepareReactLoopAgent(ctx, AgentId('first-driver'), { model: 'mock' }, session) @@ -252,6 +255,7 @@ describe('ReactLoopAgent', () => { it('disposer is idempotent (double-stop)', async () => { // The internal start seam exposes one idle driver's disposer for repeated invocation. const ctx = new Context() + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('test')) const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) @@ -361,6 +365,7 @@ describe('ReactLoopAgent', () => { // Queue the internal waiter while running, then dispose the bare driver. Its disposed branch // must chain the loop's `done` promise rather than resolve before exit. const ctx = new Context() + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(LlmService) await ctx.plugin(SessionStore) await ctx.plugin(SystemPrompt) diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index cad830e827..7568ba0765 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -14,6 +14,7 @@ import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -24,6 +25,7 @@ async function harness(adapter: MockAdapter) { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx @@ -194,6 +196,7 @@ describe('Agent.cancel()', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) @@ -319,6 +322,7 @@ describe('Agent.cancel()', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 8a5d9ce264..182a76a7e9 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -9,6 +9,7 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -31,6 +32,7 @@ describe('config-driven session id', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) const loopFiber = await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('deferred') }], }) @@ -53,6 +55,7 @@ describe('config-driven session id', () => { await ctx1.plugin(SystemPrompt) await ctx1.plugin(ToolRegistry) await ctx1.plugin(AgentRegistry) + await ctx1.plugin(AgentExecutionProvider) await ctx1.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg')])) @@ -70,6 +73,7 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) + await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg2')])) @@ -93,6 +97,7 @@ describe('config-driven session id', () => { await ctx1.plugin(SystemPrompt) await ctx1.plugin(ToolRegistry) await ctx1.plugin(AgentRegistry) + await ctx1.plugin(AgentExecutionProvider) await ctx1.plugin(AgentLoop, { agents: [] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first')])) @@ -109,6 +114,7 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) + await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')])) @@ -137,6 +143,7 @@ describe('config-driven session id', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) const warn = vi.spyOn((ctx.agentLoop as unknown as { ctx: { logger: { warn: (...a: unknown[]) => void } } }).ctx.logger, 'warn') .mockImplementation(() => undefined) diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index ee50261e9d..70528a7b0b 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -5,6 +5,7 @@ import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId, type ContinuationDecision } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { prepareReactLoopAgent } from '../src/agent.ts' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -19,6 +20,7 @@ async function harness(adapter: MockAdapter) { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx @@ -524,6 +526,7 @@ describe('turn numbering continues across seeded sessions', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) + await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [] }) ctx2.llm.registerAdapter(['mock'], second) @@ -664,6 +667,7 @@ describe('turn and step boundary recovery', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(Invariants) ctx.llm.registerAdapter(['mock'], adapter) @@ -1114,6 +1118,7 @@ describe('disposal and cancellation during pre-step assembly', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(Invariants) ctx.llm.registerAdapter(['mock'], adapter) @@ -1165,6 +1170,7 @@ describe('disposal and cancellation during pre-step assembly', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(Invariants) ctx.llm.registerAdapter(['mock'], adapter) @@ -1220,6 +1226,7 @@ describe('disposal and cancellation during pre-step assembly', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(Invariants) ctx.llm.registerAdapter(['mock'], adapter) @@ -1271,6 +1278,7 @@ describe('disposal and cancellation during pre-step assembly', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(Invariants) ctx.llm.registerAdapter(['mock'], adapter) @@ -1320,6 +1328,7 @@ describe('disposal and cancellation during pre-step assembly', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(Invariants) ctx.llm.registerAdapter(['mock'], adapter) diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index 5deee8e159..8c0884d0fa 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -6,6 +6,7 @@ import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -16,6 +17,7 @@ async function harness(adapter: MockAdapter) { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index 4b37210993..0c8f52c6c4 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -10,6 +10,7 @@ import AgentRegistry, { type PromptDecision, type SessionStartSource, } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -29,6 +30,7 @@ async function harness(adapter: MockAdapter) { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index fb686928b1..79f9755220 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -5,6 +5,7 @@ import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -15,6 +16,7 @@ async function harness(adapter: MockAdapter, persona = '') { await ctx.plugin(SystemPrompt, { persona }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx @@ -924,6 +926,7 @@ describe('agent loop', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('config-agent'), model: 'mock' }], }) @@ -947,6 +950,7 @@ describe('agent loop', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('config-agent'), model: 'mock', cwd: '/work/project' }], }) diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index dbc43ad985..d100000d14 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -13,6 +13,7 @@ import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import fc from 'fast-check' @@ -36,6 +37,7 @@ async function harness() { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], new EchoAdapter()) return ctx diff --git a/packages/core/agent-loop/tests/request-cache.e2e.ts b/packages/core/agent-loop/tests/request-cache.e2e.ts index 9b8513d16f..3b454236f1 100644 --- a/packages/core/agent-loop/tests/request-cache.e2e.ts +++ b/packages/core/agent-loop/tests/request-cache.e2e.ts @@ -5,6 +5,7 @@ import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -42,6 +43,7 @@ async function loopHarness(): Promise { await created.plugin(SystemPrompt, { persona: SYSTEM }) await created.plugin(ToolRegistry) await created.plugin(AgentRegistry) + await created.plugin(AgentExecutionProvider) await created.plugin(AgentLoop, { agents: [] }) await created.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) created.tools.register(defineTool({ diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index c4fe471bd0..58c1017e81 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -14,6 +14,7 @@ import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-a import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -24,6 +25,7 @@ async function harness(adapter: MockAdapter, persona = 'stable base') { await ctx.plugin(SystemPrompt, { persona }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx diff --git a/packages/core/agent-loop/tests/resume.spec.ts b/packages/core/agent-loop/tests/resume.spec.ts index 3747824231..4b90453909 100644 --- a/packages/core/agent-loop/tests/resume.spec.ts +++ b/packages/core/agent-loop/tests/resume.spec.ts @@ -10,6 +10,7 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -29,6 +30,7 @@ async function mountPersistentHarness(root: string, adapter: MockAdapter): Promi await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SessionPersistenceJsonl, { root }) ctx.llm.registerAdapter(['mock'], adapter) @@ -138,6 +140,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) + await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) @@ -166,6 +169,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) + await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) @@ -388,6 +392,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) const loopFiber = await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SessionPersistenceJsonl, { root }) ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('next')])) @@ -449,6 +454,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) + await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) @@ -502,6 +508,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) + await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) @@ -531,6 +538,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) + await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) @@ -561,6 +569,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) await expect(ctx.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('nope') })) diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index 40272ac42b..53e91defff 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -7,6 +7,7 @@ import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId, agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { scopeOf } from '@deepseek-ai/dsh-scope' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -18,6 +19,7 @@ async function harnessWithLoop(adapter: MockAdapter = new MockAdapter([textRespo await ctx.plugin(SystemPrompt, { persona: 'You are the deployment.' }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) const loopFiber = await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return { ctx, loopFiber } diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index 13e731b7b8..813f7892d9 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -14,6 +14,7 @@ import SystemPrompt, { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -24,6 +25,7 @@ async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['too await ctx.plugin(SystemPrompt, { persona: 'stable base', ...toolOrder !== undefined ? { toolOrder } : {} }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx diff --git a/packages/core/agent-loop/tests/turn-stop.spec.ts b/packages/core/agent-loop/tests/turn-stop.spec.ts index c275fee88c..944c6fd265 100644 --- a/packages/core/agent-loop/tests/turn-stop.spec.ts +++ b/packages/core/agent-loop/tests/turn-stop.spec.ts @@ -5,6 +5,7 @@ import SessionStore, { type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId, type ContinuationStop } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -17,6 +18,7 @@ async function harness(adapter: MockAdapter): Promise { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(Invariants) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx diff --git a/packages/core/agent-loop/tsconfig.json b/packages/core/agent-loop/tsconfig.json index 5d7cf98bb7..1e17efa41f 100644 --- a/packages/core/agent-loop/tsconfig.json +++ b/packages/core/agent-loop/tsconfig.json @@ -35,6 +35,9 @@ { "path": "../../core/agent" }, + { + "path": "../../core/agent-execution" + }, { "path": "../../core/scope" } diff --git a/packages/core/agent/tests/gen-cordis-catalog.spec.ts b/packages/core/agent/tests/gen-cordis-catalog.spec.ts index 856ef899f7..53847b0e97 100644 --- a/packages/core/agent/tests/gen-cordis-catalog.spec.ts +++ b/packages/core/agent/tests/gen-cordis-catalog.spec.ts @@ -160,6 +160,26 @@ export class FixService { expect(services[0]?.methods).toHaveLength(3) }) + it('extracts an interface service as an abstract seam', () => { + const services = collectServices(makeService(`/** Fixture service interface. */ +export interface FixService { + /** + * Do the thing. + * @param id - which thing to do. + * @returns the outcome of doing it. + */ + run(id: string): string +}`)) + expect(services).toHaveLength(1) + expect(services[0]).toMatchObject({ + key: 'fix', + type: 'FixService', + abstract: true, + doc: 'Fixture service interface.', + }) + expect(services[0]?.methods).toEqual(['run(id: string): string']) + }) + it('hard-errors on a public method with no JSDoc at all', () => { expect(() => collectServices(makeService( '/** Fixture service. */\nexport class FixService {\n run(id: string): string { return id }\n}', diff --git a/packages/examples/README.md b/packages/examples/README.md index 5ee0206d0f..71867e0da6 100644 --- a/packages/examples/README.md +++ b/packages/examples/README.md @@ -4,7 +4,7 @@ Pre-composed plugin bundles a thin leaf `cordis.yml` loads instead of assembling | Package | npm name | Role | |---|---|---| -| `agent-spine-demo/` | `@deepseek-ai/dsh-agent-spine-demo` | The executor-less/UI-less agent spine as one bundle plugin (`timer` + `llm` + sessions + system-prompt + tools + skills + agents + invariants + `tool-bash` + `tool-skill` + `agent-loop`) | +| `agent-spine-demo/` | `@deepseek-ai/dsh-agent-spine-demo` | The executor-less/UI-less agent spine as one bundle plugin (`timer` + `llm` + sessions + system-prompt + tools + skills + agents + agent-execution + invariants + `tool-bash` + `tool-skill` + `agent-loop`) | | `stdio-demo/` | `@deepseek-ai/dsh-stdio-demo` | Terminal stdio chat app: the spine + console logger + readline UI + a pre-created `main` agent, with a boot `bin` | | `acp-demo/` | `@deepseek-ai/dsh-acp-demo` | ACP server app: the spine + JSONL persistence + the [`acp`](../ui/acp/README.md) bridge (no stdout logger), with a boot `bin` | | `jsonrpc-demo/` | `@deepseek-ai/dsh-jsonrpc-demo` | Bin-only runtime that boots an external `cordis.yml` for the stdio JSON-RPC SDK client | diff --git a/packages/examples/agent-spine-demo/README.md b/packages/examples/agent-spine-demo/README.md index eb56f9515c..442b8e1366 100644 --- a/packages/examples/agent-spine-demo/README.md +++ b/packages/examples/agent-spine-demo/README.md @@ -17,6 +17,7 @@ Read this package for the whole plugin tree and its composition order. @deepseek-ai/dsh-skill skill provider registry @deepseek-ai/dsh-skill-local local filesystem skill provider @deepseek-ai/dsh-agent agent registry + agent/* event vocabulary +@deepseek-ai/dsh-agent-execution process-local ambient Agent execution context @deepseek-ai/dsh-tasks generic background-task registry @deepseek-ai/dsh-invariants dev-mode event-contract assertions @deepseek-ai/dsh-tool-bash the model-facing bash schema diff --git a/packages/examples/agent-spine-demo/package.json b/packages/examples/agent-spine-demo/package.json index d328043507..84e4259741 100644 --- a/packages/examples/agent-spine-demo/package.json +++ b/packages/examples/agent-spine-demo/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-agent-spine-demo", - "description": "The default executor-less/UI-less agent spine as one Cordis bundle plugin (timer + llm + sessions + system-prompt + tools + skills + agents + tasks + invariants + tool-bash + tool-skill + tool-tasks + agent-loop)", + "description": "The default executor-less/UI-less agent spine as one Cordis bundle plugin (timer + llm + sessions + system-prompt + tools + skills + agents + agent-execution + tasks + invariants + tool-bash + tool-skill + tool-tasks + agent-loop)", "version": "0.0.1", "private": true, "type": "module", @@ -24,6 +24,7 @@ "peerDependencies": { "@cordisjs/plugin-timer": "^1.1.2", "@deepseek-ai/dsh-agent": "^0.0.1", + "@deepseek-ai/dsh-agent-execution": "^0.0.1", "@deepseek-ai/dsh-agent-loop": "^0.0.1", "@deepseek-ai/dsh-invariants": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", @@ -41,6 +42,7 @@ "devDependencies": { "@cordisjs/plugin-timer": "workspace:^", "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", diff --git a/packages/examples/agent-spine-demo/src/index.ts b/packages/examples/agent-spine-demo/src/index.ts index b3d6ca22bc..439897b347 100644 --- a/packages/examples/agent-spine-demo/src/index.ts +++ b/packages/examples/agent-spine-demo/src/index.ts @@ -18,6 +18,7 @@ import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools import SkillService, { type Config as SkillRegistryConfig } from '@deepseek-ai/dsh-skill' import * as SkillLocal from '@deepseek-ai/dsh-skill-local' import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import TaskService from '@deepseek-ai/dsh-tasks' import * as invariants from '@deepseek-ai/dsh-invariants' import * as toolBash from '@deepseek-ai/dsh-tool-bash' @@ -116,6 +117,7 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(SkillService, config.skills?.registry ?? {}) ctx.plugin(SkillLocal, config.skills?.local ?? {}) ctx.plugin(AgentRegistry) + ctx.plugin(AgentExecutionProvider) ctx.plugin(TaskService) ctx.plugin(invariants) ctx.plugin(toolBash, config.toolBash ?? {}) diff --git a/packages/examples/agent-spine-demo/tsconfig.json b/packages/examples/agent-spine-demo/tsconfig.json index faea4b949f..09cad875f1 100644 --- a/packages/examples/agent-spine-demo/tsconfig.json +++ b/packages/examples/agent-spine-demo/tsconfig.json @@ -41,6 +41,9 @@ { "path": "../../core/agent" }, + { + "path": "../../core/agent-execution" + }, { "path": "../../core/agent-loop" }, diff --git a/packages/fs/tool-fs/package.json b/packages/fs/tool-fs/package.json index c21c806e98..98439e8163 100644 --- a/packages/fs/tool-fs/package.json +++ b/packages/fs/tool-fs/package.json @@ -35,6 +35,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-fs-policy": "workspace:^", "@deepseek-ai/dsh-fs": "workspace:^", diff --git a/packages/fs/tool-fs/tests/harness.ts b/packages/fs/tool-fs/tests/harness.ts index 0487962922..4dc4bb8437 100644 --- a/packages/fs/tool-fs/tests/harness.ts +++ b/packages/fs/tool-fs/tests/harness.ts @@ -4,6 +4,7 @@ import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import LocalFileSystem from '@deepseek-ai/dsh-fs-local' import * as FsPolicy from '@deepseek-ai/dsh-fs-policy' @@ -22,6 +23,7 @@ export async function fsHarness(fsCwd: string, persona = ''): Promise { await ctx.plugin(SystemPrompt, { persona }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) await ctx.plugin(LocalFileSystem, { cwd: fsCwd }) diff --git a/packages/guard/repeat-tool-guard/package.json b/packages/guard/repeat-tool-guard/package.json index 0cc99b6976..8df2eac25f 100644 --- a/packages/guard/repeat-tool-guard/package.json +++ b/packages/guard/repeat-tool-guard/package.json @@ -31,6 +31,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", diff --git a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts index 565f1076b5..355c5ed2a8 100644 --- a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts +++ b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts @@ -5,6 +5,7 @@ import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as RepeatToolGuard from '@deepseek-ai/dsh-repeat-tool-guard' import type { Config } from '@deepseek-ai/dsh-repeat-tool-guard' @@ -26,6 +27,7 @@ async function harness(config: Config = {}): Promise { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(RepeatToolGuard, config) ctx.tools.register(defineTool({ name: 'probe', description: 'p', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) @@ -368,6 +370,7 @@ describe('config validation fails loud', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) return ctx } diff --git a/packages/hooks/hooks-claude/package.json b/packages/hooks/hooks-claude/package.json index 21f08965d8..03858f1aaf 100644 --- a/packages/hooks/hooks-claude/package.json +++ b/packages/hooks/hooks-claude/package.json @@ -35,6 +35,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-bash": "workspace:^", "@deepseek-ai/dsh-bash-local": "workspace:^", diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 506d613c73..c298a8d3f3 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -9,6 +9,7 @@ import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' @@ -47,6 +48,7 @@ async function harnessWithFiber(configDir: string, adapter: MockAdapter): Promis await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) const hooks = await ctx.plugin(HooksClaude, { configPath: join(configDir, 'hooks.json') }) @@ -342,6 +344,7 @@ describe('hooks-claude bridge — load resilience', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksClaude, { configPath: '/nonexistent/hooks.json' }) @@ -364,6 +367,7 @@ describe('hooks-claude bridge — load resilience', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) const fiber = await ctx.plugin(HooksClaude, { configPath: join(dir, 'hooks.json') }) diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index f376708688..db61f4846f 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -8,6 +8,7 @@ import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' @@ -35,6 +36,7 @@ async function harness(configPath: string, adapter: MockAdapter, opts: HarnessOp await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksClaude, { configPath, ...opts }) @@ -334,6 +336,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) // Direct apply with only configPath — bypasses schemastery's defaults, so @@ -599,6 +602,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) // Executor default cwd = serverDir (deliberately NOT the session cwd). await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir }) @@ -632,6 +636,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) // Executor default cwd = serverDir (deliberately NOT the child session cwd). await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir }) diff --git a/packages/hooks/hooks-codex/package.json b/packages/hooks/hooks-codex/package.json index fe667b0302..1928b763ea 100644 --- a/packages/hooks/hooks-codex/package.json +++ b/packages/hooks/hooks-codex/package.json @@ -34,6 +34,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-bash": "workspace:^", "@deepseek-ai/dsh-bash-local": "workspace:^", diff --git a/packages/hooks/hooks-codex/tests/bridge.spec.ts b/packages/hooks/hooks-codex/tests/bridge.spec.ts index d4a5797b96..fcf0617bff 100644 --- a/packages/hooks/hooks-codex/tests/bridge.spec.ts +++ b/packages/hooks/hooks-codex/tests/bridge.spec.ts @@ -9,6 +9,7 @@ import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' @@ -45,6 +46,7 @@ async function harness(dir: string, adapter: MockAdapter): Promise { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'test-model' }) @@ -146,6 +148,7 @@ describe('hooks-codex bridge', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) const fiber = await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'm' }) @@ -172,6 +175,7 @@ describe('hooks-codex bridge', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) const fiber = await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'm' }) diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index c287d86b23..1dec4a4886 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -8,6 +8,7 @@ import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' @@ -26,6 +27,7 @@ function hooks(d: string, h: unknown): string { async function harness(configPath: string, adapter: MockAdapter, opts: { stderrSummaryMaxChars?: number } = {}): Promise { const ctx = new Context() await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksCodex, { configPath, model: 'm', ...opts }) @@ -239,6 +241,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = new Context() await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) ctx.logger.warn = warn as never @@ -544,6 +547,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = new Context() await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir }) await ctx.plugin(HooksCodex, { configPath: join(serverDir, 'hooks.json'), model: 'm' }) diff --git a/packages/sdk/helper/src/features/builtin/spine.ts b/packages/sdk/helper/src/features/builtin/spine.ts index caf066865e..d2fb877ec4 100644 --- a/packages/sdk/helper/src/features/builtin/spine.ts +++ b/packages/sdk/helper/src/features/builtin/spine.ts @@ -36,6 +36,10 @@ class SpineOption extends FeatureOption { }, ['persona'], config => requiredString(config, 'persona')), ...npmCordisConfigEntry(ID, { id: 'tools', name: '@deepseek-ai/dsh-tools' }, []), ...npmCordisConfigEntry(ID, { id: 'agent', name: '@deepseek-ai/dsh-agent' }), + ...npmCordisConfigEntry(ID, { + id: 'agent-execution', + name: '@deepseek-ai/dsh-agent-execution', + }), ...npmCordisConfigEntry(ID, { id: 'invariants', name: '@deepseek-ai/dsh-invariants' }), ...npmCordisConfigEntry(ID, { id: 'agent-loop', diff --git a/packages/subagent/subagent-fork/package.json b/packages/subagent/subagent-fork/package.json index 8794884518..3cfecd435c 100644 --- a/packages/subagent/subagent-fork/package.json +++ b/packages/subagent/subagent-fork/package.json @@ -33,6 +33,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", diff --git a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts index 8060a77fd4..b4066ff932 100644 --- a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts +++ b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts @@ -5,6 +5,7 @@ import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' @@ -32,6 +33,7 @@ async function setup(script: Script) { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(Invariants) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) await ctx.plugin(Spawn, { providerName: 'spawn' }) diff --git a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts index b5e129e54f..7871f5d13d 100644 --- a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts +++ b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts @@ -6,6 +6,7 @@ import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' @@ -39,6 +40,7 @@ async function setup(script: Script) { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(Invariants) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) await ctx.plugin(fork, { providerName: 'fork' }) diff --git a/packages/subagent/subagent-inprocess/package.json b/packages/subagent/subagent-inprocess/package.json index aa80dcac3e..6676a3992c 100644 --- a/packages/subagent/subagent-inprocess/package.json +++ b/packages/subagent/subagent-inprocess/package.json @@ -32,6 +32,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", diff --git a/packages/subagent/subagent-inprocess/tests/structured.spec.ts b/packages/subagent/subagent-inprocess/tests/structured.spec.ts index a2c55995c2..e8d19fe4c5 100644 --- a/packages/subagent/subagent-inprocess/tests/structured.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/structured.spec.ts @@ -6,6 +6,7 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' import type { ContinuationDecision } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' @@ -56,6 +57,7 @@ async function setup(script: Script, options: SetupOptions = {}) { } await ctx.plugin(AgentRegistry) await ctx.plugin(Invariants) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) const disposeProvider = ctx.subagents.registerProvider({ diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index 0005246523..cecad34bfc 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -5,6 +5,7 @@ import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -21,6 +22,7 @@ async function setup(script: Script) { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(Invariants) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) diff --git a/packages/subagent/subagent-spawn/package.json b/packages/subagent/subagent-spawn/package.json index f2500a4a56..c4629e72c2 100644 --- a/packages/subagent/subagent-spawn/package.json +++ b/packages/subagent/subagent-spawn/package.json @@ -31,6 +31,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-bash-local": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", diff --git a/packages/subagent/subagent-spawn/tests/harness.ts b/packages/subagent/subagent-spawn/tests/harness.ts index e4ee2e6ab7..4d47900663 100644 --- a/packages/subagent/subagent-spawn/tests/harness.ts +++ b/packages/subagent/subagent-spawn/tests/harness.ts @@ -4,6 +4,7 @@ import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' @@ -30,6 +31,7 @@ export async function spawnHarness(workdir: string): Promise { await ctx.plugin(SystemPrompt, { persona: 'You are a coding agent. Report only when the requested work is done.' }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 }) diff --git a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts index 43ec8ee1ac..df93357dbc 100644 --- a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts +++ b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts @@ -7,6 +7,7 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' @@ -32,6 +33,7 @@ async function setup(script: Script) { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(Invariants) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) await ctx.plugin(spawn, { providerName: 'spawn' }) @@ -309,6 +311,7 @@ describe('dsh-subagent-spawn', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(Invariants) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) @@ -341,6 +344,7 @@ describe('dsh-subagent-spawn', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) diff --git a/packages/todo/tool-todo/package.json b/packages/todo/tool-todo/package.json index 9ff69d7c76..dd1fbdbcc6 100644 --- a/packages/todo/tool-todo/package.json +++ b/packages/todo/tool-todo/package.json @@ -29,6 +29,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", diff --git a/packages/todo/tool-todo/tests/integration.spec.ts b/packages/todo/tool-todo/tests/integration.spec.ts index 739367a699..52ebc57683 100644 --- a/packages/todo/tool-todo/tests/integration.spec.ts +++ b/packages/todo/tool-todo/tests/integration.spec.ts @@ -6,6 +6,7 @@ import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -23,6 +24,7 @@ async function harness(adapter: MockAdapter): Promise { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(ToolTodo) ctx.llm.registerAdapter(['mock'], adapter) diff --git a/packages/ui/acp/package.json b/packages/ui/acp/package.json index 71efc51a07..173c68a66c 100644 --- a/packages/ui/acp/package.json +++ b/packages/ui/acp/package.json @@ -41,6 +41,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-bash": "workspace:^", "@deepseek-ai/dsh-bash-local": "workspace:^", diff --git a/packages/ui/acp/tests/harness.ts b/packages/ui/acp/tests/harness.ts index 440120943f..be019b1e92 100644 --- a/packages/ui/acp/tests/harness.ts +++ b/packages/ui/acp/tests/harness.ts @@ -11,6 +11,7 @@ import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' @@ -193,6 +194,7 @@ export async function makeBridgeHarness(options: { await ctx.plugin(SystemPrompt, { persona: options.persona ?? '' }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SessionPersistenceJsonl, { root: options.storageDir }) await ctx.plugin(UserInteractionService) diff --git a/packages/workflow/workflow-workerthread/package.json b/packages/workflow/workflow-workerthread/package.json index 485e252c97..4c07c8f118 100644 --- a/packages/workflow/workflow-workerthread/package.json +++ b/packages/workflow/workflow-workerthread/package.json @@ -41,6 +41,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-brand": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", diff --git a/packages/workflow/workflow-workerthread/tests/integration.spec.ts b/packages/workflow/workflow-workerthread/tests/integration.spec.ts index 0e1727f877..5897342535 100644 --- a/packages/workflow/workflow-workerthread/tests/integration.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/integration.spec.ts @@ -5,6 +5,7 @@ import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -32,6 +33,7 @@ async function setup(script: Script) { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(Invariants) + await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) await ctx.plugin(spawn, { providerName: 'spawn' }) diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts index 1d6f61432a..f502798194 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts @@ -5,6 +5,7 @@ import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -34,6 +35,7 @@ async function harness(): Promise { await built.plugin(SystemPrompt) await built.plugin(ToolRegistry) await built.plugin(AgentRegistry) + await built.plugin(AgentExecutionProvider) await built.plugin(AgentLoop, { agents: [] }) await built.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) await built.plugin(SubagentService) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index b1a3a78030..37b9a70edc 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -152,6 +152,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -225,6 +228,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -259,6 +265,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -293,6 +302,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -336,6 +348,15 @@ importers: specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) + packages/core/agent-execution: + devDependencies: + '@deepseek-ai/dsh-agent': + specifier: workspace:^ + version: link:../agent + cordis: + specifier: ^4.0.0-rc.7 + version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) + packages/core/agent-loop: dependencies: schemastery: @@ -345,6 +366,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../agent-execution '@deepseek-ai/dsh-invariants': specifier: workspace:^ version: link:../../support/invariants @@ -492,6 +516,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -645,6 +672,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -685,6 +715,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -725,6 +758,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -765,6 +801,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -819,7 +858,7 @@ importers: dependencies: '@earendil-works/pi-ai': specifier: ^0.79.1 - version: 0.79.3(ws@8.21.0)(zod@4.4.3) + version: 0.79.3(@modelcontextprotocol/sdk@1.29.0(zod@4.4.3))(ws@8.21.0)(zod@4.4.3) schemastery: specifier: ^3.18.0 version: 3.18.0 @@ -1149,6 +1188,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -1185,6 +1227,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -1222,6 +1267,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -1461,6 +1509,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -1495,6 +1546,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -1891,6 +1945,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -1945,6 +2002,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../packages/core/agent + '@deepseek-ai/dsh-agent-execution': + specifier: workspace:^ + version: link:../../packages/core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../packages/core/agent-loop @@ -3059,6 +3119,10 @@ packages: cpu: [x64] os: [win32] + '@pkgjs/parseargs@0.11.0': + resolution: {integrity: sha512-+1VkjdD0QBLPodGrJUeqarH8VAIvQODIbwh9XpP5Syisf7YoQgsJKPNFoqqLQlu+VQ/tVSshMR6loPMn8U+dPg==} + engines: {node: '>=14'} + '@protobufjs/aspromise@1.1.2': resolution: {integrity: sha512-j+gKExEuLmKwvz3OgROXtrJ2UG2x8Ch2YZUxahh+s1F2HZ+wAceUNLkvy6zKCPVRkU++ZWQrdxsUeQXmcg4uoQ==} @@ -6137,11 +6201,11 @@ snapshots: '@csstools/css-tokenizer@4.0.0': {} - '@earendil-works/pi-ai@0.79.3(ws@8.21.0)(zod@4.4.3)': + '@earendil-works/pi-ai@0.79.3(@modelcontextprotocol/sdk@1.29.0(zod@4.4.3))(ws@8.21.0)(zod@4.4.3)': dependencies: '@anthropic-ai/sdk': 0.91.1(zod@4.4.3) '@aws-sdk/client-bedrock-runtime': 3.1048.0 - '@google/genai': 1.52.0 + '@google/genai': 1.52.0(@modelcontextprotocol/sdk@1.29.0(zod@4.4.3)) '@mistralai/mistralai': 2.2.1 '@smithy/node-http-handler': 4.7.3 http-proxy-agent: 7.0.2 @@ -6299,12 +6363,14 @@ snapshots: '@exodus/bytes@1.15.1': {} - '@google/genai@1.52.0': + '@google/genai@1.52.0(@modelcontextprotocol/sdk@1.29.0(zod@4.4.3))': dependencies: google-auth-library: 10.7.0 p-retry: 4.6.2 protobufjs: 7.6.4 ws: 8.21.0 + optionalDependencies: + '@modelcontextprotocol/sdk': 1.29.0(zod@4.4.3) transitivePeerDependencies: - bufferutil - supports-color @@ -6563,6 +6629,9 @@ snapshots: '@oxc-resolver/binding-win32-x64-msvc@11.20.0': optional: true + '@pkgjs/parseargs@0.11.0': + optional: true + '@protobufjs/aspromise@1.1.2': {} '@protobufjs/base64@1.1.2': {} @@ -8034,6 +8103,8 @@ snapshots: jackspeak@3.4.3: dependencies: '@isaacs/cliui': 8.0.2 + optionalDependencies: + '@pkgjs/parseargs': 0.11.0 jiti@2.7.0: {} diff --git a/python/sdk-runtime/package.json b/python/sdk-runtime/package.json index 7fba79083a..ab651d0dfd 100644 --- a/python/sdk-runtime/package.json +++ b/python/sdk-runtime/package.json @@ -10,6 +10,7 @@ "@cordisjs/plugin-timer": "workspace:^", "@deepseek-ai/dsh-acp": "workspace:^", "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-spine-demo": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-app-boot": "workspace:^", diff --git a/scripts/gen-cordis-catalog.ts b/scripts/gen-cordis-catalog.ts index be265b1014..fcee663b13 100644 --- a/scripts/gen-cordis-catalog.ts +++ b/scripts/gen-cordis-catalog.ts @@ -26,6 +26,8 @@ const FENCE = 'ts cordis-catalog' // TODO(catalog-type-links): verify or generate link-map coverage. export const LINK_MAP: Record = { Agent: 'core.md', + AgentExecution: 'core.md', + AgentExecutionService: 'core.md', ContentBlock: 'core.md', Message: 'core.md', MessageSource: 'core.md', @@ -84,13 +86,13 @@ interface ServiceEntry { key: string /** The service class/interface name, e.g. `LlmService`. */ type: string - /** Whether the service class is abstract (a seam interface). */ + /** Whether the service declaration is abstract (a seam interface). */ abstract: boolean - /** Class-level JSDoc prose, one line per paragraph. */ + /** Declaration-level JSDoc prose, one line per paragraph. */ doc: string /** Public method signatures (bodies stripped), in source order. */ methods: string[] - /** Source pointer of the class declaration. */ + /** Source pointer of the service declaration. */ source: string } @@ -172,8 +174,8 @@ export function collectEvents(scanRoot: string = root): EventEntry[] { return entries } -/** Walk every harness `interface Context` block + its service class, hard- - * erroring (aggregated) on any JSDoc-completeness violation: a class or public +/** Walk every harness `interface Context` block + its service declaration, + * hard-erroring (aggregated) on any JSDoc-completeness violation: a service or public * method without JSDoc prose, an undocumented parameter, a stale `@param`, a * missing `@returns` on a non-void method, or an inferred (unannotated) return * type the pure-AST walk cannot classify. @@ -199,18 +201,23 @@ export function collectServices(scanRoot: string = root): ServiceEntry[] { } } if (keyToType.size === 0) continue - // Find each service class declared in the same file and emit an entry. + // Find each service declaration in the same file and emit an entry. for (const [key, type] of keyToType) { - const cls = sf.statements.find( - (s): s is ts.ClassDeclaration => ts.isClassDeclaration(s) && s.name?.text === type, + const declaration = sf.statements.find( + (s): s is ts.ClassDeclaration | ts.InterfaceDeclaration => + (ts.isClassDeclaration(s) || ts.isInterfaceDeclaration(s)) && s.name?.text === type, ) - if (!cls) continue // a Pick-mixin member (e.g. timer helpers), not a class here - const abstract = cls.modifiers?.some(m => m.kind === ts.SyntaxKind.AbstractKeyword) ?? false - const clsDoc = parseJsDoc(rawJsDoc(text, cls)).doc - if (!clsDoc) violations.push(`service ctx.${key} (${pointer(rel, sf, cls)}): class ${type} has no JSDoc.`) + if (!declaration) continue // a Pick-mixin member (e.g. timer helpers), not a declaration here + const abstract = ts.isInterfaceDeclaration(declaration) + || (declaration.modifiers?.some(m => m.kind === ts.SyntaxKind.AbstractKeyword) ?? false) + const declarationDoc = parseJsDoc(rawJsDoc(text, declaration)).doc + if (!declarationDoc) { + const kind = ts.isInterfaceDeclaration(declaration) ? 'interface' : 'class' + violations.push(`service ctx.${key} (${pointer(rel, sf, declaration)}): ${kind} ${type} has no JSDoc.`) + } const methods: string[] = [] - for (const member of cls.members) { - if (!ts.isMethodDeclaration(member)) continue + for (const member of declaration.members) { + if (!ts.isMethodDeclaration(member) && !ts.isMethodSignature(member)) continue // Only instance methods callable through `ctx.` are surface; // private, protected, and static methods are not. const nonPublic = member.modifiers?.some(m => @@ -238,9 +245,9 @@ export function collectServices(scanRoot: string = root): ServiceEntry[] { key, type, abstract, - doc: clsDoc, + doc: declarationDoc, methods, - source: pointer(rel, sf, cls), + source: pointer(rel, sf, declaration), }) } } diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 31df485e1d..ad131c93ba 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -152,6 +152,14 @@ const SERVICE_ROLES: ServiceRole[] = [ consumers: ['agent-loop', 'acp', 'subagent-inprocess', 'stdio-demo', 'invariants'], note: 'Owns live Agent handles and the create/resume factory seam.', }, + { + key: 'agentExecution', + pkg: 'agent-execution', + title: 'Agent execution context', + mode: 'core', + consumers: ['agent-loop'], + note: 'Carries the exact initiating Agent across one process-local asynchronous driver chain; explicit identities remain authoritative at external boundaries.', + }, { key: 'agentLoop', pkg: 'agent-loop', diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index c3e4533ba5..221372aa5c 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -11,6 +11,8 @@ { "doc": "docs/core-data-structures/core.md", "symbol": "LlmCallConfig", "source": "packages/llm/llm/src/call-config.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "SessionEvent", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "Agent", "source": "packages/core/agent/src/types.ts" }, + { "doc": "docs/core-data-structures/core.md", "symbol": "AgentExecution", "source": "packages/core/agent-execution/src/types.ts" }, + { "doc": "docs/core-data-structures/core.md", "symbol": "AgentExecutionService", "source": "packages/core/agent-execution/src/index.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "HookContext", "source": "packages/core/agent/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "PromptDecision", "source": "packages/core/agent/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "ContinuationDecision", "source": "packages/core/agent/src/types.ts" }, diff --git a/scripts/verify-package-readme-model-experience.ts b/scripts/verify-package-readme-model-experience.ts index 8220324210..6a35a3caf3 100644 --- a/scripts/verify-package-readme-model-experience.ts +++ b/scripts/verify-package-readme-model-experience.ts @@ -28,6 +28,7 @@ interface SentenceContract { * so an absent section cannot be mistaken for forgotten documentation. */ const NO_MODEL_EXPERIENCE_SECTION: Readonly> = { + 'packages/core/agent-execution': 'The package is model-agnostic ambient control infrastructure; model-facing consumers own any resulting request surface.', 'packages/core/scope': 'The package is a model-agnostic registration and lifecycle primitive; model-facing consumers own any context selection.', 'packages/util/brand': 'The package is a type-only primitive erased at compile time.', } diff --git a/tsconfig.build.json b/tsconfig.build.json index 3a57169005..ce7403242c 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -21,6 +21,7 @@ { "path": "./packages/session-query/session-query" }, { "path": "./packages/core/system-prompt" }, { "path": "./packages/core/agent" }, + { "path": "./packages/core/agent-execution" }, { "path": "./packages/context/time-context" }, { "path": "./packages/ui/user-interaction" }, { "path": "./packages/ui/user-approval" }, diff --git a/tsconfig.json b/tsconfig.json index 6585a987d6..34e9028918 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -32,6 +32,7 @@ { "path": "./packages/session-query/session-query" }, { "path": "./packages/core/system-prompt" }, { "path": "./packages/core/agent" }, + { "path": "./packages/core/agent-execution" }, { "path": "./packages/context/time-context" }, { "path": "./packages/ui/user-interaction" }, { "path": "./packages/ui/user-approval" }, From 182c622eab436569bbfac4db0cb1d4117f67a6de Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Thu, 16 Jul 2026 16:42:04 +0800 Subject: [PATCH 211/359] docs: stay within architecture word budget --- docs/architecture.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/architecture.md b/docs/architecture.md index 16f3ee0541..0e1a3238a7 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -127,7 +127,7 @@ Durability is a plugin concern. Persistence backends buffer synchronous `session Messages are arrays of typed content blocks (`text`, `reasoning`, `tool-call`, `tool-result`). The union derives from the merge-extensible `ContentBlockMap`; the same pattern types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New block types are coordinated across adapters, UI bridges, compaction pricing, and persistence, so block types remain a repo-wide contract. -Streaming uses raw chunks (`block-start` through `finish`) and `BlockAssembler`. The loop logs and assembles chunks, storing assistant provider/model provenance plus replay state. An `LlmAdapter` implements `stream()`, registers provider routes, and may expose advisory selector metadata; the adapter still resolves and validates model ids. Replay state reaches a target only when both routes map to the same adapter instance, which owns validation and conversion. The contract lives in [llm-streaming.md](core-data-structures/llm-streaming.md). +Streaming uses raw chunks (`block-start` through `finish`) and `BlockAssembler`. The loop logs and assembles chunks, storing provider/model provenance plus replay state. An `LlmAdapter` implements `stream()`, registers provider routes, and may expose selector metadata; it resolves and validates model ids. Replay state reaches targets only when both routes map to one adapter instance, which owns validation and conversion. The contract lives in [llm-streaming.md](core-data-structures/llm-streaming.md). ## Extension And Composition From 5a5591205f0ff9fbf5958e58f1f5c35469db7c93 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Thu, 16 Jul 2026 16:58:34 +0800 Subject: [PATCH 212/359] docs(rfc): acknowledge experimental ALS teardown API --- .../architecture/2026-07-15-agent-execution-context.i18n.yaml | 4 ++-- .../architecture/2026-07-15-agent-execution-context.md | 2 ++ .../architecture/2026-07-15-agent-execution-context.zh.md | 2 ++ 3 files changed, 6 insertions(+), 2 deletions(-) diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.i18n.yaml index 24dfc87f70..9e77718e75 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-agent-execution-context.md: 9f41aee74dbd94fa5acf93bface57618c604ec17 -2026-07-15-agent-execution-context.zh.md: 4747a506b4fb8a0ff798043ec772a4e810f84d7f +2026-07-15-agent-execution-context.md: bbc33bb6a27c0222ec7ef582a5e5c20cdd566cd8 +2026-07-15-agent-execution-context.zh.md: 64bebc6e70519426bd88e2ea9bb9d40d64f1c58b diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md index 9f41aee74d..bbc33bb6a2 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md @@ -68,4 +68,6 @@ Deep infrastructure gains one trusted process-local initiating Agent without wid The dependency is implicit in function signatures and carries a live capability object. Consumers must restrict it to cross-cutting infrastructure, treat ambient presence as neither liveness nor authorization, and retain explicit cancellation and ownership checks. ALS also has an always-on propagation cost and does not cross worker, process, HTTP, or durable queue boundaries. +The teardown design deliberately accepts Node's [Stability 1 (Experimental)](https://nodejs.org/api/async_context.html#asynclocalstoragedisable) `AsyncLocalStorage.disable()` dependency. Node requires `disable()` before an ALS instance can be garbage-collected, which matters when HMR replaces provider-owned instances; the service state guard prevents a later `run()` from re-entering the instance after disposal. + The frame deliberately omits turn, step, signal, cwd, sandbox, and authorization. A real consumer that cannot use existing explicit fields must justify any refinement separately; a stale copied field may at most mislabel telemetry, never grant control. diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md index 4747a506b4..64bebc6e70 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md @@ -68,4 +68,6 @@ export interface AgentExecutionService { 该依赖不会出现在函数签名中，并且携带一个存活能力对象。消费方必须将其限制在横切基础设施中，把隐式存在视为既不证明存活、也不授予权限，并保留显式取消和归属检查。ALS 还有常驻传播成本，也无法跨越 worker、进程、HTTP 或持久化队列边界。 +该 teardown 设计有意接受 Node [Stability 1（实验性）](https://nodejs.org/api/async_context.html#asynclocalstoragedisable) 的 `AsyncLocalStorage.disable()` 依赖。Node 要求在 ALS 实例可被垃圾回收前调用 `disable()`，这对 HMR 替换提供方所拥有的实例尤为重要；服务状态守卫会阻止 dispose 后通过后续 `run()` 重新进入该实例。 + 该帧有意省略轮次、步骤、signal、cwd、沙箱和授权。若真实消费方无法使用现有显式字段，必须另行论证扩展；陈旧字段最多只能误标遥测数据，绝不能授予控制权。 From 231aeabe55f3d58b5f02cd0f9a1495c529613db9 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 17:11:41 +0800 Subject: [PATCH 213/359] docs(compact): align recovery RFC with singleton meter --- ...compaction-pressure-and-overflow-recovery.i18n.yaml | 4 ++-- ...r-call-compaction-pressure-and-overflow-recovery.md | 10 +++++----- ...all-compaction-pressure-and-overflow-recovery.zh.md | 10 +++++----- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml index dbb9c76bbf..7cfb11d29d 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: 92167dc7d444a3620abfbaab721260ed1c828db9 -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: fe3b6617b25a58ef2c1c311df088f9c805fe9ef4 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: 7d68bc32d3860bf5edd94c4eda76922c91ae6af2 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 2315bd4d9ca9b93eb9a8d4850f917e6aa1bc6476 diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md index 92167dc7d4..7d68bc32d3 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md @@ -18,7 +18,7 @@ Successful calls are not the only pressure signal. A provider can reject a reque The loop fires awaited serial `agent/post-step(agent, turn, step, signal)` after assistant output, every dispatched or synthetic tool result, post-tool context, and steering are durable, but before `step/end`. This placement gives pressure policy the complete successful-call state without splitting an assistant tool call from its result. A listener failure is an ordinary turn failure; it never enters model-request recovery. -`dsh-compact-basic` resolves the exact latest routed model from the durable request header and asks that model's `ctx.tokenMeter` handle to measure the canonical logged envelope and current surface. It does not fall back to `AgentOptions.model` for automatic pressure. A headerless session has no completed routed request to assess and produces no work. A durable unknown model throws `TOKEN_METER_MODEL_UNCONFIGURED` with its exact name and fails the otherwise-successful turn; operational selection or summarization failures warn and continue with full history. +`dsh-compact-basic` reads the exact latest routed model from the durable request header only to establish that a completed route exists, then asks the singleton `ctx.tokenMeter` to measure the canonical logged envelope and current surface. It does not fall back to `AgentOptions.model` for automatic pressure. A headerless session has no completed routed request to assess and produces no work; any durable non-empty model name uses the same estimator. Operational measurement or summarization failures warn and continue with full history. ### Request recovery is limited to the final model boundary @@ -32,11 +32,11 @@ If cancellation lands after assistant tool calls are durable but before all call `CompactService.compactIfNeeded(agent, trigger, signal)` accepts `trigger: 'pressure' | 'context-overflow'`. The interface gains no estimation methods or token types; `ctx.tokenMeter` remains the reusable accounting owner. -For `pressure`, compact-basic applies the selected meter profile's threshold and retained-tail policy, compares scalar and surface `logRevision`, and uses the same meter for range pricing, provenance, shadowed token counts, and non-shrinking-summary rejection. The common defaults remain threshold ratio `0.8`, retained history `floor(contextWindow × 0.16)`, summarization model `''`, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. +For `pressure`, compact-basic applies the service-wide threshold and retained-tail policy to one unified `ctx.tokenMeter.measure()` result. The same singleton meter owns range pricing, provenance, shadowed token counts, and non-shrinking-summary rejection. The common defaults remain threshold ratio `0.8`, retained history `floor(contextWindow × 0.16)`, summarization model `''`, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. For canonical overflow, compact-basic bypasses scalar pressure and the normal retained-token budget. It chooses the maximal tool-balanced head range while leaving the newest indivisible unit, then attempts exactly one shrinking compaction under the same signal. The automatic listener snapshots `session.surface.replaceGeneration` and returns `{ action: 'retry' }` only when compaction succeeds and the generation increases. A backend returning a result without replacement cannot authorize retry. -`maxOverflowRetries` is optional and defaults to `1`; `0` disables overflow recovery without disabling pressure. `auto: false` registers neither automatic listener. Noncanonical errors, exhausted attempts, an already-aborted signal, missing or unknown routed models, no safe range, no generation change, and recovery throws all delegate to the next listener. With no later recovery, the loop reports the original provider error object and code. Cancellation or disposal remains authoritative even if recovery work completes concurrently. +`maxOverflowRetries` is optional and defaults to `1`; `0` disables overflow recovery without disabling pressure. `auto: false` registers neither automatic listener. Noncanonical errors, exhausted attempts, an already-aborted signal, a missing routed model, no safe range, no generation change, and recovery throws all delegate to the next listener. With no later recovery, the loop reports the original provider error object and code. Cancellation or disposal remains authoritative even if recovery work completes concurrently. The default summarizer still resolves explicit configuration, then the latest logged route, then agent options. Because direct `llm/stream` middleware may reroute that auxiliary call, `compact/summary.model` records the final mutable `GenerateOptions.model` observed after dispatch rather than the pre-waterfall candidate. @@ -44,7 +44,7 @@ The default summarizer still resolves explicit configuration, then the latest lo Lifecycle tests pin post-step ordering after durable tool/context/steering work, content-less and max-token successes, final-adapter dispatch/iterator/in-band boundaries, retry numbering, attempt reset, cancellation, disposal, synthetic tool results, and original error identity. -Compact tests pin low-friction defaults, actual routed-model selection, exact unknown-model behavior, below-threshold forced overflow, newest tool-pair retention, non-shrinking rejection, generation proof, caps, disabled listeners, single downstream delegation, and auxiliary summary routing provenance. Real-loop composition covers both thrown and in-band overflow: the failed step closes, compaction lands between attempts, and the next numbered request is reconstructed from the replacement surface. +Compact tests pin low-friction service-wide defaults, actual routed-model selection, unlisted-model measurement, unified pressure-and-retention decisions, below-threshold forced overflow, newest tool-pair retention, non-shrinking rejection, generation proof, caps, disabled listeners, single downstream delegation, and auxiliary summary routing provenance. Real-loop composition covers both thrown and in-band overflow: the failed step closes, compaction lands between attempts, and the next numbered request is reconstructed from the replacement surface. ## Alternatives considered @@ -52,7 +52,7 @@ Compact tests pin low-friction defaults, actual routed-model selection, exact un - **Retry the same numbered step** — rejected because recovery appends durable events after the failed boundary. A new step preserves balanced nesting and reconstructability. - **Retry whenever `compactIfNeeded` returns a result** — rejected because a custom backend can report success without changing model-visible state. `replaceGeneration` is the authoritative proof. - **Let compact-basic parse provider wording** — rejected because classification belongs at adapters and must cover both thrown and in-band delivery. -- **Use a universal model/window fallback during recovery** — rejected because destructive policy under the wrong context capacity can hide the original provider failure. Unknown durable routes delegate unchanged. +- **Fall back to `AgentOptions.model` when no durable route exists** — rejected because automatic policy must describe a completed logged request. Headerless pressure and recovery delegate unchanged. ## Consequences diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md index fe3b6617b2..2315bd4d9c 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md @@ -18,7 +18,7 @@ Status: implemented 循环在 assistant 输出、所有已分发或合成的工具结果、工具后上下文与 steering 都持久化之后、`step/end` 之前，触发等待式串行 `agent/post-step(agent, turn, step, signal)`。该位置让压力策略看到完整的成功调用状态，同时不会拆开 assistant 工具调用与其结果。监听器失败属于普通 turn 失败，绝不会进入模型请求恢复。 -`dsh-compact-basic` 从持久请求头解析精确的最新实际路由模型，并让该模型的 `ctx.tokenMeter` handle 计量规范日志信封与当前表层。自动压力不会回退到 `AgentOptions.model`。没有请求头的会话尚无已完成路由请求可供判断，因此不执行工作。持久记录的未知模型会携带精确名称抛出 `TOKEN_METER_MODEL_UNCONFIGURED`，使原本成功的 turn 失败；操作性的选择或摘要失败则警告并继续使用完整历史。 +`dsh-compact-basic` 从持久请求头读取精确的最新实际路由模型，只用它确认已经存在完整路由，随后让单例 `ctx.tokenMeter` 计量规范日志信封与当前表层。自动压力不会回退到 `AgentOptions.model`。没有请求头的会话尚无已完成路由请求可供判断，因此不执行工作；任意持久记录的非空模型名都使用同一个估算器。操作性的计量或摘要失败会发出警告，并继续使用完整历史。 ### 请求恢复只覆盖最终模型边界 @@ -32,11 +32,11 @@ Status: implemented `CompactService.compactIfNeeded(agent, trigger, signal)` 接收 `trigger: 'pressure' | 'context-overflow'`。接口不增加估算方法或 token 类型；`ctx.tokenMeter` 继续作为可复用的核算所有者。 -对于 `pressure`，compact-basic 应用所选 meter profile 的阈值与保留尾部策略，比较标量和表层的 `logRevision`，并用同一个 meter 完成范围定价、来源、被遮蔽 token 数与非缩小摘要拒绝。通用默认值保持为阈值比例 `0.8`、保留历史 `floor(contextWindow × 0.16)`、摘要模型 `''`、`maxTokens: 8192`、`compactionRetries: 1` 与 `auto: true`。 +对于 `pressure`，compact-basic 把服务级阈值与保留尾部策略应用到一次统一的 `ctx.tokenMeter.measure()` 结果。范围定价、来源、被遮蔽 token 数与非缩小摘要拒绝也由同一个单例 meter 完成。通用默认值保持为阈值比例 `0.8`、保留历史 `floor(contextWindow × 0.16)`、摘要模型 `''`、`maxTokens: 8192`、`compactionRetries: 1` 与 `auto: true`。 对于规范化溢出，compact-basic 绕过标量压力与普通保留 token 预算。它在保留最新不可分割单元的同时，选择最大的工具配对平衡头部范围，并在同一 signal 下只尝试一次缩小压缩。自动监听器先记录 `session.surface.replaceGeneration`，只有压缩成功且 generation 增加时才返回 `{ action: 'retry' }`。后端若只返回结果但没有替换表层，不能授权重试。 -`maxOverflowRetries` 可选且默认为 `1`；`0` 只禁用溢出恢复，不会禁用压力检查。`auto: false` 不注册任何自动监听器。非规范化错误、尝试耗尽、已经中止的 signal、缺失或未知路由模型、没有安全范围、generation 未变化，以及恢复抛错都会委托给下一个监听器。若没有后续恢复，循环报告原始提供方错误对象与代码。即使恢复工作并发完成，取消或销毁仍具有最终优先级。 +`maxOverflowRetries` 可选且默认为 `1`；`0` 只禁用溢出恢复，不会禁用压力检查。`auto: false` 不注册任何自动监听器。非规范化错误、尝试耗尽、已经中止的 signal、缺失路由模型、没有安全范围、generation 未变化，以及恢复抛错都会委托给下一个监听器。若没有后续恢复，循环报告原始提供方错误对象与代码。即使恢复工作并发完成，取消或销毁仍具有最终优先级。 默认摘要器仍依次解析显式配置、最近记录的路由与 agent options。因为直接 `llm/stream` 中间件可以重新路由该辅助调用，`compact/summary.model` 记录分发后最终可变的 `GenerateOptions.model`，而不是 waterfall 之前的候选值。 @@ -44,7 +44,7 @@ Status: implemented 生命周期测试固定 post-step 位于持久工具、上下文与 steering 工作之后，覆盖无内容与达到 token 上限的成功、最终适配器分发/迭代器/带内边界、重试编号、尝试重置、取消、销毁、合成工具结果与原始错误身份。 -压缩测试固定低摩擦默认值、实际路由模型选择、精确未知模型行为、低于阈值的强制溢出、最新工具配对保留、非缩小拒绝、generation 证明、上限、禁用监听器、单次下游委托与辅助摘要路由来源。真实循环组合同时覆盖抛出式和带内溢出：失败 step 关闭，压缩落在两次尝试之间，下一个编号请求从替换表层重建。 +压缩测试固定低摩擦服务级默认值、实际路由模型选择、未列出模型计量、统一压力与保留决策、低于阈值的强制溢出、最新工具配对保留、非缩小拒绝、generation 证明、上限、禁用监听器、单次下游委托与辅助摘要路由来源。真实循环组合同时覆盖抛出式和带内溢出：失败 step 关闭，压缩落在两次尝试之间，下一个编号请求从替换表层重建。 ## 考虑过的替代方案 @@ -52,7 +52,7 @@ Status: implemented - **重试相同编号的 step**——不予采纳，因为恢复会在失败边界之后追加持久事件。新 step 保持边界配对与可重建性。 - **只要 `compactIfNeeded` 返回结果就重试**——不予采纳，因为自定义后端可能报告成功却没有改变模型可见状态。`replaceGeneration` 才是权威证明。 - **让 compact-basic 解析提供方措辞**——不予采纳，因为分类属于适配器，而且必须同时覆盖抛出式与带内交付。 -- **恢复时使用通用模型/窗口回退**——不予采纳，因为基于错误上下文容量执行破坏性策略可能掩盖原始提供方失败。未知持久路由会原样委托。 +- **没有持久路由时回退到 `AgentOptions.model`**——不予采纳，因为自动策略必须描述已完成且已记录的请求。没有请求头的压力检查与恢复会原样委托。 ## 后果 From d3b959389a3e76c4e36d29215c84b6749d124269 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Thu, 16 Jul 2026 17:39:53 +0800 Subject: [PATCH 214/359] test(support): add shared AgentLoop testkit --- docs/config-catalog.md | 1 + docs/module-graph.md | 7 ++ examples/coding-agent/tests/harness.ts | 14 +-- examples/cordis-agent/tests/harness.ts | 14 +-- packages/README.md | 2 +- packages/bash/tool-bash/package.json | 1 + .../bash/tool-bash/tests/integration.spec.ts | 13 +-- packages/compact/compact-basic/package.json | 2 +- .../tests/compact-loop-repro.spec.ts | 14 +-- packages/context/time-context/package.json | 1 + .../time-context/tests/time-context.spec.ts | 15 ++-- packages/cordis/tool-cordis/package.json | 1 + .../tool-cordis/tests/integration.spec.ts | 13 +-- packages/fs/tool-fs/package.json | 1 + packages/fs/tool-fs/tests/harness.ts | 13 +-- packages/guard/repeat-tool-guard/package.json | 2 +- .../tests/repeat-tool-guard.spec.ts | 22 ++--- packages/hooks/hooks-claude/package.json | 2 +- .../hooks/hooks-claude/tests/bridge.spec.ts | 27 ++---- .../hooks/hooks-claude/tests/coverage.spec.ts | 33 ++----- packages/hooks/hooks-codex/package.json | 2 +- .../hooks/hooks-codex/tests/bridge.spec.ts | 27 ++---- .../hooks/hooks-codex/tests/coverage.spec.ts | 21 +++-- packages/subagent/subagent-fork/package.json | 3 +- .../tests/multi-subagent.spec.ts | 13 +-- .../subagent-fork/tests/subagent-fork.spec.ts | 11 +-- .../subagent/subagent-inprocess/package.json | 1 + .../tests/structured.spec.ts | 16 ++-- .../tests/subagent-inprocess.spec.ts | 13 +-- packages/subagent/subagent-spawn/package.json | 3 +- .../subagent/subagent-spawn/tests/harness.ts | 15 ++-- .../tests/subagent-spawn.spec.ts | 23 +---- packages/support/README.md | 3 +- packages/support/agent-loop-testkit/README.md | 27 ++++++ .../support/agent-loop-testkit/package.json | 41 +++++++++ .../support/agent-loop-testkit/src/index.ts | 46 ++++++++++ .../tests/agent-loop-testkit.spec.ts | 20 +++++ .../support/agent-loop-testkit/tsconfig.json | 33 +++++++ packages/todo/tool-todo/package.json | 1 + .../todo/tool-todo/tests/integration.spec.ts | 13 +-- packages/ui/acp/package.json | 1 + packages/ui/acp/tests/harness.ts | 15 ++-- .../workflow-workerthread/package.json | 1 + .../tests/integration.spec.ts | 13 +-- pnpm-lock.yaml | 90 ++++++++++++++----- .../verify-package-readme-model-experience.ts | 1 + tsconfig.build.json | 1 + tsconfig.json | 1 + 48 files changed, 361 insertions(+), 292 deletions(-) create mode 100644 packages/support/agent-loop-testkit/README.md create mode 100644 packages/support/agent-loop-testkit/package.json create mode 100644 packages/support/agent-loop-testkit/src/index.ts create mode 100644 packages/support/agent-loop-testkit/tests/agent-loop-testkit.spec.ts create mode 100644 packages/support/agent-loop-testkit/tsconfig.json diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 91fe7c6497..e346e0114d 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1279,6 +1279,7 @@ Imported as libraries by other packages; a `cordis.yml` cannot load them. - `@deepseek-ai/create-sdk` ([`packages/sdk/create-sdk/src/index.ts`](../packages/sdk/create-sdk/src/index.ts)) - `@deepseek-ai/dsh-acp-snapshot` ([`packages/support/acp-snapshot/src/index.ts`](../packages/support/acp-snapshot/src/index.ts)) +- `@deepseek-ai/dsh-agent-loop-testkit` ([`packages/support/agent-loop-testkit/src/index.ts`](../packages/support/agent-loop-testkit/src/index.ts)) - `@deepseek-ai/dsh-app-boot` ([`packages/ui/app-boot/src/index.ts`](../packages/ui/app-boot/src/index.ts)) - `@deepseek-ai/dsh-brand` ([`packages/util/brand/src/index.ts`](../packages/util/brand/src/index.ts)) - `@deepseek-ai/dsh-helper` ([`packages/sdk/helper/src/index.ts`](../packages/sdk/helper/src/index.ts)) diff --git a/docs/module-graph.md b/docs/module-graph.md index 82763bdc55..df4e680ee0 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -86,6 +86,7 @@ flowchart TD end subgraph group_support["packages/support"] pkg_acp_snapshot["acp-snapshot"] + pkg_agent_loop_testkit["agent-loop-testkit"] pkg_invariants["invariants"] pkg_llm_replay["llm-replay"] pkg_loader_smoke["loader-smoke"] @@ -274,6 +275,11 @@ flowchart TD pkg_hooks_codex --> pkg_llm pkg_hooks_codex --> pkg_session pkg_hooks_codex --> pkg_tools + pkg_agent_loop_testkit --> pkg_agent + pkg_agent_loop_testkit --> pkg_llm + pkg_agent_loop_testkit --> pkg_session + pkg_agent_loop_testkit --> pkg_system_prompt + pkg_agent_loop_testkit --> pkg_tools pkg_acp --> pkg_agent pkg_acp --> pkg_bash pkg_acp --> pkg_llm @@ -435,6 +441,7 @@ flowchart TD | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-cordis`](../packages/cordis/tool-cordis) | `cordis` | [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | | [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | +| [`agent-loop-testkit`](../packages/support/agent-loop-testkit) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`permission`](../packages/ui/permission), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`user-interaction`](../packages/ui/user-interaction) | | [`tool-ask-user`](../packages/ui/tool-ask-user) | `ui` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) | diff --git a/examples/coding-agent/tests/harness.ts b/examples/coding-agent/tests/harness.ts index dd0bc42a1b..22c8c3f662 100644 --- a/examples/coding-agent/tests/harness.ts +++ b/examples/coding-agent/tests/harness.ts @@ -1,11 +1,7 @@ import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' @@ -50,11 +46,9 @@ export interface CodingHarnessOptions { export async function codingHarness(workdir: string, options: CodingHarnessOptions = {}): Promise { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt, { persona: options.persona ?? '' }) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx, { + systemPrompt: { persona: options.persona ?? '' }, + }) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 }) diff --git a/examples/cordis-agent/tests/harness.ts b/examples/cordis-agent/tests/harness.ts index 78e5b0bb93..260a68bfbb 100644 --- a/examples/cordis-agent/tests/harness.ts +++ b/examples/cordis-agent/tests/harness.ts @@ -1,10 +1,6 @@ import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import * as ToolCordis from '@deepseek-ai/dsh-tool-cordis' @@ -23,11 +19,9 @@ const PERSONA = 'You are cordis-agent, a self-referential harness demo. ' export async function cordisHarness(): Promise { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt, { persona: PERSONA }) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx, { + systemPrompt: { persona: PERSONA }, + }) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) await ctx.plugin(ToolCordis) diff --git a/packages/README.md b/packages/README.md index 8f1bf3dde2..a3e0b1ac0a 100644 --- a/packages/README.md +++ b/packages/README.md @@ -31,7 +31,7 @@ Packages live at `packages///`; groups are containers, while names r | [`sdk/`](sdk/README.md) | Project SDK tooling | Product — stable surface | | [`ui/`](ui/README.md) | Editor/client integration surfaces: ACP bridge, JSON-RPC SDK server, user-approval/user-interaction seams, ask-user tool | Product — stable surface | | [`examples/`](examples/README.md) | Demo bundles (agent-spine + stdio/ACP/JSON-RPC bins) the leaves load | Support — example infra | -| [`support/`](support/README.md) | Support infrastructure (invariants, replay, Loader smokes) | Support — lower compatibility expectations | +| [`support/`](support/README.md) | Support infrastructure (testkits, invariants, replay, Loader smokes) | Support — lower compatibility expectations | | [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (the `Branded` primitive) | Support — small, stable, harness-dep-free | Groups distinguish product API from support infrastructure. New packages join an existing group; a new group updates its README and this table. diff --git a/packages/bash/tool-bash/package.json b/packages/bash/tool-bash/package.json index 035b16aeec..c8d082f46a 100644 --- a/packages/bash/tool-bash/package.json +++ b/packages/bash/tool-bash/package.json @@ -38,6 +38,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-user-approval": "workspace:^", "@deepseek-ai/dsh-bash": "workspace:^", "@deepseek-ai/dsh-bash-local": "workspace:^", diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index 238176b8a6..0a2a1ba883 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -1,12 +1,9 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import TaskService from '@deepseek-ai/dsh-tasks' import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' @@ -21,11 +18,7 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent */ async function harness(adapter: MockAdapter) { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(TaskService) await ctx.plugin(ToolTasks) diff --git a/packages/compact/compact-basic/package.json b/packages/compact/compact-basic/package.json index 32852a060f..fae0af5c62 100644 --- a/packages/compact/compact-basic/package.json +++ b/packages/compact/compact-basic/package.json @@ -31,11 +31,11 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-compact": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", - "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.7" } diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index dbf8a3b737..f2d1a60ad8 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -1,14 +1,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' import { isToolPairingBalanced } from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import { defineTool } from '@deepseek-ai/dsh-tools' +import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as Invariants from '@deepseek-ai/dsh-invariants' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' import type { SurfaceEvent } from '@deepseek-ai/dsh-session' @@ -60,12 +58,8 @@ class StepwiseToolAdapter extends LlmAdapter { async function harness(toolSteps: number): Promise<{ ctx: Context; compact: ReproCompactService }> { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(Invariants) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], new StepwiseToolAdapter(toolSteps)) ctx.tools.register(defineTool({ diff --git a/packages/context/time-context/package.json b/packages/context/time-context/package.json index f319c7a5b1..906adf854e 100644 --- a/packages/context/time-context/package.json +++ b/packages/context/time-context/package.json @@ -32,6 +32,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", diff --git a/packages/context/time-context/tests/time-context.spec.ts b/packages/context/time-context/tests/time-context.spec.ts index 562b002b68..92637e8277 100644 --- a/packages/context/time-context/tests/time-context.spec.ts +++ b/packages/context/time-context/tests/time-context.spec.ts @@ -1,14 +1,15 @@ import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import LlmService, { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' +import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' -import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' +import { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' -import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' +import { defineTool } from '@deepseek-ai/dsh-tools' import AgentLoop from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as timeContext from '@deepseek-ai/dsh-time-context' import type { Config } from '@deepseek-ai/dsh-time-context' @@ -89,11 +90,7 @@ class ScriptedAdapter extends LlmAdapter { async function loopHarness(adapter: ScriptedAdapter, config: Config = {}): Promise { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(timeContext, config) ctx.llm.registerAdapter(['mock'], adapter) diff --git a/packages/cordis/tool-cordis/package.json b/packages/cordis/tool-cordis/package.json index fd9c35e48e..e13de3e58b 100644 --- a/packages/cordis/tool-cordis/package.json +++ b/packages/cordis/tool-cordis/package.json @@ -33,6 +33,7 @@ "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", diff --git a/packages/cordis/tool-cordis/tests/integration.spec.ts b/packages/cordis/tool-cordis/tests/integration.spec.ts index 94331df7c0..8892dd47e5 100644 --- a/packages/cordis/tool-cordis/tests/integration.spec.ts +++ b/packages/cordis/tool-cordis/tests/integration.spec.ts @@ -1,11 +1,8 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as ToolCordis from '../src/index.ts' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' import { REVERSE_TOOL_CODE } from './helpers.ts' @@ -20,11 +17,7 @@ import { REVERSE_TOOL_CODE } from './helpers.ts' async function harness(adapter: MockAdapter): Promise { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(ToolCordis) ctx.llm.registerAdapter(['mock'], adapter) diff --git a/packages/fs/tool-fs/package.json b/packages/fs/tool-fs/package.json index c21c806e98..f9ef3136bf 100644 --- a/packages/fs/tool-fs/package.json +++ b/packages/fs/tool-fs/package.json @@ -36,6 +36,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-fs-policy": "workspace:^", "@deepseek-ai/dsh-fs": "workspace:^", "@deepseek-ai/dsh-fs-local": "workspace:^", diff --git a/packages/fs/tool-fs/tests/harness.ts b/packages/fs/tool-fs/tests/harness.ts index 0487962922..3666447ad9 100644 --- a/packages/fs/tool-fs/tests/harness.ts +++ b/packages/fs/tool-fs/tests/harness.ts @@ -1,10 +1,7 @@ import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' import AgentLoop from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import LocalFileSystem from '@deepseek-ai/dsh-fs-local' import * as FsPolicy from '@deepseek-ai/dsh-fs-policy' import * as ToolFs from '@deepseek-ai/dsh-tool-fs' @@ -17,11 +14,7 @@ import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' */ export async function fsHarness(fsCwd: string, persona = ''): Promise { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt, { persona }) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx, { systemPrompt: { persona } }) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) await ctx.plugin(LocalFileSystem, { cwd: fsCwd }) diff --git a/packages/guard/repeat-tool-guard/package.json b/packages/guard/repeat-tool-guard/package.json index 0cc99b6976..92d49c548f 100644 --- a/packages/guard/repeat-tool-guard/package.json +++ b/packages/guard/repeat-tool-guard/package.json @@ -32,9 +32,9 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", - "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.7" } diff --git a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts index 565f1076b5..81fe63aaca 100644 --- a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts +++ b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts @@ -1,11 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import LlmService, { CallId } from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import { CallId } from '@deepseek-ai/dsh-llm' +import type { SessionEvent } from '@deepseek-ai/dsh-session' +import { defineTool } from '@deepseek-ai/dsh-tools' +import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as RepeatToolGuard from '@deepseek-ai/dsh-repeat-tool-guard' import type { Config } from '@deepseek-ai/dsh-repeat-tool-guard' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -21,11 +21,7 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent /** Boot the core spine + the guard; the caller registers adapters and extra listeners. */ async function harness(config: Config = {}): Promise { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(RepeatToolGuard, config) ctx.tools.register(defineTool({ name: 'probe', description: 'p', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) @@ -363,11 +359,7 @@ describe('fold onto the downstream decision', () => { describe('config validation fails loud', () => { async function spine(): Promise { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) return ctx } diff --git a/packages/hooks/hooks-claude/package.json b/packages/hooks/hooks-claude/package.json index 21f08965d8..abb68a061e 100644 --- a/packages/hooks/hooks-claude/package.json +++ b/packages/hooks/hooks-claude/package.json @@ -36,13 +36,13 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-bash": "workspace:^", "@deepseek-ai/dsh-bash-local": "workspace:^", "@deepseek-ai/dsh-hook-protocol": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", - "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.7" } diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 506d613c73..6d9e89d5ed 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -4,12 +4,11 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context, type Fiber } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import type { SessionEvent } from '@deepseek-ai/dsh-session' +import { defineTool } from '@deepseek-ai/dsh-tools' +import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -42,11 +41,7 @@ async function harness(configDir: string, adapter: MockAdapter): Promise { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) const hooks = await ctx.plugin(HooksClaude, { configPath: join(configDir, 'hooks.json') }) @@ -337,11 +332,7 @@ describe('hooks-claude bridge — load resilience', () => { it('a missing config file registers no hooks and does not crash the loop', async () => { const adapter = new MockAdapter([textResponse('fine')]) const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksClaude, { configPath: '/nonexistent/hooks.json' }) @@ -359,11 +350,7 @@ describe('hooks-claude bridge — load resilience', () => { const dir = writeConfig({ UserPromptSubmit: [{ hooks: [{ type: 'command', command: 'exit 2' }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) const fiber = await ctx.plugin(HooksClaude, { configPath: join(dir, 'hooks.json') }) diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index f376708688..5fb975b3dd 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -3,12 +3,11 @@ import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync } from 'node: import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import type { SessionEvent } from '@deepseek-ai/dsh-session' +import { defineTool } from '@deepseek-ai/dsh-tools' +import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -30,11 +29,7 @@ function hooks(d: string, h: unknown): string { type HarnessOpts = { pluginRoot?: string; projectDir?: string; stderrSummaryMaxChars?: number } async function harness(configPath: string, adapter: MockAdapter, opts: HarnessOpts = {}): Promise { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksClaude, { configPath, ...opts }) @@ -329,11 +324,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) // Direct apply with only configPath — bypasses schemastery's defaults, so @@ -594,11 +585,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server hooks(serverDir, { PreToolUse: [{ hooks: [{ type: 'command', command: 'pwd > where' }] }] }) const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) // Executor default cwd = serverDir (deliberately NOT the session cwd). await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir }) @@ -627,11 +614,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server const marker = join(childDir, 'stopwhere') hooks(serverDir, { SubagentStop: [{ hooks: [{ type: 'command', command: 'pwd > stopwhere' }] }] }) const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) // Executor default cwd = serverDir (deliberately NOT the child session cwd). await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir }) diff --git a/packages/hooks/hooks-codex/package.json b/packages/hooks/hooks-codex/package.json index fe667b0302..a481162a11 100644 --- a/packages/hooks/hooks-codex/package.json +++ b/packages/hooks/hooks-codex/package.json @@ -35,12 +35,12 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-bash": "workspace:^", "@deepseek-ai/dsh-bash-local": "workspace:^", "@deepseek-ai/dsh-hook-protocol": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", - "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.7" } diff --git a/packages/hooks/hooks-codex/tests/bridge.spec.ts b/packages/hooks/hooks-codex/tests/bridge.spec.ts index d4a5797b96..72e3f45184 100644 --- a/packages/hooks/hooks-codex/tests/bridge.spec.ts +++ b/packages/hooks/hooks-codex/tests/bridge.spec.ts @@ -4,12 +4,11 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import type { SessionEvent } from '@deepseek-ai/dsh-session' +import { defineTool } from '@deepseek-ai/dsh-tools' +import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -40,11 +39,7 @@ function writeHooks(dir: string, hooks: unknown): void { async function harness(dir: string, adapter: MockAdapter): Promise { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'test-model' }) @@ -141,11 +136,7 @@ describe('hooks-codex bridge', () => { writeHooks(dir, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: deny }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) const fiber = await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'm' }) @@ -167,11 +158,7 @@ describe('hooks-codex bridge', () => { const slow = script(dir, 'slow.sh', `#!/usr/bin/env bash\necho $$ > "${pidFile}"\ntouch "${marker}"\nsleep 30\n`) writeHooks(dir, { SessionStart: [{ hooks: [{ type: 'command', command: slow }] }] }) const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) const fiber = await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'm' }) diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index c287d86b23..6d2ac699eb 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -3,12 +3,11 @@ import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync, readFileSync import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import type { SessionEvent } from '@deepseek-ai/dsh-session' +import { defineTool } from '@deepseek-ai/dsh-tools' +import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -25,8 +24,8 @@ function hooks(d: string, h: unknown): string { async function harness(configPath: string, adapter: MockAdapter, opts: { stderrSummaryMaxChars?: number } = {}): Promise { const ctx = new Context() - await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] }) + await mountAgentLoopTestDependencies(ctx) + await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksCodex, { configPath, model: 'm', ...opts }) ctx.llm.registerAdapter(['mock'], adapter) @@ -238,8 +237,8 @@ describe('hooks-codex coverage — decision mapping paths', () => { const warn = vi.fn() const adapter = new MockAdapter([textResponse('ok')]) const ctx = new Context() - await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] }) + await mountAgentLoopTestDependencies(ctx) + await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) ctx.logger.warn = warn as never // Direct apply (schema bypass) → the `model ?? ''` fallback is exercised. @@ -543,8 +542,8 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(serverDir, { PreToolUse: [{ hooks: [{ type: 'command', command: 'pwd > where' }] }] }) const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = new Context() - await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] }) + await mountAgentLoopTestDependencies(ctx) + await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, cwd: serverDir }) await ctx.plugin(HooksCodex, { configPath: join(serverDir, 'hooks.json'), model: 'm' }) ctx.llm.registerAdapter(['mock'], adapter) diff --git a/packages/subagent/subagent-fork/package.json b/packages/subagent/subagent-fork/package.json index 8794884518..63f548d217 100644 --- a/packages/subagent/subagent-fork/package.json +++ b/packages/subagent/subagent-fork/package.json @@ -34,14 +34,13 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", "@deepseek-ai/dsh-subagent-inprocess": "workspace:^", "@deepseek-ai/dsh-subagent-spawn": "workspace:^", - "@deepseek-ai/dsh-system-prompt": "workspace:^", - "@deepseek-ai/dsh-tools": "workspace:^", "@cordisjs/plugin-loader": "^1.0.0-rc.5", "cordis": "^4.0.0-rc.7" } diff --git a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts index 8060a77fd4..110c4f83e4 100644 --- a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts +++ b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts @@ -1,11 +1,8 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import * as Spawn from '@deepseek-ai/dsh-subagent-spawn' @@ -26,11 +23,7 @@ function start(ctx: Context, provider: string, request: Omit Promise.resolve({ logs: [] })), } as never) } - await ctx.plugin(AgentRegistry) await ctx.plugin(Invariants) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index 0005246523..e7d856e112 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -1,11 +1,8 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' import AgentLoop from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' import { MockAdapter, textResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -15,11 +12,7 @@ type Script = ConstructorParameters[0] async function setup(script: Script) { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(Invariants) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) diff --git a/packages/subagent/subagent-spawn/package.json b/packages/subagent/subagent-spawn/package.json index f2500a4a56..1a986e69aa 100644 --- a/packages/subagent/subagent-spawn/package.json +++ b/packages/subagent/subagent-spawn/package.json @@ -32,6 +32,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-bash-local": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", @@ -39,10 +40,8 @@ "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", "@deepseek-ai/dsh-subagent-inprocess": "workspace:^", - "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tool-bash": "workspace:^", "@deepseek-ai/dsh-tool-subagent": "workspace:^", - "@deepseek-ai/dsh-tools": "workspace:^", "@cordisjs/plugin-loader": "^1.0.0-rc.5", "cordis": "^4.0.0-rc.7" } diff --git a/packages/subagent/subagent-spawn/tests/harness.ts b/packages/subagent/subagent-spawn/tests/harness.ts index e4ee2e6ab7..bb0b49fbcb 100644 --- a/packages/subagent/subagent-spawn/tests/harness.ts +++ b/packages/subagent/subagent-spawn/tests/harness.ts @@ -1,10 +1,7 @@ import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' import AgentLoop from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -21,15 +18,13 @@ import * as ToolSubagent from '@deepseek-ai/dsh-tool-subagent' */ export async function spawnHarness(workdir: string): Promise { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) // This harness installs only the global default persona, so both parent and // spawned children render it. It stays neutral for both roles; the // delegation nudge lives in the e2e's user prompt and the subagent tool's // own description. - await ctx.plugin(SystemPrompt, { persona: 'You are a coding agent. Report only when the requested work is done.' }) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx, { + systemPrompt: { persona: 'You are a coding agent. Report only when the requested work is done.' }, + }) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 }) diff --git a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts index 43ec8ee1ac..3862f110c5 100644 --- a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts +++ b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts @@ -1,13 +1,10 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import AgentLoop from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -26,11 +23,7 @@ type Script = ConstructorParameters[0] async function setup(script: Script) { const ctx = new Context() const adapter = new MockAdapter(script) - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(Invariants) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) @@ -303,11 +296,7 @@ describe('dsh-subagent-spawn', () => { // Rebuild the stack by hand so we hold the backend's fiber. const ctx = new Context() const adapter = new MockAdapter(['hang']) - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(Invariants) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) @@ -336,11 +325,7 @@ describe('dsh-subagent-spawn', () => { it('a start racing an already-unloading backend cannot begin child creation', async () => { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) diff --git a/packages/support/README.md b/packages/support/README.md index d1bb1883ed..a85fffcdac 100644 --- a/packages/support/README.md +++ b/packages/support/README.md @@ -5,9 +5,10 @@ Packages that exist to serve development, testing, and the examples rather than | Package | Role | ctx key | |---|---|---| | `acp-snapshot/` | ACP snapshot suite kit: subprocess scenario harness + golden normalizers + the `defineAcpSnapshotSuite` factory | (library — imported by example `*.snapshot.ts` suites) | +| `agent-loop-testkit/` | Shared prerequisite mounting for tests that exercise the concrete agent loop | (library — imported by AgentLoop integration tests) | | `invariants/` | Runtime event-contract assertions for development diagnostics | (listens on `session/*`, `agent/*`) | | `loader-smoke/` | Shared real-Loader subprocess harness for keyless example smokes | (library — imported by example e2e suites) | | `llm-replay/` | Record/replay adapter: short-circuits `llm/stream` from a recorded session JSONL (keyless snapshot tests) | (listens on `llm/stream`) | | `subagent-mock/` | Scripted `SubagentProvider` for deterministic seam/tool tests | (registers on `ctx.subagents`) | -`invariants` is development support but has no environment guard: it runs wherever registered, and the default `dsh-agent-spine-demo` bundle mounts it unconditionally. `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the snapshot tier's harness/normalizer/suite machinery, while `loader-smoke` owns the parallel stdio/Loader process boundary used by keyless example e2e suites. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers. +`invariants` is development support but has no environment guard: it runs wherever registered, and the default `dsh-agent-spine-demo` bundle mounts it unconditionally. `agent-loop-testkit` centralizes the mandatory service spine for hand-built AgentLoop tests without owning their loop or scenario. `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the snapshot tier's harness/normalizer/suite machinery, while `loader-smoke` owns the parallel stdio/Loader process boundary used by keyless example e2e suites. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers. diff --git a/packages/support/agent-loop-testkit/README.md b/packages/support/agent-loop-testkit/README.md new file mode 100644 index 0000000000..350a8643e1 --- /dev/null +++ b/packages/support/agent-loop-testkit/README.md @@ -0,0 +1,27 @@ +# `@deepseek-ai/dsh-agent-loop-testkit` + +Shared prerequisite mounting for tests that exercise the concrete `AgentLoop`. `mountAgentLoopTestDependencies(ctx, options?)` installs the LLM, session, system-prompt, tool, and agent services in dependency order, then returns before the loop is mounted. + +The caller registers adapters and optional plugins, mounts `AgentLoop` with the configuration under test, and disposes its own Context. System-prompt and tool-registry configuration can be forwarded through `options`; the helper does not provide test defaults beyond those owned by the services. A plugin-load failure rejects the helper call, while services activated earlier in the sequence remain owned by the caller's Context. + +```ts +import { Context } from 'cordis' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' + +const ctx = new Context() + +await mountAgentLoopTestDependencies(ctx) +// Register the test adapter and any optional plugins here. +await ctx.plugin(AgentLoop, { agents: [] }) +``` + +Tests of injection failures, partial topology, service load order, or service teardown mount their dependencies directly instead of using this helper. + +## Model Experience + +None, as this test-only composition helper neither drives nor modifies model requests. + +## Known Limitations and Deferred Work + +- **Only the mandatory prerequisite spine is shared** — adapters, optional plugins, `AgentLoop`, agents, and Context teardown remain caller-owned so scenario-specific ordering stays visible. diff --git a/packages/support/agent-loop-testkit/package.json b/packages/support/agent-loop-testkit/package.json new file mode 100644 index 0000000000..423bd3e80d --- /dev/null +++ b/packages/support/agent-loop-testkit/package.json @@ -0,0 +1,41 @@ +{ + "name": "@deepseek-ai/dsh-agent-loop-testkit", + "description": "Shared prerequisite mounting for tests that exercise the concrete agent loop", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@deepseek-ai/dsh-agent": "^0.0.1", + "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", + "@deepseek-ai/dsh-system-prompt": "^0.0.1", + "@deepseek-ai/dsh-tools": "^0.0.1", + "cordis": "^4.0.0-rc.7" + }, + "devDependencies": { + "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", + "@deepseek-ai/dsh-system-prompt": "workspace:^", + "@deepseek-ai/dsh-tools": "workspace:^", + "cordis": "^4.0.0-rc.7" + } +} diff --git a/packages/support/agent-loop-testkit/src/index.ts b/packages/support/agent-loop-testkit/src/index.ts new file mode 100644 index 0000000000..c7b0cb7304 --- /dev/null +++ b/packages/support/agent-loop-testkit/src/index.ts @@ -0,0 +1,46 @@ +/** + * Shared mounting for the services required before tests load the concrete + * agent loop. The caller retains ownership of the context, loop, adapters, + * optional plugins, and teardown. + * @module @deepseek-ai/dsh-agent-loop-testkit + */ + +import type { Context } from 'cordis' +import AgentRegistry from '@deepseek-ai/dsh-agent' +import LlmService from '@deepseek-ai/dsh-llm' +import SessionStore from '@deepseek-ai/dsh-session' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry from '@deepseek-ai/dsh-tools' +import type { Config as ToolRegistryConfig } from '@deepseek-ai/dsh-tools' + +/** Configuration forwarded to the prerequisite service plugins. */ +export interface AgentLoopTestDependenciesOptions { + /** Configuration for the system-prompt registry. */ + readonly systemPrompt?: SystemPromptConfig + /** Configuration for the tool registry. */ + readonly tools?: ToolRegistryConfig +} + +/** + * Mount the standard prerequisite services for an AgentLoop test. + * + * The function deliberately does not mount AgentLoop or register an adapter, + * so tests retain control of load order and the topology under test. The + * context owns every mounted service and remains responsible for disposal. A + * plugin-load failure rejects the promise; services activated earlier in the + * sequence remain context-owned and unwind with that context. + * @param ctx - test context that owns the mounted services. + * @param options - optional service configuration forwarded without mutation. + * @returns after every prerequisite service has activated. + */ +export async function mountAgentLoopTestDependencies( + ctx: Context, + options: AgentLoopTestDependenciesOptions = {}, +): Promise { + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt, options.systemPrompt ?? {}) + await ctx.plugin(ToolRegistry, options.tools ?? {}) + await ctx.plugin(AgentRegistry) +} diff --git a/packages/support/agent-loop-testkit/tests/agent-loop-testkit.spec.ts b/packages/support/agent-loop-testkit/tests/agent-loop-testkit.spec.ts new file mode 100644 index 0000000000..aa125b561f --- /dev/null +++ b/packages/support/agent-loop-testkit/tests/agent-loop-testkit.spec.ts @@ -0,0 +1,20 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' +import { renderPrompt } from '@deepseek-ai/dsh-system-prompt' +import { mountAgentLoopTestDependencies } from '../src/index.ts' + +describe('dsh-agent-loop-testkit', () => { + it('mounts a configurable prerequisite spine that can activate AgentLoop', async () => { + const ctx = new Context() + await mountAgentLoopTestDependencies(ctx, { + systemPrompt: { persona: 'Test persona.' }, + tools: { mode: 'native' }, + }) + + expect(renderPrompt(await ctx.systemPrompt.assemble())).toContain('Test persona.') + await expect(ctx.plugin(AgentLoop, { agents: [] })).resolves.toBeDefined() + + await ctx.fiber.dispose() + }) +}) diff --git a/packages/support/agent-loop-testkit/tsconfig.json b/packages/support/agent-loop-testkit/tsconfig.json new file mode 100644 index 0000000000..5e5b3c47f2 --- /dev/null +++ b/packages/support/agent-loop-testkit/tsconfig.json @@ -0,0 +1,33 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../../vendor/cosmokit" + }, + { + "path": "../../../vendor/cordis" + }, + { + "path": "../../core/agent" + }, + { + "path": "../../llm/llm" + }, + { + "path": "../../core/session" + }, + { + "path": "../../core/system-prompt" + }, + { + "path": "../../core/tools" + } + ] +} diff --git a/packages/todo/tool-todo/package.json b/packages/todo/tool-todo/package.json index 9ff69d7c76..bab0f1230c 100644 --- a/packages/todo/tool-todo/package.json +++ b/packages/todo/tool-todo/package.json @@ -30,6 +30,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", diff --git a/packages/todo/tool-todo/tests/integration.spec.ts b/packages/todo/tool-todo/tests/integration.spec.ts index 739367a699..c13a0f76f8 100644 --- a/packages/todo/tool-todo/tests/integration.spec.ts +++ b/packages/todo/tool-todo/tests/integration.spec.ts @@ -1,12 +1,9 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -18,11 +15,7 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent */ async function harness(adapter: MockAdapter): Promise { const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(ToolTodo) ctx.llm.registerAdapter(['mock'], adapter) diff --git a/packages/ui/acp/package.json b/packages/ui/acp/package.json index 71efc51a07..0a28c4f6da 100644 --- a/packages/ui/acp/package.json +++ b/packages/ui/acp/package.json @@ -42,6 +42,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-bash": "workspace:^", "@deepseek-ai/dsh-bash-local": "workspace:^", "@deepseek-ai/dsh-fs-local": "workspace:^", diff --git a/packages/ui/acp/tests/harness.ts b/packages/ui/acp/tests/harness.ts index 440120943f..f8e2e37627 100644 --- a/packages/ui/acp/tests/harness.ts +++ b/packages/ui/acp/tests/harness.ts @@ -5,13 +5,10 @@ */ import { Context } from 'cordis' -import LlmService, { CallId, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm' +import { CallId, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm' import { LlmAdapter } from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' import AgentLoop from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import LocalFileSystem from '@deepseek-ai/dsh-fs-local' @@ -188,11 +185,9 @@ export async function makeBridgeHarness(options: { const adapter = new MockAdapter(options.script ?? []) const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt, { persona: options.persona ?? '' }) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx, { + systemPrompt: { persona: options.persona ?? '' }, + }) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SessionPersistenceJsonl, { root: options.storageDir }) await ctx.plugin(UserInteractionService) diff --git a/packages/workflow/workflow-workerthread/package.json b/packages/workflow/workflow-workerthread/package.json index 485e252c97..1cd6e07e17 100644 --- a/packages/workflow/workflow-workerthread/package.json +++ b/packages/workflow/workflow-workerthread/package.json @@ -42,6 +42,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", + "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-brand": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", diff --git a/packages/workflow/workflow-workerthread/tests/integration.spec.ts b/packages/workflow/workflow-workerthread/tests/integration.spec.ts index 0e1727f877..7b30f13f4f 100644 --- a/packages/workflow/workflow-workerthread/tests/integration.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/integration.spec.ts @@ -1,11 +1,8 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' -import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop from '@deepseek-ai/dsh-agent-loop' +import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' import * as spawn from '@deepseek-ai/dsh-subagent-spawn' @@ -26,11 +23,7 @@ type Script = ConstructorParameters[0] async function setup(script: Script) { const ctx = new Context() const adapter = new MockAdapter(script) - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) + await mountAgentLoopTestDependencies(ctx) await ctx.plugin(Invariants) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index b1a3a78030..7b12699ad8 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -155,6 +155,9 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop + '@deepseek-ai/dsh-agent-loop-testkit': + specifier: workspace:^ + version: link:../../support/agent-loop-testkit '@deepseek-ai/dsh-bash': specifier: workspace:^ version: link:../bash @@ -228,6 +231,9 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop + '@deepseek-ai/dsh-agent-loop-testkit': + specifier: workspace:^ + version: link:../../support/agent-loop-testkit '@deepseek-ai/dsh-compact': specifier: workspace:^ version: link:../compact @@ -240,9 +246,6 @@ importers: '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session - '@deepseek-ai/dsh-system-prompt': - specifier: workspace:^ - version: link:../../core/system-prompt '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools @@ -262,6 +265,9 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop + '@deepseek-ai/dsh-agent-loop-testkit': + specifier: workspace:^ + version: link:../../support/agent-loop-testkit '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm @@ -296,6 +302,9 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop + '@deepseek-ai/dsh-agent-loop-testkit': + specifier: workspace:^ + version: link:../../support/agent-loop-testkit '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm @@ -648,6 +657,9 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop + '@deepseek-ai/dsh-agent-loop-testkit': + specifier: workspace:^ + version: link:../../support/agent-loop-testkit '@deepseek-ai/dsh-fs': specifier: workspace:^ version: link:../fs @@ -688,15 +700,15 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop + '@deepseek-ai/dsh-agent-loop-testkit': + specifier: workspace:^ + version: link:../../support/agent-loop-testkit '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session - '@deepseek-ai/dsh-system-prompt': - specifier: workspace:^ - version: link:../../core/system-prompt '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools @@ -728,6 +740,9 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop + '@deepseek-ai/dsh-agent-loop-testkit': + specifier: workspace:^ + version: link:../../support/agent-loop-testkit '@deepseek-ai/dsh-bash': specifier: workspace:^ version: link:../../bash/bash @@ -746,9 +761,6 @@ importers: '@deepseek-ai/dsh-subagent': specifier: workspace:^ version: link:../../subagent/subagent - '@deepseek-ai/dsh-system-prompt': - specifier: workspace:^ - version: link:../../core/system-prompt '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools @@ -768,6 +780,9 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop + '@deepseek-ai/dsh-agent-loop-testkit': + specifier: workspace:^ + version: link:../../support/agent-loop-testkit '@deepseek-ai/dsh-bash': specifier: workspace:^ version: link:../../bash/bash @@ -783,9 +798,6 @@ importers: '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session - '@deepseek-ai/dsh-system-prompt': - specifier: workspace:^ - version: link:../../core/system-prompt '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools @@ -1152,6 +1164,9 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop + '@deepseek-ai/dsh-agent-loop-testkit': + specifier: workspace:^ + version: link:../../support/agent-loop-testkit '@deepseek-ai/dsh-invariants': specifier: workspace:^ version: link:../../support/invariants @@ -1170,12 +1185,6 @@ importers: '@deepseek-ai/dsh-subagent-spawn': specifier: workspace:^ version: link:../subagent-spawn - '@deepseek-ai/dsh-system-prompt': - specifier: workspace:^ - version: link:../../core/system-prompt - '@deepseek-ai/dsh-tools': - specifier: workspace:^ - version: link:../../core/tools cordis: specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) @@ -1188,6 +1197,9 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop + '@deepseek-ai/dsh-agent-loop-testkit': + specifier: workspace:^ + version: link:../../support/agent-loop-testkit '@deepseek-ai/dsh-invariants': specifier: workspace:^ version: link:../../support/invariants @@ -1225,6 +1237,9 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop + '@deepseek-ai/dsh-agent-loop-testkit': + specifier: workspace:^ + version: link:../../support/agent-loop-testkit '@deepseek-ai/dsh-bash-local': specifier: workspace:^ version: link:../../bash/bash-local @@ -1246,18 +1261,12 @@ importers: '@deepseek-ai/dsh-subagent-inprocess': specifier: workspace:^ version: link:../subagent-inprocess - '@deepseek-ai/dsh-system-prompt': - specifier: workspace:^ - version: link:../../core/system-prompt '@deepseek-ai/dsh-tool-bash': specifier: workspace:^ version: link:../../bash/tool-bash '@deepseek-ai/dsh-tool-subagent': specifier: workspace:^ version: link:../tool-subagent - '@deepseek-ai/dsh-tools': - specifier: workspace:^ - version: link:../../core/tools cordis: specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) @@ -1321,6 +1330,30 @@ importers: specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) + packages/support/agent-loop-testkit: + devDependencies: + '@deepseek-ai/dsh-agent': + specifier: workspace:^ + version: link:../../core/agent + '@deepseek-ai/dsh-agent-loop': + specifier: workspace:^ + version: link:../../core/agent-loop + '@deepseek-ai/dsh-llm': + specifier: workspace:^ + version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + '@deepseek-ai/dsh-system-prompt': + specifier: workspace:^ + version: link:../../core/system-prompt + '@deepseek-ai/dsh-tools': + specifier: workspace:^ + version: link:../../core/tools + cordis: + specifier: ^4.0.0-rc.7 + version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) + packages/support/invariants: devDependencies: '@deepseek-ai/dsh-agent': @@ -1464,6 +1497,9 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop + '@deepseek-ai/dsh-agent-loop-testkit': + specifier: workspace:^ + version: link:../../support/agent-loop-testkit '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm @@ -1498,6 +1534,9 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop + '@deepseek-ai/dsh-agent-loop-testkit': + specifier: workspace:^ + version: link:../../support/agent-loop-testkit '@deepseek-ai/dsh-bash': specifier: workspace:^ version: link:../../bash/bash @@ -1894,6 +1933,9 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop + '@deepseek-ai/dsh-agent-loop-testkit': + specifier: workspace:^ + version: link:../../support/agent-loop-testkit '@deepseek-ai/dsh-brand': specifier: workspace:^ version: link:../../util/brand diff --git a/scripts/verify-package-readme-model-experience.ts b/scripts/verify-package-readme-model-experience.ts index 8220324210..bfcb6f684e 100644 --- a/scripts/verify-package-readme-model-experience.ts +++ b/scripts/verify-package-readme-model-experience.ts @@ -57,6 +57,7 @@ const SENTENCE_MODEL_EXPERIENCE: Readonly> = { 'packages/subagent/subagent': { kind: 'indirect', reason: 'The provider registry delegates parent-model rendering to dsh-tool-subagent.' }, 'packages/subagent/subagent-subprocess': { kind: 'indirect', reason: 'Only process-based subagent backends compose a child model request.' }, 'packages/support/acp-snapshot': { kind: 'none', reason: 'The test harness observes and normalizes transcripts without changing live requests.' }, + 'packages/support/agent-loop-testkit': { kind: 'none', reason: 'The test helper mounts services but neither drives nor modifies model requests.' }, 'packages/support/invariants': { kind: 'none', reason: 'The observer validates requests but never rewrites their context.' }, 'packages/support/loader-smoke': { kind: 'none', reason: 'The test harness observes child-process streams without changing live requests.' }, 'packages/support/llm-replay': { kind: 'none', reason: 'The keyless adapter invokes no provider model.' }, diff --git a/tsconfig.build.json b/tsconfig.build.json index 3a57169005..edb1479088 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -56,6 +56,7 @@ { "path": "./packages/web/tool-web" }, { "path": "./packages/timeout/timeout-policy" }, { "path": "./packages/support/invariants" }, + { "path": "./packages/support/agent-loop-testkit" }, { "path": "./packages/ui/acp" }, { "path": "./packages/examples/acp-demo" }, { "path": "./packages/ui/app-boot" }, diff --git a/tsconfig.json b/tsconfig.json index 6585a987d6..5a09464252 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -67,6 +67,7 @@ { "path": "./packages/web/tool-web" }, { "path": "./packages/timeout/timeout-policy" }, { "path": "./packages/support/invariants" }, + { "path": "./packages/support/agent-loop-testkit" }, { "path": "./packages/ui/acp" }, { "path": "./packages/examples/acp-demo" }, { "path": "./packages/ui/app-boot" }, From 46e63a004c5be02841e5c9047870d3c4c2b3f47a Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 17:47:51 +0800 Subject: [PATCH 215/359] time-context: durable per-step history (round 1) --- docs/config-catalog.md | 8 +- docs/event-producer-consumer.md | 2 +- docs/module-graph.md | 3 +- docs/rfc/INDEX.md | 1 + .../2026-07-14-time-context-plugin.i18n.yaml | 4 +- .../feature/2026-07-14-time-context-plugin.md | 2 + .../2026-07-14-time-context-plugin.zh.md | 2 + ...16-durable-per-step-time-context.i18n.yaml | 6 + ...026-07-16-durable-per-step-time-context.md | 68 ++++ ...-07-16-durable-per-step-time-context.zh.md | 68 ++++ packages/context/README.md | 2 +- packages/context/time-context/README.md | 40 +- packages/context/time-context/package.json | 3 +- packages/context/time-context/src/index.ts | 165 ++++---- .../time-context/tests/time-context.e2e.ts | 43 ++- .../time-context/tests/time-context.spec.ts | 357 ++++++++---------- packages/context/time-context/tsconfig.json | 2 +- 17 files changed, 432 insertions(+), 344 deletions(-) create mode 100644 docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.i18n.yaml create mode 100644 docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.md create mode 100644 docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.zh.md diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 91fe7c6497..4dc1e1346b 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -867,19 +867,17 @@ Source: [`packages/core/system-prompt/src/index.ts:143`](../packages/core/system ## `@deepseek-ai/dsh-time-context` -Requires: `systemPrompt` +Requires: `agents` ```ts config-catalog -/** Request-time clock formatting and refresh policy. Invalid values fail plugin load. */ +/** Request-time clock formatting. Invalid values fail plugin load. */ export interface Config { /** IANA time zone used for the rendered timestamp. Omit to resolve the Node process's system zone at plugin load. */ timeZone?: string - /** Maximum age of a reading within one turn, in milliseconds (default 60,000; `0` refreshes every step). */ - refreshIntervalMs?: number } ``` -Source: [`packages/context/time-context/src/index.ts:22`](../packages/context/time-context/src/index.ts) +Source: [`packages/context/time-context/src/index.ts:20`](../packages/context/time-context/src/index.ts) ## `@deepseek-ai/dsh-tool-bash` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index d8c924b24d..1b2923e63e 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -10,7 +10,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:139`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:148`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:283`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:202`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:202`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`time-context`](../packages/context/time-context), [`user-approval`](../packages/ui/user-approval) | | `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:212`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | | `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:167`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:224`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | diff --git a/docs/module-graph.md b/docs/module-graph.md index 82763bdc55..dc35d8c88b 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -203,7 +203,6 @@ flowchart TD pkg_user_interaction --> pkg_agent pkg_user_interaction --> pkg_llm pkg_time_context --> pkg_agent - pkg_time_context --> pkg_system_prompt pkg_tasks --> pkg_agent pkg_tasks --> pkg_brand pkg_tasks --> pkg_session @@ -418,7 +417,7 @@ flowchart TD | [`invariants`](../packages/support/invariants) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session) | | [`user-approval`](../packages/ui/user-approval) | `ui` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) | | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) | -| [`time-context`](../packages/context/time-context) | `context` | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt) | +| [`time-context`](../packages/context/time-context) | `context` | [`agent`](../packages/core/agent) | | [`tasks`](../packages/tasks/tasks) | `tasks` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) | | [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) | | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index a60579ef4c..f298077d94 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -81,6 +81,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Exact session query service](implemented/feature/2026-07-10-session-query-service.md) | 2026-07-10 | | [Configure subagent persona, tool visibility, and depth](implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) | 2026-07-12 | | [Optional time-context plugin](implemented/feature/2026-07-14-time-context-plugin.md) | 2026-07-14 | +| [Durable per-step time context](implemented/feature/2026-07-16-durable-per-step-time-context.md) | 2026-07-16 | ### Simplification diff --git a/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.i18n.yaml b/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.i18n.yaml index cb5d12c562..06f0c510e6 100644 --- a/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.i18n.yaml +++ b/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-14-time-context-plugin.md: 105bf53550f087fdefb1e6fe0ec493f8628d3e18 -2026-07-14-time-context-plugin.zh.md: 60e9004b1453e75e1bcd84870ad7f18d200a95d8 +2026-07-14-time-context-plugin.md: aa24c6246718cfe0bb3ed63d0791cf890514d9fe +2026-07-14-time-context-plugin.zh.md: c077cc5a38d7c559b4f5101450a1a8268a204f1c diff --git a/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.md b/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.md index 105bf53550..aa24c62467 100644 --- a/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.md +++ b/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.md @@ -6,6 +6,8 @@ English | [中文](2026-07-14-time-context-plugin.zh.md) ## Problem +The dynamic system-prompt storage and refresh decision in this record is superseded by [Durable per-step time context](2026-07-16-durable-per-step-time-context.md). The opt-in package, zoned formatting, and validation remain; the follow-up owns the current model-visible and durability contract. + An agent request has no live clock unless a deployment puts one in prompt text or gives the model a query tool. Static text becomes stale, while a tool call adds overhead to ordinary reasoning about dates, deadlines, or idle time. Without elapsed time, the model cannot distinguish an immediate follow-up from one sent hours after the preceding message. Prompt assembly can derive both facts per step from durable session timestamps, and request-header logging can record the exact rendered value. Accumulating stale readings in conversation history or waking idle agents would violate the existing request lifecycle. diff --git a/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.zh.md b/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.zh.md index 60e9004b14..c077cc5a38 100644 --- a/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.zh.md +++ b/docs/rfc/implemented/feature/2026-07-14-time-context-plugin.zh.md @@ -6,6 +6,8 @@ Status: implemented ## 问题 +本记录中的动态系统提示词存储和刷新决策已由[持久的逐步骤时间上下文](2026-07-16-durable-per-step-time-context.md)取代。选择加入式 package（包）、分区时间格式和校验仍然保留；后续 RFC 负责当前的模型可见与持久性契约。 + 如果部署方既未在提示词中提供时钟，也未给模型提供查询工具，agent（智能体）请求就无法获得实时准确的时间。静态文本会变得陈旧，而对于日期、截止时间或闲置时长等常规推理，调用工具会增加开销。缺少已经过去的时长时，模型无法区分紧接着发送的消息与上一条消息几小时后才发送的消息。 提示词组装流程可以在每个步骤中根据持久会话时间戳派生这两项信息，请求头日志则可以记录实际渲染的确切值。在会话历史中累积陈旧读数或唤醒空闲 agent 都会违反现有请求生命周期。 diff --git a/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.i18n.yaml b/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.i18n.yaml new file mode 100644 index 0000000000..b8d7b45e9b --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-16-durable-per-step-time-context.md: eac975fd2a85d18d8323ba7651995516226ab887 +2026-07-16-durable-per-step-time-context.zh.md: fe38239729a00f71138ad3b37ce2c1d6f7895a60 diff --git a/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.md b/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.md new file mode 100644 index 0000000000..eac975fd2a --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.md @@ -0,0 +1,68 @@ +# RFC: Durable per-step time context + +Status: implemented + +English | [中文](2026-07-16-durable-per-step-time-context.zh.md) + +## Problem + +A request-only clock can tell the model the current time, but replacing that value in the system prompt removes the evidence behind earlier time-sensitive reasoning. Multi-step turns need each request to see its own reading and the readings that shaped preceding steps. The request must remain reconstructable after restart, and automatic compaction must account for the same timing context the model receives. + +Refresh intervals make the displayed time depend on process-local cache state rather than the durable session. They also let multiple steps share a reading even though each step is a distinct model request. + +## Decision + +`@deepseek-ai/dsh-time-context` is an opt-in function plugin in `packages/context/time-context/`. It registers a prepended `agent/pre-step` listener and calls `agent.inject()` once for every step whose signal is not already aborted. The injected `context/message` carries source `{ kind: 'plugin', plugin: 'time-context' }` and append surface metadata. + +The listener records context before the matching `step/start`. Its prepended registration runs before ordinary automatic compaction listeners, so pressure estimation and any resulting surface rewrite observe the pending step's time context. The message then enters the history snapshot used by that step. + +The plugin has one optional config key, `timeZone`. An omitted value resolves the Node process's IANA zone once at plugin load; an explicit value is validated by `Intl.DateTimeFormat`. The timestamp includes the numeric UTC offset and resolved IANA zone. There is no refresh interval or timer because every step records a reading. + +### Text and elapsed baselines + +The first step in a turn receives: + +```text +Time recorded before turn , step 1: +Elapsed since the preceding model-visible message: . +``` + +The baseline is the latest preceding user, assistant, tool-result, context, or steering message. This includes the accepted prompt that opened an ordinary message turn. If no model-visible message exists, the duration is `unavailable`. + +Later steps receive: + +```text +Time recorded before turn , step : +Elapsed since the preceding step context: . +``` + +Their baseline is the durable event timestamp of the preceding time-context message in the same turn. Duration formatting uses compact whole-second units and clamps backward wall-clock movement to zero. The explicit turn and step make every retained reading historically attributable after later turns append more context. + +### Durability and request reconstruction + +Each reading remains a normal surface node until compaction shadows it. A later request therefore sees the cumulative unshadowed readings that affected earlier steps, rather than a system-prompt value rewritten in place. + +The plugin contributes nothing to system-prompt assembly. `request/header` and `request/header-delta` contain no time-context text; request reconstruction obtains the reading from the durable surface prefix at the matching `step/start`. The plugin depends on the agent registry for its lifecycle listener and does not require the system-prompt service at runtime. + +## Testing + +Unit and real-loop tests pin formatting, both elapsed baselines, backward-clock clamping, time-zone validation, aborted-signal behavior, listener disposal, source and surface metadata, ordering before `step/start` and ordinary pre-step listeners, exactly one event per transmitted request, cumulative multi-step visibility, and absence from request headers. A keyless subprocess e2e boots the real Loader and stdio app, drives two turns, and verifies the persisted context events externally. + +## Supersedes + +This decision supersedes the dynamic system-prompt storage and refresh policy in [Optional time-context plugin](2026-07-14-time-context-plugin.md). It keeps the package location, opt-in deployment stance, timestamp formatting, process-zone default, and load-time validation. Durable per-step history replaces the `context:time` prompt section, refresh cache, `refreshIntervalMs`, and request-header deltas. + +## Alternatives considered + +- **Keep the dynamic system-prompt section and refresh cache** — rejected because replacement erases earlier readings, cache state is not replayable, and a frozen request envelope would make the value stale for an entire loop instance. +- **Replace the preceding context surface node** — rejected because replacement preserves the old node's position or shadows intervening conversation; neither represents when the new reading became visible. +- **Inject from a background timer** — rejected because idle time has no pending request to consume the value, and timer-driven injection would create durable turns solely to report time passing. +- **Expose time only through a tool** — rejected because ordinary temporal reasoning would require an avoidable tool round trip and would not guarantee a reading before every step. +- **Use `agent/session-prefix`** — rejected because one loop-instance prefix cannot represent distinct step timestamps and does not accumulate historically attributable readings. + +## Consequences + +- Every opted-in model request receives a fresh, reconstructable time reading before the step opens. +- Timing context grows by one two-line message per step until compaction shadows older surface nodes; historical truth costs more tokens than a replace-in-place system section. +- The first-step duration normally measures from the prompt that opened the turn, while later-step durations measure model and tool processing since the preceding step context. +- An omitted `timeZone` still reflects the deployment process rather than a remote user, and elapsed time still uses durable harness append boundaries rather than client-origin timestamps. diff --git a/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.zh.md b/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.zh.md new file mode 100644 index 0000000000..fe38239729 --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.zh.md @@ -0,0 +1,68 @@ +# RFC: 持久的逐步骤时间上下文 + +Status: implemented + +[English](2026-07-16-durable-per-step-time-context.md) | 中文 + +## 问题 + +仅存在于请求中的时钟可以告诉模型当前时间，但在系统提示词中替换这个值会移除先前时效性推理所依据的证据。在包含多个步骤的轮次中，每个请求既需要看到自己的读数，也需要看到影响先前步骤的读数。系统必须能在重启后重建请求，自动压缩（compaction）也必须核算模型实际收到的同一份时间上下文。 + +刷新间隔使显示的时间取决于进程本地缓存状态，而不是持久会话。它还允许多个步骤共用同一个读数，即使每个步骤对应不同的模型请求。 + +## 决策 + +`@deepseek-ai/dsh-time-context` 是位于 `packages/context/time-context/`、需要显式启用的函数插件。它注册一个前置的 `agent/pre-step` 监听器，并为信号尚未取消的每个步骤调用一次 `agent.inject()`。注入的 `context/message` 携带来源 `{ kind: 'plugin', plugin: 'time-context' }` 和追加表层元数据。 + +监听器在匹配的 `step/start` 之前记录上下文。它采用前置注册，因此先于普通自动压缩监听器运行，使压力估算和由此产生的表层重写都能观察到待执行步骤的时间上下文。随后，该消息进入该步骤使用的历史快照。 + +插件只有一个可选配置键 `timeZone`。省略时，插件在加载时解析一次 Node 进程的 IANA 时区；显式值由 `Intl.DateTimeFormat` 校验。时间戳包含数字 UTC 偏移和解析后的 IANA 时区。由于每个步骤都会记录读数，因此插件没有刷新间隔或计时器。 + +### 文本与时长基线 + +轮次中的第一个步骤收到： + +```text +Time recorded before turn , step 1: +Elapsed since the preceding model-visible message: . +``` + +基线是前一条用户消息、助手消息、工具结果、上下文消息或 steering（中途引导）消息。对于普通消息轮次，这包括开启轮次的已接受提示词。如果不存在模型可见消息，时长为 `unavailable`。 + +后续步骤收到： + +```text +Time recorded before turn , step : +Elapsed since the preceding step context: . +``` + +其基线是同一轮次中上一条时间上下文消息的持久事件时间戳。时长采用紧凑的整秒单位，并在系统挂钟向后移动时钳制为零。显式的轮次号和步骤号使每个保留的读数在后续轮次追加更多上下文后仍可按历史归属。 + +### 持久性与请求重建 + +每个读数都作为普通表层节点保留，直至压缩将其隐藏。因此，后续请求会看到影响先前步骤且尚未被隐藏的累计读数，而不是一个被原地改写的系统提示词值。 + +插件不向系统提示词组装贡献任何内容。`request/header` 和 `request/header-delta` 不包含时间上下文文本；请求重建从匹配 `step/start` 时的持久表层前缀取得读数。插件通过 agent 注册表使用生命周期监听器，运行时不需要系统提示词服务。 + +## 测试 + +单元测试和真实 agent loop（智能体循环）测试固定格式化、两种时长基线、挂钟后退钳制、时区校验、已取消信号行为、监听器 dispose（资源释放）、来源与表层元数据、相对于 `step/start` 和普通预步骤监听器的顺序、每个已发送请求恰好一个事件、多步骤累计可见性，以及请求头中不存在时间上下文。无密钥子进程 e2e 测试通过真实 Loader 和 stdio 应用启动，驱动两个轮次，并从外部校验持久化的上下文事件。 + +## 取代的决策 + +本决策取代[可选时间上下文插件](2026-07-14-time-context-plugin.md)中的动态系统提示词存储和刷新策略。它保留包位置、选择加入式部署、时间戳格式、进程时区默认值和加载时校验。持久的逐步骤历史取代 `context:time` 提示词区段、刷新缓存、`refreshIntervalMs` 和请求头增量。 + +## 考虑过的替代方案 + +- **保留动态系统提示词区段和刷新缓存**——不予采纳，因为替换会抹去先前读数，缓存状态无法回放，而且冻结的请求内容集合会使该值在整个 agent loop 实例期间保持陈旧。 +- **替换前一条上下文表层节点**——不予采纳，因为替换会保留旧节点的位置或隐藏中间的会话内容；两者都不能表达新读数何时开始可见。 +- **通过后台计时器注入**——不予采纳，因为空闲期间没有待处理请求消费该值，而且计时器驱动的注入会仅为报告时间流逝而创建持久轮次。 +- **只通过工具提供时间**——不予采纳，因为普通时间推理会产生本可避免的工具往返，也不能保证每个步骤之前都有读数。 +- **使用 `agent/session-prefix`**——不予采纳，因为一个 loop 实例前缀无法表示不同的步骤时间戳，也不会累计具有历史归属的读数。 + +## 后果 + +- 选择加入的每个模型请求都会在步骤开始前获得新鲜且可重建的时间读数。 +- 在压缩隐藏旧表层节点之前，时间上下文会按每个步骤一条两行消息的速度增长；与原地替换的系统提示词区段相比，保持历史真实性会消耗更多 token。 +- 第一个步骤的时长通常从开启轮次的提示词起算，后续步骤的时长则反映自上一条步骤上下文以来的模型与工具处理时间。 +- 省略 `timeZone` 时仍采用部署进程而非远程用户的时区，时长仍采用 harness 的持久追加边界而非客户端来源时间戳。 diff --git a/packages/context/README.md b/packages/context/README.md index 0045c6629c..b765f101c4 100644 --- a/packages/context/README.md +++ b/packages/context/README.md @@ -4,4 +4,4 @@ Opt-in plugins that add bounded model-visible request context without defining a | Package | Role | ctx key | |---|---|---| -| `time-context/` | Current time and elapsed-time system-prompt context | (none) | +| `time-context/` | Durable per-step current time and elapsed-time context | (none) | diff --git a/packages/context/time-context/README.md b/packages/context/time-context/README.md index 84d487445b..a5b058b1e3 100644 --- a/packages/context/time-context/README.md +++ b/packages/context/time-context/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-time-context -Opt-in dynamic system-prompt context with the current zoned time and elapsed time since the latest model-visible message before the turn. `dsh-agent-spine-demo` and shipped examples do not mount it. Decision record: [the time-context RFC](../../../docs/rfc/implemented/feature/2026-07-14-time-context-plugin.md). +Opt-in durable context with the current zoned time and elapsed time at every model step. `dsh-agent-spine-demo` and shipped examples do not mount it. Decision record: [the durable time-context RFC](../../../docs/rfc/implemented/feature/2026-07-16-durable-per-step-time-context.md). ## Config @@ -8,36 +8,44 @@ Opt-in dynamic system-prompt context with the current zoned time and elapsed tim - id: time-context name: '@deepseek-ai/dsh-time-context' config: - timeZone: Asia/Shanghai # optional IANA override; omit for the process zone - refreshIntervalMs: 60000 # default; 0 refreshes on every step + timeZone: Asia/Shanghai # optional IANA override; omit for the process zone ``` -When `timeZone` is omitted, the plugin resolves the Node process's system zone once at plugin load. Node honors `TZ`; without that override, the host or container supplies the zone. An explicit `timeZone` must be an IANA identifier and is validated at plugin load. `refreshIntervalMs` must be a non-negative safe integer. Every turn's first request refreshes; later steps reuse the reading until its age reaches the interval. `0` refreshes every step. Refresh occurs only during request assembly and creates no timer work. +When `timeZone` is omitted, the plugin resolves the Node process's system zone once at plugin load. Node honors `TZ`; without that override, the host or container supplies the zone. An explicit `timeZone` must be an IANA identifier and is validated at plugin load. -## Message baseline +## Timing semantics -The duration starts at the latest user, assistant, tool-result, context, or steering message before the current `turn/start`. Every refresh in the turn retains that baseline, so the current prompt does not collapse the interval to approximately zero. The first turn reports that no earlier message exists. The durable clock source is session-event append time, not client send time. +The plugin prepends an `agent/pre-step` listener. Every non-aborted step appends one `context/message` through `agent.inject()` before `step/start` and ordinary automatic compaction, with source `{ kind: 'plugin', plugin: 'time-context' }`. -The loop records the dynamic section in `request/header` / `request/header-delta`. Requests therefore remain reconstructable, carry one timing block, and retain no earlier readings in conversation history. +Step 1 measures from the latest preceding model-visible message, including the prompt that opened the turn. Later steps measure from the preceding time-context event. Both baselines use durable session-event timestamps; backward wall-clock movement clamps elapsed time to zero. A missing first-step baseline reports `unavailable`. + +The time reading stays in derived conversation history until a later compaction shadows it. Request headers and header deltas contain no time-context state, so the durable message plus the matching `step/start` reconstruct each request's reading. ## Model Experience -### Temporal system prompt +### Per-step temporal context -**What the model sees**: Every request in an active turn includes the two lines below. `` is an ISO-shaped local timestamp with numeric offset and IANA zone; `` is compact whole-second units or the first-turn fallback. +**What the model sees**: Before each step, one source-tagged context message containing the two lines below. `` is an ISO-shaped local timestamp with numeric offset and IANA zone; durations use compact whole-second units. -**Token effect**: Fixed two-line cost per request. A refresh replaces the request-header section; prior readings do not accumulate. +**Token effect**: One two-line message accumulates per step until compaction shadows older history. -#### Temporal context section +#### First step ```markdown -Current time: -Time since previous message: . +Time recorded before turn , step 1: +Elapsed since the preceding model-visible message: . +``` + +#### Later steps + +```markdown +Time recorded before turn , step : +Elapsed since the preceding step context: . ``` ## Known Limitations and Deferred Work -- **Request-bound refresh only** — no clock update is emitted while the agent is waiting inside a model call or tool; the next assembled step refreshes once the configured interval has elapsed. -- **Whole-second display** — timestamps and durations omit sub-second precision even when `refreshIntervalMs` is below 1,000. -- **Session-event baseline** — elapsed time starts from the durable append timestamp, not a client transport's original send timestamp. +- **Whole-second display** — timestamps and durations omit sub-second precision even though durable event times retain milliseconds. +- **Session-event baseline** — elapsed time starts from durable append timestamps, not a client transport's original send timestamp. - **Process-local default zone** — omission uses the Node process's `TZ`, host, or container zone captured at plugin load, not a remote user's zone; configure an explicit IANA zone when those differ. +- **History cost between compactions** — one reading remains model-visible for every unshadowed step so prior timing claims stay historically truthful. diff --git a/packages/context/time-context/package.json b/packages/context/time-context/package.json index f319c7a5b1..dac0667c81 100644 --- a/packages/context/time-context/package.json +++ b/packages/context/time-context/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-time-context", - "description": "Opt-in system-prompt context with the current time and elapsed time since the previous message", + "description": "Opt-in durable per-step context with the current time and elapsed time", "version": "0.0.1", "private": true, "type": "module", @@ -26,7 +26,6 @@ }, "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", - "@deepseek-ai/dsh-system-prompt": "^0.0.1", "cordis": "^4.0.0-rc.7" }, "devDependencies": { diff --git a/packages/context/time-context/src/index.ts b/packages/context/time-context/src/index.ts index cccd433811..0478e2e616 100644 --- a/packages/context/time-context/src/index.ts +++ b/packages/context/time-context/src/index.ts @@ -1,8 +1,6 @@ /** - * Opt-in request-time clock context. Active turns receive the current zoned - * time and elapsed time since the preceding model-visible message. The loop - * logs each rendered value as request-header state rather than conversation - * history. + * Opt-in per-step clock context. Every pending model request receives a + * durable, source-attributed time reading in conversation history. * * @module @deepseek-ai/dsh-time-context */ @@ -10,77 +8,27 @@ import type { Context } from 'cordis' import z from 'schemastery' import type { Agent } from '@deepseek-ai/dsh-agent' -import type { AssembleContext } from '@deepseek-ai/dsh-system-prompt' +import type { Message } from '@deepseek-ai/dsh-llm' /** Cordis plugin name used by loader diagnostics. */ export const name = 'time-context' -/** The system-prompt registry that owns the dynamic request section. */ -export const inject = ['systemPrompt'] +/** The agent registry that owns the pre-step lifecycle seam. */ +export const inject = ['agents'] -/** Request-time clock formatting and refresh policy. Invalid values fail plugin load. */ +/** Request-time clock formatting. Invalid values fail plugin load. */ export interface Config { /** IANA time zone used for the rendered timestamp. Omit to resolve the Node process's system zone at plugin load. */ timeZone?: string - /** Maximum age of a reading within one turn, in milliseconds (default 60,000; `0` refreshes every step). */ - refreshIntervalMs?: number } -/** Schemastery validation and defaults for {@link Config}. */ +/** Schemastery validation for {@link Config}. */ export const Config: z = z.object({ timeZone: z.string(), - refreshIntervalMs: z.number().default(60_000), }) -interface OpenTurn { - turn: number - startSeq: number -} - -/** Cached text and the fixed inter-turn baseline used by one agent's open turn. */ -interface RenderState { - turn: number - renderedAt: number - previousMessageTime: number | undefined - text: string -} - type TimestampPart = 'day' | 'hour' | 'minute' | 'month' | 'second' | 'timeZoneName' | 'year' -function openTurn(agent: Agent): OpenTurn | undefined { - for (const event of [...agent.session.events].reverse()) { - switch (event.type) { - case 'turn/end': - return undefined - case 'turn/start': - return { turn: event.data.turn, startSeq: event.seq } - default: - // Merge-extensible session events: only turn boundaries matter here. - break - } - } - return undefined -} - -/** Find the latest model-visible timestamp strictly before one turn boundary. */ -function previousMessageTime(agent: Agent, turnStartSeq: number): number | undefined { - for (const event of [...agent.session.events].reverse()) { - if (event.seq >= turnStartSeq) continue - switch (event.type) { - case 'user/message': - case 'assistant/message': - case 'tool/result': - case 'context/message': - case 'steering/message': - return event.time - default: - // Merge-extensible session events: non-surface records are not messages. - break - } - } - return undefined -} - /** Format an epoch millisecond value as an ISO-shaped timestamp with offset and IANA zone. */ function formatTimestamp(now: number, formatter: Intl.DateTimeFormat, timeZone: string): string { const parts = Object.fromEntries( @@ -107,31 +55,59 @@ function formatDuration(elapsedMs: number): string { return parts.join(' ') } +/** Find the latest model-visible event, excluding this plugin's pending append. */ +function precedingMessageTime(agent: Agent): number | undefined { + for (const event of [...agent.session.events].reverse()) { + switch (event.type) { + case 'user/message': + case 'assistant/message': + case 'tool/result': + case 'context/message': + case 'steering/message': + return event.time + default: + // Merge-extensible session events: non-surface records are not messages. + break + } + } + return undefined +} + +/** Find the preceding time-context event within the open turn. */ +function precedingStepContextTime(agent: Agent, turn: number): number | undefined { + for (const event of [...agent.session.events].reverse()) { + if (event.type === 'turn/start' && event.data.turn === turn) return undefined + if (event.type === 'context/message' + && event.data.source.kind === 'plugin' + && event.data.source.plugin === name) { + return event.time + } + } + return undefined +} + function renderText( now: number, + turn: number, + step: number, previous: number | undefined, formatter: Intl.DateTimeFormat, timeZone: string, ): string { - const elapsed = previous === undefined - ? 'unavailable (no earlier message in this session)' - : formatDuration(now - previous) - return `Current time: ${formatTimestamp(now, formatter, timeZone)}\nTime since previous message: ${elapsed}.` + const elapsed = previous === undefined ? 'unavailable' : formatDuration(now - previous) + const baseline = step === 1 ? 'model-visible message' : 'step context' + return `Time recorded before turn ${turn}, step ${step}: ${formatTimestamp(now, formatter, timeZone)}\n` + + `Elapsed since the preceding ${baseline}: ${elapsed}.` } /** - * Register the request-time clock section for the lifetime of `ctx`. - * @param ctx - plugin context; the section registration is disposed with it. - * @param config - validated time zone and intra-turn refresh interval. - * @throws when the time zone or refresh interval is invalid. + * Register a prepended pre-step listener for the lifetime of `ctx`. + * @param ctx - plugin context; the listener is disposed with it. + * @param config - validated time zone configuration. + * @throws when the configured or process time zone cannot be resolved. */ export function apply(ctx: Context, config: Config): void { const timeZone = config.timeZone - const refreshIntervalMs = config.refreshIntervalMs as number - if (!Number.isSafeInteger(refreshIntervalMs) || refreshIntervalMs < 0) { - throw new Error(`time-context: refreshIntervalMs must be a non-negative safe integer, got ${refreshIntervalMs}`) - } - let formatter: Intl.DateTimeFormat try { formatter = new Intl.DateTimeFormat('en-US', { @@ -152,32 +128,23 @@ export function apply(ctx: Context, config: Config): void { throw new Error(message, { cause: error }) } const resolvedTimeZone = formatter.resolvedOptions().timeZone - const states = new WeakMap() - ctx.systemPrompt.section({ - name: 'context:time', - order: 10, - text(context: AssembleContext): string { - const agent = context.agent - if (agent === undefined) return '' - const currentTurn = openTurn(agent) - if (currentTurn === undefined) return '' - - const now = Date.now() - const prior = states.get(agent) - if (prior !== undefined - && prior.turn === currentTurn.turn - && now >= prior.renderedAt - && now - prior.renderedAt < refreshIntervalMs) { - return prior.text - } - - const previous = prior?.turn === currentTurn.turn - ? prior.previousMessageTime - : previousMessageTime(agent, currentTurn.startSeq) - const text = renderText(now, previous, formatter, resolvedTimeZone) - states.set(agent, { turn: currentTurn.turn, renderedAt: now, previousMessageTime: previous, text }) - return text - }, - }) + ctx.on('agent/pre-step', ( + agent: Agent, + turn: number, + step: number, + _fullSystemPrompt: string, + _sessionPrefix: readonly Message[], + signal: AbortSignal, + ) => { + if (signal.aborted) return + const now = Date.now() + const previous = step === 1 + ? precedingMessageTime(agent) + : precedingStepContextTime(agent, turn) + agent.inject( + [{ type: 'text', text: renderText(now, turn, step, previous, formatter, resolvedTimeZone) }], + { source: { kind: 'plugin', plugin: name } }, + ) + }, { prepend: true }) } diff --git a/packages/context/time-context/tests/time-context.e2e.ts b/packages/context/time-context/tests/time-context.e2e.ts index f83b451ef7..66966bb439 100644 --- a/packages/context/time-context/tests/time-context.e2e.ts +++ b/packages/context/time-context/tests/time-context.e2e.ts @@ -4,7 +4,7 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' import { afterEach, describe, expect, it } from 'vitest' -import { foldRequestHeader, type SessionEvent } from '@deepseek-ai/dsh-session' +import type { SessionEvent } from '@deepseek-ai/dsh-session' const binScript = fileURLToPath(new URL('../../../examples/stdio-demo/src/bin.ts', import.meta.url)) const configPath = fileURLToPath(new URL('./fixtures/cordis.yml', import.meta.url)) @@ -12,7 +12,8 @@ const repoTsconfig = fileURLToPath(new URL('../../../../tsconfig.json', import.m const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) const PROCESS_TIMEOUT_MS = 30_000 const TEST_TIMEOUT_MS = PROCESS_TIMEOUT_MS + 15_000 -const FIRST_REPLY = 'You said: "first". Try "echo " to see a tool call.' +const FIRST_REPLY = '[main turn 1] You said: "Time recorded before turn 1, step 1:' +const SECOND_REPLY = '[main turn 2] You said: "Time recorded before turn 2, step 1:' let child: ChildProcessWithoutNullStreams | undefined let workdir: string | undefined @@ -60,7 +61,7 @@ async function runTwoTurns(): Promise<{ stdout: string; stderr: string }> { proc.stdout.setEncoding('utf8') proc.stdout.on('data', (chunk: string) => { stdout += chunk - if (!sentSecond && stdout.includes(`${FIRST_REPLY}\n> `)) { + if (!sentSecond && stdout.includes(FIRST_REPLY) && stdout.includes('Try "echo " to see a tool call.\n> ')) { sentSecond = true proc.stdin.end('second\n') } @@ -84,12 +85,12 @@ async function runTwoTurns(): Promise<{ stdout: string; stderr: string }> { } describe('time-context through a real cordis.yml and stdio process', () => { - it('uses the process zone and persists both first-turn and elapsed-time request context', async () => { + it('uses the process zone and persists one ordered context event per request', async () => { const { stdout, stderr } = await runTwoTurns() expect(stderr).not.toContain('UNHANDLED') expect(stdout).toContain('time-context e2e ready.') expect(stdout).toContain(FIRST_REPLY) - expect(stdout).toContain('You said: "second".') + expect(stdout).toContain(SECOND_REPLY) const logs = await jsonlFiles(join(workdir as string, '.sessions')) expect(logs).toHaveLength(1) @@ -97,19 +98,29 @@ describe('time-context through a real cordis.yml and stdio process', () => { const events = lines.slice(1).map(line => JSON.parse(line) as SessionEvent) expect(events.filter(event => event.type === 'turn/end')).toHaveLength(2) - const firstHeader = events.find(event => event.type === 'request/header') - if (firstHeader?.type !== 'request/header') throw new Error('missing initial request/header event') - expect(firstHeader.data.header.system).toMatch( - /Current time: \d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}\+08:00\[Asia\/Shanghai\]/, + const contexts = events.filter(event => event.type === 'context/message') + const starts = events.filter(event => event.type === 'step/start') + expect(contexts).toHaveLength(2) + expect(starts).toHaveLength(2) + for (let index = 0; index < contexts.length; index += 1) { + expect(contexts[index]!.seq).toBeLessThan(starts[index]!.seq) + expect(contexts[index]!.surfaceOp).toBe('append') + expect(contexts[index]!.data.source).toEqual({ kind: 'plugin', plugin: 'time-context' }) + } + const contextText = contexts.map(event => event.data.content + .filter(block => block.type === 'text') + .map(block => block.text) + .join('\n')) + expect(contextText[0]).toMatch( + /Time recorded before turn 1, step 1: \d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}\+08:00\[Asia\/Shanghai\]/, ) - expect(firstHeader.data.header.system).toContain( - 'Time since previous message: unavailable (no earlier message in this session).', + expect(contextText[0]).toMatch( + /Elapsed since the preceding model-visible message: (?:\d+d )?(?:\d+h )?(?:\d+m )?\d+s\./, ) + expect(contextText[1]).toMatch(/Time recorded before turn 2, step 1:/) - const finalSystem = foldRequestHeader(events)?.system - expect(finalSystem).toContain('[Asia/Shanghai]') - expect(finalSystem).toMatch( - /Time since previous message: (?:\d+d )?(?:\d+h )?(?:\d+m )?\d+s\./, - ) + const headers = events.filter(event => event.type === 'request/header' + || event.type === 'request/header-delta') + expect(JSON.stringify(headers)).not.toContain('Time recorded before') }, TEST_TIMEOUT_MS) }) diff --git a/packages/context/time-context/tests/time-context.spec.ts b/packages/context/time-context/tests/time-context.spec.ts index 562b002b68..6df7957fb7 100644 --- a/packages/context/time-context/tests/time-context.spec.ts +++ b/packages/context/time-context/tests/time-context.spec.ts @@ -3,7 +3,7 @@ import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import LlmService, { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' -import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' +import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' @@ -14,6 +14,7 @@ import type { Config } from '@deepseek-ai/dsh-time-context' const BASE = Date.parse('2026-07-14T00:00:00.000Z') const ORIGINAL_TIME_ZONE = process.env['TZ'] +const SIGNAL = new AbortController().signal beforeEach(() => { process.env['TZ'] = 'UTC' @@ -30,18 +31,29 @@ afterEach(() => { async function mount(config: Config = {}) { const ctx = new Context() - await ctx.plugin(SystemPrompt) + await ctx.plugin(AgentRegistry) const fiber = await ctx.plugin(timeContext, config) return { ctx, fiber } } function sessionAgent(session: Session, id = 'agent'): Agent { - return { id: AgentId(id), session } as unknown as Agent -} - -async function sectionText(ctx: Context, agent?: Agent): Promise { - const assembly = await ctx.systemPrompt.assemble(agent === undefined ? {} : { agent }) - return assembly.sections.find(section => section.name === 'context:time')?.text + return { + id: AgentId(id), + options: {}, + session, + status: 'running', + ctx: new Context(), + send() {}, + steer() {}, + inject(content, options) { + session.append('context/message', { + content, + source: options?.source ?? { kind: 'user' }, + }, { surfaceOp: 'append' }) + }, + cancel() {}, + whenIdle: () => Promise.resolve(), + } } function openMessageTurn(session: Session, turn: number): void { @@ -52,6 +64,22 @@ function openMessageTurn(session: Session, turn: number): void { }, { surfaceOp: 'append' }) } +function contextTexts(session: Session): string[] { + return session.events + .filter(event => event.type === 'context/message') + .map(event => event.data.content.find(block => block.type === 'text')?.text ?? '') +} + +async function fire( + ctx: Context, + agent: Agent, + turn: number, + step: number, + signal: AbortSignal = SIGNAL, +): Promise { + await ctx.serial('agent/pre-step', agent, turn, step, '', [], signal) +} + function textResponse(text: string): StreamChunk[] { return [ { type: 'block-start', index: 0, blockType: 'text' }, @@ -100,173 +128,92 @@ async function loopHarness(adapter: ScriptedAdapter, config: Config = {}): Promi return ctx } -describe('temporal section rendering', () => { - it('renders the first turn in UTC with the explicit no-previous-message fallback', async () => { - const { ctx } = await mount() +function requestText(request: GenerateOptions): string { + return request.messages + .flatMap(message => message.content) + .filter(block => block.type === 'text') + .map(block => block.text) + .join('\n') +} + +describe('durable step context', () => { + it('records turn, step, zoned time, and the preceding model-visible message baseline', async () => { + const { ctx } = await mount({ timeZone: 'Asia/Shanghai' }) const session = new Session(SessionId('first')) openMessageTurn(session, 1) - - expect(await sectionText(ctx, sessionAgent(session))).toBe( - 'Current time: 2026-07-14T00:00:00+00:00[UTC]\n' - + 'Time since previous message: unavailable (no earlier message in this session).', - ) - }) - - it('renders a non-UTC numeric offset and all compact duration units', async () => { - const { ctx } = await mount({ timeZone: 'Asia/Shanghai' }) - const session = new Session(SessionId('offset')) - session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - session.append('assistant/message', { - turn: 1, - step: 1, - content: [{ type: 'text', text: 'previous' }], - }, { surfaceOp: 'append' }) - session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) vi.setSystemTime(BASE + 90_061_000) - openMessageTurn(session, 2) - expect(await sectionText(ctx, sessionAgent(session))).toBe( - 'Current time: 2026-07-15T09:01:01+08:00[Asia/Shanghai]\n' - + 'Time since previous message: 1d 1h 1m 1s.', + await fire(ctx, sessionAgent(session), 1, 1) + + expect(contextTexts(session)).toEqual([ + 'Time recorded before turn 1, step 1: 2026-07-15T09:01:01+08:00[Asia/Shanghai]\n' + + 'Elapsed since the preceding model-visible message: 1d 1h 1m 1s.', + ]) + const event = session.events.at(-1) + expect(event?.type).toBe('context/message') + if (event?.type !== 'context/message') throw new Error('missing time context') + expect(event.data.source).toEqual({ kind: 'plugin', plugin: 'time-context' }) + expect(event.surfaceOp).toBe('append') + }) + + it('reports an unavailable first-step baseline when no model-visible message precedes it', async () => { + const { ctx } = await mount() + const session = new Session(SessionId('unavailable')) + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + + await fire(ctx, sessionAgent(session), 1, 1) + + expect(contextTexts(session)[0]).toContain( + 'Elapsed since the preceding model-visible message: unavailable.', ) }) - it('clamps a backward wall-clock adjustment to a zero duration', async () => { + it('uses the preceding durable step-context timestamp after step one', async () => { const { ctx } = await mount() - const session = new Session(SessionId('backward-duration')) - session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - session.append('assistant/message', { - turn: 1, - step: 1, - content: [{ type: 'text', text: 'future by adjusted clock' }], - }, { surfaceOp: 'append' }) - session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + const session = new Session(SessionId('later-step')) + const agent = sessionAgent(session) + openMessageTurn(session, 3) + await fire(ctx, agent, 3, 1) + vi.setSystemTime(BASE + 61_000) + + await fire(ctx, agent, 3, 2) + + expect(contextTexts(session)[1]).toBe( + 'Time recorded before turn 3, step 2: 2026-07-14T00:01:01+00:00[UTC]\n' + + 'Elapsed since the preceding step context: 1m 1s.', + ) + }) + + it('clamps backward wall-clock movement against the preceding context to zero', async () => { + const { ctx } = await mount() + const session = new Session(SessionId('backward')) + const agent = sessionAgent(session) + openMessageTurn(session, 1) + await fire(ctx, agent, 1, 1) vi.setSystemTime(BASE - 5_000) - openMessageTurn(session, 2) - expect(await sectionText(ctx, sessionAgent(session))).toContain('Time since previous message: 0s.') + await fire(ctx, agent, 1, 2) + + expect(contextTexts(session)[1]).toContain('Elapsed since the preceding step context: 0s.') }) - const previousMessageCases = [ - ['user/message', (session: Session): void => { - session.append('user/message', { content: [{ type: 'text', text: 'u' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - }], - ['assistant/message', (session: Session): void => { - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, { surfaceOp: 'append' }) - }], - ['tool/result', (session: Session): void => { - session.append('tool/result', { - turn: 1, - step: 1, - callId: CallId('previous'), - content: [{ type: 'text', text: 'r' }], - isError: false, - }, { surfaceOp: 'append' }) - }], - ['context/message', (session: Session): void => { - session.append('context/message', { - content: [{ type: 'text', text: 'c' }], - source: { kind: 'plugin', plugin: 'test' }, - }, { surfaceOp: 'append' }) - }], - ['steering/message', (session: Session): void => { - session.append('steering/message', { - turn: 1, - content: [{ type: 'text', text: 's' }], - source: { kind: 'user' }, - }, { surfaceOp: 'append' }) - }], - ] as const - - it.each(previousMessageCases)('uses a prior %s as the duration baseline', async (_name, appendPrevious) => { + it('runs before ordinary pre-step listeners and skips an already-aborted step', async () => { const { ctx } = await mount() - const session = new Session(SessionId(`previous-${_name}`)) - session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - appendPrevious(session) - session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - vi.setSystemTime(BASE + 5_000) - openMessageTurn(session, 2) - - expect(await sectionText(ctx, sessionAgent(session))).toContain('Time since previous message: 5s.') - }) - - it('contributes empty text without an active agent turn', async () => { - const { ctx } = await mount() - expect(await sectionText(ctx)).toBe('') - - const empty = sessionAgent(new Session(SessionId('empty'))) - expect(await sectionText(ctx, empty)).toBe('') - - const closedSession = new Session(SessionId('closed')) - openMessageTurn(closedSession, 1) - closedSession.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - expect(await sectionText(ctx, sessionAgent(closedSession))).toBe('') - }) -}) - -describe('refresh policy', () => { - it('reuses within the interval, refreshes at expiry, and refreshes after a backward clock jump', async () => { - const { ctx } = await mount({ refreshIntervalMs: 60_000 }) - const session = new Session(SessionId('interval')) + const session = new Session(SessionId('ordering')) const agent = sessionAgent(session) openMessageTurn(session, 1) + let ordinarySawContext = false + ctx.on('agent/pre-step', (subject) => { + ordinarySawContext = subject.session.events.some(event => event.type === 'context/message') + }) - const first = await sectionText(ctx, agent) - vi.setSystemTime(BASE + 30_000) - expect(await sectionText(ctx, agent)).toBe(first) - vi.setSystemTime(BASE + 60_000) - const expired = await sectionText(ctx, agent) - expect(expired).toContain('2026-07-14T00:01:00+00:00[UTC]') - vi.setSystemTime(BASE + 59_000) - expect(await sectionText(ctx, agent)).toContain('2026-07-14T00:00:59+00:00[UTC]') - }) + await fire(ctx, agent, 1, 1) + const abort = new AbortController() + abort.abort() + await fire(ctx, agent, 1, 2, abort.signal) - it('refreshes every assembly when refreshIntervalMs is zero', async () => { - const { ctx } = await mount({ refreshIntervalMs: 0 }) - const session = new Session(SessionId('every-step')) - const agent = sessionAgent(session) - openMessageTurn(session, 1) - const first = await sectionText(ctx, agent) - vi.setSystemTime(BASE + 1_000) - expect(await sectionText(ctx, agent)).not.toBe(first) - }) - - it('always refreshes for a new turn and keeps the preceding message baseline', async () => { - const { ctx } = await mount({ refreshIntervalMs: 60_000 }) - const session = new Session(SessionId('turn-refresh')) - const agent = sessionAgent(session) - openMessageTurn(session, 1) - const first = await sectionText(ctx, agent) - vi.setSystemTime(BASE + 1_000) - session.append('assistant/message', { - turn: 1, - step: 1, - content: [{ type: 'text', text: 'done' }], - }, { surfaceOp: 'append' }) - session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - vi.setSystemTime(BASE + 2_000) - openMessageTurn(session, 2) - - const second = await sectionText(ctx, agent) - expect(second).not.toBe(first) - expect(second).toContain('Time since previous message: 1s.') - }) - - it('keeps refresh caches independent per agent', async () => { - const { ctx } = await mount({ refreshIntervalMs: 60_000 }) - const sessionA = new Session(SessionId('agent-a')) - const sessionB = new Session(SessionId('agent-b')) - const agentA = sessionAgent(sessionA, 'a') - const agentB = sessionAgent(sessionB, 'b') - openMessageTurn(sessionA, 1) - openMessageTurn(sessionB, 1) - const aFirst = await sectionText(ctx, agentA) - vi.setSystemTime(BASE + 30_000) - const bFirst = await sectionText(ctx, agentB) - vi.setSystemTime(BASE + 40_000) - - expect(await sectionText(ctx, agentA)).toBe(aFirst) - expect(bFirst).toContain('2026-07-14T00:00:30+00:00[UTC]') + expect(ordinarySawContext).toBe(true) + expect(contextTexts(session)).toHaveLength(1) }) }) @@ -278,49 +225,44 @@ describe('configuration and lifecycle', () => { const session = new Session(SessionId('system-zone')) openMessageTurn(session, 1) - expect(await sectionText(ctx, sessionAgent(session))).toContain( - 'Current time: 2026-07-14T08:00:00+08:00[Asia/Shanghai]', + await fire(ctx, sessionAgent(session), 1, 1) + + expect(contextTexts(session)[0]).toContain('2026-07-14T08:00:00+08:00[Asia/Shanghai]') + }) + + it('fails loud for an invalid explicit zone or an unavailable process zone', async () => { + const invalid = new Context() + await invalid.plugin(AgentRegistry) + await expect(invalid.plugin(timeContext, { timeZone: 'Not/A_Real_Zone' })).rejects.toThrow( + /invalid IANA timeZone/, ) - }) - it('fails loud for negative, fractional, unsafe, and invalid-zone config', async () => { - for (const refreshIntervalMs of [-1, 1.5, Number.MAX_SAFE_INTEGER + 1]) { - const ctx = new Context() - await ctx.plugin(SystemPrompt) - await expect(ctx.plugin(timeContext, { refreshIntervalMs })).rejects.toThrow(/non-negative safe integer/) - } - - const ctx = new Context() - await ctx.plugin(SystemPrompt) - await expect(ctx.plugin(timeContext, { timeZone: 'Not/A_Real_Zone' })).rejects.toThrow(/invalid IANA timeZone/) - }) - - it('fails loud when the process system zone cannot be resolved', async () => { vi.spyOn(Intl, 'DateTimeFormat').mockImplementationOnce(() => { throw new RangeError('system zone unavailable') }) - const ctx = new Context() - await ctx.plugin(SystemPrompt) - - await expect(ctx.plugin(timeContext, {})).rejects.toThrow(/failed to resolve the system time zone/) + const unresolved = new Context() + await unresolved.plugin(AgentRegistry) + await expect(unresolved.plugin(timeContext, {})).rejects.toThrow(/failed to resolve the system time zone/) }) - it('removes its section when the plugin fiber disposes', async () => { + it('removes its listener when the plugin fiber disposes', async () => { const { ctx, fiber } = await mount() const session = new Session(SessionId('dispose')) const agent = sessionAgent(session) openMessageTurn(session, 1) - expect(await sectionText(ctx, agent)).toContain('Current time:') + await fire(ctx, agent, 1, 1) await fiber.dispose() - expect(await sectionText(ctx, agent)).toBeUndefined() + await fire(ctx, agent, 1, 2) + + expect(contextTexts(session)).toHaveLength(1) }) }) -describe('real agent-loop request logging', () => { - it('refreshes a long turn in the system prompt and records the header delta without context history', async () => { - const adapter = new ScriptedAdapter([toolCallResponse(), textResponse('done'), textResponse('next turn')]) - const ctx = await loopHarness(adapter, { refreshIntervalMs: 60_000 }) +describe('real agent-loop request history', () => { + it('persists one ordered context per request, accumulates readings, and leaves system headers unchanged', async () => { + const adapter = new ScriptedAdapter([toolCallResponse(), textResponse('done')]) + const ctx = await loopHarness(adapter) ctx.tools.register(defineTool({ name: 'tick', description: 'advance fake time', @@ -334,38 +276,55 @@ describe('real agent-loop request logging', () => { agent.send([{ type: 'text', text: 'start' }]) await agent.whenIdle() - expect(adapter.requests).toHaveLength(2) - expect(adapter.requests[0]!.system).toContain('2026-07-14T00:00:00+00:00[UTC]') - expect(adapter.requests[1]!.system).toContain('2026-07-14T00:01:01+00:00[UTC]') - expect(agent.session.events.some(event => event.type === 'context/message')).toBe(false) - expect(agent.session.events.filter(event => event.type === 'request/header-delta')).toHaveLength(1) - expect(foldRequestHeader(agent.session.events)?.system).toBe(adapter.requests[1]!.system) - vi.setSystemTime(BASE + 361_000) - agent.send([{ type: 'text', text: 'again' }]) - await agent.whenIdle() - expect(adapter.requests[2]!.system).toContain('Time since previous message: 5m 0s.') + expect(adapter.requests).toHaveLength(2) + const contexts = agent.session.events.filter(event => event.type === 'context/message') + const starts = agent.session.events.filter(event => event.type === 'step/start') + expect(contexts).toHaveLength(adapter.requests.length) + expect(starts).toHaveLength(adapter.requests.length) + for (let index = 0; index < contexts.length; index += 1) { + expect(contexts[index]!.seq).toBeLessThan(starts[index]!.seq) + } + expect(contexts.every(event => event.data.source.kind === 'plugin' + && event.data.source.plugin === 'time-context' + && event.surfaceOp === 'append')).toBe(true) + + const firstRequestText = requestText(adapter.requests[0]!) + const secondRequestText = requestText(adapter.requests[1]!) + expect(firstRequestText).toContain('Time recorded before turn 1, step 1:') + expect(firstRequestText).toContain('Elapsed since the preceding model-visible message: 0s.') + expect(firstRequestText).not.toContain('Time recorded before turn 1, step 2:') + expect(secondRequestText).toContain('Time recorded before turn 1, step 1:') + expect(secondRequestText).toContain('Time recorded before turn 1, step 2:') + expect(secondRequestText).toContain('Elapsed since the preceding step context: 1m 1s.') + + for (const request of adapter.requests) expect(request.system).not.toContain('Time recorded before') + const headers = agent.session.events.filter(event => event.type === 'request/header' + || event.type === 'request/header-delta') + expect(JSON.stringify(headers)).not.toContain('Time recorded before') + expect(agent.session.events.filter(event => event.type === 'request/header-delta')).toHaveLength(0) await ctx.fiber.dispose() }) }) describe('real Loader export path', () => { - it('keeps the namespace metadata and boots through unwrapExports', async () => { + it('keeps namespace metadata and boots the agent listener through unwrapExports', async () => { expect('default' in timeContext).toBe(false) const loader = Object.create(Loader.prototype) as Loader const unwrapped = loader.unwrapExports(timeContext) as Record expect(unwrapped).toBe(timeContext) expect(unwrapped.name).toBe('time-context') - expect(unwrapped.inject).toEqual(['systemPrompt']) + expect(unwrapped.inject).toEqual(['agents']) expect(unwrapped.Config).toBeDefined() expect(typeof unwrapped.apply).toBe('function') const ctx = new Context() - await ctx.plugin(SystemPrompt) + await ctx.plugin(AgentRegistry) const plugin = loader.unwrapExports(timeContext) as Parameters[0] await ctx.plugin(plugin) const session = new Session(SessionId('loader')) openMessageTurn(session, 1) - expect(await sectionText(ctx, sessionAgent(session))).toContain('Current time:') + await fire(ctx, sessionAgent(session), 1, 1) + expect(contextTexts(session)[0]).toContain('Time recorded before turn 1, step 1:') }) }) diff --git a/packages/context/time-context/tsconfig.json b/packages/context/time-context/tsconfig.json index eda3a81772..f8e14d8aa2 100644 --- a/packages/context/time-context/tsconfig.json +++ b/packages/context/time-context/tsconfig.json @@ -9,7 +9,7 @@ { "path": "../../../vendor/cosmokit" }, { "path": "../../../vendor/cordis" }, { "path": "../../../vendor/schemastery" }, - { "path": "../../core/system-prompt" }, + { "path": "../../llm/llm" }, { "path": "../../core/agent" } ] } From c5381de8b26b16c796f5c5582a48bff0969a5059 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 17:57:45 +0800 Subject: [PATCH 216/359] time-context: cover missing baselines (round 2) --- .../time-context/tests/time-context.spec.ts | 23 +++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/packages/context/time-context/tests/time-context.spec.ts b/packages/context/time-context/tests/time-context.spec.ts index 6df7957fb7..fdcce39912 100644 --- a/packages/context/time-context/tests/time-context.spec.ts +++ b/packages/context/time-context/tests/time-context.spec.ts @@ -184,6 +184,29 @@ describe('durable step context', () => { ) }) + it('reports an unavailable later-step baseline at the matching turn boundary', async () => { + const { ctx } = await mount() + const session = new Session(SessionId('later-step-boundary')) + openMessageTurn(session, 4) + + await fire(ctx, sessionAgent(session), 4, 2) + + expect(contextTexts(session)[0]).toContain( + 'Elapsed since the preceding step context: unavailable.', + ) + }) + + it('reports an unavailable later-step baseline when event lookup is exhausted', async () => { + const { ctx } = await mount() + const session = new Session(SessionId('later-step-exhausted')) + + await fire(ctx, sessionAgent(session), 1, 2) + + expect(contextTexts(session)[0]).toContain( + 'Elapsed since the preceding step context: unavailable.', + ) + }) + it('clamps backward wall-clock movement against the preceding context to zero', async () => { const { ctx } = await mount() const session = new Session(SessionId('backward')) From b1e19d8b697865d20db02facd990052e9d6347d0 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Thu, 16 Jul 2026 18:07:23 +0800 Subject: [PATCH 217/359] fix(core): drain cross-realm execution promises --- docs/cordis-catalog/services.md | 2 +- packages/core/agent-execution/src/index.ts | 3 ++- .../tests/agent-execution.spec.ts | 26 +++++++++++++++++++ 3 files changed, 29 insertions(+), 2 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index dc4976238f..ac002b3e4b 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -21,7 +21,7 @@ run(execution: AgentExecution | undefined, operation: () => T): T Types: [AgentExecution](../core-data-structures/core.md) -Source: [`packages/core/agent-execution/src/index.ts:17`](../../packages/core/agent-execution/src/index.ts) +Source: [`packages/core/agent-execution/src/index.ts:18`](../../packages/core/agent-execution/src/index.ts) ## `ctx.agentLoop` — `AgentLoop` diff --git a/packages/core/agent-execution/src/index.ts b/packages/core/agent-execution/src/index.ts index 3aef4c1856..cb2683dbaa 100644 --- a/packages/core/agent-execution/src/index.ts +++ b/packages/core/agent-execution/src/index.ts @@ -6,6 +6,7 @@ import type { Context } from 'cordis' import { AsyncLocalStorage } from 'node:async_hooks' +import { isPromise } from 'node:util/types' import type { AgentExecution } from './types.ts' export type { AgentExecution } from './types.ts' @@ -75,7 +76,7 @@ class DefaultAgentExecutionService implements AgentExecutionService { this.releaseRun() throw error } - if (result instanceof Promise) { + if (isPromise(result)) { void result.then( () => { this.releaseRun() }, () => { this.releaseRun() }, diff --git a/packages/core/agent-execution/tests/agent-execution.spec.ts b/packages/core/agent-execution/tests/agent-execution.spec.ts index ccf17f6722..e03010c569 100644 --- a/packages/core/agent-execution/tests/agent-execution.spec.ts +++ b/packages/core/agent-execution/tests/agent-execution.spec.ts @@ -1,5 +1,6 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' +import { runInNewContext } from 'node:vm' import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import type { AgentExecution, AgentExecutionService } from '@deepseek-ai/dsh-agent-execution' @@ -133,4 +134,29 @@ describe('AgentExecutionProvider', () => { expect(() => service.current()).toThrow('agent execution service is disposed') expect(() => service.require()).toThrow('agent execution service is disposed') }) + + it('drains cross-realm Promise boundaries before disposal', async () => { + const { service, dispose } = await harness() + const active = execution('cross-realm') + const release = Promise.withResolvers() + const operation = runInNewContext( + '(async () => { await release; inspect() })', + { + release: release.promise, + inspect: () => { expect(service.require()).toBe(active) }, + }, + ) as () => Promise + const pending = service.run(active, operation) + expect(pending).not.toBeInstanceOf(Promise) + + let disposed = false + const disposal = dispose().then(() => { disposed = true }) + await Promise.resolve() + expect(disposed).toBe(false) + + release.resolve(true) + await pending + await disposal + expect(disposed).toBe(true) + }) }) From 6ce9f16030299d5262f4a19865c7f718c11b606c Mon Sep 17 00:00:00 2001 From: lintianle Date: Thu, 16 Jul 2026 18:12:22 +0800 Subject: [PATCH 218/359] website: wire the site into the repo gates; make every tutorial example compile MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - website joins the pnpm workspace; root scripts website:dev/website:build; run-gates gains a website-build gate (ci-primary + ci-static) — the VitePress build doubles as the site's dead-link check; AGENTS.md documents the commands. - doc-typecheck + verify-type-equiv now scan website/zh-CN/**/*.md; every ```typescript fence converted to ```ts and made standalone-compilable (55 compiled, 1 ignore-check). Phantom APIs the compiler caught are fixed: invented event names (agent/turn-end, tool/call, llm/pre-request, ready, dispose) replaced with real catalog events or per-plugin declare-module merges; presentCall/inject/Config claims corrected to the real shapes. - guide/config.md entry-fields table completed against loader EntryOptions; its coding-agent example brought in line with examples/coding-agent. --- AGENTS.md | 3 + knip.json | 2 +- package.json | 7 +- pnpm-lock.yaml | 1448 +++++++++++++++++ pnpm-workspace.yaml | 1 + scripts/doc-typecheck.ts | 5 +- scripts/run-gates.ts | 2 + scripts/verify-type-equiv.ts | 2 +- website/zh-CN/design/composability.md | 11 +- website/zh-CN/design/context-model.md | 29 +- website/zh-CN/design/reactive-coeffects.md | 16 +- website/zh-CN/design/revertible-effects.md | 17 +- website/zh-CN/develop/basic/config.md | 54 +- website/zh-CN/develop/basic/index.md | 45 +- website/zh-CN/develop/basic/tool.md | 115 +- website/zh-CN/develop/framework/events.md | 150 +- website/zh-CN/develop/framework/index.md | 54 +- website/zh-CN/develop/framework/service.md | 62 +- website/zh-CN/develop/practice/index.md | 6 +- website/zh-CN/develop/practice/llm-adapter.md | 129 +- website/zh-CN/guide/config.md | 18 +- 21 files changed, 1949 insertions(+), 227 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index 20abf56c87..70bd5b3ddf 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -30,6 +30,7 @@ packages/ Harness packages at packages///, all named @deepseek-ai examples/ Runnable demos: thin cordis.yml leaves over the app packages (see examples/AGENTS.md) docs/ architecture, generated catalogs, RFCs, postmortems, cookbook (see docs/AGENTS.md) scripts/ repo gates and generators +website/ VitePress docs site (zh-CN) ``` Per-package map: the group READMEs, indexed from [packages/README.md](packages/README.md). @@ -48,6 +49,7 @@ pnpm run lint pnpm run build # tsc emits lib/types, tsdown bundles runtime pnpm run hygiene # knip + publint + workspace constraints + NodeNext consumer check pnpm run doc-sync # all documentation gates; see the doc-sync script in package.json +pnpm run website:build # VitePress build (doubles as the site's dead-link check) pnpm run demo:echo # mock-model REPL, no key needed pnpm run demo:repl # real REPL coding agent (needs DEEPSEEK_API_KEY) pnpm run demo:cordis # self-referential demo: the agent modifies its own runtime (needs key) @@ -65,6 +67,7 @@ pnpm run lint pnpm run test:coverage pnpm run test:snapshot pnpm run doc-sync +pnpm run website:build pnpm run verify-module-graph pnpm run build pnpm run hygiene diff --git a/knip.json b/knip.json index 1c5b0f6b6f..6ddfa29130 100644 --- a/knip.json +++ b/knip.json @@ -1,7 +1,7 @@ { "$schema": "https://unpkg.com/knip@5/schema.json", "exclude": ["duplicates"], - "ignoreWorkspaces": ["vendor/*"], + "ignoreWorkspaces": ["vendor/*", "website"], "workspaces": { ".": { "entry": [ diff --git a/package.json b/package.json index c4cc307893..588346fc0f 100644 --- a/package.json +++ b/package.json @@ -9,7 +9,8 @@ }, "workspaces": [ "vendor/*", - "packages/*/*" + "packages/*/*", + "website" ], "scripts": { "build": "tsc -b tsconfig.build.json && tsdown", @@ -60,6 +61,8 @@ "verify-persistence-catalog": "tsx scripts/gen-persistence-catalog.ts --check", "gen-module-graph": "tsx scripts/gen-module-graph.ts", "verify-module-graph": "tsx scripts/gen-module-graph.ts --check", + "website:dev": "pnpm --filter @deepseek-ai/website run dev", + "website:build": "pnpm --filter @deepseek-ai/website run build", "constraints": "tsx scripts/check-workspace-constraints.ts", "doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-mermaid && pnpm run verify-rfc-classification && pnpm run verify-rfc-format && pnpm run verify-type-equiv && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets", "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-node-next-types", @@ -74,12 +77,14 @@ "@agentclientprotocol/sdk": "0.25.1", "@stylistic/eslint-plugin": "^5.10.0", "@types/jsdom": "^28.0.3", + "@types/js-yaml": "^4.0.9", "@types/mdast": "^4.0.4", "@types/node": "^22.20.0", "@vitest/coverage-v8": "^4.1.8", "eslint": "^10.4.1", "fast-check": "^4.8.0", "jsdom": "29.1.1", + "js-yaml": "^4.1.0", "knip": "^6.16.1", "lefthook": "^2.1.9", "mdast-util-from-markdown": "^2.0.3", diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 4425c6bd41..52575ae3de 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -14,6 +14,9 @@ importers: '@stylistic/eslint-plugin': specifier: ^5.10.0 version: 5.10.0(eslint@10.5.0(jiti@2.7.0)) + '@types/js-yaml': + specifier: ^4.0.9 + version: 4.0.9 '@types/jsdom': specifier: ^28.0.3 version: 28.0.3 @@ -32,6 +35,9 @@ importers: fast-check: specifier: ^4.8.0 version: 4.8.0 + js-yaml: + specifier: ^4.1.0 + version: 4.2.0 jsdom: specifier: 29.1.1 version: 29.1.1 @@ -1480,6 +1486,15 @@ importers: specifier: ^1.8.1 version: 1.8.1 + website: + devDependencies: + vitepress: + specifier: ^1.6.3 + version: 1.6.4(@algolia/client-search@5.55.2)(@types/node@25.9.3)(lightningcss@1.32.0)(postcss@8.5.15)(search-insights@2.17.3)(typescript@6.0.3) + vue: + specifier: ^3.5.13 + version: 3.5.39(typescript@6.0.3) + packages: '@agentclientprotocol/sdk@0.25.1': @@ -1487,6 +1502,82 @@ packages: peerDependencies: zod: ^3.25.0 || ^4.0.0 + '@algolia/abtesting@1.21.2': + resolution: {integrity: sha512-uXj0rgk30EpsKvOpuS+R+1XFDrnm56hED1Lz56e8uBkZdKCxw99LS2U8eXBqAHYU8kpkbsnV1GC8velBG070Hg==} + engines: {node: '>= 14.0.0'} + + '@algolia/autocomplete-core@1.17.7': + resolution: {integrity: sha512-BjiPOW6ks90UKl7TwMv7oNQMnzU+t/wk9mgIDi6b1tXpUek7MW0lbNOUHpvam9pe3lVCf4xPFT+lK7s+e+fs7Q==} + + '@algolia/autocomplete-plugin-algolia-insights@1.17.7': + resolution: {integrity: sha512-Jca5Ude6yUOuyzjnz57og7Et3aXjbwCSDf/8onLHSQgw1qW3ALl9mrMWaXb5FmPVkV3EtkD2F/+NkT6VHyPu9A==} + peerDependencies: + search-insights: '>= 1 < 3' + + '@algolia/autocomplete-preset-algolia@1.17.7': + resolution: {integrity: sha512-ggOQ950+nwbWROq2MOCIL71RE0DdQZsceqrg32UqnhDz8FlO9rL8ONHNsI2R1MH0tkgVIDKI/D0sMiUchsFdWA==} + peerDependencies: + '@algolia/client-search': '>= 4.9.1 < 6' + algoliasearch: '>= 4.9.1 < 6' + + '@algolia/autocomplete-shared@1.17.7': + resolution: {integrity: sha512-o/1Vurr42U/qskRSuhBH+VKxMvkkUVTLU6WZQr+L5lGZZLYWyhdzWjW0iGXY7EkwRTjBqvN2EsR81yCTGV/kmg==} + peerDependencies: + '@algolia/client-search': '>= 4.9.1 < 6' + algoliasearch: '>= 4.9.1 < 6' + + '@algolia/client-abtesting@5.55.2': + resolution: {integrity: sha512-y7Epol8HcjlBxKXHhyhfFPFhm78B3P6x9cCbCyGTdxjsdVCptXCy5hpkZWxjGpnaLHvWsHS4QRF0TiBOLst2xg==} + engines: {node: '>= 14.0.0'} + + '@algolia/client-analytics@5.55.2': + resolution: {integrity: sha512-8Pxj2VVmpM2d+UZufnlTq7T1QIcYPVugLV5XC50PnHsV5uRM9CSoYkg2Y+CwqwRk2La0xK5QsfZ0obIU+9XftQ==} + engines: {node: '>= 14.0.0'} + + '@algolia/client-common@5.55.2': + resolution: {integrity: sha512-9L4IpIYUqA63a7sw1trnHQGUvwiAjKz67nsgDnal98JGAc7wyposRb0Iag+eiMuyzFFaSHLe2/rGyIo+PafRBA==} + engines: {node: '>= 14.0.0'} + + '@algolia/client-insights@5.55.2': + resolution: {integrity: sha512-ZBm2ytY5EHFcj+kjNsXxMNO/TGlOHe2fBFXGKHJOM1bk1rAy4o2YI+d9oV/w/jrqx44pvJMJlc8X6vKnCuDgUQ==} + engines: {node: '>= 14.0.0'} + + '@algolia/client-personalization@5.55.2': + resolution: {integrity: sha512-3FGVW/jDk7sdYwqa2NKnF/qXWcttc4bvGrwNbvqz3VoWSRv42CNvRk+3Y9QJFIUf1vY50hAuVWUoFKdyc8vaXA==} + engines: {node: '>= 14.0.0'} + + '@algolia/client-query-suggestions@5.55.2': + resolution: {integrity: sha512-JsG8LovDAYul5t8e533tZ3O1uZILxso5zsTtB7ONc5RJ8ACdTxAAC/jaOnsBNYb+x+STP7fzx/Iro55v5DNgoQ==} + engines: {node: '>= 14.0.0'} + + '@algolia/client-search@5.55.2': + resolution: {integrity: sha512-5wDnoIfC75zJ2MSHv5SSzTlRL2z7jQMbqQ5jrzottuq2p3oBObv8pD/JpXWu8pRaimaxNr3/Bs/KZIGVXxJ7hg==} + engines: {node: '>= 14.0.0'} + + '@algolia/ingestion@1.55.2': + resolution: {integrity: sha512-da+SC6ikpza98W7C5ChsKEQDvZc8PQLQ0sxmQ5yMRsHpdD3iPKnclJA6ViB5Nr5T9qOX+IDswC6AyqY4V3rtug==} + engines: {node: '>= 14.0.0'} + + '@algolia/monitoring@1.55.2': + resolution: {integrity: sha512-Y8kEcPqCiIEeaGv83l9RRA09mfYECqAJHNnOyEtZc9UirI6XBMUyFVss/sSeYUiV/Lf30hkbWcl00V1uXsf86Q==} + engines: {node: '>= 14.0.0'} + + '@algolia/recommend@5.55.2': + resolution: {integrity: sha512-5zmobuCQqFZkx+84Nt+suL7vo6jTh2CfAs2ndDSeTS2QHvnzP8YEEGWtWftjyACI0cK/FuH8urWwCHP+d2j8TA==} + engines: {node: '>= 14.0.0'} + + '@algolia/requester-browser-xhr@5.55.2': + resolution: {integrity: sha512-qnGUUuWG66dRMnr33owLsrYIh9fHVxtU4R2rd3SpneAHuoAUcGbDOWNrj05glVU6M8yOqo9gQ22K8zpz0I8Xpg==} + engines: {node: '>= 14.0.0'} + + '@algolia/requester-fetch@5.55.2': + resolution: {integrity: sha512-lKZ5uhafMvR7dWCJEyuaeyZitid1I3ICx+k0vGf5x/ktdIQvc7bndCiOPpmIDqUmN26FE3jTehkAzSqee95G2Q==} + engines: {node: '>= 14.0.0'} + + '@algolia/requester-node-http@5.55.2': + resolution: {integrity: sha512-Zc90xvKWUvxcNicvvTO9Pr/hT2TAnkixOIzJm/KMj5Ptm2pKjk71ngTsdkbRtJQvhZ2Kr9N1YdIjLrNHB5P2xw==} + engines: {node: '>= 14.0.0'} + '@antfu/install-pkg@1.1.0': resolution: {integrity: sha512-MGQsmw10ZyI+EJo45CdSER4zEb+p31LpDAFp2Z3gkSd1yqVZGi0Ebx++YTEMonJy4oChEMLsxZ64j8FH6sSqtQ==} @@ -1727,6 +1818,29 @@ packages: resolution: {integrity: sha512-QxULHAm7cNu72w97JUNCBFODFaXpbDg+dP8b/oWFAZ2MTRppA3U00Y2L1HqaS4J6yBqxwa/Y3nMBaxVKbB/NsA==} engines: {node: '>=20.19.0'} + '@docsearch/css@3.8.2': + resolution: {integrity: sha512-y05ayQFyUmCXze79+56v/4HpycYF3uFqB78pLPrSV5ZKAlDuIAAJNhaRi8tTdRNXh05yxX/TyNnzD6LwSM89vQ==} + + '@docsearch/js@3.8.2': + resolution: {integrity: sha512-Q5wY66qHn0SwA7Taa0aDbHiJvaFJLOJyHmooQ7y8hlwwQLQ/5WwCcoX0g7ii04Qi2DJlHsd0XXzJ8Ypw9+9YmQ==} + + '@docsearch/react@3.8.2': + resolution: {integrity: sha512-xCRrJQlTt8N9GU0DG4ptwHRkfnSnD/YpdeaXe02iKfqs97TkZJv60yE+1eq/tjPcVnTW8dP5qLP7itifFVV5eg==} + peerDependencies: + '@types/react': '>= 16.8.0 < 19.0.0' + react: '>= 16.8.0 < 19.0.0' + react-dom: '>= 16.8.0 < 19.0.0' + search-insights: '>= 1 < 3' + peerDependenciesMeta: + '@types/react': + optional: true + react: + optional: true + react-dom: + optional: true + search-insights: + optional: true + '@earendil-works/pi-ai@0.79.3': resolution: {integrity: sha512-lMSput/haP5uZAGbXhS5rAYd3GB7GYdJkoAUxg3VFummBeqGqGqllaTWrbHFN12kVGyVfWHhdySNXkiqVh65Iw==} engines: {node: '>=22.19.0'} @@ -1750,102 +1864,204 @@ packages: '@emnapi/wasi-threads@1.2.2': resolution: {integrity: sha512-c95qOXkHdydNKhscBTebqEC1CVAZpyqOfVfBzQ1qgzyl3gfeldUjIggDbIZgDKsHLgnsM+igH7TJ/eAasaVuMA==} + '@esbuild/aix-ppc64@0.21.5': + resolution: {integrity: sha512-1SDgH6ZSPTlggy1yI6+Dbkiz8xzpHJEVAlF/AM1tHPLsf5STom9rwtjE4hKAF20FfXXNTFqEYXyJNWh1GiZedQ==} + engines: {node: '>=12'} + cpu: [ppc64] + os: [aix] + '@esbuild/aix-ppc64@0.28.1': resolution: {integrity: sha512-Svl7tq8k/08+p6CXPpRjQ1fKX+1odH/BQbb48fV6fj3CWHhsoIOoY87w1oHXm0qEpkIK3ZfVgp0hed3XBXzXMQ==} engines: {node: '>=18'} cpu: [ppc64] os: [aix] + '@esbuild/android-arm64@0.21.5': + resolution: {integrity: sha512-c0uX9VAUBQ7dTDCjq+wdyGLowMdtR/GoC2U5IYk/7D1H1JYC0qseD7+11iMP2mRLN9RcCMRcjC4YMclCzGwS/A==} + engines: {node: '>=12'} + cpu: [arm64] + os: [android] + '@esbuild/android-arm64@0.28.1': resolution: {integrity: sha512-34EGEbCIAgosYz6goLcopX6Mo7NyGv9tfwEM2/7Ce2VcVRk568iSvniGWcUXIy7wEDR1wzolcxcriFVrWYcwBg==} engines: {node: '>=18'} cpu: [arm64] os: [android] + '@esbuild/android-arm@0.21.5': + resolution: {integrity: sha512-vCPvzSjpPHEi1siZdlvAlsPxXl7WbOVUBBAowWug4rJHb68Ox8KualB+1ocNvT5fjv6wpkX6o/iEpbDrf68zcg==} + engines: {node: '>=12'} + cpu: [arm] + os: [android] + '@esbuild/android-arm@0.28.1': resolution: {integrity: sha512-0k2F129Xdio1TdJfzJ8sy1Q47vUD2NnwdhiAf7drUN1EBTfPf4hsFCtmMgu/6m8JSzsBrlmVjudMBQqOfG8usQ==} engines: {node: '>=18'} cpu: [arm] os: [android] + '@esbuild/android-x64@0.21.5': + resolution: {integrity: sha512-D7aPRUUNHRBwHxzxRvp856rjUHRFW1SdQATKXH2hqA0kAZb1hKmi02OpYRacl0TxIGz/ZmXWlbZgjwWYaCakTA==} + engines: {node: '>=12'} + cpu: [x64] + os: [android] + '@esbuild/android-x64@0.28.1': resolution: {integrity: sha512-dbwY7ltSMDWsRatcRpCnES4F+im88OCUgGZjy52shC7GqHRE/cYlxNbB4Z4UpJswpcc4Qxd2oE/ufM0p61IKng==} engines: {node: '>=18'} cpu: [x64] os: [android] + '@esbuild/darwin-arm64@0.21.5': + resolution: {integrity: sha512-DwqXqZyuk5AiWWf3UfLiRDJ5EDd49zg6O9wclZ7kUMv2WRFr4HKjXp/5t8JZ11QbQfUS6/cRCKGwYhtNAY88kQ==} + engines: {node: '>=12'} + cpu: [arm64] + os: [darwin] + '@esbuild/darwin-arm64@0.28.1': resolution: {integrity: sha512-TZbWkQY7kvTAXbXUT7uVACR5cMHsDiSz9z7ZKAX/RTq/WJEk3QyRr0wZpNhBDX+/0CtdqUIJlOiodQcta6tY3Q==} engines: {node: '>=18'} cpu: [arm64] os: [darwin] + '@esbuild/darwin-x64@0.21.5': + resolution: {integrity: sha512-se/JjF8NlmKVG4kNIuyWMV/22ZaerB+qaSi5MdrXtd6R08kvs2qCN4C09miupktDitvh8jRFflwGFBQcxZRjbw==} + engines: {node: '>=12'} + cpu: [x64] + os: [darwin] + '@esbuild/darwin-x64@0.28.1': resolution: {integrity: sha512-zfdzgK9ACBNZLI/CyHTOx81SyNbM6YXn7rxSgX97VjyiPl9W1i4Ka4fgKECEoFCKGpvBj5qArWIGgQjOwkgskQ==} engines: {node: '>=18'} cpu: [x64] os: [darwin] + '@esbuild/freebsd-arm64@0.21.5': + resolution: {integrity: sha512-5JcRxxRDUJLX8JXp/wcBCy3pENnCgBR9bN6JsY4OmhfUtIHe3ZW0mawA7+RDAcMLrMIZaf03NlQiX9DGyB8h4g==} + engines: {node: '>=12'} + cpu: [arm64] + os: [freebsd] + '@esbuild/freebsd-arm64@0.28.1': resolution: {integrity: sha512-wG2EA8ENdEI0qhkSZMjfqrdY+ziCYCPMmtZjjIwOmXFjmyzEHn+UUxk5of+SYsjtfs3VpnlC7QLzSI5hY/rOAw==} engines: {node: '>=18'} cpu: [arm64] os: [freebsd] + '@esbuild/freebsd-x64@0.21.5': + resolution: {integrity: sha512-J95kNBj1zkbMXtHVH29bBriQygMXqoVQOQYA+ISs0/2l3T9/kj42ow2mpqerRBxDJnmkUDCaQT/dfNXWX/ZZCQ==} + engines: {node: '>=12'} + cpu: [x64] + os: [freebsd] + '@esbuild/freebsd-x64@0.28.1': resolution: {integrity: sha512-i7dZ9vQgnvSCzi/rYCXNgtF/U+eKZNJBzu3eTQbRgHnM7tNSizLOkRFAl3qzVc/Op/u5YkHHa4pf/3DOYHthLQ==} engines: {node: '>=18'} cpu: [x64] os: [freebsd] + '@esbuild/linux-arm64@0.21.5': + resolution: {integrity: sha512-ibKvmyYzKsBeX8d8I7MH/TMfWDXBF3db4qM6sy+7re0YXya+K1cem3on9XgdT2EQGMu4hQyZhan7TeQ8XkGp4Q==} + engines: {node: '>=12'} + cpu: [arm64] + os: [linux] + '@esbuild/linux-arm64@0.28.1': resolution: {integrity: sha512-yHs+0uc8+nvEAfAfxrWQKK5peSNzBc4PegcMO0EJ2hT71uA7vB8Ihg2e77R2P7SG5uYjPbHlLLmve4LLLRCf0g==} engines: {node: '>=18'} cpu: [arm64] os: [linux] + '@esbuild/linux-arm@0.21.5': + resolution: {integrity: sha512-bPb5AHZtbeNGjCKVZ9UGqGwo8EUu4cLq68E95A53KlxAPRmUyYv2D6F0uUI65XisGOL1hBP5mTronbgo+0bFcA==} + engines: {node: '>=12'} + cpu: [arm] + os: [linux] + '@esbuild/linux-arm@0.28.1': resolution: {integrity: sha512-qVXBOHQS+d5Y722GwJzJUtOLlX7km3CraOaGormF1pDtPd2C/l1SHRPgjLunLGe51Sh5YYWKMFDyV4SxgMQYTQ==} engines: {node: '>=18'} cpu: [arm] os: [linux] + '@esbuild/linux-ia32@0.21.5': + resolution: {integrity: sha512-YvjXDqLRqPDl2dvRODYmmhz4rPeVKYvppfGYKSNGdyZkA01046pLWyRKKI3ax8fbJoK5QbxblURkwK/MWY18Tg==} + engines: {node: '>=12'} + cpu: [ia32] + os: [linux] + '@esbuild/linux-ia32@0.28.1': resolution: {integrity: sha512-d1z4ZuP0ajrfz/FhGT4vv278rX8KnPPJx8i5+AtK7TYbx9Le9F1hyzurZpkEyjkGa9dUGhQow4C1NmeGvqxN2w==} engines: {node: '>=18'} cpu: [ia32] os: [linux] + '@esbuild/linux-loong64@0.21.5': + resolution: {integrity: sha512-uHf1BmMG8qEvzdrzAqg2SIG/02+4/DHB6a9Kbya0XDvwDEKCoC8ZRWI5JJvNdUjtciBGFQ5PuBlpEOXQj+JQSg==} + engines: {node: '>=12'} + cpu: [loong64] + os: [linux] + '@esbuild/linux-loong64@0.28.1': resolution: {integrity: sha512-M5sRjUVZrkm1OAPR3dlOYzNmN+loZKGVi1VUQGrwuqLcbR6qeAz+famMhjASeH3YVKvZz+zT1jlh/keC3Rj/lg==} engines: {node: '>=18'} cpu: [loong64] os: [linux] + '@esbuild/linux-mips64el@0.21.5': + resolution: {integrity: sha512-IajOmO+KJK23bj52dFSNCMsz1QP1DqM6cwLUv3W1QwyxkyIWecfafnI555fvSGqEKwjMXVLokcV5ygHW5b3Jbg==} + engines: {node: '>=12'} + cpu: [mips64el] + os: [linux] + '@esbuild/linux-mips64el@0.28.1': resolution: {integrity: sha512-mRObBZeHh2OxcBFPWE/FjylkRgZdYuiTR3vaTozquCGOH14iP9oN4x4Ge81CoIDYQrXmIxpFumJBu5MtZpnQJQ==} engines: {node: '>=18'} cpu: [mips64el] os: [linux] + '@esbuild/linux-ppc64@0.21.5': + resolution: {integrity: sha512-1hHV/Z4OEfMwpLO8rp7CvlhBDnjsC3CttJXIhBi+5Aj5r+MBvy4egg7wCbe//hSsT+RvDAG7s81tAvpL2XAE4w==} + engines: {node: '>=12'} + cpu: [ppc64] + os: [linux] + '@esbuild/linux-ppc64@0.28.1': resolution: {integrity: sha512-slScBsMAb3GFDcdrCgLwZtPYRoH2H/youv10QiZyRjmsP48fznoveWytSgCI/R0ZcUgpc0ZhIUEx6LHts8yrfQ==} engines: {node: '>=18'} cpu: [ppc64] os: [linux] + '@esbuild/linux-riscv64@0.21.5': + resolution: {integrity: sha512-2HdXDMd9GMgTGrPWnJzP2ALSokE/0O5HhTUvWIbD3YdjME8JwvSCnNGBnTThKGEB91OZhzrJ4qIIxk/SBmyDDA==} + engines: {node: '>=12'} + cpu: [riscv64] + os: [linux] + '@esbuild/linux-riscv64@0.28.1': resolution: {integrity: sha512-kw0owk1o0GFETUJyW0jc0G4Yzs0BHZn0JDZ8JRT088vjJYX777BAs1fDGxAC+q831qOs2DTC96mNsG2opdfyyQ==} engines: {node: '>=18'} cpu: [riscv64] os: [linux] + '@esbuild/linux-s390x@0.21.5': + resolution: {integrity: sha512-zus5sxzqBJD3eXxwvjN1yQkRepANgxE9lgOW2qLnmr8ikMTphkjgXu1HR01K4FJg8h1kEEDAqDcZQtbrRnB41A==} + engines: {node: '>=12'} + cpu: [s390x] + os: [linux] + '@esbuild/linux-s390x@0.28.1': resolution: {integrity: sha512-/lAIjX8aYFRByhh6L5rYtPEDRqa9de/4V/juOXcta5frjvzXO4/sqEtyytse0g3zZFuWu5cDN0MkLz2qRDD2Ag==} engines: {node: '>=18'} cpu: [s390x] os: [linux] + '@esbuild/linux-x64@0.21.5': + resolution: {integrity: sha512-1rYdTpyv03iycF1+BhzrzQJCdOuAOtaqHTWJZCWvijKD2N5Xu0TtVC8/+1faWqcP9iBCWOmjmhoH94dH82BxPQ==} + engines: {node: '>=12'} + cpu: [x64] + os: [linux] + '@esbuild/linux-x64@0.28.1': resolution: {integrity: sha512-u/anNYF2mmVOEDwLtnQ1wOr3EZ9sTNGLWrsYGYwHWzGA3Si84IOkHXlbWTD1NB+9/1lcnweYKO54uhxZydNzfA==} engines: {node: '>=18'} @@ -1858,6 +2074,12 @@ packages: cpu: [arm64] os: [netbsd] + '@esbuild/netbsd-x64@0.21.5': + resolution: {integrity: sha512-Woi2MXzXjMULccIwMnLciyZH4nCIMpWQAs049KEeMvOcNADVxo0UBIQPfSmxB3CWKedngg7sWZdLvLczpe0tLg==} + engines: {node: '>=12'} + cpu: [x64] + os: [netbsd] + '@esbuild/netbsd-x64@0.28.1': resolution: {integrity: sha512-aeL6lAnN89Hz43Mlh1G8ARasbuoYvSITDEx0tHh5b7jJnHcssqgjy9Yx430GDpmCa6OyrKoS0aNRjKundRizGg==} engines: {node: '>=18'} @@ -1870,6 +2092,12 @@ packages: cpu: [arm64] os: [openbsd] + '@esbuild/openbsd-x64@0.21.5': + resolution: {integrity: sha512-HLNNw99xsvx12lFBUwoT8EVCsSvRNDVxNpjZ7bPn947b8gJPzeHWyNVhFsaerc0n3TsbOINvRP2byTZ5LKezow==} + engines: {node: '>=12'} + cpu: [x64] + os: [openbsd] + '@esbuild/openbsd-x64@0.28.1': resolution: {integrity: sha512-i/ZLIOafE0Z8cI/XANJAixoJL/uRAoS2xOA3rb0xN+KK0K177cMAsQYkzHtBrtMXAKuAc7HGgcWiZ/sRC1Nxgw==} engines: {node: '>=18'} @@ -1882,24 +2110,48 @@ packages: cpu: [arm64] os: [openharmony] + '@esbuild/sunos-x64@0.21.5': + resolution: {integrity: sha512-6+gjmFpfy0BHU5Tpptkuh8+uw3mnrvgs+dSPQXQOv3ekbordwnzTVEb4qnIvQcYXq6gzkyTnoZ9dZG+D4garKg==} + engines: {node: '>=12'} + cpu: [x64] + os: [sunos] + '@esbuild/sunos-x64@0.28.1': resolution: {integrity: sha512-BEjgtECkL3vY+SaSQ6nzVfiALUeFxpawyp8Jmf5PtYhf1Ug40N1h/hxlhts+f1FvSvarEigdxS3BlSMI2PJLcQ==} engines: {node: '>=18'} cpu: [x64] os: [sunos] + '@esbuild/win32-arm64@0.21.5': + resolution: {integrity: sha512-Z0gOTd75VvXqyq7nsl93zwahcTROgqvuAcYDUr+vOv8uHhNSKROyU961kgtCD1e95IqPKSQKH7tBTslnS3tA8A==} + engines: {node: '>=12'} + cpu: [arm64] + os: [win32] + '@esbuild/win32-arm64@0.28.1': resolution: {integrity: sha512-lCv9eK/H6ZJWbE7bh2nw54CZ9M2nupBxJcTsdk/QQnWkdSjKGuxmmH8/GWrlT1eMmZfn4dGcCjRte397WqfQXA==} engines: {node: '>=18'} cpu: [arm64] os: [win32] + '@esbuild/win32-ia32@0.21.5': + resolution: {integrity: sha512-SWXFF1CL2RVNMaVs+BBClwtfZSvDgtL//G/smwAc5oVK/UPu2Gu9tIaRgFmYFFKrmg3SyAjSrElf0TiJ1v8fYA==} + engines: {node: '>=12'} + cpu: [ia32] + os: [win32] + '@esbuild/win32-ia32@0.28.1': resolution: {integrity: sha512-zvb/mB2bSCoJOpoCBgYKKpX6YM6mJBlBUVUtVj41DlZJVEB6/0CKlRYxP5wWl1C1ILiCoAU5wZZ4q1P3qeS6Eg==} engines: {node: '>=18'} cpu: [ia32] os: [win32] + '@esbuild/win32-x64@0.21.5': + resolution: {integrity: sha512-tQd/1efJuzPC6rCFwEvLtci/xNFcTZknmXs98FYDfGE4wP9ClFV98nyKrzJKVPMhdDnjzLhdUyMX4PsQAPjwIw==} + engines: {node: '>=12'} + cpu: [x64] + os: [win32] + '@esbuild/win32-x64@0.28.1': resolution: {integrity: sha512-bm4Mowrv+GXMlpWX++EcXw/iLyd1o3+bJkC2DkWXYVvgZCqD/bSj9ctZeAMC3cIxgjRVR2Dufaiu4YPxr5gW1A==} engines: {node: '>=18'} @@ -1974,6 +2226,9 @@ packages: resolution: {integrity: sha512-bV0Tgo9K4hfPCek+aMAn81RppFKv2ySDQeMoSZuvTASywNTnVJCArCZE2FWqpvIatKu7VMRLWlR1EazvVhDyhQ==} engines: {node: '>=18.18'} + '@iconify-json/simple-icons@1.2.90': + resolution: {integrity: sha512-zt2o2ZvQpHVvZJARIkZ51RnaHY2oqcPJMvHE+mVnxkSr+c33fnX4gciiXu+wyX5ei+s0qbVX1wD0DWBbaGBYMA==} + '@iconify/types@2.0.0': resolution: {integrity: sha512-+wluvCrRhXrhyOmRDJ3q8mux9JkKy5SJ/v8ol2tu4FVjyYvtEzkc/3pK15ET6RKg4b4w4BmTk1+gsCUhf21Ykg==} @@ -2471,6 +2726,168 @@ packages: '@rolldown/pluginutils@1.0.1': resolution: {integrity: sha512-2j9bGt5Jh8hj+vPtgzPtl72j0yRxHAyumoo6TNfAjsLB04UtpSvPbPcDcBMxz7n+9CYB0c1GxQFxYRg2jimqGw==} + '@rollup/rollup-android-arm-eabi@4.62.2': + resolution: {integrity: sha512-6o7ZLZK+BeenkZCFNDXqpbjw9bD6nuWonvS/lwQJp7NoVVxm6p3qE7qQ5jGuBjiFsgvqjD8mZAU5oWxTmbOeOg==} + cpu: [arm] + os: [android] + + '@rollup/rollup-android-arm64@4.62.2': + resolution: {integrity: sha512-BaH7BllCACHoH1LguOU56UItGfUWjujlO65kS9LAodViaN4bwIKd7oeW/ZHJ/4ljr/7MIiENnNy3HJ0zXv8Zkw==} + cpu: [arm64] + os: [android] + + '@rollup/rollup-darwin-arm64@4.62.2': + resolution: {integrity: sha512-v39RCCvj4He82I9sFmk+M1VZ0PLM9sfsLVikjfx2hYBNALhrrOR2D3JjQA6AhlaSOgcR+RzrKY7e1+bT6SUO/A==} + cpu: [arm64] + os: [darwin] + + '@rollup/rollup-darwin-x64@4.62.2': + resolution: {integrity: sha512-yl0y2vq3S3lHeuXhEdss6TWfKW8vkujImO12tn4ZkG/4oghr09LvdYm2RElVjokTQiUvDUGXLGsYeLqUMCKpGA==} + cpu: [x64] + os: [darwin] + + '@rollup/rollup-freebsd-arm64@4.62.2': + resolution: {integrity: sha512-tT4pvt4qXD+vEoezupCWi+a1F0vvDiksiHc+PxRlYTOH1I6/X4id9jPxTP+Fg+545euaFT1jJVs4CEdHZAU1vw==} + cpu: [arm64] + os: [freebsd] + + '@rollup/rollup-freebsd-x64@4.62.2': + resolution: {integrity: sha512-6nU5F2wCW+qvCBhTn1pdIU3bzsIoF7EUwsCDRxilWGprQR6yd508YnH9+OKFCwpfS8pjZqDUmnCAr7exax0XCg==} + cpu: [x64] + os: [freebsd] + + '@rollup/rollup-linux-arm-gnueabihf@4.62.2': + resolution: {integrity: sha512-n1GJHPOvpIfhi3TmrCeh6S6URt9BFCt0KQE3qvexyGCTAKpR4Lg+eWvNZEqu7epxwus/8ElT3hacYEucm49SZg==} + cpu: [arm] + os: [linux] + libc: [glibc] + + '@rollup/rollup-linux-arm-musleabihf@4.62.2': + resolution: {integrity: sha512-JqgflS8wEB+UXV/vS1RpRbifGBeN4D5lz8D8oOFbFZw4vedvdOgCFAjfBmIMdW3yL10XpQQ0Ambepw6MXrhOnA==} + cpu: [arm] + os: [linux] + libc: [musl] + + '@rollup/rollup-linux-arm64-gnu@4.62.2': + resolution: {integrity: sha512-wnFJkogWvN4jm/hQRF2UBaeUmk20j5+DmHvoyWii2b8HJDyvz1MF2OU/6ynXt2KR63rbZLWkFpoytpdc/yBuSA==} + cpu: [arm64] + os: [linux] + libc: [glibc] + + '@rollup/rollup-linux-arm64-musl@4.62.2': + resolution: {integrity: sha512-HVu2bp0zhvJ8xHEV9+UUs7S90VadmBSY3LcIMvozbPo4AuMGDWlz3ymHLHZPX4hR67TKTt8Qp5PJ5RBg/i+RMQ==} + cpu: [arm64] + os: [linux] + libc: [musl] + + '@rollup/rollup-linux-loong64-gnu@4.62.2': + resolution: {integrity: sha512-mQqqAV8QaoSgr9I2fKDLY2BAVvmKjWoGiu/cSYQonsLvtqwEn1E4QYfnCOcp5zoEqNhsDYin1s6jx/VJmrxlZg==} + cpu: [loong64] + os: [linux] + libc: [glibc] + + '@rollup/rollup-linux-loong64-musl@4.62.2': + resolution: {integrity: sha512-IxKLoxCQ2IWi6bT2akyDUBGsOImDKB+sPp4EsTmwFQ/fMwpCKm8uLSSgP/Kx/QYUgKis6SEZ5/Nlhup0DIA0PQ==} + cpu: [loong64] + os: [linux] + libc: [musl] + + '@rollup/rollup-linux-ppc64-gnu@4.62.2': + resolution: {integrity: sha512-Mk5ha2RQSgyFfmYYLkBpPnUk8D8FriBxesO1u9O75X0mHgXL1UQcH5Itl2lurWL2tj0RxV9b9tJgipac0hRY9A==} + cpu: [ppc64] + os: [linux] + libc: [glibc] + + '@rollup/rollup-linux-ppc64-musl@4.62.2': + resolution: {integrity: sha512-CjvEnqJL/0/TQ3TXX3OPIJ/kmBellrWd4heXUmHeJlTnmwjKpSJzoehLaL6Xk0ZnMHBu9dZuFADNOrtjF4v+2w==} + cpu: [ppc64] + os: [linux] + libc: [musl] + + '@rollup/rollup-linux-riscv64-gnu@4.62.2': + resolution: {integrity: sha512-1SiZbzwdkaDURsew/tSOrooKiYy7EQGT6m8ufavAi9NEyQb/6VuIxFXAL1fqa4iZe3g4NbNk4P7J32z2tw5Mgg==} + cpu: [riscv64] + os: [linux] + libc: [glibc] + + '@rollup/rollup-linux-riscv64-musl@4.62.2': + resolution: {integrity: sha512-nQts12zJ3NQRoE6uYljOH89v7szzLDvG2JD/vsX+vGXU8w/At1GowTZ5/7qeFQ8m7L55rpR8Okugnuo5bgjy2Q==} + cpu: [riscv64] + os: [linux] + libc: [musl] + + '@rollup/rollup-linux-s390x-gnu@4.62.2': + resolution: {integrity: sha512-E9/ll019jhPIJgpzfZoIkBGhcz+kKNgVWYRY0zr9srBdPPFVpvOKW8VaJKUbeK+eZXyQF9ltME+Kk6affeaPgg==} + cpu: [s390x] + os: [linux] + libc: [glibc] + + '@rollup/rollup-linux-x64-gnu@4.62.2': + resolution: {integrity: sha512-5BqxR/pshjey51iliyzTD5Xi3EN0aLmQ2lZ3lvefVV9c82BvrLo2/6OT55iifpWBufs6kdwWbuOKS841DrmK9A==} + cpu: [x64] + os: [linux] + libc: [glibc] + + '@rollup/rollup-linux-x64-musl@4.62.2': + resolution: {integrity: sha512-uNN83XxQrRAh/w0/pmAfibcwyb6YWt4gP+dpnQKPVJshAloQ785ii8CT8ZCIxkGg9opVsvAlGhFitSm6D1Jjpg==} + cpu: [x64] + os: [linux] + libc: [musl] + + '@rollup/rollup-openbsd-x64@4.62.2': + resolution: {integrity: sha512-srjEIxSH3LRnJN6THczDHWQplqEMFiAJrTab0msUryh9kwNpkICf3Ea6q6MN/2cZwRFUNx5w+h6Hpi4QuHS6Zg==} + cpu: [x64] + os: [openbsd] + + '@rollup/rollup-openharmony-arm64@4.62.2': + resolution: {integrity: sha512-8hOJnxgbyObnCm5AlRA3A931xX19xq80RjVTKgJOvEKWqJruP/Uf12IbAOaDjjEXYRewwHLfmF0YRIdK3OwKWA==} + cpu: [arm64] + os: [openharmony] + + '@rollup/rollup-win32-arm64-msvc@4.62.2': + resolution: {integrity: sha512-mmF4AY1i0hG/bLWUctUq59gtmgaSIRa3cu/A3JFRp/sCNEme2bgDEiDS22P9FbnJB8NJNF4jPJiSP5RHQpUTDg==} + cpu: [arm64] + os: [win32] + + '@rollup/rollup-win32-ia32-msvc@4.62.2': + resolution: {integrity: sha512-DZgkknc6jhHrk46V25vbAM0zZkyP0nSDkJB8/dRkLTxv470dOmWDqGoEJl/9A0dFfS7yE3REOwNDxpHwSLSt0Q==} + cpu: [ia32] + os: [win32] + + '@rollup/rollup-win32-x64-gnu@4.62.2': + resolution: {integrity: sha512-T6xr6ucWSFto+VGajA8YH26LdpHRuP4YLHEKAtCWvJDOlnmWcDZVCI2Jmjr+IFHDlt2zRaTAKE4tfjTaWLgJBg==} + cpu: [x64] + os: [win32] + + '@rollup/rollup-win32-x64-msvc@4.62.2': + resolution: {integrity: sha512-BfzEnDJOt9T8M989/lA37EcJgat01wLRnoi5dQf3QzOH7jzpqTAzdDbVfRljVr5r+jzKqpbHeyOfAaXxAd0PAA==} + cpu: [x64] + os: [win32] + + '@shikijs/core@2.5.0': + resolution: {integrity: sha512-uu/8RExTKtavlpH7XqnVYBrfBkUc20ngXiX9NSrBhOVZYv/7XQRKUyhtkeflY5QsxC0GbJThCerruZfsUaSldg==} + + '@shikijs/engine-javascript@2.5.0': + resolution: {integrity: sha512-VjnOpnQf8WuCEZtNUdjjwGUbtAVKuZkVQ/5cHy/tojVVRIRtlWMYVjyWhxOmIq05AlSOv72z7hRNRGVBgQOl0w==} + + '@shikijs/engine-oniguruma@2.5.0': + resolution: {integrity: sha512-pGd1wRATzbo/uatrCIILlAdFVKdxImWJGQ5rFiB5VZi2ve5xj3Ax9jny8QvkaV93btQEwR/rSz5ERFpC5mKNIw==} + + '@shikijs/langs@2.5.0': + resolution: {integrity: sha512-Qfrrt5OsNH5R+5tJ/3uYBBZv3SuGmnRPejV9IlIbFH3HTGLDlkqgHymAlzklVmKBjAaVmkPkyikAV/sQ1wSL+w==} + + '@shikijs/themes@2.5.0': + resolution: {integrity: sha512-wGrk+R8tJnO0VMzmUExHR+QdSaPUl/NKs+a4cQQRWyoc3YFbUzuLEi/KWK1hj+8BfHRKm2jNhhJck1dfstJpiw==} + + '@shikijs/transformers@2.5.0': + resolution: {integrity: sha512-SI494W5X60CaUwgi8u4q4m4s3YAFSxln3tzNjOSYqq54wlVgz0/NbbXEb3mdLbqMBztcmS7bVTaEd2w0qMmfeg==} + + '@shikijs/types@2.5.0': + resolution: {integrity: sha512-ygl5yhxki9ZLNuNpPitBWvcy9fsSKKaRuO4BAlMyagszQidxcpLAr0qiW/q43DtSIDxO6hEbtYLiFZNXO/hdGw==} + + '@shikijs/vscode-textmate@10.0.2': + resolution: {integrity: sha512-83yeghZ2xxin3Nj8z1NMd/NCuca+gsYXswywDy5bHvwlWL8tpTQmzGeUuHd9FC3E/SBEMvzJRwWEOz5gGes9Qg==} + '@smithy/core@3.24.7': resolution: {integrity: sha512-KoUi4M1f3BG6kzN1FnCwL7oyFptTbyBJKjR6yhSib+JHRdUmM1o+VwsFtJ66NZCkCzVfJMWRHJNo0R0jznp0Pg==} engines: {node: '>=18.0.0'} @@ -2637,6 +3054,12 @@ packages: '@types/geojson@7946.0.16': resolution: {integrity: sha512-6C8nqWur3j98U6+lXDfTUWIfgvZU+EumvpHKcYjujKH7woYyLj2sUmff0tRhrqM7BohUw7Pz3ZB1jj2gW9Fvmg==} + '@types/hast@3.0.5': + resolution: {integrity: sha512-rp/ezSWaD1m44dPKICGhiskI13nVr7qTloFwDa/IYkhhf5nzwP+zIQcIJh3WIFSBOy/H1PzB40jPjMDksN4F+g==} + + '@types/js-yaml@4.0.9': + resolution: {integrity: sha512-k4MGaQl5TGo/iipqb2UDG2UwjXziSWkh0uysQelTlJpX1qGlpUZYm8PnO4DxG1qBomtJUdYJ6qR6xdIah10JLg==} + '@types/jsdom@28.0.3': resolution: {integrity: sha512-/HQ2uFoetFTXuye8vzIcHw2z6Fwi7Hi/qcgC+RoS9NCyewiqxhVGqlG+ViGB6lkax481R6dmhf1I7lIGlzJStQ==} @@ -2646,9 +3069,18 @@ packages: '@types/json-schema@7.0.15': resolution: {integrity: sha512-5+fP8P8MFNC+AyZCDxrB2pkZFPGzqQWUzpSeuuVLvm8VMcorNYavBqoFcxK8bQz4Qsbn4oUEEem4wDLfcysGHA==} + '@types/linkify-it@5.0.0': + resolution: {integrity: sha512-sVDA58zAw4eWAffKOaQH5/5j3XeayukzDk+ewSsnv3p4yJEZHCCzMDiZM8e0OUrRvmpGZ85jf4yDHkHsgBNr9Q==} + + '@types/markdown-it@14.1.2': + resolution: {integrity: sha512-promo4eFwuiW+TfGxhi+0x3czqTYJkG8qB17ZUJiVF10Xm7NLVRSLUsfRTU/6h1e24VvRnXCx+hG7li58lkzog==} + '@types/mdast@4.0.4': resolution: {integrity: sha512-kGaNbPh1k7AFzgpud/gMdvIm5xuECykRR+JnWKQno9TAXVa6WIVCGTPvYGekIDL4uwCZQSYbUxNBSb1aUo79oA==} + '@types/mdurl@2.0.0': + resolution: {integrity: sha512-RGdgjQUZba5p6QEFAVx2OGb8rQDL/cPRG7GiedRzMcJ1tYnUANBncjbSB1NRGwbvjcPeikRABz2nshyPk1bhWg==} + '@types/ms@2.1.0': resolution: {integrity: sha512-GsCCIZDE/p3i96vtEqx+7dBUGXrc7zeSK3wwPHIaRThS+9OhWIXRqzs4d6k1SVU8g91DrNRWxWUGhp5KXQb2VA==} @@ -2673,6 +3105,9 @@ packages: '@types/unist@3.0.3': resolution: {integrity: sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q==} + '@types/web-bluetooth@0.0.21': + resolution: {integrity: sha512-oIQLCGWtcFZy2JW77j9k8nHzAOpqMHLQejDA48XXMWH6tjCQHz5RCFz1bzsmROyL6PUm+LLnUiI4BCn221inxA==} + '@typescript-eslint/eslint-plugin@8.61.0': resolution: {integrity: sha512-bFNvl9ZczlVb+wR2Akszf3gHfKVj/8WanXaGJ3UstTA7brNKg0cNdk6X1Psu5V7MZ2oQtzZKOEzIUehaoxbDGw==} engines: {node: ^18.18.0 || ^20.9.0 || >=21.1.0} @@ -2732,9 +3167,19 @@ packages: resolution: {integrity: sha512-QVLZu3ZPQEE+HICQyAMZ2yLQhxf0meY/wx6Hx14YcTNj13JB3qHlX3lJ02L3fLGHgERRH71kvYDwiXIguT3AjQ==} engines: {node: ^18.18.0 || ^20.9.0 || >=21.1.0} + '@ungap/structured-clone@1.3.3': + resolution: {integrity: sha512-60YRaenCQcVjYEKOcG824+DRGGIQ3VKErcBoAEDJZz5bKIs2ZG+X/H9Nk+Q6EVkwJk5QNApxbrc5QtBSwtrXAg==} + '@upsetjs/venn.js@2.0.0': resolution: {integrity: sha512-WbBhLrooyePuQ1VZxrJjtLvTc4NVfpOyKx0sKqioq9bX1C1m7Jgykkn8gLrtwumBioXIqam8DLxp88Adbue6Hw==} + '@vitejs/plugin-vue@5.2.4': + resolution: {integrity: sha512-7Yx/SXSOcQq5HiiV3orevHUFn+pmMB4cgbEkDYgnkUWb0WfeQ/wa2yFv6D5ICiCQOVpjA7vYDXrC7AGO8yjDHA==} + engines: {node: ^18.0.0 || >=20.0.0} + peerDependencies: + vite: ^5.0.0 || ^6.0.0 + vue: ^3.2.25 + '@vitest/coverage-v8@4.1.8': resolution: {integrity: sha512-lt3kovsyHwYe00wq4D1ti0Z974fWj4NLp6siqiyEufUpyFwK9Yhi7rBhac9JL5aA0zoMrJqc4vYPZRUnI7l7nw==} peerDependencies: @@ -2773,6 +3218,94 @@ packages: '@vitest/utils@4.1.8': resolution: {integrity: sha512-uOJamYALNhfJ6iolExyQM40yIQwDqYnkKtQ5VCiSe17E33H0aQ/u+1GlRuz4LZBk6Mm3sg90G9hEbmEt37C1Zg==} + '@vue/compiler-core@3.5.39': + resolution: {integrity: sha512-16KBTEXAJCpDr0mwlw+AZyhu8iyC7R3S2vBwsI7QnWJU6X3WKc9VKeNEZpiMdZ569qWhz9574L3vV55qRL0Vtw==} + + '@vue/compiler-dom@3.5.39': + resolution: {integrity: sha512-oQPigALqYbNxTNPvNgSOe+czwVExfbVF02lz8jP0S3AXJiu3jxYDygNUiqSep4ezzW8XgnubqH63My2A7JR/vg==} + + '@vue/compiler-sfc@3.5.39': + resolution: {integrity: sha512-d0ki86iOyN8LoZPBmk5SJWNwHP19CnDDCfuo//+2WJa2g5Ke0Jay983PIBIcSSzldC68I8DrD5GrHV3OSDfodg==} + + '@vue/compiler-ssr@3.5.39': + resolution: {integrity: sha512-Ce7/wvwMHai74bdszfXExdazFigYnlF9zgCmEQUcM1j0fOymlouZ7XilTYNo8oUjhlnjYOZbGrcYKuqjz89Ucw==} + + '@vue/devtools-api@7.7.10': + resolution: {integrity: sha512-KxtEpUOOpFz/qOGRrAwA36QF7DqIA+FXgCYit9mk9wjbaZt0sXOFz81ElOZtKA4HbWHUdwNjZHBFsFFyp5BZiA==} + + '@vue/devtools-kit@7.7.10': + resolution: {integrity: sha512-3WNi2Kq4tbpVbmhml7RiphmAt0279oh3fKNeWMQIrltfX8Q91b4i5PL8DtyNKdwmcsGrV4fg+erwWOmD05CLIw==} + + '@vue/devtools-shared@7.7.10': + resolution: {integrity: sha512-wOPslzB8vTvpxwdaOcR2qAbwmuSP0L+rhpoC6Cf56V3Jip+HWb7PQQXOUPgBNQARpXsbQX/+mvi8kKucmBGRwQ==} + + '@vue/reactivity@3.5.39': + resolution: {integrity: sha512-TpsuBJ9gGlZa5d23XcM2y8EXanz9dZeVDQBXRwzy46ItgvM+rWpzs+UVM0wcRLxGvcav0HE5jz2gNL53xlRAog==} + + '@vue/runtime-core@3.5.39': + resolution: {integrity: sha512-9GLtNyRvPAUMbX+7ono0RC2j0guo2LXVi8LvcmAooImACUKm0oFf0jjwbX8/H0AE/t1nxhAkn8RSl9PMCzzxZw==} + + '@vue/runtime-dom@3.5.39': + resolution: {integrity: sha512-7Y6aAGboKcXAZ3ECuUy7RrS5yy2r47dhTp2SKaJmYxjopImaVFaNa5Ne66NwGovsrxVAl5S5rwc7m22UG7Lmww==} + + '@vue/server-renderer@3.5.39': + resolution: {integrity: sha512-yZSakiAGw85rZfG7UM8akMnIF+FmeiNk47uvHf2nVBBSe+dIKUhZuZq9+XgJhbV3nS5Z4ALH23/MpXofW+mbcw==} + peerDependencies: + vue: 3.5.39 + + '@vue/shared@3.5.39': + resolution: {integrity: sha512-l1rrBtBfTnmxvtsvdQDXltUUy8S1Y+ZaqdfUzmAnJkTd8Z8rv5v/ytW+TKiqEOWyHPoqtPlNFSs0lhRmYVSHVA==} + + '@vueuse/core@12.8.2': + resolution: {integrity: sha512-HbvCmZdzAu3VGi/pWYm5Ut+Kd9mn1ZHnn4L5G8kOQTPs/IwIAmJoBrmYk2ckLArgMXZj0AW3n5CAejLUO+PhdQ==} + + '@vueuse/integrations@12.8.2': + resolution: {integrity: sha512-fbGYivgK5uBTRt7p5F3zy6VrETlV9RtZjBqd1/HxGdjdckBgBM4ugP8LHpjolqTj14TXTxSK1ZfgPbHYyGuH7g==} + peerDependencies: + async-validator: ^4 + axios: ^1 + change-case: ^5 + drauu: ^0.4 + focus-trap: ^7 + fuse.js: ^7 + idb-keyval: ^6 + jwt-decode: ^4 + nprogress: ^0.2 + qrcode: ^1.5 + sortablejs: ^1 + universal-cookie: ^7 + peerDependenciesMeta: + async-validator: + optional: true + axios: + optional: true + change-case: + optional: true + drauu: + optional: true + focus-trap: + optional: true + fuse.js: + optional: true + idb-keyval: + optional: true + jwt-decode: + optional: true + nprogress: + optional: true + qrcode: + optional: true + sortablejs: + optional: true + universal-cookie: + optional: true + + '@vueuse/metadata@12.8.2': + resolution: {integrity: sha512-rAyLGEuoBJ/Il5AmFHiziCPdQzRt88VxR+Y/A/QhJ1EWtWqPBBAxTAFaSkviwEuOEZNtW8pvkPgoCZQ+HxqW1A==} + + '@vueuse/shared@12.8.2': + resolution: {integrity: sha512-dznP38YzxZoNloI0qpEfpkms8knDtaoQ6Y/sfS0L7Yki4zh40LFHEhur0odJC6xTHG5dxWVPiUWBXn+wCG2s5w==} + acorn-jsx@5.3.2: resolution: {integrity: sha512-rq9s+JNhf0IChjtDXxllJ7g41oZk5SlXtp0LHwyA5cejwn7vKmKp4pPri6YEePv2PU65sAsegbXtIinmDFDXgQ==} peerDependencies: @@ -2790,6 +3323,10 @@ packages: ajv@6.15.0: resolution: {integrity: sha512-fgFx7Hfoq60ytK2c7DhnF8jIvzYgOMxfugjLOSMHjLIPgenqa7S7oaagATUq99mV6IYvN2tRmC0wnTYX6iPbMw==} + algoliasearch@5.55.2: + resolution: {integrity: sha512-OyacJsaeuLUvGWOynNqYc6sx88XvyoG39wMT8SYqL3l9wwaorDW/LPRbUPfhzw0bWsUWzNCZTnFYOrWFBKsUaw==} + engines: {node: '>= 14.0.0'} + ansis@4.3.1: resolution: {integrity: sha512-BJ8/l4R5LRE7hW9WdSuGYrLSHi2ynxeFpDFbH0K/CgNeY/tyhk+vO6TYxXC5r5CpUhNVX310xzPsN/H9lCdfOA==} engines: {node: '>=14'} @@ -2824,6 +3361,9 @@ packages: bignumber.js@9.3.1: resolution: {integrity: sha512-Ko0uX15oIUS7wJ3Rb30Fs6SkVbLmPBAKdlm7q9+ak9bbIeFf0MwuBsQV6z7+X768/cHsfg+WlysDWJcmthjsjQ==} + birpc@2.9.0: + resolution: {integrity: sha512-KrayHS5pBi69Xi9JmvoqrIgYGDkD6mcSe/i6YKi3w5kekCLzrX4+nawcXqrj2tIp50Kw/mT/s3p+GVK0A0sKxw==} + birpc@4.0.0: resolution: {integrity: sha512-LShSxJP0KTmd101b6DRyGBj57LZxSDYWKitQNW/mi8GRMvZb078Uf9+pveax1DrVL89vm7mWe+TovdI/UDOuPw==} @@ -2848,6 +3388,12 @@ packages: resolution: {integrity: sha512-NUPRluOfOiTKBKvWPtSD4PhFvWCqOi0BGStNWs57X9js7XGTprSmFoz5F0tWhR4WPjNeR9jXqdC7/UpSJTnlRg==} engines: {node: '>=18'} + character-entities-html4@2.1.0: + resolution: {integrity: sha512-1v7fgQRj6hnSwFpq1Eu0ynr/CDEw0rXo2B61qXrLNdHZmPKgb7fqS1a2JwF0rISo9q77jDI8VMEHoApn8qDoZA==} + + character-entities-legacy@3.0.0: + resolution: {integrity: sha512-RpPp0asT/6ufRm//AJVwpViZbGM/MkjQFxJccQRHmISF/22NBtsHqAWmL+/pmkPWoIUJdWyeVleTl1wydHATVQ==} + character-entities@2.0.2: resolution: {integrity: sha512-shx7oQ0Awen/BRIdkjkvz54PnEEI/EjwXDSIZp86/KKdbafHh1Df/RYGBhn4hbe2+uKC9FnT5UCEdyPz3ai9hQ==} @@ -2855,6 +3401,9 @@ packages: resolution: {integrity: sha512-Qgzu8kfBvo+cA4962jnP1KkS6Dop5NS6g7R5LFYJr4b8Ub94PPQXUksCw9PvXoeXPRRddRNC5C1JQUR2SMGtnA==} engines: {node: '>= 14.16.0'} + comma-separated-tokens@2.0.3: + resolution: {integrity: sha512-Fu4hJdvzeylCfQPp9SGWidpzrMs7tTrlu6Vb8XGaRGck8QSNZJJp538Wrb60Lax4fPwR64ViY468OIUTbRlGZg==} + commander@7.2.0: resolution: {integrity: sha512-QrWXB+ZQSVPmIWIhtEO9H+gwHaMGYiF5ChvoJ+K9ZGHG/sVsa6yiesAD1GC/x46sET00Xlwo1u49RVVVzvcSkw==} engines: {node: '>= 10'} @@ -2866,6 +3415,10 @@ packages: convert-source-map@2.0.0: resolution: {integrity: sha512-Kvp459HrV2FEJ1CAsi1Ku+MY3kasH19TFykTz2xWmMeq6bk2NU3XXvfJ+Q61m0xktWwt+1HSYf3JZsTms3aRJg==} + copy-anything@4.0.5: + resolution: {integrity: sha512-7Vv6asjS4gMOuILabD3l739tsaxFQmC+a7pLZm02zyvs8p977bL3zEgq3yDk5rn9B0PbYgIv++jmHcuUab4RhA==} + engines: {node: '>=18'} + cordis@4.0.0-rc.6: resolution: {integrity: sha512-GzUv7zCKh3FlgM3/Ad2S03UpYO3v4u1GcKa7ig4K2je4lCrgJ/S64ziiZI6XNyKEa1tZwdzj4oBQrhYDLgfEiA==} hasBin: true @@ -2895,6 +3448,9 @@ packages: resolution: {integrity: sha512-X7sjQzceUhu1u7Y/ylrRZFU2FS6LRiFVp6rKLPg23y3x3c3DOKAwuXGDp+PAGjh6CSnCjYeAul8pcT8bAl+lSA==} engines: {node: ^10 || ^12.20.0 || ^14.13.0 || >=15.0.0} + csstype@3.2.3: + resolution: {integrity: sha512-z1HGKcYy2xA8AGQfwrn0PAy+PB7X/GSj3UVJW9qKyn43xWa+gl5nXmU4qqLMRzWVLFC8KusUX8T/0kCiOYpAIQ==} + cytoscape-cose-bilkent@4.1.0: resolution: {integrity: sha512-wgQlVIUJF13Quxiv5e1gstZ08rnZj2XaLHGoFMYXz7SkNfCDOOteKBE6SYRfA9WxxI/iBc3ajfDoc6hb/MRAHQ==} peerDependencies: @@ -3116,10 +3672,17 @@ packages: ecdsa-sig-formatter@1.0.11: resolution: {integrity: sha512-nagl3RYrbNv6kQkeJIpt6NJZy8twLB/2vtz6yN9Z4vRKHN4/QZJIEbqohALSgwKdnksuY3k5Addp5lg8sVoVcQ==} + emoji-regex-xs@1.0.0: + resolution: {integrity: sha512-LRlerrMYoIDrT6jgpeZ2YYl/L8EulRTt5hQcYjy5AInh7HWXKimpqx68aknBFpGL2+/IcogTcaydJEgaTmOpDg==} + empathic@2.0.1: resolution: {integrity: sha512-YGRs8knHhKHVShLkFET/rWAU8kmHbOV5LwN938RHI0pljAJ1Gf6SzXsSmRaEzcXTtOOmVqJ5+WtQPL5uigY50Q==} engines: {node: '>=14'} + entities@7.0.1: + resolution: {integrity: sha512-TWrgLOFUQTH994YUyl1yT4uyavY5nNB5muff+RtWaqNVCAK408b5ZnnbNAUEWLTCpum9w6arT70i1XdQ4UeOPA==} + engines: {node: '>=0.12'} + entities@8.0.0: resolution: {integrity: sha512-zwfzJecQ/Uej6tusMqwAqU/6KL2XaB2VZ2Jg54Je6ahNBGNH6Ek6g3jjNCF0fG9EWQKGZNddNjU5F1ZQn/sBnA==} engines: {node: '>=20.19.0'} @@ -3130,6 +3693,11 @@ packages: es-toolkit@1.49.0: resolution: {integrity: sha512-G5iZ6Pc/FNRY/soKZHC+TxGDD83rHUDXxzaWhGCX44vAv/tMs56WMusnm/KMNK+luUPsgA9U28cGr4RDlSzL2g==} + esbuild@0.21.5: + resolution: {integrity: sha512-mg3OPMV4hXywwpoDxu3Qda5xCKQi+vCTZq8S9J/EpkhB2HzKXq4SNFZE3+NK93JYxc8VMSep+lOUSC/RVKaBqw==} + engines: {node: '>=12'} + hasBin: true + esbuild@0.28.1: resolution: {integrity: sha512-HrJrvZv5ayxBzPfwphOoNzkzOIIlifzk0KJrGK2c8R4+LKpMtpYLQeUdjnwjWv/LZlkH2laZk+4w78pi99D4Vw==} engines: {node: '>=18'} @@ -3189,6 +3757,9 @@ packages: resolution: {integrity: sha512-MMdARuVEQziNTeJD8DgMqmhwR11BRQ/cBP+pLtYdSTnf3MIO8fFeiINEbX36ZdNlfU/7A9f3gUw49B3oQsvwBA==} engines: {node: '>=4.0'} + estree-walker@2.0.2: + resolution: {integrity: sha512-Rfkk/Mp/DL7JVje3u18FxFujQlTNR2q6QfMSMB7AvCBx91NGj/ba3kCfza0f6dVDbw7YlRf/nDrn7pQrCCyQ/w==} + estree-walker@3.0.3: resolution: {integrity: sha512-7RUKfXgSMMkzt6ZuXmqapOurLGPPfgj6l9uRZ7lRGolvk0y2yocc35LdcxKC5PQZdn2DMqioAQ2NoWcrTKmm6g==} @@ -3254,6 +3825,9 @@ packages: flatted@3.4.2: resolution: {integrity: sha512-PjDse7RzhcPkIJwy5t7KPWQSZ9cAbzQXcafsetQoD7sOJRQlGikNbx7yZp2OotDnJyrDcbyRq3Ttb18iYOqkxA==} + focus-trap@7.8.0: + resolution: {integrity: sha512-/yNdlIkpWbM0ptxno3ONTuf+2g318kh2ez3KSeZN5dZ8YC6AAmgeWz+GasYYiBJPFaYcSAPeu4GfhUaChzIJXA==} + formatly@0.3.0: resolution: {integrity: sha512-9XNj/o4wrRFyhSMJOvsuyMwy8aUfBaZ1VrqHVfohyXf0Sw0e+yfKG+xZaY3arGCOMdwFsqObtzVOc1gU9KiT9w==} engines: {node: '>=18.3.0'} @@ -3305,6 +3879,15 @@ packages: resolution: {integrity: sha512-EykJT/Q1KjTWctppgIAgfSO0tKVuZUjhgMr17kqTumMl6Afv3EISleU7qZUzoXDFTAHTDC4NOoG/ZxU3EvlMPQ==} engines: {node: '>=8'} + hast-util-to-html@9.0.5: + resolution: {integrity: sha512-OguPdidb+fbHQSU4Q4ZiLKnzWo8Wwsf5bZfbvu7//a9oTYoqD/fWpe96NuHkoS9h0ccGOTe0C4NGXdtS0iObOw==} + + hast-util-whitespace@3.0.0: + resolution: {integrity: sha512-88JUN06ipLwsnv+dVn+OIYOvAuvBMy/Qoi6O7mQHxdPXpjy+Cd6xRkWwux7DKO+4sYILtLBRIKgsdpS2gQc7qw==} + + hookable@5.5.3: + resolution: {integrity: sha512-Yc+BQe8SvoXH1643Qez1zqLRmbA5rCL+sSmk6TVos0LWVfNIB7PGncdlId77WzLGSIB5KaWgTaNTs2lNVEI6VQ==} + hookable@6.1.1: resolution: {integrity: sha512-U9LYDy1CwhMCnprUfeAZWZGByVbhd54hwepegYTK7Pi5NvqEj63ifz5z+xukznehT7i6NIZRu89Ay1AZmRsLEQ==} @@ -3315,6 +3898,9 @@ packages: html-escaper@2.0.2: resolution: {integrity: sha512-H2iMtd0I4Mt5eYiapRdIDjp+XzelXQ0tFE4JS7YFwFevXXMmOp9myNrUvCg0D6ws8iqkRPBfKHgbwig1SmlLfg==} + html-void-elements@3.0.0: + resolution: {integrity: sha512-bEqo66MRXsUGxWHV5IP0PUiAWwoEjba4VCzg0LjFJBpchPaTfyfCKTG6bc5F8ucKec3q5y6qOdGyYTSBEvhCrg==} + http-proxy-agent@7.0.2: resolution: {integrity: sha512-T1gkAiYYDWYx3V5Bmyu7HcfcvL7mUrTWiM6yOfa3PIphViJ/gFPbvidQ+veqSOHci/PxBcDabeUNCzpOODJZig==} engines: {node: '>= 14'} @@ -3364,6 +3950,10 @@ packages: is-potential-custom-element-name@1.0.1: resolution: {integrity: sha512-bCYeRA2rVibKZd+s2625gGnGF/t7DSqDs4dP7CrLA1m7jKWz6pps0LpYLJN8Q64HtmPKJ1hrN3nzPNKFEKOUiQ==} + is-what@5.5.0: + resolution: {integrity: sha512-oG7cgbmg5kLYae2N5IVd3jm2s+vldjxJzK1pcu9LfpGuQ93MQSzo0okvRna+7y5ifrD+20FE8FvjusyGaz14fw==} + engines: {node: '>=18'} + isexe@2.0.0: resolution: {integrity: sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==} @@ -3609,6 +4199,9 @@ packages: resolution: {integrity: sha512-hXdUTZYIVOt1Ex//jAQi+wTZZpUpwBj/0QsOzqegb3rGMMeJiSEu5xLHnYfBrRV4RH2+OCSOO95Is/7x1WJ4bw==} engines: {node: '>=10'} + mark.js@8.11.1: + resolution: {integrity: sha512-1I+1qpDt4idfgLQG+BNWmrqku+7/2bi5nLf4YwF8y8zXvmfiTBY3PV3ZibfrjBueCByROpuBjLLFCajqkgYoLQ==} + markdown-table@3.0.4: resolution: {integrity: sha512-wiYz4+JrLyb/DqW2hkFJxP7Vd7JuTDm77fvbM8VfEQdmSMqcImWeeRbHwZjBjIFki/VaMK2BhFi7oUUZeM5bqw==} @@ -3644,6 +4237,9 @@ packages: mdast-util-phrasing@4.1.0: resolution: {integrity: sha512-TqICwyvJJpBwvGAMZjj4J2n0X8QWp21b9l0o7eXyVJ25YNWYbJDVIyD1bZXE6WtV6RmKJVYmQAKWa0zWOABz2w==} + mdast-util-to-hast@13.2.1: + resolution: {integrity: sha512-cctsq2wp5vTsLIcaymblUriiTcZd0CwWtCbLvrOzYCDZoWyMNV8sZ7krj09FSnsiJi3WVsHLM4k6Dq/yaPyCXA==} + mdast-util-to-markdown@2.1.2: resolution: {integrity: sha512-xj68wMTvGXVOKonmog6LwyJKrYXZPvlwabaryTjLh9LuvovB/KAH+kvi8Gjj+7rJjsFi23nkUxRQv1KqSroMqA==} @@ -3744,6 +4340,12 @@ packages: resolution: {integrity: sha512-MULkVLfKGYDFYejP07QOurDLLQpcjk7Fw+7jXS2R2czRQzR56yHRveU5NDJEOviH+hETZKSkIk5c+T23GjFUMg==} engines: {node: 18 || 20 || >=22} + minisearch@7.2.0: + resolution: {integrity: sha512-dqT2XBYUOZOiC5t2HRnwADjhNS2cecp9u+TJRiJ1Qp/f5qjkeT5APcGPjHw+bz89Ms8Jp+cG4AlE+QZ/QnDglg==} + + mitt@3.0.1: + resolution: {integrity: sha512-vKivATfr97l2/QBCYAkXYDbrIWPM2IIKEl7YPhjCvKlG3kE2gm+uBo6nEXK3M5/Ffh/FLpKExzOQ3JJoJGFKBw==} + mri@1.2.0: resolution: {integrity: sha512-tzzskb3bG8LvYGFF/mDTpq3jpI6Q9wc3LEmBaghu+DdCssd1FakN7Bc0hVNmEyGq1bq3RgfkCb3cmQLpNPOroA==} engines: {node: '>=4'} @@ -3772,6 +4374,9 @@ packages: resolution: {integrity: sha512-9miFgM2OFba7hB+pRgvtV84pYTBaoTHohvmIgiRt6dRIzbwEOIaNaP+dIlGs2fNFoB0SeISs0Jz5WFVRid6Xyg==} engines: {node: '>=12.20.0'} + oniguruma-to-es@3.1.1: + resolution: {integrity: sha512-bUH8SDvPkH3ho3dvwJwfonjlQ4R80vjyvrU8YpxuROddv55vAEJrTuCuCVUhhsHbtlD9tGGbaNApGQckXhS8iQ==} + openai@6.26.0: resolution: {integrity: sha512-zd23dbWTjiJ6sSAX6s0HrCZi41JwTA1bQVs0wLQPZ2/5o2gxOJA5wh7yOAUgwYybfhDXyhwlpeQf7Mlgx8EOCA==} hasBin: true @@ -3834,6 +4439,9 @@ packages: pathe@2.0.3: resolution: {integrity: sha512-WUjGcAqP1gQacoQe+OBJsFA7Ld4DyXuUIjZ5cc75cLHvJ7dtNsTugphxIADwspS+AraAUePCKrSVtPLFj/F88w==} + perfect-debounce@1.0.0: + resolution: {integrity: sha512-xCy9V055GLEqoFaHoC1SoLIaLmWctgCUaBaWxDZ7/Zx4CTyX7cJQLJOok/orfjZAh9kEYpjJa4d0KcJmCbctZA==} + picocolors@1.1.1: resolution: {integrity: sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA==} @@ -3851,10 +4459,21 @@ packages: resolution: {integrity: sha512-FfR8sjd4em2T6fb3I2MwAJU7HWVMr9zba+enmQeeWFfCbm+UOC/0X4DS8XtpUTMwWMGbjKYP7xjfNekzyGmB3A==} engines: {node: ^10 || ^12 || >=14} + preact@10.29.7: + resolution: {integrity: sha512-DCHYrK/B10yUD3ZjLfhZ3WIE/9Vf9VFUODcRE2dRomTYDpJk6z6L9wecSfhfE6M9ZTHUdyQkoC46arIDhEV84Q==} + peerDependencies: + preact-render-to-string: '>=5' + peerDependenciesMeta: + preact-render-to-string: + optional: true + prelude-ls@1.2.1: resolution: {integrity: sha512-vkcDPrRZo1QZLbn5RLGPpg/WmIQ65qoWWhcGKf/b5eplkkarX0m9z8ppCat4mlOqUsWpyNuYgO3VRyrYHSzX5g==} engines: {node: '>= 0.8.0'} + property-information@7.2.0: + resolution: {integrity: sha512-IAtzIB6sUiWaJYrX9smp3V46pBGbBeLFRGdh25kg1334VcBlD8HzhPeNIWQH9zhGmo2itIe25EHt9dQP7G5hmg==} + protobufjs@7.6.4: resolution: {integrity: sha512-RJJPTTpvFfHcWLkIa2JFWK4XvtSzS0yEWDmunqHXli1h3JlkbcQZXDZdcWxv+JK3Xsl5/UFDPZ0iGm7DAengYw==} engines: {node: '>=12.0.0'} @@ -3878,6 +4497,15 @@ packages: resolution: {integrity: sha512-GDhwkLfywWL2s6vEjyhri+eXmfH6j1L7JE27WhqLeYzoh/A3DBaYGEj2H/HFZCn/kMfim73FXxEJTw06WtxQwg==} engines: {node: '>= 14.18.0'} + regex-recursion@6.0.2: + resolution: {integrity: sha512-0YCaSCq2VRIebiaUviZNs0cBz1kg5kVS2UKUfNIx8YVs1cN3AV7NTctO5FOKBA+UT2BPJIWZauYHPqJODG50cg==} + + regex-utilities@2.3.0: + resolution: {integrity: sha512-8VhliFJAWRaUiVvREIiW2NXXTmHs4vMNnSzuJVhscgmGav3g9VDxLrQndI3dZZVVdp0ZO/5v0xmX516/7M9cng==} + + regex@6.1.0: + resolution: {integrity: sha512-6VwtthbV4o/7+OaAF9I5L5V3llLEsoPyq9P1JVXkedTP33c7MfCG0/5NOPcSJn0TzXcG9YUrR0gQSWioew3LDg==} + require-from-string@2.0.2: resolution: {integrity: sha512-Xf0nWe6RseziFMu+Ap9biiUbmplq6S9/p+7w7YXP/JBHhrUDDUhwa+vANyubuqfZWTveU//DYVGsDG7RKL/vEw==} engines: {node: '>=0.10.0'} @@ -3889,6 +4517,9 @@ packages: resolution: {integrity: sha512-XQBQ3I8W1Cge0Seh+6gjj03LbmRFWuoszgK9ooCpwYIrhhoO80pfq4cUkU5DkknwfOfFteRwlZ56PYOGYyFWdg==} engines: {node: '>= 4'} + rfdc@1.4.1: + resolution: {integrity: sha512-q1b3N5QkRUWUl7iyylaaj3kOpIT0N2i9MqIEQXP73GVsN9cw3fdx8X63cEmWhJGi2PPCF23Ijp7ktmd39rawIA==} + robust-predicates@3.0.3: resolution: {integrity: sha512-NS3levdsRIUOmiJ8FZWCP7LG3QpJyrs/TE0Zpf1yvZu8cAJJ6QMW92H1c7kWpdIHo8RvmLxN/o2JXTKHp74lUA==} @@ -3921,6 +4552,11 @@ packages: engines: {node: ^20.19.0 || >=22.12.0} hasBin: true + rollup@4.62.2: + resolution: {integrity: sha512-RFnrW4lhXA3s3eqHDZvN654g8OTjzRfqpIRJYczCGB6HzphckVAi/Qh4tbPUbRuDi7s1Llv8g/NspLkttY3gTA==} + engines: {node: '>=18.0.0', npm: '>=8.0.0'} + hasBin: true + roughjs@4.6.6: resolution: {integrity: sha512-ZUz/69+SYpFN/g/lUlo2FXcIjRkSu3nDarreVdGGndHEBJ6cXPdKguS8JGxwj5HA5xIbVKSmLgr5b3AWxtRfvQ==} @@ -3944,6 +4580,9 @@ packages: schemastery@3.18.0: resolution: {integrity: sha512-Jw2uxjoyyqc/yeurmChUEc/jbi8GsrdXV/KmqRUDZXJAXAmrJiPsz8vKa17l/VckyzljHZ9oGaul443CQiXxtA==} + search-insights@2.17.3: + resolution: {integrity: sha512-RQPdCYTa8A68uM2jwxoY842xDhvx3E5LFL1LxvxCNMev4o5mLuokczhzjAgGwUZBAmOKZknArSxLKmXtIi2AxQ==} + semver@7.8.4: resolution: {integrity: sha512-rUCObTnP32Q08R2uuIrt7r9PlEonuTmtuXYcW6s5kjdlj3xbnwe+21yXptAUYcMAABLkYYTtnmzb3w3EDZfueA==} engines: {node: '>=10'} @@ -3957,6 +4596,9 @@ packages: resolution: {integrity: sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A==} engines: {node: '>=8'} + shiki@2.5.0: + resolution: {integrity: sha512-mI//trrsaiCIPsja5CNfsyNOqgAZUb6VpJA+340toL42UpzQlXpwRV9nch69X6gaUxrr9kaOOa6e3y3uAkGFxQ==} + siginfo@2.0.0: resolution: {integrity: sha512-ybx0WO1/8bSBLEWXZvEd7gMW3Sn3JFlW3TvX1nREbDLRNQNaeNN8WK0meBwPdAaOI7TtRRRJn/Es1zhrrCHu7g==} @@ -3968,12 +4610,22 @@ packages: resolution: {integrity: sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA==} engines: {node: '>=0.10.0'} + space-separated-tokens@2.0.2: + resolution: {integrity: sha512-PEGlAwrG8yXGXRjW32fGbg66JAlOAwbObuqVoJpv/mRgoWDQfgH1wDPvtzWyUSNAXBGSk8h755YDbbcEy3SH2Q==} + + speakingurl@14.0.1: + resolution: {integrity: sha512-1POYv7uv2gXoyGFpBCmpDVSNV74IfsWlDW216UPjbWufNf+bSU6GdbDsxdcxtfwb4xlI3yxzOTKClUosxARYrQ==} + engines: {node: '>=0.10.0'} + stackback@0.0.2: resolution: {integrity: sha512-1XMJE5fQo1jGH6Y/7ebnwPOBEkIEnT4QF32d5R1+VXdXveM0IBMJt8zfaxX1P3QhVwrYe+576+jkANtSS2mBbw==} std-env@4.1.0: resolution: {integrity: sha512-Rq7ybcX2RuC55r9oaPVEW7/xu3tj8u4GeBYHBWCychFtzMIr86A7e3PPEBPT37sHStKX3+TiX/Fr/ACmJLVlLQ==} + stringify-entities@4.0.4: + resolution: {integrity: sha512-IwfBptatlO+QCJUo19AqvrPNqlVMpW9YEL2LIVY+Rpv2qsjCGxaDLNRgeGsQWJhfItebuJhsGSLjaBbNSQ+ieg==} + strip-json-comments@5.0.3: resolution: {integrity: sha512-1tB5mhVo7U+ETBKNf92xT4hrQa3pm0MZ0PQvuDnWgAAGHDsfp4lPSpiS6psrSiet87wyGPh9ft6wmhOMQ0hDiw==} engines: {node: '>=14.16'} @@ -3984,6 +4636,10 @@ packages: stylis@4.4.0: resolution: {integrity: sha512-5Z9ZpRzfuH6l/UAvCPAPUo3665Nk2wLaZU3x+TLHKVzIz33+sbJqbtrYoC3KD4/uVOr2Zp+L0LySezP9OHV9yA==} + superjson@2.2.6: + resolution: {integrity: sha512-H+ue8Zo4vJmV2nRjpx86P35lzwDT3nItnIsocgumgr0hHMQ+ZGq5vrERg9kJBo5AWGmxZDhzDo+WVIJqkB0cGA==} + engines: {node: '>=16'} + supports-color@7.2.0: resolution: {integrity: sha512-qpCAvRl9stuOHveKsn7HncJRvv501qIacKzQlO/+Lwxc9+0q2wLyv4Dfvt80/DPn2pqOBsJdDiogXGR9+OvwRw==} engines: {node: '>=8'} @@ -3995,6 +4651,9 @@ packages: symbol-tree@3.2.4: resolution: {integrity: sha512-9QNk5KwDF+Bvz+PyObkmSYjI5ksVUYtjW7AU22r2NKcfLJcXp96hkDWU3+XndOsUb+AQ9QhfzfCT2O+CNWT5Tw==} + tabbable@6.5.0: + resolution: {integrity: sha512-wieBHXygIm7OyQOu5hQlkk62/WyCFYGlWg7L6/ZCUZwx0o398Zkn4pVmMyfYhfMG8kGrj/Krt8eIk6UKC6VzwA==} + tinybench@2.9.0: resolution: {integrity: sha512-0+DUvqWMValLmha6lr4kD8iAMK1HzV0/aKnCtWb9v9641TnP/MFb7Pc2bxoxQjTXAErryXVgUOfv2YqNllqGeg==} @@ -4029,6 +4688,9 @@ packages: resolution: {integrity: sha512-L0Orpi8qGpRG//Nd+H90vFB+3iHnue1zSSGmNOOCh1GLJ7rUKVwV2HvijphGQS2UmhUZewS9VgvxYIdgr+fG1A==} hasBin: true + trim-lines@3.0.1: + resolution: {integrity: sha512-kRj8B+YHZCc9kQYdWfJB2/oUl9rA99qbowYYBtr4ui4mZyAQ2JpvVBd/6U2YloATfqBhBTSMhTpgBHtU0Mf3Rg==} + ts-algebra@2.0.0: resolution: {integrity: sha512-FPAhNPFMrkwz76P7cdjdmiShwMynZYN6SgOujD1urY4oNm80Ou9oMdmbR45LotcKOXoy7wSmHkRFE6Mxbrhefw==} @@ -4134,6 +4796,9 @@ packages: unist-util-is@6.0.1: resolution: {integrity: sha512-LsiILbtBETkDz8I9p1dQ0uyRUWuaQzd/cuEeS1hoRSyW5E5XGmTzlwY1OrNzzakGowI9Dr/I8HVaw4hTtnxy8g==} + unist-util-position@5.0.0: + resolution: {integrity: sha512-fucsC7HjXvkB5R3kTCO7kUjRdrS0BJt3M/FPxmHMBOm8JQi2BsHAHFsy27E0EolP8rp0NzXsJ+jNPyDWvOJZPA==} + unist-util-stringify-position@4.0.0: resolution: {integrity: sha512-0ASV06AAoKCDkS2+xw5RXJywruurpbC4JZSm7nr7MOt1ojAzvyyaO+UxZf18j8FCF6kmzCZKcAgN/yu2gm2XgQ==} @@ -4150,11 +4815,48 @@ packages: resolution: {integrity: sha512-6ZxzVpzDXDa3bJWaHilVayA+BH/1zmxCJoVgvmqJnid/gPoKHxUrS/aC/T6LGQtNHT+XHG9fXPJB4d+IrU30Ew==} hasBin: true + vfile-message@4.0.3: + resolution: {integrity: sha512-QTHzsGd1EhbZs4AsQ20JX1rC3cOlt/IWJruk893DfLRr57lcnOeMaWG4K0JrRta4mIJZKth2Au3mM3u03/JWKw==} + + vfile@6.0.3: + resolution: {integrity: sha512-KzIbH/9tXat2u30jf+smMwFCsno4wHVdNmzFyL+T/L3UGqqk6JKfVqOFOZEpZSHADH1k40ab6NUIXZq422ov3Q==} + vite-tsconfig-paths@6.1.1: resolution: {integrity: sha512-2cihq7zliibCCZ8P9cKJrQBkfgdvcFkOOc3Y02o3GWUDLgqjWsZudaoiuOwO/gzTzy17cS5F7ZPo4bsnS4DGkg==} peerDependencies: vite: '*' + vite@5.4.21: + resolution: {integrity: sha512-o5a9xKjbtuhY6Bi5S3+HvbRERmouabWbyUcpXXUA1u+GNUKoROi9byOJ8M0nHbHYHkYICiMlqxkg1KkYmm25Sw==} + engines: {node: ^18.0.0 || >=20.0.0} + hasBin: true + peerDependencies: + '@types/node': ^18.0.0 || >=20.0.0 + less: '*' + lightningcss: ^1.21.0 + sass: '*' + sass-embedded: '*' + stylus: '*' + sugarss: '*' + terser: ^5.4.0 + peerDependenciesMeta: + '@types/node': + optional: true + less: + optional: true + lightningcss: + optional: true + sass: + optional: true + sass-embedded: + optional: true + stylus: + optional: true + sugarss: + optional: true + terser: + optional: true + vite@8.0.16: resolution: {integrity: sha512-h9bXPmJichP5fLmVQo3PyaGSDE2n3aPuomeAlVRm0JLmt4rY6zmPKd59HYI4LNW8oTK7tlTsuC7l/m7awx9Jcw==} engines: {node: ^20.19.0 || >=22.12.0} @@ -4198,6 +4900,18 @@ packages: yaml: optional: true + vitepress@1.6.4: + resolution: {integrity: sha512-+2ym1/+0VVrbhNyRoFFesVvBvHAVMZMK0rw60E3X/5349M1GuVdKeazuksqopEdvkKwKGs21Q729jX81/bkBJg==} + hasBin: true + peerDependencies: + markdown-it-mathjax3: ^4 + postcss: ^8 + peerDependenciesMeta: + markdown-it-mathjax3: + optional: true + postcss: + optional: true + vitest@4.1.8: resolution: {integrity: sha512-flY6ScbCIt9HThs+C5HS7jvGOB560DJtk/Z15IQROTA6zEy49Nh8T/dofWTQL+n3vswqn87sbJNiuqw1SDp5Ig==} engines: {node: ^20.0.0 || ^22.0.0 || >=24.0.0} @@ -4239,6 +4953,14 @@ packages: jsdom: optional: true + vue@3.5.39: + resolution: {integrity: sha512-xmZCYabFGcirU8r0fTuvl/LICc1OU620rnqepaJDL/a141ZigkG7AyaxQLdqJ02ZRYzWe6YPaDHeQx7MfknQfA==} + peerDependencies: + typescript: '*' + peerDependenciesMeta: + typescript: + optional: true + w3c-xmlserializer@5.0.0: resolution: {integrity: sha512-o8qghlI8NZHU1lLPrpi2+Uq7abh4GGPpYANlalzWxyWteJOCsr/P+oPBA49TOLu5FTZO4d3F9MnWJfiMo4BkmA==} engines: {node: '>=18'} @@ -4326,6 +5048,118 @@ snapshots: dependencies: zod: 4.4.3 + '@algolia/abtesting@1.21.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/autocomplete-core@1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2)(search-insights@2.17.3)': + dependencies: + '@algolia/autocomplete-plugin-algolia-insights': 1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2)(search-insights@2.17.3) + '@algolia/autocomplete-shared': 1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2) + transitivePeerDependencies: + - '@algolia/client-search' + - algoliasearch + - search-insights + + '@algolia/autocomplete-plugin-algolia-insights@1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2)(search-insights@2.17.3)': + dependencies: + '@algolia/autocomplete-shared': 1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2) + search-insights: 2.17.3 + transitivePeerDependencies: + - '@algolia/client-search' + - algoliasearch + + '@algolia/autocomplete-preset-algolia@1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2)': + dependencies: + '@algolia/autocomplete-shared': 1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2) + '@algolia/client-search': 5.55.2 + algoliasearch: 5.55.2 + + '@algolia/autocomplete-shared@1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2)': + dependencies: + '@algolia/client-search': 5.55.2 + algoliasearch: 5.55.2 + + '@algolia/client-abtesting@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/client-analytics@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/client-common@5.55.2': {} + + '@algolia/client-insights@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/client-personalization@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/client-query-suggestions@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/client-search@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/ingestion@1.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/monitoring@1.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/recommend@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/requester-browser-xhr@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + + '@algolia/requester-fetch@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + + '@algolia/requester-node-http@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@antfu/install-pkg@1.1.0': dependencies: package-manager-detector: 1.6.0 @@ -4674,6 +5508,31 @@ snapshots: '@csstools/css-tokenizer@4.0.0': {} + '@docsearch/css@3.8.2': {} + + '@docsearch/js@3.8.2(@algolia/client-search@5.55.2)(search-insights@2.17.3)': + dependencies: + '@docsearch/react': 3.8.2(@algolia/client-search@5.55.2)(search-insights@2.17.3) + preact: 10.29.7 + transitivePeerDependencies: + - '@algolia/client-search' + - '@types/react' + - preact-render-to-string + - react + - react-dom + - search-insights + + '@docsearch/react@3.8.2(@algolia/client-search@5.55.2)(search-insights@2.17.3)': + dependencies: + '@algolia/autocomplete-core': 1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2)(search-insights@2.17.3) + '@algolia/autocomplete-preset-algolia': 1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2) + '@docsearch/css': 3.8.2 + algoliasearch: 5.55.2 + optionalDependencies: + search-insights: 2.17.3 + transitivePeerDependencies: + - '@algolia/client-search' + '@earendil-works/pi-ai@0.79.3(ws@8.21.0)(zod@4.4.3)': dependencies: '@anthropic-ai/sdk': 0.91.1(zod@4.4.3) @@ -4726,81 +5585,150 @@ snapshots: tslib: 2.8.1 optional: true + '@esbuild/aix-ppc64@0.21.5': + optional: true + '@esbuild/aix-ppc64@0.28.1': optional: true + '@esbuild/android-arm64@0.21.5': + optional: true + '@esbuild/android-arm64@0.28.1': optional: true + '@esbuild/android-arm@0.21.5': + optional: true + '@esbuild/android-arm@0.28.1': optional: true + '@esbuild/android-x64@0.21.5': + optional: true + '@esbuild/android-x64@0.28.1': optional: true + '@esbuild/darwin-arm64@0.21.5': + optional: true + '@esbuild/darwin-arm64@0.28.1': optional: true + '@esbuild/darwin-x64@0.21.5': + optional: true + '@esbuild/darwin-x64@0.28.1': optional: true + '@esbuild/freebsd-arm64@0.21.5': + optional: true + '@esbuild/freebsd-arm64@0.28.1': optional: true + '@esbuild/freebsd-x64@0.21.5': + optional: true + '@esbuild/freebsd-x64@0.28.1': optional: true + '@esbuild/linux-arm64@0.21.5': + optional: true + '@esbuild/linux-arm64@0.28.1': optional: true + '@esbuild/linux-arm@0.21.5': + optional: true + '@esbuild/linux-arm@0.28.1': optional: true + '@esbuild/linux-ia32@0.21.5': + optional: true + '@esbuild/linux-ia32@0.28.1': optional: true + '@esbuild/linux-loong64@0.21.5': + optional: true + '@esbuild/linux-loong64@0.28.1': optional: true + '@esbuild/linux-mips64el@0.21.5': + optional: true + '@esbuild/linux-mips64el@0.28.1': optional: true + '@esbuild/linux-ppc64@0.21.5': + optional: true + '@esbuild/linux-ppc64@0.28.1': optional: true + '@esbuild/linux-riscv64@0.21.5': + optional: true + '@esbuild/linux-riscv64@0.28.1': optional: true + '@esbuild/linux-s390x@0.21.5': + optional: true + '@esbuild/linux-s390x@0.28.1': optional: true + '@esbuild/linux-x64@0.21.5': + optional: true + '@esbuild/linux-x64@0.28.1': optional: true '@esbuild/netbsd-arm64@0.28.1': optional: true + '@esbuild/netbsd-x64@0.21.5': + optional: true + '@esbuild/netbsd-x64@0.28.1': optional: true '@esbuild/openbsd-arm64@0.28.1': optional: true + '@esbuild/openbsd-x64@0.21.5': + optional: true + '@esbuild/openbsd-x64@0.28.1': optional: true '@esbuild/openharmony-arm64@0.28.1': optional: true + '@esbuild/sunos-x64@0.21.5': + optional: true + '@esbuild/sunos-x64@0.28.1': optional: true + '@esbuild/win32-arm64@0.21.5': + optional: true + '@esbuild/win32-arm64@0.28.1': optional: true + '@esbuild/win32-ia32@0.21.5': + optional: true + '@esbuild/win32-ia32@0.28.1': optional: true + '@esbuild/win32-x64@0.21.5': + optional: true + '@esbuild/win32-x64@0.28.1': optional: true @@ -4863,6 +5791,10 @@ snapshots: '@humanwhocodes/retry@0.4.3': {} + '@iconify-json/simple-icons@1.2.90': + dependencies: + '@iconify/types': 2.0.0 + '@iconify/types@2.0.0': {} '@iconify/utils@3.1.3': @@ -5169,6 +6101,121 @@ snapshots: '@rolldown/pluginutils@1.0.1': {} + '@rollup/rollup-android-arm-eabi@4.62.2': + optional: true + + '@rollup/rollup-android-arm64@4.62.2': + optional: true + + '@rollup/rollup-darwin-arm64@4.62.2': + optional: true + + '@rollup/rollup-darwin-x64@4.62.2': + optional: true + + '@rollup/rollup-freebsd-arm64@4.62.2': + optional: true + + '@rollup/rollup-freebsd-x64@4.62.2': + optional: true + + '@rollup/rollup-linux-arm-gnueabihf@4.62.2': + optional: true + + '@rollup/rollup-linux-arm-musleabihf@4.62.2': + optional: true + + '@rollup/rollup-linux-arm64-gnu@4.62.2': + optional: true + + '@rollup/rollup-linux-arm64-musl@4.62.2': + optional: true + + '@rollup/rollup-linux-loong64-gnu@4.62.2': + optional: true + + '@rollup/rollup-linux-loong64-musl@4.62.2': + optional: true + + '@rollup/rollup-linux-ppc64-gnu@4.62.2': + optional: true + + '@rollup/rollup-linux-ppc64-musl@4.62.2': + optional: true + + '@rollup/rollup-linux-riscv64-gnu@4.62.2': + optional: true + + '@rollup/rollup-linux-riscv64-musl@4.62.2': + optional: true + + '@rollup/rollup-linux-s390x-gnu@4.62.2': + optional: true + + '@rollup/rollup-linux-x64-gnu@4.62.2': + optional: true + + '@rollup/rollup-linux-x64-musl@4.62.2': + optional: true + + '@rollup/rollup-openbsd-x64@4.62.2': + optional: true + + '@rollup/rollup-openharmony-arm64@4.62.2': + optional: true + + '@rollup/rollup-win32-arm64-msvc@4.62.2': + optional: true + + '@rollup/rollup-win32-ia32-msvc@4.62.2': + optional: true + + '@rollup/rollup-win32-x64-gnu@4.62.2': + optional: true + + '@rollup/rollup-win32-x64-msvc@4.62.2': + optional: true + + '@shikijs/core@2.5.0': + dependencies: + '@shikijs/engine-javascript': 2.5.0 + '@shikijs/engine-oniguruma': 2.5.0 + '@shikijs/types': 2.5.0 + '@shikijs/vscode-textmate': 10.0.2 + '@types/hast': 3.0.5 + hast-util-to-html: 9.0.5 + + '@shikijs/engine-javascript@2.5.0': + dependencies: + '@shikijs/types': 2.5.0 + '@shikijs/vscode-textmate': 10.0.2 + oniguruma-to-es: 3.1.1 + + '@shikijs/engine-oniguruma@2.5.0': + dependencies: + '@shikijs/types': 2.5.0 + '@shikijs/vscode-textmate': 10.0.2 + + '@shikijs/langs@2.5.0': + dependencies: + '@shikijs/types': 2.5.0 + + '@shikijs/themes@2.5.0': + dependencies: + '@shikijs/types': 2.5.0 + + '@shikijs/transformers@2.5.0': + dependencies: + '@shikijs/core': 2.5.0 + '@shikijs/types': 2.5.0 + + '@shikijs/types@2.5.0': + dependencies: + '@shikijs/vscode-textmate': 10.0.2 + '@types/hast': 3.0.5 + + '@shikijs/vscode-textmate@10.0.2': {} + '@smithy/core@3.24.7': dependencies: '@aws-crypto/crc32': 5.2.0 @@ -5376,6 +6423,12 @@ snapshots: '@types/geojson@7946.0.16': {} + '@types/hast@3.0.5': + dependencies: + '@types/unist': 3.0.3 + + '@types/js-yaml@4.0.9': {} + '@types/jsdom@28.0.3': dependencies: '@types/node': 25.9.3 @@ -5387,10 +6440,19 @@ snapshots: '@types/json-schema@7.0.15': {} + '@types/linkify-it@5.0.0': {} + + '@types/markdown-it@14.1.2': + dependencies: + '@types/linkify-it': 5.0.0 + '@types/mdurl': 2.0.0 + '@types/mdast@4.0.4': dependencies: '@types/unist': 3.0.3 + '@types/mdurl@2.0.0': {} + '@types/ms@2.1.0': {} '@types/node@22.20.0': @@ -5412,6 +6474,8 @@ snapshots: '@types/unist@3.0.3': {} + '@types/web-bluetooth@0.0.21': {} + '@typescript-eslint/eslint-plugin@8.61.0(@typescript-eslint/parser@8.61.0(eslint@10.5.0(jiti@2.7.0))(typescript@6.0.3))(eslint@10.5.0(jiti@2.7.0))(typescript@6.0.3)': dependencies: '@eslint-community/regexpp': 4.12.2 @@ -5503,11 +6567,18 @@ snapshots: '@typescript-eslint/types': 8.61.0 eslint-visitor-keys: 5.0.1 + '@ungap/structured-clone@1.3.3': {} + '@upsetjs/venn.js@2.0.0': optionalDependencies: d3-selection: 3.0.0 d3-transition: 3.0.1(d3-selection@3.0.0) + '@vitejs/plugin-vue@5.2.4(vite@5.4.21(@types/node@25.9.3)(lightningcss@1.32.0))(vue@3.5.39(typescript@6.0.3))': + dependencies: + vite: 5.4.21(@types/node@25.9.3)(lightningcss@1.32.0) + vue: 3.5.39(typescript@6.0.3) + '@vitest/coverage-v8@4.1.8(vitest@4.1.8)': dependencies: '@bcoe/v8-coverage': 1.0.2 @@ -5571,6 +6642,105 @@ snapshots: convert-source-map: 2.0.0 tinyrainbow: 3.1.0 + '@vue/compiler-core@3.5.39': + dependencies: + '@babel/parser': 7.29.7 + '@vue/shared': 3.5.39 + entities: 7.0.1 + estree-walker: 2.0.2 + source-map-js: 1.2.1 + + '@vue/compiler-dom@3.5.39': + dependencies: + '@vue/compiler-core': 3.5.39 + '@vue/shared': 3.5.39 + + '@vue/compiler-sfc@3.5.39': + dependencies: + '@babel/parser': 7.29.7 + '@vue/compiler-core': 3.5.39 + '@vue/compiler-dom': 3.5.39 + '@vue/compiler-ssr': 3.5.39 + '@vue/shared': 3.5.39 + estree-walker: 2.0.2 + magic-string: 0.30.21 + postcss: 8.5.15 + source-map-js: 1.2.1 + + '@vue/compiler-ssr@3.5.39': + dependencies: + '@vue/compiler-dom': 3.5.39 + '@vue/shared': 3.5.39 + + '@vue/devtools-api@7.7.10': + dependencies: + '@vue/devtools-kit': 7.7.10 + + '@vue/devtools-kit@7.7.10': + dependencies: + '@vue/devtools-shared': 7.7.10 + birpc: 2.9.0 + hookable: 5.5.3 + mitt: 3.0.1 + perfect-debounce: 1.0.0 + speakingurl: 14.0.1 + superjson: 2.2.6 + + '@vue/devtools-shared@7.7.10': + dependencies: + rfdc: 1.4.1 + + '@vue/reactivity@3.5.39': + dependencies: + '@vue/shared': 3.5.39 + + '@vue/runtime-core@3.5.39': + dependencies: + '@vue/reactivity': 3.5.39 + '@vue/shared': 3.5.39 + + '@vue/runtime-dom@3.5.39': + dependencies: + '@vue/reactivity': 3.5.39 + '@vue/runtime-core': 3.5.39 + '@vue/shared': 3.5.39 + csstype: 3.2.3 + + '@vue/server-renderer@3.5.39(vue@3.5.39(typescript@6.0.3))': + dependencies: + '@vue/compiler-ssr': 3.5.39 + '@vue/shared': 3.5.39 + vue: 3.5.39(typescript@6.0.3) + + '@vue/shared@3.5.39': {} + + '@vueuse/core@12.8.2(typescript@6.0.3)': + dependencies: + '@types/web-bluetooth': 0.0.21 + '@vueuse/metadata': 12.8.2 + '@vueuse/shared': 12.8.2(typescript@6.0.3) + vue: 3.5.39(typescript@6.0.3) + transitivePeerDependencies: + - typescript + + '@vueuse/integrations@12.8.2(focus-trap@7.8.0)(typescript@6.0.3)': + dependencies: + '@vueuse/core': 12.8.2(typescript@6.0.3) + '@vueuse/shared': 12.8.2(typescript@6.0.3) + vue: 3.5.39(typescript@6.0.3) + optionalDependencies: + focus-trap: 7.8.0 + transitivePeerDependencies: + - typescript + + '@vueuse/metadata@12.8.2': {} + + '@vueuse/shared@12.8.2(typescript@6.0.3)': + dependencies: + vue: 3.5.39(typescript@6.0.3) + transitivePeerDependencies: + - typescript + acorn-jsx@5.3.2(acorn@8.17.0): dependencies: acorn: 8.17.0 @@ -5586,6 +6756,23 @@ snapshots: json-schema-traverse: 0.4.1 uri-js: 4.4.1 + algoliasearch@5.55.2: + dependencies: + '@algolia/abtesting': 1.21.2 + '@algolia/client-abtesting': 5.55.2 + '@algolia/client-analytics': 5.55.2 + '@algolia/client-common': 5.55.2 + '@algolia/client-insights': 5.55.2 + '@algolia/client-personalization': 5.55.2 + '@algolia/client-query-suggestions': 5.55.2 + '@algolia/client-search': 5.55.2 + '@algolia/ingestion': 1.55.2 + '@algolia/monitoring': 1.55.2 + '@algolia/recommend': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + ansis@4.3.1: {} anynum@1.0.0: {} @@ -5616,6 +6803,8 @@ snapshots: bignumber.js@9.3.1: {} + birpc@2.9.0: {} + birpc@4.0.0: {} bowser@2.14.1: {} @@ -5632,18 +6821,28 @@ snapshots: chai@6.2.2: {} + character-entities-html4@2.1.0: {} + + character-entities-legacy@3.0.0: {} + character-entities@2.0.2: {} chokidar@4.0.3: dependencies: readdirp: 4.1.2 + comma-separated-tokens@2.0.3: {} + commander@7.2.0: {} commander@8.3.0: {} convert-source-map@2.0.0: {} + copy-anything@4.0.5: + dependencies: + is-what: 5.5.0 + cordis@4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4): dependencies: '@standard-schema/spec': 1.1.0 @@ -5681,6 +6880,8 @@ snapshots: mdn-data: 2.27.1 source-map-js: 1.2.1 + csstype@3.2.3: {} + cytoscape-cose-bilkent@4.1.0(cytoscape@3.34.0): dependencies: cose-base: 1.0.3 @@ -5916,14 +7117,44 @@ snapshots: dependencies: safe-buffer: 5.2.1 + emoji-regex-xs@1.0.0: {} + empathic@2.0.1: {} + entities@7.0.1: {} + entities@8.0.0: {} es-module-lexer@2.1.0: {} es-toolkit@1.49.0: {} + esbuild@0.21.5: + optionalDependencies: + '@esbuild/aix-ppc64': 0.21.5 + '@esbuild/android-arm': 0.21.5 + '@esbuild/android-arm64': 0.21.5 + '@esbuild/android-x64': 0.21.5 + '@esbuild/darwin-arm64': 0.21.5 + '@esbuild/darwin-x64': 0.21.5 + '@esbuild/freebsd-arm64': 0.21.5 + '@esbuild/freebsd-x64': 0.21.5 + '@esbuild/linux-arm': 0.21.5 + '@esbuild/linux-arm64': 0.21.5 + '@esbuild/linux-ia32': 0.21.5 + '@esbuild/linux-loong64': 0.21.5 + '@esbuild/linux-mips64el': 0.21.5 + '@esbuild/linux-ppc64': 0.21.5 + '@esbuild/linux-riscv64': 0.21.5 + '@esbuild/linux-s390x': 0.21.5 + '@esbuild/linux-x64': 0.21.5 + '@esbuild/netbsd-x64': 0.21.5 + '@esbuild/openbsd-x64': 0.21.5 + '@esbuild/sunos-x64': 0.21.5 + '@esbuild/win32-arm64': 0.21.5 + '@esbuild/win32-ia32': 0.21.5 + '@esbuild/win32-x64': 0.21.5 + esbuild@0.28.1: optionalDependencies: '@esbuild/aix-ppc64': 0.28.1 @@ -6029,6 +7260,8 @@ snapshots: estraverse@5.3.0: {} + estree-walker@2.0.2: {} + estree-walker@3.0.3: dependencies: '@types/estree': 1.0.9 @@ -6090,6 +7323,10 @@ snapshots: flatted@3.4.2: {} + focus-trap@7.8.0: + dependencies: + tabbable: 6.5.0 + formatly@0.3.0: dependencies: fd-package-json: 2.0.0 @@ -6148,6 +7385,26 @@ snapshots: has-flag@4.0.0: {} + hast-util-to-html@9.0.5: + dependencies: + '@types/hast': 3.0.5 + '@types/unist': 3.0.3 + ccount: 2.0.1 + comma-separated-tokens: 2.0.3 + hast-util-whitespace: 3.0.0 + html-void-elements: 3.0.0 + mdast-util-to-hast: 13.2.1 + property-information: 7.2.0 + space-separated-tokens: 2.0.2 + stringify-entities: 4.0.4 + zwitch: 2.0.4 + + hast-util-whitespace@3.0.0: + dependencies: + '@types/hast': 3.0.5 + + hookable@5.5.3: {} + hookable@6.1.1: {} html-encoding-sniffer@6.0.0: @@ -6158,6 +7415,8 @@ snapshots: html-escaper@2.0.2: {} + html-void-elements@3.0.0: {} + http-proxy-agent@7.0.2: dependencies: agent-base: 7.1.4 @@ -6198,6 +7457,8 @@ snapshots: is-potential-custom-element-name@1.0.1: {} + is-what@5.5.0: {} + isexe@2.0.0: {} istanbul-lib-coverage@3.2.2: {} @@ -6430,6 +7691,8 @@ snapshots: dependencies: semver: 7.8.4 + mark.js@8.11.1: {} + markdown-table@3.0.4: {} marked@16.4.2: {} @@ -6520,6 +7783,18 @@ snapshots: '@types/mdast': 4.0.4 unist-util-is: 6.0.1 + mdast-util-to-hast@13.2.1: + dependencies: + '@types/hast': 3.0.5 + '@types/mdast': 4.0.4 + '@ungap/structured-clone': 1.3.3 + devlop: 1.1.0 + micromark-util-sanitize-uri: 2.0.1 + trim-lines: 3.0.1 + unist-util-position: 5.0.0 + unist-util-visit: 5.1.0 + vfile: 6.0.3 + mdast-util-to-markdown@2.1.2: dependencies: '@types/mdast': 4.0.4 @@ -6757,6 +8032,10 @@ snapshots: dependencies: brace-expansion: 5.0.6 + minisearch@7.2.0: {} + + mitt@3.0.1: {} + mri@1.2.0: {} ms@2.1.3: {} @@ -6775,6 +8054,12 @@ snapshots: obug@2.1.3: {} + oniguruma-to-es@3.1.1: + dependencies: + emoji-regex-xs: 1.0.0 + regex: 6.1.0 + regex-recursion: 6.0.2 + openai@6.26.0(ws@8.21.0)(zod@4.4.3): optionalDependencies: ws: 8.21.0 @@ -6867,6 +8152,8 @@ snapshots: pathe@2.0.3: {} + perfect-debounce@1.0.0: {} + picocolors@1.1.1: {} picomatch@4.0.4: {} @@ -6884,8 +8171,12 @@ snapshots: picocolors: 1.1.1 source-map-js: 1.2.1 + preact@10.29.7: {} + prelude-ls@1.2.1: {} + property-information@7.2.0: {} + protobufjs@7.6.4: dependencies: '@protobufjs/aspromise': 1.1.2 @@ -6915,12 +8206,24 @@ snapshots: readdirp@4.1.2: {} + regex-recursion@6.0.2: + dependencies: + regex-utilities: 2.3.0 + + regex-utilities@2.3.0: {} + + regex@6.1.0: + dependencies: + regex-utilities: 2.3.0 + require-from-string@2.0.2: {} resolve-pkg-maps@1.0.0: {} retry@0.13.1: {} + rfdc@1.4.1: {} + robust-predicates@3.0.3: {} rolldown-plugin-dts@0.25.2(oxc-resolver@11.20.0)(rolldown@1.1.1)(typescript@6.0.3): @@ -6981,6 +8284,37 @@ snapshots: '@rolldown/binding-win32-arm64-msvc': 1.1.1 '@rolldown/binding-win32-x64-msvc': 1.1.1 + rollup@4.62.2: + dependencies: + '@types/estree': 1.0.9 + optionalDependencies: + '@rollup/rollup-android-arm-eabi': 4.62.2 + '@rollup/rollup-android-arm64': 4.62.2 + '@rollup/rollup-darwin-arm64': 4.62.2 + '@rollup/rollup-darwin-x64': 4.62.2 + '@rollup/rollup-freebsd-arm64': 4.62.2 + '@rollup/rollup-freebsd-x64': 4.62.2 + '@rollup/rollup-linux-arm-gnueabihf': 4.62.2 + '@rollup/rollup-linux-arm-musleabihf': 4.62.2 + '@rollup/rollup-linux-arm64-gnu': 4.62.2 + '@rollup/rollup-linux-arm64-musl': 4.62.2 + '@rollup/rollup-linux-loong64-gnu': 4.62.2 + '@rollup/rollup-linux-loong64-musl': 4.62.2 + '@rollup/rollup-linux-ppc64-gnu': 4.62.2 + '@rollup/rollup-linux-ppc64-musl': 4.62.2 + '@rollup/rollup-linux-riscv64-gnu': 4.62.2 + '@rollup/rollup-linux-riscv64-musl': 4.62.2 + '@rollup/rollup-linux-s390x-gnu': 4.62.2 + '@rollup/rollup-linux-x64-gnu': 4.62.2 + '@rollup/rollup-linux-x64-musl': 4.62.2 + '@rollup/rollup-openbsd-x64': 4.62.2 + '@rollup/rollup-openharmony-arm64': 4.62.2 + '@rollup/rollup-win32-arm64-msvc': 4.62.2 + '@rollup/rollup-win32-ia32-msvc': 4.62.2 + '@rollup/rollup-win32-x64-gnu': 4.62.2 + '@rollup/rollup-win32-x64-msvc': 4.62.2 + fsevents: 2.3.3 + roughjs@4.6.6: dependencies: hachure-fill: 0.5.2 @@ -7007,6 +8341,8 @@ snapshots: '@standard-schema/spec': 1.1.0 cosmokit: 1.8.1 + search-insights@2.17.3: {} + semver@7.8.4: {} shebang-command@2.0.0: @@ -7015,16 +8351,36 @@ snapshots: shebang-regex@3.0.0: {} + shiki@2.5.0: + dependencies: + '@shikijs/core': 2.5.0 + '@shikijs/engine-javascript': 2.5.0 + '@shikijs/engine-oniguruma': 2.5.0 + '@shikijs/langs': 2.5.0 + '@shikijs/themes': 2.5.0 + '@shikijs/types': 2.5.0 + '@shikijs/vscode-textmate': 10.0.2 + '@types/hast': 3.0.5 + siginfo@2.0.0: {} smol-toml@1.6.1: {} source-map-js@1.2.1: {} + space-separated-tokens@2.0.2: {} + + speakingurl@14.0.1: {} + stackback@0.0.2: {} std-env@4.1.0: {} + stringify-entities@4.0.4: + dependencies: + character-entities-html4: 2.1.0 + character-entities-legacy: 3.0.0 + strip-json-comments@5.0.3: {} strnum@2.4.0: @@ -7033,6 +8389,10 @@ snapshots: stylis@4.4.0: {} + superjson@2.2.6: + dependencies: + copy-anything: 4.0.5 + supports-color@7.2.0: dependencies: has-flag: 4.0.0 @@ -7041,6 +8401,8 @@ snapshots: symbol-tree@3.2.4: {} + tabbable@6.5.0: {} + tinybench@2.9.0: {} tinyexec@1.2.4: {} @@ -7068,6 +8430,8 @@ snapshots: tree-kill@1.2.2: {} + trim-lines@3.0.1: {} + ts-algebra@2.0.0: {} ts-api-utils@2.5.0(typescript@6.0.3): @@ -7151,6 +8515,10 @@ snapshots: dependencies: '@types/unist': 3.0.3 + unist-util-position@5.0.0: + dependencies: + '@types/unist': 3.0.3 + unist-util-stringify-position@4.0.0: dependencies: '@types/unist': 3.0.3 @@ -7172,6 +8540,16 @@ snapshots: uuid@14.0.1: {} + vfile-message@4.0.3: + dependencies: + '@types/unist': 3.0.3 + unist-util-stringify-position: 4.0.0 + + vfile@6.0.3: + dependencies: + '@types/unist': 3.0.3 + vfile-message: 4.0.3 + vite-tsconfig-paths@6.1.1(typescript@6.0.3)(vite@8.0.16(@types/node@22.20.0)(esbuild@0.28.1)(jiti@2.7.0)(tsx@4.22.4)(yaml@2.9.0)): dependencies: debug: 4.4.3 @@ -7182,6 +8560,16 @@ snapshots: - supports-color - typescript + vite@5.4.21(@types/node@25.9.3)(lightningcss@1.32.0): + dependencies: + esbuild: 0.21.5 + postcss: 8.5.15 + rollup: 4.62.2 + optionalDependencies: + '@types/node': 25.9.3 + fsevents: 2.3.3 + lightningcss: 1.32.0 + vite@8.0.16(@types/node@22.20.0)(esbuild@0.28.1)(jiti@2.7.0)(tsx@4.22.4)(yaml@2.9.0): dependencies: lightningcss: 1.32.0 @@ -7212,6 +8600,56 @@ snapshots: tsx: 4.22.4 yaml: 2.9.0 + vitepress@1.6.4(@algolia/client-search@5.55.2)(@types/node@25.9.3)(lightningcss@1.32.0)(postcss@8.5.15)(search-insights@2.17.3)(typescript@6.0.3): + dependencies: + '@docsearch/css': 3.8.2 + '@docsearch/js': 3.8.2(@algolia/client-search@5.55.2)(search-insights@2.17.3) + '@iconify-json/simple-icons': 1.2.90 + '@shikijs/core': 2.5.0 + '@shikijs/transformers': 2.5.0 + '@shikijs/types': 2.5.0 + '@types/markdown-it': 14.1.2 + '@vitejs/plugin-vue': 5.2.4(vite@5.4.21(@types/node@25.9.3)(lightningcss@1.32.0))(vue@3.5.39(typescript@6.0.3)) + '@vue/devtools-api': 7.7.10 + '@vue/shared': 3.5.39 + '@vueuse/core': 12.8.2(typescript@6.0.3) + '@vueuse/integrations': 12.8.2(focus-trap@7.8.0)(typescript@6.0.3) + focus-trap: 7.8.0 + mark.js: 8.11.1 + minisearch: 7.2.0 + shiki: 2.5.0 + vite: 5.4.21(@types/node@25.9.3)(lightningcss@1.32.0) + vue: 3.5.39(typescript@6.0.3) + optionalDependencies: + postcss: 8.5.15 + transitivePeerDependencies: + - '@algolia/client-search' + - '@types/node' + - '@types/react' + - async-validator + - axios + - change-case + - drauu + - fuse.js + - idb-keyval + - jwt-decode + - less + - lightningcss + - nprogress + - preact-render-to-string + - qrcode + - react + - react-dom + - sass + - sass-embedded + - search-insights + - sortablejs + - stylus + - sugarss + - terser + - typescript + - universal-cookie + vitest@4.1.8(@types/node@22.20.0)(@vitest/coverage-v8@4.1.8)(jsdom@29.1.1)(vite@8.0.16(@types/node@22.20.0)(esbuild@0.28.1)(jiti@2.7.0)(tsx@4.22.4)(yaml@2.9.0)): dependencies: '@vitest/expect': 4.1.8 @@ -7270,6 +8708,16 @@ snapshots: transitivePeerDependencies: - msw + vue@3.5.39(typescript@6.0.3): + dependencies: + '@vue/compiler-dom': 3.5.39 + '@vue/compiler-sfc': 3.5.39 + '@vue/runtime-dom': 3.5.39 + '@vue/server-renderer': 3.5.39(vue@3.5.39(typescript@6.0.3)) + '@vue/shared': 3.5.39 + optionalDependencies: + typescript: 6.0.3 + w3c-xmlserializer@5.0.0: dependencies: xml-name-validator: 5.0.0 diff --git a/pnpm-workspace.yaml b/pnpm-workspace.yaml index b2b731fc58..dee7c5674c 100644 --- a/pnpm-workspace.yaml +++ b/pnpm-workspace.yaml @@ -1,6 +1,7 @@ packages: - vendor/* - packages/*/* + - website peerDependencyRules: allowedVersions: diff --git a/scripts/doc-typecheck.ts b/scripts/doc-typecheck.ts index e57f3710ee..f7bbaab312 100644 --- a/scripts/doc-typecheck.ts +++ b/scripts/doc-typecheck.ts @@ -2,7 +2,8 @@ * Doc-sync gate (doc-sync-enforcement RFC, part 1): typecheck the fenced `ts` code blocks in our * Markdown so documentation can't drift from the API it documents. * - * Every ```ts block in README.md, docs/** and packages/* /README.md is + * Every ```ts block in README.md, docs/**, packages/* /README.md and the + * website tutorial pages (website/zh-CN/**) is * extracted to a temp typecheck project and compiled against the workspace * sources through the same project-reference boundaries used by repo * typecheck. A block that is a deliberate sketch rather than compilable code @@ -134,7 +135,7 @@ function tempTsconfig(): string { }) } -const markdownGlobs = ['README.md', 'docs/**/*.md', 'packages/*/*.md', 'packages/*/*/*.md'] +const markdownGlobs = ['README.md', 'docs/**/*.md', 'packages/*/*.md', 'packages/*/*/*.md', 'website/zh-CN/**/*.md'] const files: string[] = [] for (const pattern of markdownGlobs) { diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index 9ee5a66ed6..958ddad0ae 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -167,6 +167,7 @@ function ciPrimaryGates(): Gate[] { ...docSyncLeafGates(), pnpmScript('module-graph', 'verify-module-graph', { label: 'module graph' }), pnpmScript('knip', 'knip'), + pnpmScript('website-build', 'website:build', { label: 'website build' }), pnpmScript('build', 'build', { needs: ['typecheck'] }), pnpmScript('publint', 'publint', { needs: ['build'] }), pnpmScript('node-next-types', 'verify-node-next-types', { @@ -184,6 +185,7 @@ function ciStaticGates(): Gate[] { ...docSyncLeafGates(), pnpmScript('module-graph', 'verify-module-graph', { label: 'module graph' }), pnpmScript('knip', 'knip'), + pnpmScript('website-build', 'website:build', { label: 'website build' }), ] } diff --git a/scripts/verify-type-equiv.ts b/scripts/verify-type-equiv.ts index 85ccd642d9..9ad1a4a29d 100644 --- a/scripts/verify-type-equiv.ts +++ b/scripts/verify-type-equiv.ts @@ -35,7 +35,7 @@ const root = resolve(import.meta.dirname, '..') * added to a doc with NO manifest entry is still discovered here and reported as * an orphan, instead of being silently skipped. */ -const MARKDOWN_GLOBS = ['README.md', 'docs/**/*.md', 'packages/*/*.md', 'packages/*/*/*.md'] +const MARKDOWN_GLOBS = ['README.md', 'docs/**/*.md', 'packages/*/*.md', 'packages/*/*/*.md', 'website/zh-CN/**/*.md'] /** One manifest entry: a documented type-equiv block and its source symbol. */ interface ManifestEntry { diff --git a/website/zh-CN/design/composability.md b/website/zh-CN/design/composability.md index 8370d8e136..a52a7bb8c5 100644 --- a/website/zh-CN/design/composability.md +++ b/website/zh-CN/design/composability.md @@ -55,16 +55,21 @@ Cordis 同时解决了上述两个问题： DeepSeek Harness 将 Cordis 的可组合性应用到 Agent 开发领域： -```typescript +```ts +import type { Context } from 'cordis' +import { defineTool } from '@deepseek-ai/dsh-tools' +import type {} from '@deepseek-ai/dsh-llm' + // 一个 Harness 插件天然是可逆的 export const inject = ['tools', 'llm'] // 空间可组合：声明依赖 export function apply(ctx: Context) { // 时间可组合：注册会被自动追踪和回收 - ctx.tools.register(defineTool('my-tool', { + ctx.tools.register(defineTool({ + name: 'my-tool', description: '...', parameters: { /* ... */ }, - async execute(args) { /* ... */ }, + async execute(args) { return [] }, })) } ``` diff --git a/website/zh-CN/design/context-model.md b/website/zh-CN/design/context-model.md index cc25df88e5..6323db27df 100644 --- a/website/zh-CN/design/context-model.md +++ b/website/zh-CN/design/context-model.md @@ -50,9 +50,14 @@ Root Context - 因此服务的提供被记录在作用上下文中 - 上下文将作用与余作用关联起来，提供了统一的时间、空间可组合性 -```typescript +```ts +import { Service, type Context } from 'cordis' + // 提供服务 = 一个 effect（占用 ctx.llm 这个 "资源"） class LlmService extends Service { + constructor(ctx: Context) { + super(ctx, 'llm') + } // 当此插件卸载时，ctx.llm 被回收（effect 的逆操作） // 所有依赖 llm 的插件因 coeffect 不满足而挂起 } @@ -66,7 +71,16 @@ class LlmService extends Service { 框架将领域中的所有方法都封装为 effect 版本。开发者只需调用 `ctx` 上的方法，就能自动获得时间/空间可组合性： -```typescript +```ts +import type { Context } from 'cordis' +import type { ToolDefinition } from '@deepseek-ai/dsh-tools' +import type { LlmAdapter, Message } from '@deepseek-ai/dsh-llm' +import type { Agent } from '@deepseek-ai/dsh-agent' + +declare function validateResult(agent: Agent, turn: number, step: number, message: Message, next: () => Promise): Promise +declare const myTool: ToolDefinition +declare const adapter: LlmAdapter + export function apply(ctx: Context) { // 以下每一行都是 effect——卸载时自动逆序回收 ctx.on('agent/step-result', validateResult) @@ -82,7 +96,16 @@ export function apply(ctx: Context) { 可以逐步将现有框架中的 API 替换为可组合版本，无需一次性重写： -```typescript +```ts +import type { Context } from 'cordis' + +declare const ctx: Context +declare function handler(): void +declare const legacySystem: { + register(handler: () => void): object + unregister(token: object): void +} + // 第一步：用 ctx.effect 包装遗留 API ctx.effect(() => { const legacy = legacySystem.register(handler) diff --git a/website/zh-CN/design/reactive-coeffects.md b/website/zh-CN/design/reactive-coeffects.md index 45345f934a..2ff6cb4199 100644 --- a/website/zh-CN/design/reactive-coeffects.md +++ b/website/zh-CN/design/reactive-coeffects.md @@ -24,13 +24,19 @@ Cordis 将程序中的资源依赖抽象为**服务** (service)： - 运行时对依赖不满足的插件**等待**，而非拒绝 - 服务生命周期结束前，依赖该服务的插件**先一步被回收** -```typescript +```ts +import { Service, type Context } from 'cordis' + // LLM 适配器插件：提供 llm 服务 export class LlmService extends Service { static inject = ['http'] // 自身依赖 http // 当 http 不可用时，LlmService 自动挂起 // 挂起导致 ctx.llm 不可用 // 所有 inject: ['llm'] 的插件级联挂起 + + constructor(ctx: Context) { + super(ctx, 'llm') + } } ``` @@ -57,7 +63,11 @@ export class LlmService extends Service { ## 在 Cordis 中的实现 -```typescript +```ts +import type { Context } from 'cordis' +import type {} from '@deepseek-ai/dsh-tools' +import type {} from '@deepseek-ai/dsh-llm' + // 声明依赖 export const inject = ['tools', 'llm'] @@ -85,6 +95,6 @@ llm service 恢复 → 依赖 llm 的插件重新 PENDING → ACTIVE | LLM adapter 热替换 | 依赖 `llm` 的插件自动挂起/恢复，中间不丢状态 | | 按需加载 bash 执行器 | bash tool 只在 `bash` 服务就绪后注册 | | 子 Agent 独立服务空间 | 通过 `ctx.isolate()` 隔离服务实例，互不干扰 | -| 可选能力降级 | `inject: { web: { required: false } }` 允许 web 不可用时继续运行 | +| 可选能力降级 | 不声明 `inject`，用 `ctx.get('web')` 读取——服务不可用时返回 `undefined`，插件照常运行 | 这意味着 Harness 插件开发者无需编写防御性的 "if service exists" 检查——框架保证：当你的 `apply` 被调用时，声明的依赖一定已就绪。 diff --git a/website/zh-CN/design/revertible-effects.md b/website/zh-CN/design/revertible-effects.md index 5133400e75..3cbcfdfc06 100644 --- a/website/zh-CN/design/revertible-effects.md +++ b/website/zh-CN/design/revertible-effects.md @@ -103,7 +103,20 @@ $$ | $\text{restore}$ | `fiber.dispose()` | 执行 Fiber 的整个回收链 | | $f^{-1}$ | dispose 返回值 / cleanup 函数 | 逆操作 | -```typescript +```ts +import type { Context } from 'cordis' +import type { ToolDefinition } from '@deepseek-ai/dsh-tools' + +declare module 'cordis' { + interface Events { + 'my-plugin/event'(): void + } +} + +declare function startServer(port: number): { close(): void } +declare function handler(): void +declare const myTool: ToolDefinition + export function apply(ctx: Context) { // effect: 创建资源，返回其逆操作 ctx.effect(() => { @@ -112,7 +125,7 @@ export function apply(ctx: Context) { }) // 框架 API 内部已封装 effect - ctx.on('event', handler) // 内部: effect(addListener, removeListener) + ctx.on('my-plugin/event', handler) // 内部: effect(addListener, removeListener) ctx.tools.register(myTool) // 内部: effect(addTool, removeTool) } // 当此插件被卸载时，restore 自动按逆序执行所有 f⁻¹ diff --git a/website/zh-CN/develop/basic/config.md b/website/zh-CN/develop/basic/config.md index 49bcc4ca77..8b1edf385f 100644 --- a/website/zh-CN/develop/basic/config.md +++ b/website/zh-CN/develop/basic/config.md @@ -4,27 +4,21 @@ ## 定义 Config 类型 -在插件中导出一个 `Config` 类型和可选的默认值： +在插件中导出一个 `Config` 类型，`apply` 的第二个参数就是用户配置： -```typescript +```ts import type { Context } from 'cordis' export const name = 'my-plugin' export interface Config { - greeting: string - maxRetries: number + greeting?: string + maxRetries?: number verbose?: boolean } -export const Config = { - greeting: 'Hello', - maxRetries: 3, - verbose: false, -} - export function apply(ctx: Context, config: Config) { - console.log(config.greeting) // 用户配置或默认值 + console.log(config.greeting ?? 'Hello') // 用户配置或默认值 } ``` @@ -37,32 +31,32 @@ export function apply(ctx: Context, config: Config) { maxRetries: 5 ``` -未提供的字段使用导出的 `Config` 对象中的默认值。 +只导出类型时，配置原样传入，默认值由代码自己兜底（如上面的 `??`）。想让框架代管默认值和校验，导出一个 schema（见下节）。 ## Schema 校验 -对于需要严格校验的场景，使用 Schemastery 定义 schema： +对于需要默认值和严格校验的场景，额外导出一个 Schemastery schema（仓库约定以 `z` 引入）。加载时框架先用它校验并填充默认值，再把结果传给 `apply`： -```typescript +```ts import type { Context } from 'cordis' -import Schema from 'schemastery' +import z from 'schemastery' export const name = 'validated-plugin' export interface Config { apiKey: string - timeout: number - mode: 'fast' | 'accurate' + timeout?: number + mode?: 'fast' | 'accurate' } -export const Config = Schema.object({ - apiKey: Schema.string().required(), - timeout: Schema.number().default(30000), - mode: Schema.union(['fast', 'accurate']).default('fast'), +export const Config: z = z.object({ + apiKey: z.string().required(), + timeout: z.number().default(30000), + mode: z.union(['fast', 'accurate'] as const).default('fast'), }) export function apply(ctx: Context, config: Config) { - // config 已经过校验，类型安全 + // config 已经过校验，类型安全，默认值已填充 } ``` @@ -74,13 +68,14 @@ Schema 在插件加载时执行校验。如果配置不合法，插件会加载 Harness 的约定：**任何两个部署可能想要不同值的东西，都应该是配置字段**。 -```typescript +```ts // 错误 — 硬编码超时时间 const TIMEOUT = 30000 // 正确 — 可配置 export interface Config { - timeoutMs: number // 默认 30000 + /** 默认 30000 */ + timeoutMs?: number } ``` @@ -90,9 +85,16 @@ export interface Config { 如果配置引用了不存在的东西（比如一个不存在的模型名），应该尽早报错，而不是静默跳过： -```typescript +```ts +import type { Context } from 'cordis' +import type {} from '@deepseek-ai/dsh-llm' + +export interface Config { + model: string +} + export function apply(ctx: Context, config: Config) { - if (!ctx.llm.hasAdapter(config.model)) { + if (!ctx.llm.models().includes(config.model)) { throw new Error(`Model "${config.model}" is not registered by any LLM adapter`) } } diff --git a/website/zh-CN/develop/basic/index.md b/website/zh-CN/develop/basic/index.md index 71d6962edd..6b482f1401 100644 --- a/website/zh-CN/develop/basic/index.md +++ b/website/zh-CN/develop/basic/index.md @@ -6,7 +6,7 @@ 在 Harness 中，插件是一个导出 `apply` 函数的 TypeScript 模块。框架在加载时调用 `apply`，传入一个 `ctx`（上下文对象），你通过 `ctx` 注册能力： -```typescript +```ts import type { Context } from 'cordis' export const name = 'my-plugin' @@ -22,16 +22,14 @@ export function apply(ctx: Context) { 在你的项目目录下创建 `src/my-plugin.ts`： -```typescript +```ts import type { Context } from 'cordis' export const name = 'hello-plugin' export function apply(ctx: Context) { - // 监听 agent-loop 的 ready 事件 - ctx.on('ready', () => { - console.log('[hello-plugin] 插件已加载!') - }) + // apply 函数体在插件加载时执行 + console.log('[hello-plugin] 插件已加载!') } ``` @@ -52,7 +50,9 @@ export function apply(ctx: Context) { 如果你有需要手动清理的资源（比如一个网络连接），用 `ctx.effect()` 告诉框架怎么清理： -```typescript +```ts +import type { Context } from 'cordis' + export function apply(ctx: Context) { ctx.effect(() => { const timer = setInterval(() => { @@ -69,13 +69,23 @@ export function apply(ctx: Context) { 如果你的插件需要使用其他服务（如 `tools`、`llm`），需要声明 `inject`： -```typescript +```ts +import type { Context } from 'cordis' +import { defineTool } from '@deepseek-ai/dsh-tools' + export const name = 'my-tool-plugin' export const inject = ['tools'] export function apply(ctx: Context) { // ctx.tools 现在可用 - ctx.tools.register(/* ... */) + ctx.tools.register(defineTool({ + name: 'demo', + description: 'Demo tool.', + parameters: {}, + async execute() { + return [] + }, + })) } ``` @@ -87,7 +97,10 @@ export function apply(ctx: Context) { ### 对象形式 -```typescript +```ts +import type { Context } from 'cordis' +import type {} from '@deepseek-ai/dsh-tools' + export default { name: 'my-plugin', inject: ['tools'], @@ -99,8 +112,9 @@ export default { ### 类形式 -```typescript -import { Service } from 'cordis' +```ts +import { Service, type Context } from 'cordis' +import type {} from '@deepseek-ai/dsh-tools' export default class MyService extends Service { static inject = ['tools'] @@ -109,8 +123,9 @@ export default class MyService extends Service { super(ctx, 'myService') } - start() { - // 服务启动逻辑 + // 服务的公开方法 + greet(name: string) { + return `Hello, ${name}!` } } ``` @@ -121,7 +136,7 @@ export default class MyService extends Service { 参考仓库中的 `examples/echo-agent/src/echo-tool.ts`，这是一个注册 tool 的插件： -```typescript +```ts import type { Context } from 'cordis' import { defineTool } from '@deepseek-ai/dsh-tools' diff --git a/website/zh-CN/develop/basic/tool.md b/website/zh-CN/develop/basic/tool.md index 96d58da78d..d9e6f10b80 100644 --- a/website/zh-CN/develop/basic/tool.md +++ b/website/zh-CN/develop/basic/tool.md @@ -4,7 +4,7 @@ Tool 是模型可以调用的能力。本文介绍如何用 `defineTool` 编写 ## 最小示例 -```typescript +```ts import type { Context } from 'cordis' import { defineTool } from '@deepseek-ai/dsh-tools' @@ -32,28 +32,34 @@ export function apply(ctx: Context) { ### 基本类型 -```typescript -parameters: { +```ts +import type { SchemaSpec } from '@deepseek-ai/dsh-tools' + +const parameters = { path: { type: 'string', required: true }, limit: { type: 'number' }, recursive: { type: 'boolean' }, -} +} satisfies SchemaSpec // 推导类型: { path: string; limit?: number; recursive?: boolean } ``` ### 枚举 -```typescript -parameters: { +```ts +import type { SchemaSpec } from '@deepseek-ai/dsh-tools' + +const parameters = { mode: { type: 'string', required: true, enum: ['read', 'write', 'append'] }, -} +} satisfies SchemaSpec // 推导类型: { mode: string } (运行时校验 enum 值) ``` ### 嵌套对象 -```typescript -parameters: { +```ts +import type { SchemaSpec } from '@deepseek-ai/dsh-tools' + +const parameters = { options: { type: 'object', properties: { @@ -61,19 +67,21 @@ parameters: { retries: { type: 'number' }, }, }, -} +} satisfies SchemaSpec // 推导类型: { options?: { timeout?: number; retries?: number } } ``` ### 数组 -```typescript -parameters: { +```ts +import type { SchemaSpec } from '@deepseek-ai/dsh-tools' + +const parameters = { tags: { type: 'array', items: { type: 'string' }, }, -} +} satisfies SchemaSpec // 推导类型: { tags?: string[] } ``` @@ -92,29 +100,44 @@ parameters: { `execute` 接收经过校验的 `args`（类型自动推导）和一个 `exec` 上下文对象： -```typescript -async execute(args, exec) { - // args: 根据 parameters 自动推导的类型 - // exec: ToolExecution 对象，提供执行上下文 +```ts +import { defineTool } from '@deepseek-ai/dsh-tools' - // 返回 ContentBlock 数组 - return [{ type: 'text', text: 'result here' }] -} +defineTool({ + name: 'demo', + description: 'Demo tool.', + parameters: {}, + async execute(args, exec) { + // args: 根据 parameters 自动推导的类型 + // exec: ToolExecution 对象，提供执行上下文 + + // 返回 ContentBlock 数组 + return [{ type: 'text', text: 'result here' }] + }, +}) ``` ### 返回值 `execute` 必须返回一个 `ContentBlock[]`，告诉模型 tool 的执行结果： -```typescript +```ts +import type { ContentBlock } from '@deepseek-ai/dsh-llm' + +declare const matchResults: string[] + // 文本结果 -return [{ type: 'text', text: 'file content here...' }] +function textResult(): ContentBlock[] { + return [{ type: 'text', text: 'file content here...' }] +} // 多个 block -return [ - { type: 'text', text: 'Found 3 matches:' }, - { type: 'text', text: matchResults.join('\n') }, -] +function multiBlockResult(): ContentBlock[] { + return [ + { type: 'text', text: 'Found 3 matches:' }, + { type: 'text', text: matchResults.join('\n') }, + ] +} ``` ### 参数校验 @@ -127,20 +150,28 @@ return [ Tool 可以定义 UI 渲染方法，用于在终端或 ACP 客户端中展示 tool call 和 result： -```typescript +```ts +import { defineTool } from '@deepseek-ai/dsh-tools' + defineTool({ name: 'bash', - // ... + description: 'Run a shell command.', + parameters: { + command: { type: 'string', required: true }, + }, + async execute(args) { + return [{ type: 'text', text: `ran: ${args.command}` }] + }, presentCall(args) { return { - intent: 'terminal', - title: `bash(${JSON.stringify(args.command).slice(0, 60)})`, + card: 'terminal', + title: args.command.slice(0, 60), } }, presentResult(args, result) { return { - intent: 'terminal', - body: result.content.map(b => b.type === 'text' ? b.text : '').join(''), + card: 'terminal', + output: result.content.map(b => b.type === 'text' ? b.text : '').join(''), } }, }) @@ -152,20 +183,32 @@ defineTool({ `ctx.tools.register()` 返回值就是 disposer。但由于你在 `ctx` 上调用，框架已经自动追踪了这个注册——插件卸载时会自动移除 tool。你不需要手动调用 disposer。 -```typescript +```ts +import type { Context } from 'cordis' +import { defineTool } from '@deepseek-ai/dsh-tools' + +declare const ctx: Context + // 这样就够了: -ctx.tools.register(defineTool({ /* ... */ })) +ctx.tools.register(defineTool({ + name: 'noop', + description: 'Do nothing.', + parameters: {}, + async execute() { + return [] + }, +})) // 不需要: // const dispose = ctx.tools.register(...) -// ctx.on('dispose', dispose) +// ctx.effect(() => dispose) ``` ## 完整实战示例 一个文件计数 tool： -```typescript +```ts import type { Context } from 'cordis' import { defineTool } from '@deepseek-ai/dsh-tools' import { readdir } from 'node:fs/promises' diff --git a/website/zh-CN/develop/framework/events.md b/website/zh-CN/develop/framework/events.md index 0546fd68e7..d2ddcf17a2 100644 --- a/website/zh-CN/develop/framework/events.md +++ b/website/zh-CN/develop/framework/events.md @@ -6,7 +6,17 @@ ### 监听事件 -```typescript +```ts +import type { Context } from 'cordis' + +declare module 'cordis' { + interface Events { + 'event-name'(payload: string): void + } +} + +declare const ctx: Context + ctx.on('event-name', (payload) => { // 处理事件 }) @@ -14,7 +24,18 @@ ctx.on('event-name', (payload) => { ### 触发事件 -```typescript +```ts +import type { Context } from 'cordis' + +declare module 'cordis' { + interface Events { + 'event-name'(payload: string): void + } +} + +declare const ctx: Context +declare const payload: string + ctx.emit('event-name', payload) ``` @@ -26,12 +47,24 @@ Cordis 提供多种事件触发模式，适用于不同场景： 所有监听器并行执行，不关心返回值： -```typescript +```ts +import type { Context } from 'cordis' + +declare module 'cordis' { + interface Events { + 'my-plugin/turn-end'(agentId: string, turnIndex: number): void + } +} + +declare const ctx: Context +declare const agentId: string +declare const turnIndex: number + // 触发 -ctx.emit('agent/turn-end', { agentId, turnIndex }) +ctx.emit('my-plugin/turn-end', agentId, turnIndex) // 监听 -ctx.on('agent/turn-end', ({ agentId, turnIndex }) => { +ctx.on('my-plugin/turn-end', (agentId, turnIndex) => { console.log(`Turn ${turnIndex} ended`) }) ``` @@ -40,7 +73,19 @@ ctx.on('agent/turn-end', ({ agentId, turnIndex }) => { 依次调用监听器，第一个返回非 `undefined` 值的结果作为最终值： -```typescript +```ts +import type { Context } from 'cordis' + +declare module 'cordis' { + interface Events { + 'some-check'(input: string): string | undefined + } +} + +declare const ctx: Context +declare const input: string +declare function shouldBlock(input: string): boolean + // 触发 const result = ctx.bail('some-check', input) @@ -48,6 +93,7 @@ const result = ctx.bail('some-check', input) ctx.on('some-check', (input) => { if (shouldBlock(input)) return 'blocked' // 返回 undefined 继续传递给下一个监听器 + return undefined }) ``` @@ -55,24 +101,47 @@ ctx.on('some-check', (input) => { 所有监听器按注册顺序依次执行（异步安全）： -```typescript +```ts +import type { Context } from 'cordis' + +declare module 'cordis' { + interface Events { + 'setup-phase'(context: object): Promise | void + } +} + +declare const ctx: Context +declare const context: object + await ctx.serial('setup-phase', context) ``` ### waterfall — 管道 -每个监听器接收前一个的输出，形成数据管道。**必须调用 `next()` 传递给下游**，不调用即为否决： +监听器围绕默认实现层层包裹，形成数据管道。**必须调用 `next()` 委托给下游**，不调用即为否决： -```typescript -// 触发 -const finalMessages = await ctx.waterfall('llm/pre-request', messages) +```ts +import type { Context } from 'cordis' +import type { Message } from '@deepseek-ai/dsh-llm' + +declare module 'cordis' { + interface Events { + 'my-plugin/messages'(messages: Message[], next: () => Promise): Promise + } +} + +declare const ctx: Context +declare const messages: Message[] +declare const extraMessage: Message + +// 触发：最后一个参数是默认实现（所有监听器都调用 next 时的最终值） +const finalMessages = await ctx.waterfall('my-plugin/messages', messages, async () => messages) // 监听（必须调用 next） -ctx.on('llm/pre-request', async (messages, next) => { - // 可以修改 messages - messages.push(extraMessage) - // 必须调用 next() 传递给下一个监听器 - return next(messages) +ctx.on('my-plugin/messages', async (messages, next) => { + // next() 委托给下游监听器（最终到达默认实现），返回值可以被加工 + const result = await next() + return [...result, extraMessage] }) ``` @@ -84,11 +153,13 @@ Waterfall 监听器**必须调用 `next()`**。不调用 `next` 等于否决整 Harness 使用 TypeScript 声明合并来为事件提供类型安全： -```typescript +```ts +import type {} from 'cordis' + declare module 'cordis' { interface Events { - 'my-plugin/ready': (payload: { id: string }) => void - 'my-plugin/check': (input: string) => boolean | undefined + 'my-plugin/ready'(payload: { id: string }): void + 'my-plugin/check'(input: string): boolean | undefined } } @@ -101,24 +172,30 @@ declare module 'cordis' { Harness 事件遵循 `namespace/action` 命名： ``` -agent/pre-step — agent 执行一步之前 -agent/post-step — agent 执行一步之后 -tool/call — tool 被调用 -tool/result — tool 返回结果 -llm/pre-request — LLM 请求发送前 -session/event — 会话事件被记录 -compact/start — 压缩开始 -compact/end — 压缩结束 +agent/pre-step — 每个 step 开始前的检查点（serial） +agent/step-result — step 的 assistant 消息组装完成（waterfall） +tools/pre-execute — tool 执行前的允许/拒绝门（waterfall） +tools/post-execute — tool 执行后的检查/改写缝（waterfall） +llm/stream — 每次流式模型调用的环绕点（waterfall） +session/event — 会话事件被记录（emit） +session/flush — 会话持久化检查点（parallel） ``` +完整的事件列表（含每个事件的签名与派发模式）见仓库中的 `docs/cordis-catalog/events.md`。 + ## 事件也是效果 通过 `ctx.on()` 注册的监听器会在插件卸载时自动移除： -```typescript +```ts +import type { Context } from 'cordis' +import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent' + +declare function handler(agent: Agent, status: AgentStatus): void + export function apply(ctx: Context) { // 这个监听器在插件 dispose 时自动清理 - ctx.on('agent/turn-end', handler) + ctx.on('agent/status', handler) } ``` @@ -126,22 +203,21 @@ export function apply(ctx: Context) { 一个记录所有 tool 调用的简单插件： -```typescript +```ts import type { Context } from 'cordis' +import type {} from '@deepseek-ai/dsh-tools' export const name = 'tool-logger' export function apply(ctx: Context) { - ctx.on('tool/call', ({ name, args }) => { - console.log(`[tool] ${name}(${JSON.stringify(args)})`) - }) - - ctx.on('tool/result', ({ name, result }) => { + ctx.on('tools/execute', async (exec, next) => { + console.log(`[tool] ${exec.name}(${JSON.stringify(exec.arguments)})`) + const result = await next() const text = result.content - .filter(b => b.type === 'text') - .map(b => b.text) + .map(b => b.type === 'text' ? b.text : '') .join('') console.log(`[tool result] ${text.slice(0, 100)}`) + return result }) } ``` diff --git a/website/zh-CN/develop/framework/index.md b/website/zh-CN/develop/framework/index.md index 8d2f7c2b8a..d9c6def99a 100644 --- a/website/zh-CN/develop/framework/index.md +++ b/website/zh-CN/develop/framework/index.md @@ -25,7 +25,11 @@ ACTIVE → UNLOADING → DISPOSED 声明了 `inject` 的插件不会立即加载，而是等待依赖的服务就绪： -```typescript +```ts +import type { Context } from 'cordis' +import type {} from '@deepseek-ai/dsh-tools' +import type {} from '@deepseek-ai/dsh-llm' + export const inject = ['tools', 'llm'] export function apply(ctx: Context) { @@ -39,10 +43,21 @@ export function apply(ctx: Context) { 通过 `ctx` 做的任何注册，在插件卸载时都会自动撤销： -```typescript +```ts +import type { Context } from 'cordis' + +declare module 'cordis' { + interface Events { + 'my-plugin/some-event'(): void + } +} + +declare function handler(): void +declare function createConnection(): { close(): void } + export function apply(ctx: Context) { // 事件监听——卸载时自动移除 - ctx.on('some-event', handler) + ctx.on('my-plugin/some-event', handler) // 自定义资源——卸载时调用返回的函数 ctx.effect(() => { @@ -64,7 +79,11 @@ export function apply(ctx: Context) { `ctx.plugin()` 创建子 Fiber，它继承父上下文但有独立的生命周期： -```typescript +```ts +import type { Context } from 'cordis' + +declare function childPlugin(ctx: Context): void + export function apply(ctx: Context) { // 注册一个子插件 ctx.plugin(childPlugin) @@ -77,11 +96,16 @@ export function apply(ctx: Context) { 当你需要提前终止一个插件实例： -```typescript +```ts +import type { Context } from 'cordis' + +declare const ctx: Context +declare function myPlugin(ctx: Context): void + const fiber = ctx.plugin(myPlugin) // 之后可以手动 dispose -fiber.dispose() +await fiber.dispose() ``` `dispose` 保证： @@ -101,18 +125,14 @@ fiber.dispose() ## 实战：理解生命周期 -```typescript +`apply` 函数体就是加载钩子；卸载没有专门的事件——把清理逻辑放进 `ctx.effect()` 的返回函数即可： + +```ts +import type { Context } from 'cordis' + export function apply(ctx: Context) { console.log('plugin loading') - ctx.on('ready', () => { - console.log('context ready') - }) - - ctx.on('dispose', () => { - console.log('plugin disposing') - }) - ctx.effect(() => { console.log('effect registered') return () => console.log('effect cleaned up') @@ -124,12 +144,10 @@ export function apply(ctx: Context) { ``` plugin loading effect registered -context ready ``` -卸载时输出（逆序）： +卸载时输出： ``` -plugin disposing effect cleaned up ``` diff --git a/website/zh-CN/develop/framework/service.md b/website/zh-CN/develop/framework/service.md index 08d9a1b2c8..7508d02675 100644 --- a/website/zh-CN/develop/framework/service.md +++ b/website/zh-CN/develop/framework/service.md @@ -6,10 +6,17 @@ 在 Harness 中，`tools`、`llm`、`agents` 都是服务。服务是挂载在 `ctx` 上的命名能力： -```typescript +```ts +import type { Context } from 'cordis' +import type {} from '@deepseek-ai/dsh-tools' +import type {} from '@deepseek-ai/dsh-llm' +import type {} from '@deepseek-ai/dsh-agent' + +declare const ctx: Context + ctx.tools // ToolRegistry 服务 ctx.llm // LLM 服务 -ctx.agents // Agent 服务 +ctx.agents // Agent 注册表服务 ``` 任何插件都可以提供一个新服务，供其他插件使用。 @@ -18,12 +25,22 @@ ctx.agents // Agent 服务 声明 `inject` 来使用已有服务： -```typescript +```ts +import type { Context } from 'cordis' +import { defineTool } from '@deepseek-ai/dsh-tools' + export const inject = ['tools'] export function apply(ctx: Context) { // ctx.tools 在这里一定存在且就绪 - ctx.tools.register(/* ... */) + ctx.tools.register(defineTool({ + name: 'demo', + description: 'Demo tool.', + parameters: {}, + async execute() { + return [] + }, + })) } ``` @@ -33,8 +50,9 @@ export function apply(ctx: Context) { ### 使用 Service 基类 -```typescript +```ts import { Service, type Context } from 'cordis' +import type {} from '@deepseek-ai/dsh-llm' export default class MetricsService extends Service { static inject = ['llm'] // 本服务也可以依赖其他服务 @@ -52,7 +70,9 @@ export default class MetricsService extends Service { 加载这个插件后，其他插件就可以通过 `ctx.metrics` 访问它： -```typescript +```ts +import type { Context } from 'cordis' + export const inject = ['metrics'] export function apply(ctx: Context) { @@ -64,7 +84,7 @@ export function apply(ctx: Context) { 使用 TypeScript 声明合并让 `ctx.metrics` 有正确类型： -```typescript +```ts import { Service, type Context } from 'cordis' declare module 'cordis' { @@ -84,14 +104,21 @@ export default class MetricsService extends Service { ## 依赖的行为 -### 必选依赖 vs 可选依赖 +### 必选依赖 vs 可选读取 + +`inject` 声明的依赖都是必选的：服务不存在时，插件不会加载。如果只想"有则用之"，用 `ctx.get()` 读取——服务不存在时返回 `undefined`，插件照常加载： + +```ts +import type { Context } from 'cordis' -```typescript // 必选：服务不存在时，插件不会加载 export const inject = ['tools'] -// 可选：服务不存在时，插件仍然加载，但 ctx.xxx 可能是 undefined -export const inject = { optional: ['metrics'] } +export function apply(ctx: Context) { + // 可选读取：不声明 inject，服务不存在时返回 undefined + const metrics = ctx.get('metrics') + metrics?.record('plugin_loaded', 1) +} ``` ### 服务消失时的行为 @@ -133,13 +160,14 @@ export const inject = { optional: ['metrics'] } |--------|--------|------| | `tools` | dsh-tools | Tool 注册表 | | `llm` | dsh-llm | LLM 调用 + 适配器注册 | -| `agents` | dsh-agent | Agent 实例管理 | -| `session` | dsh-session | 会话事件流 | +| `agents` | dsh-agent | Agent 注册表 | +| `agentLoop` | dsh-agent-loop | Agent 创建与循环执行 | +| `sessions` | dsh-session | 会话存储与事件流 | | `systemPrompt` | dsh-system-prompt | 系统提示词组装 | -| `bash` | dsh-bash-local | Bash 命令执行 | -| `fs` | dsh-fs-local | 文件系统操作 | -| `subagent` | dsh-subagent | 子代理委派 | -| `persistence` | dsh-session-persistence | 会话持久化 | +| `bash` | dsh-bash（实现：dsh-bash-local） | Bash 命令执行 | +| `fs` | dsh-fs（实现：dsh-fs-local） | 文件系统操作 | +| `subagents` | dsh-subagent | 子代理委派 | +| `sessionPersistence` | dsh-session-persistence（实现：-jsonl / -sqlite） | 会话持久化 | ## 下一步 diff --git a/website/zh-CN/develop/practice/index.md b/website/zh-CN/develop/practice/index.md index dd0ec1cb60..9781138c50 100644 --- a/website/zh-CN/develop/practice/index.md +++ b/website/zh-CN/develop/practice/index.md @@ -64,7 +64,7 @@ ### 第一步：定义接口 -```typescript +```ts // packages/my-cap/my-cap/src/index.ts import { Service, type Context } from 'cordis' @@ -94,7 +94,7 @@ export interface MyCapResult { ### 第二步：编写实现 -```typescript +```ts ignore-check // packages/my-cap/my-cap-local/src/index.ts import type { Context } from 'cordis' import { MyCapService, type MyCapRequest, type MyCapResult } from '@deepseek-ai/dsh-my-cap' @@ -115,7 +115,7 @@ export function apply(ctx: Context) { ### 第三步：编写消费者 (tool) -```typescript +```ts // packages/my-cap/tool-my-cap/src/index.ts import type { Context } from 'cordis' import { defineTool } from '@deepseek-ai/dsh-tools' diff --git a/website/zh-CN/develop/practice/llm-adapter.md b/website/zh-CN/develop/practice/llm-adapter.md index 20b1fa2c88..ce60b8078f 100644 --- a/website/zh-CN/develop/practice/llm-adapter.md +++ b/website/zh-CN/develop/practice/llm-adapter.md @@ -8,7 +8,7 @@ LLM 适配器是一个继承 `LlmAdapter` 的类，实现 `stream()` 方法， ## 最小实现 -```typescript +```ts import type { Context } from 'cordis' import { LlmAdapter, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm' @@ -45,47 +45,51 @@ export function apply(ctx: Context, config: Config) { `stream()` 必须按以下协议 yield chunk： -```typescript -// 1. 每个内容块以 block-start 开始 -yield { type: 'block-start', index: 0, blockType: 'text' } +```ts +import { CallId, type StreamChunk } from '@deepseek-ai/dsh-llm' -// 2. 文本块使用 text-delta -yield { type: 'text-delta', index: 0, text: 'Hello' } -yield { type: 'text-delta', index: 0, text: ' world' } +async function* demo(): AsyncIterable { + // 1. 每个内容块以 block-start 开始 + yield { type: 'block-start', index: 0, blockType: 'text' } -// 3. 每个内容块以 block-end 结束（携带完整 block） -yield { - type: 'block-end', - index: 0, - block: { type: 'text', text: 'Hello world' }, -} + // 2. 文本块使用 text-delta + yield { type: 'text-delta', index: 0, text: 'Hello' } + yield { type: 'text-delta', index: 0, text: ' world' } -// 4. Tool call 块 -yield { type: 'block-start', index: 1, blockType: 'tool-call' } -yield { - type: 'tool-call-delta', - index: 1, - id: CallId('call-123'), - name: 'bash', - argumentsDelta: '{"command":"ls"}', -} -yield { - type: 'block-end', - index: 1, - block: { - type: 'tool-call', + // 3. 每个内容块以 block-end 结束（携带完整 block） + yield { + type: 'block-end', + index: 0, + block: { type: 'text', text: 'Hello world' }, + } + + // 4. Tool call 块 + yield { type: 'block-start', index: 1, blockType: 'tool-call' } + yield { + type: 'tool-call-delta', + index: 1, id: CallId('call-123'), name: 'bash', - arguments: '{"command":"ls"}', - }, + argumentsDelta: '{"command":"ls"}', + } + yield { + type: 'block-end', + index: 1, + block: { + type: 'tool-call', + id: CallId('call-123'), + name: 'bash', + arguments: '{"command":"ls"}', + }, + } + + // 5. Token 用量 + yield { type: 'usage', usage: { inputTokens: 100, outputTokens: 50 } } + + // 6. 结束原因 + yield { type: 'finish', reason: { kind: 'stop' } } + // 或: { kind: 'tool-calls' } 表示模型想调用 tool } - -// 5. Token 用量 -yield { type: 'usage', usage: { inputTokens: 100, outputTokens: 50 } } - -// 6. 结束原因 -yield { type: 'finish', reason: { kind: 'stop' } } -// 或: { kind: 'tool-calls' } 表示模型想调用 tool ``` ### 关键规则 @@ -100,28 +104,31 @@ yield { type: 'finish', reason: { kind: 'stop' } } `stream()` 接收的请求包含： -```typescript -interface GenerateOptions { - /** 模型名 */ - model: string - /** 对话历史 */ - messages: Message[] - /** 可用的 tool 列表 */ - tools?: ToolSpec[] - /** 系统提示词 */ - system?: string - /** 最大输出 token */ - maxTokens?: number - /** 温度 */ - temperature?: number -} +```ts +import type { GenerateOptions } from '@deepseek-ai/dsh-llm' + +declare const options: GenerateOptions + +options.model // 模型名 +options.messages // 对话历史 (Message[]) +options.tools // 可用的 tool schema 列表 (ToolSchema[]) +options.system // 系统提示词 +options.maxTokens // 最大输出 token +options.temperature // 温度 +options.signal // 取消信号（必须响应） ``` 你的适配器需要将这些映射到具体 API 的参数。 ## 注册适配器 -```typescript +```ts +import type { Context } from 'cordis' +import type { LlmAdapter } from '@deepseek-ai/dsh-llm' + +declare const ctx: Context +declare const adapter: LlmAdapter + ctx.llm.registerAdapter(['model-name-1', 'model-name-2'], adapter) ``` @@ -158,12 +165,18 @@ mock 适配器是学习 StreamChunk 协议的最佳起点——它用纯本地 适配器中的异常会被 agent-loop 捕获并转化为 `LlmError`，告知上层。不需要在 `stream()` 内部做错误恢复——让异常冒泡即可。 -```typescript -async *stream(options: GenerateOptions): AsyncIterable { - const response = await fetch(this.endpoint, { /* ... */ }) - if (!response.ok) { - throw new Error(`API error: ${response.status}`) +```ts +import { LlmAdapter, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm' + +class HttpAdapter extends LlmAdapter { + private endpoint = 'https://api.example.com/v1/chat' + + async *stream(options: GenerateOptions): AsyncIterable { + const response = await fetch(this.endpoint, { method: 'POST' }) + if (!response.ok) { + throw new Error(`API error: ${response.status}`) + } + // ... 正常流式处理 } - // ... 正常流式处理 } ``` diff --git a/website/zh-CN/guide/config.md b/website/zh-CN/guide/config.md index d555a0a478..3f194edc79 100644 --- a/website/zh-CN/guide/config.md +++ b/website/zh-CN/guide/config.md @@ -87,6 +87,7 @@ Harness 使用 `cordis.yml` 描述一个 Agent 加载哪些插件、以什么参 # 自动压缩：对话太长时自动总结旧内容，腾出上下文空间 # contextWindow 是模型能看到的 token 上限 # thresholdRatio 超过这个比例就触发压缩 +# compactionRetries 是压缩后仍超标时的额外重试次数 - id: compact-basic name: '@deepseek-ai/dsh-compact-basic' config: @@ -94,6 +95,7 @@ Harness 使用 `cordis.yml` 描述一个 Agent 加载哪些插件、以什么参 thresholdRatio: 0.8 retainTokens: 20480 maxTokens: 8192 + compactionRetries: 1 # 子代理：把子任务分配给独立的 Agent 去做 # subagent 是服务注册，spawn/fork 是两种委派方式： @@ -125,6 +127,16 @@ Harness 使用 `cordis.yml` 描述一个 Agent 加载哪些插件、以什么参 provider: fork toolName: subagent_fork +# 动态工作流：模型编写一段编排脚本，引擎在独立 worker 线程里运行它， +# 并通过上面的 spawn 后端把 agent() 调用分发为子代理 +- id: workflow-workerthread + name: '@deepseek-ai/dsh-workflow-workerthread' + config: + provider: spawn + +- id: tool-workflow + name: '@deepseek-ai/dsh-tool-workflow' + # 任务追踪：模型可以用 todo_write 记录和更新任务清单 - id: tool-todo name: '@deepseek-ai/dsh-tool-todo' @@ -156,9 +168,13 @@ Harness 使用 `cordis.yml` 描述一个 Agent 加载哪些插件、以什么参 | 字段 | 类型 | 必填 | 说明 | |------|------|------|------| | `name` | string | 是 | 插件来源（npm 包名或相对路径） | -| `id` | string | 否 | 实例标识符，用于日志和调试 | +| `id` | string | 否 | 实例标识符，用于日志和调试。省略时由 loader 生成并写回 | | `config` | object | 否 | 传递给插件的配置 | | `disabled` | boolean | 否 | 设为 `true` 临时禁用该插件 | +| `group` | boolean | 否 | 标记该条目为嵌套分组（`config` 为子条目列表） | +| `inject` | array \| object | 否 | 声明该插件依赖的服务 | +| `intercept` | object | 否 | 按服务名拦截并覆盖下游配置 | +| `isolate` | object | 否 | 服务隔离：服务名 → `true` 或隔离标签 | ### 插件来源 (`name`) From 83cb48441ea14d03fb98b9105cbadd4fddc966ff Mon Sep 17 00:00:00 2001 From: lintianle Date: Thu, 16 Jul 2026 18:12:36 +0800 Subject: [PATCH 219/359] vendor(cordis): document the full plugin-author surface (@param/@returns everywhere) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Comment-only enrichment across cordis/src/*.ts — Context, EventsService (+ the ctx merges), Fiber, RegistryService, ReflectService, Service, logger — so the website API generator can render a complete reference and hard-error on any future undocumented member (vendor sync included). Logged as local modification 6 in vendor/README.md; retire it when upstreamed to the fork. INHERITED_SERVICES/EVENTS source pointers refreshed for the shifted lines; cordis catalogs regenerated. --- docs/cordis-catalog/events.md | 16 ++-- docs/cordis-catalog/services.md | 8 +- scripts/gen-cordis-catalog.ts | 24 ++--- vendor/README.md | 1 + vendor/cordis/src/context.ts | 57 +++++++++++- vendor/cordis/src/events.ts | 156 ++++++++++++++++++++++++++++++-- vendor/cordis/src/fiber.ts | 117 ++++++++++++++++++++++-- vendor/cordis/src/logger.ts | 10 +- vendor/cordis/src/reflect.ts | 125 +++++++++++++++++++++++++ vendor/cordis/src/registry.ts | 97 +++++++++++++++++++- vendor/cordis/src/service.ts | 31 ++++++- 11 files changed, 587 insertions(+), 55 deletions(-) diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index a9dfb7e05c..78fee7e8e0 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -427,14 +427,14 @@ Source: [`packages/workflow/workflow/src/index.ts:62`](../../packages/workflow/w The framework events every plugin also sees, beyond the harness vocabulary above. This is pinned vendor source ([vendoring policy](../../vendor/README.md)); it is summarized here so the page is a complete picture of the event bus, without elevating framework internals to the harness tier's prominence. -- `internal/plugin` — A plugin fiber was created. ([`vendor/cordis/src/events.ts:197`](../../vendor/cordis/src/events.ts)) -- `internal/status` — A fiber changed lifecycle state. ([`vendor/cordis/src/events.ts:198`](../../vendor/cordis/src/events.ts)) -- `internal/service` — Interception hook for a service binding (no core producer). ([`vendor/cordis/src/events.ts:199`](../../vendor/cordis/src/events.ts)) -- `internal/update` — Waterfall: a fiber config update is being applied. ([`vendor/cordis/src/events.ts:200`](../../vendor/cordis/src/events.ts)) -- `internal/get` — Waterfall: a service is being read from the store. ([`vendor/cordis/src/events.ts:201`](../../vendor/cordis/src/events.ts)) -- `internal/set` — Waterfall: a service is being written to the store. ([`vendor/cordis/src/events.ts:202`](../../vendor/cordis/src/events.ts)) -- `internal/listener` — A listener was registered. ([`vendor/cordis/src/events.ts:203`](../../vendor/cordis/src/events.ts)) -- `internal/dispatch` — An event is being dispatched to listeners. ([`vendor/cordis/src/events.ts:204`](../../vendor/cordis/src/events.ts)) +- `internal/plugin` — A plugin fiber was created. ([`vendor/cordis/src/events.ts:328`](../../vendor/cordis/src/events.ts)) +- `internal/status` — A fiber changed lifecycle state. ([`vendor/cordis/src/events.ts:330`](../../vendor/cordis/src/events.ts)) +- `internal/service` — Interception hook for a service binding (no core producer). ([`vendor/cordis/src/events.ts:332`](../../vendor/cordis/src/events.ts)) +- `internal/update` — Waterfall: a fiber config update is being applied. ([`vendor/cordis/src/events.ts:334`](../../vendor/cordis/src/events.ts)) +- `internal/get` — Waterfall: a service is being read from the store. ([`vendor/cordis/src/events.ts:336`](../../vendor/cordis/src/events.ts)) +- `internal/set` — Waterfall: a service is being written to the store. ([`vendor/cordis/src/events.ts:338`](../../vendor/cordis/src/events.ts)) +- `internal/listener` — A listener was registered. ([`vendor/cordis/src/events.ts:340`](../../vendor/cordis/src/events.ts)) +- `internal/dispatch` — An event is being dispatched to listeners. ([`vendor/cordis/src/events.ts:342`](../../vendor/cordis/src/events.ts)) - `hmr/change` — A watched source file changed on disk. ([`vendor/hmr/src/index.ts:20`](../../vendor/hmr/src/index.ts)) - `hmr/reload` — Plugins are being reloaded after a change. ([`vendor/hmr/src/index.ts:21`](../../vendor/hmr/src/index.ts)) - `exit` — The process is exiting on a signal. ([`vendor/loader/src/index.ts:23`](../../vendor/loader/src/index.ts)) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 79902ba2fc..edd5434977 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -282,12 +282,12 @@ Source: [`packages/workflow/workflow/src/index.ts:210`](../../packages/workflow/ The framework `ctx` surface every plugin also sees, beyond the harness services above. This is pinned vendor source ([vendoring policy](../../vendor/README.md)); it is summarized here so the page is a complete picture of what `ctx` offers, without elevating framework internals to the harness tier's prominence. -- `ctx.on / ctx.once` — Register an event listener (disposable). ([`vendor/cordis/src/events.ts:29`](../../vendor/cordis/src/events.ts)) -- `ctx.emit / ctx.parallel / ctx.serial / ctx.bail / ctx.waterfall` — Dispatch an event (sync / awaited / first-bail / veto-chain). ([`vendor/cordis/src/events.ts:29`](../../vendor/cordis/src/events.ts)) -- `ctx.plugin / ctx.inject` — Load a plugin / declare required services. ([`vendor/cordis/src/registry.ts:144`](../../vendor/cordis/src/registry.ts)) +- `ctx.on / ctx.once` — Register an event listener (disposable). ([`vendor/cordis/src/events.ts:34`](../../vendor/cordis/src/events.ts)) +- `ctx.emit / ctx.parallel / ctx.serial / ctx.bail / ctx.waterfall` — Dispatch an event (sync / awaited / first-bail / veto-chain). ([`vendor/cordis/src/events.ts:34`](../../vendor/cordis/src/events.ts)) +- `ctx.plugin / ctx.inject` — Load a plugin / declare required services. ([`vendor/cordis/src/registry.ts:164`](../../vendor/cordis/src/registry.ts)) - `ctx.effect` — Register a disposable side effect tied to the fiber. ([`vendor/cordis/src/fiber.ts:9`](../../vendor/cordis/src/fiber.ts)) - `ctx.get / ctx.set / ctx.provide / ctx.accessor / ctx.mixin` — Low-level service-store access and binding. ([`vendor/cordis/src/reflect.ts:7`](../../vendor/cordis/src/reflect.ts)) -- `ctx.extend / ctx.isolate / ctx.intercept` — Derive a child context (scoped services / isolation / interception). ([`vendor/cordis/src/context.ts:35`](../../vendor/cordis/src/context.ts)) +- `ctx.extend / ctx.isolate / ctx.intercept` — Derive a child context (scoped services / isolation / interception). ([`vendor/cordis/src/context.ts:42`](../../vendor/cordis/src/context.ts)) - `ctx.root / ctx.scope / ctx.fiber / ctx.registry / ctx.reflect / ctx.events / ctx.logger` — Ambient handles onto the running context graph. ([`vendor/cordis/src/context.ts:16`](../../vendor/cordis/src/context.ts)) - `ctx.timer (+ interval / timeout / throttle / debounce / setTimeout / setInterval)` — Disposable timer helpers. The `timer` key is provided at runtime; the six helpers are mixed onto ctx directly (declared via Pick). ([`vendor/timer/src/index.ts:4`](../../vendor/timer/src/index.ts)) - `ctx.loader` — The config Loader that booted the app (present under the loader). ([`vendor/loader/src/index.ts:30`](../../vendor/loader/src/index.ts)) diff --git a/scripts/gen-cordis-catalog.ts b/scripts/gen-cordis-catalog.ts index 9b8141807e..dc2023f4cc 100644 --- a/scripts/gen-cordis-catalog.ts +++ b/scripts/gen-cordis-catalog.ts @@ -310,14 +310,14 @@ export function collectServices(scanRoot: string = root): ServiceEntry[] { * sibling check is N/A; keep them current on a vendor bump. */ const INHERITED_EVENTS: InheritedEntry[] = [ - { name: 'internal/plugin', summary: 'A plugin fiber was created.', source: 'vendor/cordis/src/events.ts:197' }, - { name: 'internal/status', summary: 'A fiber changed lifecycle state.', source: 'vendor/cordis/src/events.ts:198' }, - { name: 'internal/service', summary: 'Interception hook for a service binding (no core producer).', source: 'vendor/cordis/src/events.ts:199' }, - { name: 'internal/update', summary: 'Waterfall: a fiber config update is being applied.', source: 'vendor/cordis/src/events.ts:200' }, - { name: 'internal/get', summary: 'Waterfall: a service is being read from the store.', source: 'vendor/cordis/src/events.ts:201' }, - { name: 'internal/set', summary: 'Waterfall: a service is being written to the store.', source: 'vendor/cordis/src/events.ts:202' }, - { name: 'internal/listener', summary: 'A listener was registered.', source: 'vendor/cordis/src/events.ts:203' }, - { name: 'internal/dispatch', summary: 'An event is being dispatched to listeners.', source: 'vendor/cordis/src/events.ts:204' }, + { name: 'internal/plugin', summary: 'A plugin fiber was created.', source: 'vendor/cordis/src/events.ts:328' }, + { name: 'internal/status', summary: 'A fiber changed lifecycle state.', source: 'vendor/cordis/src/events.ts:330' }, + { name: 'internal/service', summary: 'Interception hook for a service binding (no core producer).', source: 'vendor/cordis/src/events.ts:332' }, + { name: 'internal/update', summary: 'Waterfall: a fiber config update is being applied.', source: 'vendor/cordis/src/events.ts:334' }, + { name: 'internal/get', summary: 'Waterfall: a service is being read from the store.', source: 'vendor/cordis/src/events.ts:336' }, + { name: 'internal/set', summary: 'Waterfall: a service is being written to the store.', source: 'vendor/cordis/src/events.ts:338' }, + { name: 'internal/listener', summary: 'A listener was registered.', source: 'vendor/cordis/src/events.ts:340' }, + { name: 'internal/dispatch', summary: 'An event is being dispatched to listeners.', source: 'vendor/cordis/src/events.ts:342' }, { name: 'hmr/change', summary: 'A watched source file changed on disk.', source: 'vendor/hmr/src/index.ts:20' }, { name: 'hmr/reload', summary: 'Plugins are being reloaded after a change.', source: 'vendor/hmr/src/index.ts:21' }, { name: 'exit', summary: 'The process is exiting on a signal.', source: 'vendor/loader/src/index.ts:23' }, @@ -328,12 +328,12 @@ const INHERITED_EVENTS: InheritedEntry[] = [ ] export const INHERITED_SERVICES: InheritedEntry[] = [ - { name: 'ctx.on / ctx.once', summary: 'Register an event listener (disposable).', source: 'vendor/cordis/src/events.ts:29' }, - { name: 'ctx.emit / ctx.parallel / ctx.serial / ctx.bail / ctx.waterfall', summary: 'Dispatch an event (sync / awaited / first-bail / veto-chain).', source: 'vendor/cordis/src/events.ts:29' }, - { name: 'ctx.plugin / ctx.inject', summary: 'Load a plugin / declare required services.', source: 'vendor/cordis/src/registry.ts:144' }, + { name: 'ctx.on / ctx.once', summary: 'Register an event listener (disposable).', source: 'vendor/cordis/src/events.ts:34' }, + { name: 'ctx.emit / ctx.parallel / ctx.serial / ctx.bail / ctx.waterfall', summary: 'Dispatch an event (sync / awaited / first-bail / veto-chain).', source: 'vendor/cordis/src/events.ts:34' }, + { name: 'ctx.plugin / ctx.inject', summary: 'Load a plugin / declare required services.', source: 'vendor/cordis/src/registry.ts:164' }, { name: 'ctx.effect', summary: 'Register a disposable side effect tied to the fiber.', source: 'vendor/cordis/src/fiber.ts:9' }, { name: 'ctx.get / ctx.set / ctx.provide / ctx.accessor / ctx.mixin', summary: 'Low-level service-store access and binding.', source: 'vendor/cordis/src/reflect.ts:7' }, - { name: 'ctx.extend / ctx.isolate / ctx.intercept', summary: 'Derive a child context (scoped services / isolation / interception).', source: 'vendor/cordis/src/context.ts:35' }, + { name: 'ctx.extend / ctx.isolate / ctx.intercept', summary: 'Derive a child context (scoped services / isolation / interception).', source: 'vendor/cordis/src/context.ts:42' }, { name: 'ctx.root / ctx.scope / ctx.fiber / ctx.registry / ctx.reflect / ctx.events / ctx.logger', summary: 'Ambient handles onto the running context graph.', source: 'vendor/cordis/src/context.ts:16' }, { name: 'ctx.timer (+ interval / timeout / throttle / debounce / setTimeout / setInterval)', summary: 'Disposable timer helpers. The `timer` key is provided at runtime; the six helpers are mixed onto ctx directly (declared via Pick).', source: 'vendor/timer/src/index.ts:4' }, { name: 'ctx.loader', summary: 'The config Loader that booted the app (present under the loader).', source: 'vendor/loader/src/index.ts:30' }, diff --git a/vendor/README.md b/vendor/README.md index bf0f0b5a8c..8487ab1086 100644 --- a/vendor/README.md +++ b/vendor/README.md @@ -35,6 +35,7 @@ Keep this log exhaustive — every divergence from upstream must be listed. 3. **All `tsconfig.json` files**: regenerated to extend the repo-root `tsconfig.base.json`, emit TypeScript intermediates to `lib/types`, and declare project references. 4. **Vendored TypeScript source internal specifiers**: changed local relative imports/exports from upstream's specifier shape to explicit `.ts` specifiers so TypeScript rewrites emitted JS to `.js` while declarations keep explicit, NodeNext-safe `.ts` specifiers. This includes `loader/src/config/isolate.ts` using `declare module './entry.ts'`. 5. **`schemastery/tsdown.config.ts` and `logger-console/tsdown.config.ts`**: ours, not upstream files — per-package build-shape overrides (dual ESM+CJS output; separate node/browser entries) for the repo-root tsdown build. They read the JS emitted under `lib/types` and then write the publish runtime entries under `lib/`. Like the regenerated tsconfigs, they are not part of the upstream sync surface. +6. **`cordis/src/*.ts` JSDoc enrichment**: added `@param`/`@returns` tags and contract documentation (disposal semantics, waterfall veto, bail conditions, error cases) across the public plugin-author surface — `Context`, `EventsService`, `Fiber`, `RegistryService`, `ReflectService`, `Service`, `LoggerService` and their `declare module './context.ts'` overloads. Comment-only; no code changes. Motivation: the website API-reference generator renders these docs and hard-errors on undocumented members. Retire this entry when the enrichment is upstreamed to the fork. ## Sync procedure diff --git a/vendor/cordis/src/context.ts b/vendor/cordis/src/context.ts index 8b21c464b2..b34b575cb9 100644 --- a/vendor/cordis/src/context.ts +++ b/vendor/cordis/src/context.ts @@ -14,14 +14,21 @@ import { Fiber } from './fiber.ts' * be read from `ctx`. */ export interface Context { + /** Isolation map: service name → scope label. Lookups for a name resolve within its label. */ [symbols.isolate]: Dict + /** Intercept map: service name → config merged into that service's per-plugin config. */ [symbols.intercept]: Dict /** @experimental */ root: this + /** Base URL used to resolve relative plugin/module specifiers, if the runtime sets one. */ baseUrl?: string + /** The event bus. Its methods are also mixed onto `ctx` (`ctx.on`, `ctx.emit`, ...). */ events: EventsService + /** The logging service. Call `ctx.logger(name)` for a named logger. */ logger: LoggerService + /** The reflection layer backing the context proxy (`ctx.get`, `ctx.provide`, ...). */ reflect: ReflectService + /** The plugin registry. Its methods are mixed onto `ctx` (`ctx.plugin`, `ctx.inject`). */ registry: RegistryService } @@ -33,12 +40,24 @@ export interface Context { * contexts without mutating their parent. */ export class Context { + /** Symbol key under which a disposer exposes its {@link EffectMeta} diagnostics tree. */ static readonly effect: unique symbol = symbols.effect + /** Symbol key for a context's listener filter, consulted on every event dispatch. */ static readonly filter: unique symbol = symbols.filter + /** Symbol key of the isolation map (see the `Context[symbols.isolate]` property). */ static readonly isolate: unique symbol = symbols.isolate + /** Symbol key of the intercept map (see the `Context[symbols.intercept]` property). */ static readonly intercept: unique symbol = symbols.intercept - /** Returns true for Cordis context proxies and context prototypes. */ + /** + * Returns true for Cordis context proxies and context prototypes. + * + * Works across realms and across multiple copies of cordis, because the + * brand is keyed by a global symbol rather than by `instanceof`. + * + * @param value — the value to test. + * @returns `true` if `value` is a Cordis context, narrowing its type. + */ static is(value: any): value is Context { return !!value?.[Context.is as any] } @@ -68,7 +87,15 @@ export class Context { return `Context <${this.fiber.name}>` } - /** Create a child context with extra metadata on top of the current scope. */ + /** + * Create a child context with extra metadata on top of the current scope. + * + * The child prototypally inherits every property of this context; own + * properties of `meta` shadow the inherited ones. The parent is not mutated. + * + * @param meta — own properties (including symbol keys) to define on the child. + * @returns a child context inheriting from this one. + */ extend(meta = {}): this { const shadow = Reflect.getOwnPropertyDescriptor(this, symbols.shadow)?.value const self = Object.create(getTraceable(this, this)) @@ -79,14 +106,36 @@ export class Context { return Object.assign(Object.create(self), { [symbols.shadow]: shadow }) } - /** Create a child context with an independent service scope for `name`. */ + /** + * Create a child context with an independent service scope for `name`. + * + * Below the returned context, reads and writes of the service `name` + * resolve against the new label instead of the parent's, so a different + * implementation can be provided without affecting the parent scope. + * Passing the same `label` to two `isolate()` calls joins their scopes. + * + * @param name — the service name to isolate. + * @param label — scope label to join; defaults to a fresh unique symbol. + * @returns a child context whose `name` service resolves in the new scope. + */ isolate(name: string, label?: symbol) { const shadow = Object.create(this[symbols.isolate]) shadow[name] = label ?? Symbol(name) return this.extend({ [symbols.isolate]: shadow }) } - /** Add service-specific intercept config for plugins started below this context. */ + /** + * Add service-specific intercept config for plugins started below this + * context. + * + * Plugins loaded under the returned context see `config` merged into the + * service's resolved config (ancestor entries first; see + * `Service[symbols.resolveConfig]`). The parent context is not affected. + * + * @param name — the service name whose config to intercept. + * @param config — the intercept config to merge for that service. + * @returns a child context carrying the additional intercept entry. + */ intercept(name: K, config: Context[K] extends { [symbols.config]: infer T } ? T : never): this intercept(name: string, config: any): this intercept(name: string, config: any) { diff --git a/vendor/cordis/src/events.ts b/vendor/cordis/src/events.ts index 4461816537..d0d9ee7353 100644 --- a/vendor/cordis/src/events.ts +++ b/vendor/cordis/src/events.ts @@ -3,7 +3,12 @@ import { Context } from './context.ts' import { Fiber, FiberState } from './fiber.ts' import { DisposableList, symbols } from './utils.ts' -/** Return whether an event result should stop a bail-style dispatch. */ +/** + * Return whether an event result should stop a bail-style dispatch. + * + * @param value — a listener's return value. + * @returns `true` unless `value` is `null`, `false`, or `undefined`. + */ export function isBailed(value: any) { return value !== null && value !== false && value !== undefined } @@ -28,17 +33,75 @@ export type DispatchMode = 'emit' | 'parallel' | 'serial' | 'bail' | 'waterfall' declare module './context.ts' { export interface Context { /* eslint-disable max-len */ + /** + * Dispatch an event, running all listeners concurrently. + * + * @param name — the event name. + * @param args — arguments passed to every listener. + * @returns a promise resolving once every listener has settled. + */ parallel(name: K, ...args: Parameters): Promise + /** Same as above, with an explicit `this` for listeners (also used for filtering). */ parallel(thisArg: NoInfer>, name: K, ...args: Parameters): Promise + /** + * Dispatch an event synchronously, ignoring listener return values. + * + * @param name — the event name. + * @param args — arguments passed to every listener. + */ emit(name: K, ...args: Parameters): void + /** Same as above, with an explicit `this` for listeners (also used for filtering). */ emit(thisArg: NoInfer>, name: K, ...args: Parameters): void + /** + * Dispatch an event, awaiting listeners in order until one bails. + * + * @param name — the event name. + * @param args — arguments passed to each listener. + * @returns the first bail value (non-null, non-false, non-undefined), if any. + */ serial(name: K, ...args: Parameters): Promisify> + /** Same as above, with an explicit `this` for listeners (also used for filtering). */ serial(thisArg: NoInfer>, name: K, ...args: Parameters): Promisify> + /** + * Dispatch an event, calling listeners in order until one bails. + * + * @param name — the event name. + * @param args — arguments passed to each listener. + * @returns the first bail value (non-null, non-false, non-undefined), if any. + */ bail(name: K, ...args: Parameters): ReturnType + /** Same as above, with an explicit `this` for listeners (also used for filtering). */ bail(thisArg: NoInfer>, name: K, ...args: Parameters): ReturnType + /** + * Dispatch an event whose last argument is a `next` continuation. + * + * Each listener wraps the rest of the chain: calling `next()` invokes the + * next listener (finally the built-in behavior); not calling it vetoes. + * + * @param name — the event name. + * @param args — listener arguments; the final one is the innermost `next`. + * @returns the outermost listener's return value. + */ waterfall(name: K, ...args: Parameters): ReturnType + /** Same as above, with an explicit `this` for listeners (also used for filtering). */ waterfall(thisArg: NoInfer>, name: K, ...args: Parameters): ReturnType + /** + * Register an event listener owned by the current fiber. + * + * @param name — the event name to listen for. + * @param listener — called with the dispatch arguments. + * @param options — listener options; a boolean is shorthand for `prepend`. + * @returns a disposer removing the listener; `true` if it was still registered. + */ on(name: K, listener: Events[K], options?: boolean | EventOptions): () => boolean + /** + * Same as `on()`, but the listener disposes itself after its first call. + * + * @param name — the event name to listen for. + * @param listener — called at most once with the dispatch arguments. + * @param options — listener options; a boolean is shorthand for `prepend`. + * @returns a disposer removing the listener; `true` if it was still registered. + */ once(name: K, listener: Events[K], options?: boolean | EventOptions): () => boolean /* eslint-enable max-len */ } @@ -91,7 +154,13 @@ export class EventsService { }, { global: true, prepend: true }) } - /** Resolve listeners for one dispatch and apply context filtering. */ + /** + * Resolve listeners for one dispatch and apply context filtering. + * + * @param type — the dispatch mode, reported on `internal/dispatch`. + * @param args — the raw dispatch arguments; consumed up to the event name. + * @returns the matching listener callbacks, bound to the dispatch `this`. + */ dispatch(type: string, args: any[]) { const thisArg = typeof args[0] === 'object' || typeof args[0] === 'function' ? args.shift() : null const name: string = args.shift() @@ -104,17 +173,31 @@ export class EventsService { .map(hook => hook.callback.bind(thisArg)) } - /** Run listeners concurrently and wait for all of them. */ + /** + * Run listeners concurrently and wait for all of them. + * + * @param args — optional `this`, the event name, then listener arguments. + * @returns a promise resolving once every listener has settled. + */ async parallel(...args: any[]) { await Promise.all(this.dispatch('emit', args).map(cb => cb(...args))) } - /** Run listeners synchronously without waiting for returned promises. */ + /** + * Run listeners synchronously without waiting for returned promises. + * + * @param args — optional `this`, the event name, then listener arguments. + */ emit(...args: any[]) { this.dispatch('emit', args).map(cb => cb(...args)) } - /** Run listeners in order until one returns a bail value. */ + /** + * Run listeners in order, awaiting each, until one returns a bail value. + * + * @param args — optional `this`, the event name, then listener arguments. + * @returns the first bail value (see {@link isBailed}), if any. + */ async serial(...args: any[]) { for (const cb of this.dispatch('serial', args)) { const result = await cb(...args) @@ -122,7 +205,12 @@ export class EventsService { } } - /** Run listeners synchronously until one returns a bail value. */ + /** + * Run listeners synchronously until one returns a bail value. + * + * @param args — optional `this`, the event name, then listener arguments. + * @returns the first bail value (see {@link isBailed}), if any. + */ bail(...args: any[]) { for (const cb of this.dispatch('bail', args)) { const result = cb(...args) @@ -130,7 +218,16 @@ export class EventsService { } } - /** Compose listeners around the final `next` callback. */ + /** + * Compose listeners around the final `next` callback. + * + * The last dispatch argument is treated as the innermost `next`. Listeners + * run outermost-first; a listener that does not call `next()` vetoes the + * rest of the chain, including the built-in behavior. + * + * @param args — optional `this`, the event name, listener arguments, then `next`. + * @returns the outermost listener's return value. + */ waterfall(...args: any[]) { const cbs = this.dispatch('waterfall', args) const inner = args.pop() @@ -142,6 +239,15 @@ export class EventsService { return next() } + /** + * Store a listener record as an effect on the current fiber. + * + * @param label — effect label shown in fiber diagnostics. + * @param hooks — the listener list for one event. + * @param callback — the listener to store. + * @param options — placement and filtering options. + * @returns a disposer that unregisters the listener. + */ register(label: string, hooks: Hook[], callback: any, options: EventOptions): () => void { const method = options.prepend ? 'unshift' : 'push' return this.ctx.fiber.effect(() => { @@ -150,6 +256,13 @@ export class EventsService { }, label) } + /** + * Remove a stored listener record. + * + * @param hooks — the listener list for one event. + * @param callback — the listener to remove. + * @returns `true` if the listener was found and removed. + */ unregister(hooks: Hook[], callback: any) { const index = hooks.findIndex(hook => hook.callback === callback) if (index >= 0) { @@ -158,7 +271,17 @@ export class EventsService { } } - /** Register an event listener owned by the current fiber. */ + /** + * Register an event listener owned by the current fiber. + * + * The listener is removed automatically when the fiber unloads. Throws + * `CordisError('INACTIVE_EFFECT')` if the fiber is already disposed. + * + * @param name — the event name to listen for. + * @param listener — called with the dispatch arguments. + * @param options — listener options; a boolean is shorthand for `prepend`. + * @returns a disposer removing the listener; `true` if it was still registered. + */ on(name: string | symbol, listener: (...args: any) => any, options?: boolean | EventOptions) { if (typeof options !== 'object') { options = { prepend: options } @@ -175,7 +298,14 @@ export class EventsService { return this.register(label, hooks, listener, options) } - /** Register an event listener that disposes itself after the first call. */ + /** + * Register an event listener that disposes itself after the first call. + * + * @param name — the event name to listen for. + * @param listener — called at most once with the dispatch arguments. + * @param options — listener options; a boolean is shorthand for `prepend`. + * @returns a disposer removing the listener; `true` if it was still registered. + */ once(name: string, listener: (...args: any) => any, options?: boolean | EventOptions) { const dispose = this.on(name, function (...args: any[]) { dispose() @@ -194,12 +324,20 @@ export class EventsService { * diagnostics before public events are delivered. */ export interface Events { + /** A plugin fiber was created or its uid was cleared on disposal. */ 'internal/plugin'(fiber: Fiber): void + /** A fiber changed lifecycle state; receives the fiber and its previous state. */ 'internal/status'(fiber: Fiber, oldValue: FiberState): void + /** Interception hook for a service binding (no core producer). */ 'internal/service'(this: Context, name: string, value: any): void + /** Waterfall: a fiber config update is being applied; skip `next()` to veto. */ 'internal/update'(this: Fiber, config: any, noSave: boolean, next: () => void): void + /** Waterfall: a service is being read through the context proxy. */ 'internal/get'(ctx: Context, name: string, error: Error, next: () => any): any + /** Waterfall: a service is being written through the context proxy. */ 'internal/set'(ctx: Context, name: string, value: any, error: Error, next: () => boolean): boolean + /** Bail: a listener is being registered; a non-null result replaces registration. */ 'internal/listener'(this: Context, name: string, listener: any, prepend: boolean): void + /** An event is being dispatched to listeners (fired for non-internal events only). */ 'internal/dispatch'(mode: DispatchMode, name: string, args: any[], thisArg: any): void } diff --git a/vendor/cordis/src/fiber.ts b/vendor/cordis/src/fiber.ts index fd472e7733..9844e3e75d 100644 --- a/vendor/cordis/src/fiber.ts +++ b/vendor/cordis/src/fiber.ts @@ -7,6 +7,7 @@ import { StandardSchemaV1 } from '@standard-schema/spec' declare module './context.ts' { export interface Context extends Pick { + /** The fiber (plugin runtime instance) that owns this context. */ fiber: Fiber } } @@ -17,6 +18,11 @@ const kValidationError = Symbol.for('ValidationError') export class ValidationError extends TypeError { name = 'ValidationError' + /** + * Build the aggregated message from schema issues. + * + * @param issues — the standard-schema issues, one message line each. + */ constructor(issues: readonly StandardSchemaV1.Issue[]) { super(`invalid config:\n` + issues.map(issue => { if (issue.path) { @@ -32,7 +38,14 @@ Object.defineProperty(ValidationError.prototype, kValidationError, { value: true, }) -/** Validate and normalize config for a plugin runtime before it starts. */ +/** + * Validate and normalize config for a plugin runtime before it starts. + * + * @param runtime — the plugin runtime whose `Config` schema to apply. + * @param config — the raw user config. + * @returns the validated config, or `config` unchanged if the runtime has no schema. + * @throws {ValidationError} when validation reports issues. + */ export function resolveConfig(runtime: Plugin.Runtime, config: any) { if (!runtime.Config) return config // TODO: async validation @@ -51,10 +64,21 @@ interface AsyncDisposable = Awaitable> extends P (): T } -/** Function returned by an effect to release resources during disposal. */ +/** + * Function returned by an effect to release resources during disposal. + * + * Disposers run in reverse registration order when the owning fiber unloads; + * they may be async, in which case unloading awaits them. + */ export type Disposable = () => T -/** Effect body result accepted by `ctx.effect()` and plugin startup. */ +/** + * Effect body result accepted by `ctx.effect()` and plugin startup. + * + * Either a single disposer, a promise of one, or a (possibly async) iterable + * yielding several — generator effects register each yielded disposer as it + * is produced. + */ export type Effect = | SyncEffect | AsyncEffect @@ -69,7 +93,9 @@ type AsyncEffect = /** Tree node used to expose nested effect labels for diagnostics. */ export interface EffectMeta { + /** Human-readable effect label, e.g. `ctx.on("event")` or `ctx.provide("name")`. */ label: string + /** Metadata of nested effects registered while this effect ran. */ children: EffectMeta[] } @@ -80,7 +106,14 @@ interface EffectRunner { getOuterStack: () => string[] } -/** Lifecycle state for one plugin fiber. */ +/** + * Lifecycle state for one plugin fiber. + * + * `PENDING` — waiting for required services; `LOADING` — the plugin callback + * is running; `ACTIVE` — loaded and providing; `FAILED` — the callback or its + * config threw; `UNLOADING` — disposers are running; `DISPOSED` — the fiber + * was removed and cannot restart. + */ export const enum FiberState { PENDING, LOADING, @@ -92,6 +125,10 @@ export const enum FiberState { /** Framework error with a stable machine-readable code. */ export class CordisError extends Error { + /** + * @param code — the stable error code; also the default message. + * @param message — optional human-readable override. + */ constructor(public code: CordisError.Code, message?: string) { super(message ?? CordisError.Code[code]) } @@ -115,12 +152,19 @@ const INACTIVE = '__INACTIVE__' * cleanup for the plugin context returned by `ctx.plugin()`. */ export class Fiber { + /** Unique id within the registry; 0 for the root fiber, `null` once disposed. */ public uid: number | null + /** The context this fiber's plugin runs in (extends the parent context). */ public readonly ctx: Context + /** The validated plugin config (updated by `update()`). */ public config: any + /** Current lifecycle state; transitions emit `internal/status`. */ public state = FiberState.PENDING + /** Dispose this fiber: unload the plugin, then settle once cleanup finished. */ public readonly dispose: () => Promise + /** Snapshot of required service implementations while loaded; `undefined` otherwise. */ public store: Dict | undefined + /** The in-flight load/unload transition, if one is currently running. */ public inertia: Promise | undefined public readonly _hooks: Dict> = Object.create(null) @@ -133,6 +177,16 @@ export class Fiber { private _runner: EffectRunner private _store: Dict = Object.create(null) + /** + * Create a fiber. Plugin authors normally obtain fibers from `ctx.plugin()` + * rather than constructing them directly. + * + * @param parent — the context the plugin was loaded from. + * @param config — raw config, validated against the runtime's schema. + * @param inject — resolved dependency map (service name → intercept config). + * @param runtime — the shared plugin runtime, or `null` for the root fiber. + * @param getOuterStack — captures the caller stack for effect diagnostics. + */ constructor( public parent: Context, config: any, @@ -226,6 +280,7 @@ export class Fiber { } } + /** The plugin's display name, inherited from the nearest named ancestor, else `'root'`. */ get name() { let fiber: Fiber = this do { @@ -235,7 +290,12 @@ export class Fiber { return 'root' } - /** Throw if the fiber has already been disposed. */ + /** + * Throw if the fiber has already been disposed. + * + * @returns nothing when the fiber is still active. + * @throws {CordisError} `INACTIVE_EFFECT` when the fiber's uid has been cleared. + */ assertActive() { if (this.uid !== null) return throw new CordisError('INACTIVE_EFFECT') @@ -287,8 +347,21 @@ export class Fiber { }, runner.getOuterStack) } - /** Register a cleanup-aware effect on this fiber. */ + /** + * Register a cleanup-aware effect on this fiber. + * + * `execute` runs immediately; the disposers it produces are collected and + * run (in reverse order) either when the returned disposer is called or + * when the fiber unloads, whichever comes first. Calling the disposer twice + * is a no-op. Throws `CordisError('INACTIVE_EFFECT')` if the fiber is + * already disposed, and `TypeError` if `execute` returns an invalid shape. + * + * @param execute — the effect body; see {@link Effect} for accepted shapes. + * @param label — effect label shown in `getEffects()` diagnostics. + * @returns a disposer that tears the effect down and settles once done. + */ effect(execute: () => SyncEffect, label?: string): Disposable> + /** Same as above for async effects; the disposer is also awaitable. */ effect(execute: () => Effect, label?: string): AsyncDisposable> effect(execute: () => Effect, label = 'anonymous'): any { this.assertActive() @@ -355,7 +428,11 @@ export class Fiber { return wrapper } - /** Return metadata for currently registered effects. */ + /** + * Return metadata for currently registered effects. + * + * @returns one {@link EffectMeta} tree per labeled live effect. + */ getEffects() { return [...this._disposables] .map(dispose => dispose[symbols.effect]) @@ -474,7 +551,12 @@ export class Fiber { }) } - /** Wait for current lifecycle work and rethrow startup errors. */ + /** + * Wait for current lifecycle work and rethrow startup errors. + * + * @returns this fiber, once it has settled into a stable state. + * @throws the config-validation or plugin-startup error, if any. + */ async await() { while (this.inertia) { await this.inertia @@ -483,7 +565,12 @@ export class Fiber { return this } - /** Dispose and immediately reload this plugin with its current config. */ + /** + * Dispose and immediately reload this plugin with its current config. + * + * @returns a promise resolving once the reload settled. + * @throws {CordisError} `INACTIVE_EFFECT` when the fiber is already disposed. + */ async restart() { this.assertActive() this._setEpoch(INACTIVE) @@ -491,7 +578,17 @@ export class Fiber { await this.await() } - /** Validate and apply new config, then restart the plugin. */ + /** + * Validate and apply new config, then restart the plugin. + * + * Runs the `internal/update` waterfall first, so update hooks (and HMR) + * can veto or replace the restart. + * + * @param config — the new raw config; validated before anything restarts. + * @param noSave — hint for persistence hooks not to write the change back. + * @returns nothing; the restart runs behind the `internal/update` waterfall. + * @throws {ValidationError} when the new config fails validation. + */ update(config: any, noSave = false) { this.assertActive() config = resolveConfig(this.runtime!, config) diff --git a/vendor/cordis/src/logger.ts b/vendor/cordis/src/logger.ts index a1e97c165a..3c5ad10525 100644 --- a/vendor/cordis/src/logger.ts +++ b/vendor/cordis/src/logger.ts @@ -62,8 +62,11 @@ export const defaultFormatters: Record = { /** Options used when creating a named logger facade. */ export interface LoggerOptions { + /** The logger name shown with each message. */ name: string + /** Message fields merged into every record from this logger. */ meta?: Partial + /** Default maximum level exported when an exporter has no own threshold. */ level?: number } @@ -220,7 +223,12 @@ export class LoggerService { return self } - /** Register an exporter and dispose it with the current fiber. */ + /** + * Register an exporter and dispose it with the current fiber. + * + * @param exporter — the sink that receives structured log messages. + * @returns a disposer that removes the exporter. + */ exporter(exporter: Exporter) { return this.ctx.effect(() => { this.exporters.set(++this._snExporter, exporter) diff --git a/vendor/cordis/src/reflect.ts b/vendor/cordis/src/reflect.ts index 212ec4e779..e983745024 100644 --- a/vendor/cordis/src/reflect.ts +++ b/vendor/cordis/src/reflect.ts @@ -5,14 +5,66 @@ import { Fiber, FiberState } from './fiber.ts' declare module './context.ts' { interface Context { + /** + * Read a service from the store without the inject requirement. + * + * @param name — the service name. + * @param strict — when `true` (default), only return implementations + * whose providing fiber is currently active. + * @returns the service value, or `undefined` when not (yet) provided. + */ get(name: K, strict?: boolean): undefined | this[K] + /** Same as above for service names outside the typed `Context` surface. */ get(name: string, strict?: boolean): any + /** + * Overwrite a provided service's value. + * + * Only the fiber that provided the service may set it; setting an + * unprovided name throws. + * + * @param name — the service name. + * @param value — the new service value. + */ set(name: K, value: undefined | this[K]): void + /** Same as above for service names outside the typed `Context` surface. */ set(name: string, value: any): void + /** + * Register a service implementation owned by the current fiber. + * + * The service becomes visible to dependents in the same isolation scope + * once the fiber is active; it is unregistered (waking dependents) when + * the returned disposer runs or the fiber unloads. Throws if the name is + * already provided in this scope or declared as an accessor. + * + * @param name — the service name. + * @param value — the service value. + * @returns a disposer that unregisters the service. + */ provide(name: K, value: undefined | this[K]): () => void + /** Same as above for service names outside the typed `Context` surface. */ provide(name: string, value?: any): () => void + /** + * Define a computed context property backed by get/set hooks. + * + * The accessor is removed when the current fiber unloads. Throws if the + * name is already declared. + * + * @param name — the context property name. + * @param options — the `get` hook and optional `set` hook. + */ accessor(name: string, options: Omit): void + /** + * Expose selected members of a service directly on `ctx`. + * + * Each mixed-in key becomes an accessor that forwards to the service + * (binding methods to it), so e.g. `ctx.on` forwards to `ctx.events.on`. + * Mixins are removed when the current fiber unloads. + * + * @param name — the context property holding the source service. + * @param mixins — keys to forward, or a source-key → ctx-key map. + */ mixin(name: K, mixins: (keyof this & keyof this[K])[] | Dict): void + /** Same as above with a source object instead of a context property name. */ mixin(source: T, mixins: (keyof this & keyof T)[] | Dict): void } } @@ -44,22 +96,30 @@ export type Property = Property.Service | Property.Accessor export namespace Property { /** Service property backed by a provided implementation. */ export interface Service { + /** Discriminator. */ type: 'service' } /** Computed context property backed by custom get/set hooks. */ export interface Accessor { + /** Discriminator. */ type: 'accessor' + /** Compute the property value; `error` carries the caller stack for diagnostics. */ get: (this: Context, receiver: any, error: Error) => any + /** Optional setter; return `false` to reject the write. */ set?: (this: Context, value: any, receiver: any, error: Error) => boolean } } /** Concrete service implementation record stored in the root reflect service. */ export interface Impl { + /** The service name. */ name: string + /** The fiber that provided the service (owns its lifetime). */ fiber: Fiber + /** The current service value. */ value?: any + /** Optional availability predicate consulted before dependents may load. */ check?: () => boolean } @@ -70,6 +130,7 @@ export interface Impl { * the mixins that expose core service methods directly on `ctx`. */ export class ReflectService { + /** Proxy traps implementing service resolution for every context object. */ static handler: ProxyHandler = { get: (target, prop, ctx: Context) => { if (isSpecialProperty(prop)) { @@ -143,7 +204,9 @@ export class ReflectService { }, } + /** Service implementations, keyed by isolation label. */ public store: Dict = Object.create(null) + /** Declared context properties (services and accessors), by name. */ public props: Dict = Object.create(null) constructor(public ctx: Context) { @@ -158,6 +221,14 @@ export class ReflectService { this.mixin('events', ['on', 'once', 'parallel', 'emit', 'serial', 'bail', 'waterfall']) } + /** + * Read a service from the store without the inject requirement. + * + * @param name — the service name. + * @param strict — when `true`, only return implementations whose providing + * fiber is currently active. + * @returns the service value, or `undefined` when not (yet) provided. + */ get(name: string, strict = true) { return getTraceable(this.ctx, this._getImpl(name, strict)?.value) } @@ -170,6 +241,15 @@ export class ReflectService { return impl } + /** + * Overwrite a provided service's value. + * + * @param name — the service name. + * @param value — the new service value. + * @param error — carrier for the caller stack in diagnostics. + * @returns `true` on success. + * @throws when `name` was never provided, or was provided by another fiber. + */ set(name: string, value: any, error?: Error) { const key = this.ctx[symbols.isolate][name] const impl = this.store[key] @@ -183,6 +263,16 @@ export class ReflectService { return true } + /** + * Register a service implementation owned by the current fiber. + * + * See the `ctx.provide()` overload above for the full contract. + * + * @param name — the service name. + * @param value — the service value. + * @param check — optional availability predicate for dependents. + * @returns a disposer that unregisters the service. + */ provide(name: string, value?: any, check?: () => boolean) { return this.ctx.fiber.effect(() => { if (!this.props[name]) { @@ -213,6 +303,13 @@ export class ReflectService { }, `ctx.provide(${JSON.stringify(name)})`) } + /** + * Re-evaluate every fiber that requires one of the given services. + * + * @param names — the service names that changed. + * @param filter — restricts notification to matching isolation scopes. + * @returns the fibers whose dependency state was refreshed. + */ notify(names: string[], filter = (ctx: Context, name: string) => ctx[symbols.isolate][name] === this.ctx[symbols.isolate][name]) { const fibers: Fiber[] = [] for (const runtime of this.ctx.registry.values()) { @@ -232,6 +329,13 @@ export class ReflectService { return fibers } + /** + * Define a computed context property backed by get/set hooks. + * + * @param name — the context property name. + * @param options — the `get` hook and optional `set` hook. + * @returns a disposer that removes the accessor. + */ accessor(name: string, options: Omit) { return this.ctx.fiber.effect(() => { if (name in this.props) { @@ -242,6 +346,15 @@ export class ReflectService { }, `ctx.accessor(${JSON.stringify(name)})`) } + /** + * Expose selected members of a service directly on `ctx`. + * + * See the `ctx.mixin()` overload above for the full contract. + * + * @param source — a context property name or a source object. + * @param mixins — keys to forward, or a source-key → ctx-key map. + * @returns a disposer that removes all created accessors. + */ mixin(source: any, mixins: string[] | Dict) { const self = this return this.ctx.fiber.effect(function* () { @@ -270,10 +383,22 @@ export class ReflectService { }, `ctx.mixin(${JSON.stringify(source)})`) } + /** + * Attach this context's tracing wrapper to a value. + * + * @param value — the value to wrap. + * @returns the traceable wrapper (or the value itself when not applicable). + */ trace(value: T) { return getTraceable(this.ctx, value) } + /** + * Wrap a callback so calls trace `this` and arguments to this context. + * + * @param callback — the function to wrap. + * @returns a proxy delegating to `callback` with traced values. + */ bind(callback: T) { return new Proxy(callback, { apply: (target, thisArg, args) => { diff --git a/vendor/cordis/src/registry.ts b/vendor/cordis/src/registry.ts index 9dfa10a06b..05fbadcfad 100644 --- a/vendor/cordis/src/registry.ts +++ b/vendor/cordis/src/registry.ts @@ -28,6 +28,11 @@ export type InjectKey = keyof { * On classes it contributes to the plugin's static `inject` map. On methods it * delays the method call until the declared services are available. */ +/** + * @param name — the required service name. + * @param config — optional intercept config applied for that service. + * @returns the class or method decorator. + */ export function Inject(name: K, config?: Context[K] extends { [symbols.config]: infer T } ? T : never) { return function (value: any, decorator: ClassDecoratorContext | ClassMethodDecoratorContext) { if (decorator.kind === 'class') { @@ -55,7 +60,13 @@ export function Inject(name: K, config?: Context[K] extends /** Utilities for normalizing plugin dependency declarations. */ export namespace Inject { - /** Convert array/object/class-inherited inject metadata into a plain map. */ + /** + * Convert array/object/class-inherited inject metadata into a plain map. + * + * @param inject — the declaration to normalize; `null`/`undefined` add nothing. + * @param result — the map to fill (service name → intercept config or `null`). + * @returns `result`. + */ export function resolve(inject: Inject | null | undefined, result: Dict = Object.create(null)) { if (!inject) return result if (Array.isArray(inject)) { @@ -86,10 +97,15 @@ export type Plugin = export namespace Plugin { /** Shared metadata understood by the plugin registry and related tooling. */ export interface Base { + /** Display name used for fiber diagnostics and logger names. */ name?: string + /** Standard-schema validator applied to config before the plugin starts. */ Config?: StandardSchemaV1 + /** Services the plugin requires; it only loads while all are available. */ inject?: Inject + /** Service name(s) the plugin provides (read by `Service` and by loaders). */ provide?: string | string[] + /** Service names whose intercept config the plugin declares it consumes. */ intercept?: Dict } @@ -117,9 +133,13 @@ export namespace Plugin { /** Mutable registry record shared by all fibers of one plugin callback. */ export interface Runtime { + /** Display name copied from the first registered plugin shape. */ name?: string + /** Every live fiber of this plugin (one per `ctx.plugin()` call). */ fibers: DisposableList + /** The executable entrypoint all fibers share (registry identity key). */ callback: globalThis.Function + /** Standard-schema validator applied to each fiber's config. */ Config?: StandardSchemaV1 } } @@ -142,7 +162,25 @@ type GetPluginConfig

= declare module './context.ts' { export interface Context { + /** + * Run a callback once the requested services are available. + * + * Shorthand for `ctx.plugin({ inject, apply: callback })`: the callback + * is unloaded and re-run whenever a required service changes. + * + * @param deps — required services, as an array or a name → config map. + * @param callback — plugin body called with `(ctx, config)`. + * @returns the fiber; awaiting it settles once loading finished. + */ inject(deps: Inject, callback: Plugin.Function): Fiber & PromiseLike + /** + * Load a plugin in the current context. + * + * @param plugin — a function, class, or `{ apply }` object plugin. + * @param args — the plugin config, validated against its `Config` schema. + * @returns the fiber; awaiting it settles once loading finished + * (rejecting on config or startup errors). + */ plugin

(plugin: P, ...args: Spread>): Fiber & PromiseLike } } @@ -164,15 +202,22 @@ export class RegistryService { }) } + /** Allocate the next fiber uid (increments on every read). */ get counter() { return ++this._counter } + /** Number of registered plugin runtimes. */ get size() { return this._internal.size } - /** Resolve a supported plugin shape to its executable callback. */ + /** + * Resolve a supported plugin shape to its executable callback. + * + * @param plugin — a function, class, or `{ apply }` object plugin. + * @returns the callback identifying the plugin, or `undefined` if invalid. + */ resolve(plugin: Plugin): Function | undefined { // plugin.apply may throw try { @@ -181,17 +226,34 @@ export class RegistryService { } catch {} } + /** + * Look up the runtime record for a plugin. + * + * @param plugin — any supported plugin shape. + * @returns the runtime, or `undefined` when the plugin is not registered. + */ get(plugin: Plugin) { const key = this.resolve(plugin) return key && this._internal.get(key) } + /** + * Check whether a plugin has a registered runtime. + * + * @param plugin — any supported plugin shape. + * @returns `true` when at least one fiber of the plugin exists. + */ has(plugin: Plugin) { const key = this.resolve(plugin) return !!key && this._internal.has(key) } - /** Dispose every running fiber for a plugin and remove its runtime record. */ + /** + * Dispose every running fiber for a plugin and remove its runtime record. + * + * @param plugin — any supported plugin shape. + * @returns the removed runtime, or `undefined` when none was registered. + */ delete(plugin: Plugin) { const key = this.resolve(plugin) const runtime = key && this._internal.get(key) @@ -203,28 +265,53 @@ export class RegistryService { return runtime } + /** Iterate the registered plugin callbacks. */ keys() { return this._internal.keys() } + /** Iterate the registered plugin runtimes. */ values() { return this._internal.values() } + /** Iterate `[callback, runtime]` pairs. */ entries() { return this._internal.entries() } + /** + * Visit every registered runtime. + * + * @param callback — receives each runtime and its identifying callback. + */ forEach(callback: (value: Plugin.Runtime, key: Function) => void) { return this._internal.forEach(callback) } - /** Start a callback once the requested dependencies are available. */ + /** + * Start a callback once the requested dependencies are available. + * + * @param inject — required services, as an array or a name → config map. + * @param callback — plugin body called with `(ctx, config)`. + * @returns the fiber; awaiting it settles once loading finished. + */ inject(inject: Inject, callback: Plugin.Function) { return this.plugin({ inject, apply: callback, name: callback.name }) } - /** Start a plugin in the current context and return its fiber. */ + /** + * Start a plugin in the current context and return its fiber. + * + * Creates (or reuses) the plugin's runtime record, then starts a new fiber + * under the current context. Throws if `plugin` is not a supported shape or + * if the current fiber is already disposed. + * + * @param plugin — a function, class, or `{ apply }` object plugin. + * @param config — the plugin config, validated against its `Config` schema. + * @param getOuterStack — captures the caller stack for effect diagnostics. + * @returns the fiber; awaiting it settles once loading finished. + */ plugin(plugin: Plugin, config?: any, getOuterStack = buildOuterStack()) { // check if it's a valid plugin const callback = this.resolve(plugin) diff --git a/vendor/cordis/src/service.ts b/vendor/cordis/src/service.ts index 30895247c1..dc6622b68f 100644 --- a/vendor/cordis/src/service.ts +++ b/vendor/cordis/src/service.ts @@ -9,19 +9,36 @@ import { createCallable, joinPrototype, symbols, Tracker } from './utils.ts' * registered immediately and is automatically removed with the owning fiber. */ export abstract class Service { + /** Symbol key of an instance method run after construction (class plugins). */ static readonly init: unique symbol = symbols.init + /** Symbol key of the availability predicate passed to `ctx.provide()`. */ static readonly check: unique symbol = symbols.check + /** Symbol key of the phantom intercept-config type parameter. */ static readonly config: unique symbol = symbols.config + /** Symbol key of the call body making a service callable (e.g. `ctx.logger()`). */ static readonly invoke: unique symbol = symbols.invoke + /** Symbol key of the helper deriving an extended service instance. */ static readonly extend: unique symbol = symbols.extend + /** Symbol key of the tracker metadata used for context tracing. */ static readonly tracker: unique symbol = symbols.tracker + /** Symbol key of the intercept-config resolution helper below. */ static readonly resolveConfig: unique symbol = symbols.resolveConfig declare [symbols.config]: T + /** The service name this instance is registered under. */ public name!: string - /** Register this instance as `name` in the current context. */ + /** + * Register this instance as `name` in the current context. + * + * Calls `ctx.reflect.provide(name, this, this[Service.check])`, so the + * service is unregistered automatically when the owning fiber unloads. + * Services with a `[Service.invoke]` body return a callable instance. + * + * @param ctx — the context to register in (stored as `this.ctx`). + * @param name — the service name; defaults to the static `provide` field. + */ constructor(protected ctx: Context, name: string) { name ??= this.constructor['provide'] as string @@ -55,7 +72,17 @@ export abstract class Service { return Object.assign(self, props) } - /** Merge intercept config from ancestors with optional base and head values. */ + /** + * Merge intercept config from ancestors with optional base and head values. + * + * Entries added closer to the root apply first; `base` is prepended and + * `head` appended. Uses `Config.merge` when the service declares one, + * otherwise a shallow `Object.assign`. + * + * @param base — lowest-precedence config merged before all intercepts. + * @param head — highest-precedence config merged after all intercepts. + * @returns the merged config. + */ [symbols.resolveConfig](base?: T, head?: T): T { let intercept = this.ctx[Context.intercept] const configs: any[] = [] From da261385920217faa06ad6b5192fe2c6e480c8b9 Mon Sep 17 00:00:00 2001 From: lintianle Date: Thu, 16 Jul 2026 18:13:04 +0800 Subject: [PATCH 220/359] website: gate every yaml config example against the real plugin surface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit New doc-sync gate verify-website-yaml: each ```yaml block under website/zh-CN (api/ excluded — generator-owned) must parse with the loader's real schema (JSON_SCHEMA + !!js), use only EntryOptions keys, name only real workspace packages, and pass only config keys the plugin's declared Config type / schemastery schema accepts (collectConfigCatalog drives the key sets). ```yaml ignore-check opts out a deliberate-placeholder block (the capability-trio tutorial keeps its fictional package names). --- package.json | 3 +- scripts/run-gates.ts | 1 + scripts/verify-website-yaml.ts | 284 ++++++++++++++++++++++++ website/zh-CN/develop/practice/index.md | 2 +- 4 files changed, 288 insertions(+), 2 deletions(-) create mode 100644 scripts/verify-website-yaml.ts diff --git a/package.json b/package.json index 588346fc0f..acfe588c50 100644 --- a/package.json +++ b/package.json @@ -61,10 +61,11 @@ "verify-persistence-catalog": "tsx scripts/gen-persistence-catalog.ts --check", "gen-module-graph": "tsx scripts/gen-module-graph.ts", "verify-module-graph": "tsx scripts/gen-module-graph.ts --check", + "verify-website-yaml": "tsx scripts/verify-website-yaml.ts", "website:dev": "pnpm --filter @deepseek-ai/website run dev", "website:build": "pnpm --filter @deepseek-ai/website run build", "constraints": "tsx scripts/check-workspace-constraints.ts", - "doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-mermaid && pnpm run verify-rfc-classification && pnpm run verify-rfc-format && pnpm run verify-type-equiv && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets", + "doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-mermaid && pnpm run verify-rfc-classification && pnpm run verify-rfc-format && pnpm run verify-type-equiv && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets && pnpm run verify-website-yaml", "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-node-next-types", "demo:echo": "node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples/echo-agent/cordis.yml", "demo:repl": "node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples/coding-agent/cordis.yml", diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index 958ddad0ae..6384697650 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -274,6 +274,7 @@ function docSyncLeafGates(): Gate[] { pnpmScript('type-equivalence', 'verify-type-equiv', { label: 'type equivalence' }), pnpmScript('translation-pairing', 'verify-translation-pairing', { label: 'translation pairing' }), pnpmScript('doc-budgets', 'verify-doc-budgets', { label: 'doc budgets' }), + pnpmScript('website-yaml', 'verify-website-yaml', { label: 'website yaml' }), ] } diff --git a/scripts/verify-website-yaml.ts b/scripts/verify-website-yaml.ts new file mode 100644 index 0000000000..809af247e2 --- /dev/null +++ b/scripts/verify-website-yaml.ts @@ -0,0 +1,284 @@ +/** + * Doc-sync gate: verify the fenced ```yaml examples in the website against + * the loader and the workspace truth. A `cordis.yml` example that names a + * plugin that does not exist, or passes a config key the plugin never + * declared, is worse than no example — it fails silently for the reader. + * + * Scope: `website/zh-CN/**​/*.md`, EXCLUDING `website/zh-CN/api/**` (the api + * pages are generator-owned — their yaml examples are verified at generation + * time by a later stream, not re-checked here). Blocks opt out with + * ` ```yaml ignore-check ` (same philosophy as doc-typecheck's opt-out: the + * count is reported, an unchecked block is a visible decision, not a silent + * hole — placeholder plugin names in tutorials are the legitimate case). + * + * Each checked block is parsed with the loader's REAL schema — + * `JSON_SCHEMA` extended with the `!!js` scalar type exactly as + * vendor/include/src/index.ts declares it — so `!!js process.env.X` parses + * here iff it parses at runtime. Then: + * + * - Root is an ARRAY → a cordis.yml entry list. Every item must be a mapping + * with a string `name` and only the keys `EntryOptions` declares + * (vendor/loader/src/config/entry.ts plus the isolate.ts merge: + * id, name, config, group, disabled, inject, intercept, isolate). + * - `./` / `../` names are illustrative local plugins — existence is not + * checkable, skip. `group:*` names are loader built-ins; their `config` + * is itself an entry list and is recursed into. + * - Any other name must be a real workspace package (`packages/*​/*` and + * `vendor/*` package.json names). + * - For `@deepseek-ai/dsh-*` names the config-catalog generator is the + * truth: kind `config` → the yaml `config`'s top-level keys must be + * properties of the declared config type (member names of the first + * catalog paste ∪ top-level segments of the runtime schema keys); + * config-free kinds → a non-empty `config` mapping is a violation; + * seam/library kinds → name existence only (loading one directly is + * dubious, but that is a docs-prose concern, not this gate's). + * - Root is a MAPPING or scalar → a fragment (e.g. a bare `config:` excerpt): + * syntax check only. + * + * This is a checker, not a fixer: it reports `file:line message` and exits 1. + * + * Run: `tsx scripts/verify-website-yaml.ts`. + */ + +import { globSync, readFileSync } from 'node:fs' +import { resolve } from 'node:path' +import * as yaml from 'js-yaml' +import ts from 'typescript' +import { collectConfigCatalog, type CatalogEntry } from './gen-config-catalog.ts' + +const root = resolve(import.meta.dirname, '..') + +/** Mirror of the loader's yaml schema (vendor/include/src/index.ts): the + * `!!js` tag parses to an expression wrapper, everything else is JSON. */ +const JsExpr = new yaml.Type('tag:yaml.org,2002:js', { + kind: 'scalar', + resolve: data => typeof data === 'string', + construct: (data: string) => ({ __jsExpr: data }), +}) +const schema = yaml.JSON_SCHEMA.extend(JsExpr) + +/** The exact key set an entry mapping may carry: `EntryOptions` in + * vendor/loader/src/config/entry.ts plus the isolate.ts interface merge. */ +const ENTRY_KEYS = ['id', 'name', 'config', 'group', 'disabled', 'inject', 'intercept', 'isolate'] as const + +/** One `file:line message` finding. */ +interface Violation { + file: string + /** 1-based line of the block's opening fence. */ + line: number + message: string +} + +/** One extracted ```yaml block. */ +interface Block { + file: string + /** 1-based line of the opening fence. */ + line: number + kind: 'check' | 'ignore' + code: string +} + +/** Extract every ```yaml / ```yaml ignore-check block from one Markdown file. */ +function extractBlocks(file: string): Block[] { + const text = readFileSync(resolve(root, file), 'utf8') + const lines = text.split('\n') + const blocks: Block[] = [] + let open: { line: number; kind: Block['kind']; body: string[] } | null = null + + lines.forEach((raw, i) => { + const fence = /^```(\s*)(\S.*)?$/.exec(raw) + if (!fence) { + if (open) open.body.push(raw) + return + } + if (open) { + // closing fence + blocks.push({ file, line: open.line, kind: open.kind, code: open.body.join('\n') }) + open = null + return + } + // opening fence — only yaml blocks participate + const info = (fence[2] ?? '').trim() + const kind: Block['kind'] | null = + info === 'yaml' ? 'check' + : info === 'yaml ignore-check' ? 'ignore' + : null + if (kind) open = { line: i + 1, kind, body: [] } + }) + return blocks +} + +/** Every workspace package name: `packages//` and `vendor/`. */ +function knownPackages(): Set { + const names = new Set() + for (const pattern of ['packages/*/*/package.json', 'vendor/*/package.json']) { + for (const match of globSync(pattern, { cwd: root })) { + const pkg: unknown = JSON.parse(readFileSync(resolve(root, match), 'utf8')) + if (typeof pkg === 'object' && pkg !== null && 'name' in pkg && typeof pkg.name === 'string') { + names.add(pkg.name) + } + } + } + return names +} + +/** The catalog, built once on first `@deepseek-ai/dsh-*` name, keyed by pkg. */ +let catalogByPkg: Map | null = null +function catalogFor(pkg: string): CatalogEntry | undefined { + catalogByPkg ??= new Map(collectConfigCatalog().map(e => [e.pkg, e])) + return catalogByPkg.get(pkg) +} + +/** Top-level property names of the first catalog paste (the verbatim config + * type declaration), parsed as source text. */ +function pasteKeys(paste: string): Set { + const sf = ts.createSourceFile('paste.ts', paste, ts.ScriptTarget.Latest, true) + const keys = new Set() + const addMembers = (members: ts.NodeArray): void => { + for (const m of members) { + if (ts.isPropertySignature(m) || ts.isMethodSignature(m)) { + const name = m.name + keys.add(ts.isIdentifier(name) || ts.isStringLiteral(name) ? name.text : name.getText(sf)) + } + } + } + for (const stmt of sf.statements) { + if (ts.isInterfaceDeclaration(stmt)) addMembers(stmt.members) + else if (ts.isTypeAliasDeclaration(stmt) && ts.isTypeLiteralNode(stmt.type)) addMembers(stmt.type.members) + } + return keys +} + +/** The allowed top-level config keys of a kind-`config` catalog entry: the + * first paste's member names ∪ the schema keys' top-level segments + * (`agents[].id` → `agents`). Cached per entry. */ +const allowedKeysCache = new Map>() +function allowedConfigKeys(entry: CatalogEntry): Set { + const cached = allowedKeysCache.get(entry.pkg) + if (cached) return cached + const keys = pasteKeys(entry.pastes?.[0]?.text ?? '') + for (const path of entry.schemaKeys ?? []) { + const top = path.split('.')[0]?.replace(/\[\]$/, '') + if (top) keys.add(top) + } + allowedKeysCache.set(entry.pkg, keys) + return keys +} + +/** A parsed yaml mapping (arrays and `!!js` wrappers excluded). */ +function asMapping(value: unknown): Record | null { + if (typeof value !== 'object' || value === null || Array.isArray(value)) return null + if ('__jsExpr' in value) return null + return value as Record +} + +/** Check one cordis.yml entry list (recursing into `group:` sub-lists). */ +function checkEntryList( + items: unknown[], + known: Set, + block: Block, + violations: Violation[], +): void { + const flag = (message: string): void => { + violations.push({ file: block.file, line: block.line, message }) + } + items.forEach((item, index) => { + const at = `entry ${index + 1}` + const entry = asMapping(item) + if (!entry) { + flag(`${at}: not a mapping`) + return + } + const name = entry['name'] + if (typeof name !== 'string') { + flag(`${at}: missing string \`name\``) + return + } + for (const key of Object.keys(entry)) { + if (!(ENTRY_KEYS as readonly string[]).includes(key)) { + flag(`${at} (${name}): unknown entry key \`${key}\` (EntryOptions allows: ${[...ENTRY_KEYS].join(', ')})`) + } + } + // Illustrative local plugin — nothing on disk to check against. + if (name.startsWith('./') || name.startsWith('../')) return + // Loader built-in group: its config is a nested entry list. + if (name.startsWith('group:')) { + if (Array.isArray(entry['config'])) checkEntryList(entry['config'], known, block, violations) + return + } + if (!known.has(name)) { + flag(`${at}: unknown plugin \`${name}\` (not a workspace package)`) + return + } + if (!name.startsWith('@deepseek-ai/dsh-')) return + const catalog = catalogFor(name) + if (!catalog) return + const config = asMapping(entry['config']) + if (catalog.kind === 'config') { + if (!config) return + const allowed = allowedConfigKeys(catalog) + for (const key of Object.keys(config)) { + if (!allowed.has(key)) { + flag(`${at}: \`${name}\` has no config key \`${key}\` (known keys: ${[...allowed].sort().join(', ')})`) + } + } + } else if (catalog.kind === 'no-config') { + if (config && Object.keys(config).length > 0) { + flag(`${at}: \`${name}\` declares no config, but the example passes one`) + } + } + // seam / library: loading one directly is dubious, but that is a prose + // concern — this gate only vouches for name existence. + }) +} + +const files = globSync('website/zh-CN/**/*.md', { cwd: root }) + .filter(f => !f.startsWith('website/zh-CN/api/')) + .sort() + +const violations: Violation[] = [] +const known = knownPackages() +let entryLists = 0 +let fragments = 0 +let ignored = 0 +let scanned = 0 + +for (const file of files) { + for (const block of extractBlocks(file)) { + scanned++ + if (block.kind === 'ignore') { + ignored++ + continue + } + let parsed: unknown + try { + parsed = yaml.load(block.code, { schema }) + } catch (error) { + const message = error instanceof Error ? error.message.split('\n')[0] ?? 'parse error' : String(error) + violations.push({ file: block.file, line: block.line, message: `yaml parse error: ${message}` }) + continue + } + if (Array.isArray(parsed)) { + entryLists++ + checkEntryList(parsed, known, block, violations) + } else { + // Mapping or scalar root: a fragment (e.g. a bare `config:` excerpt) — + // syntax is all there is to check. + fragments++ + } + } +} + +if (violations.length === 0) { + console.log( + `verify-website-yaml: ${scanned} yaml block(s) in ${files.length} file(s): ` + + `${entryLists} entry list(s) + ${fragments} fragment(s) checked, ${ignored} ignore-check skipped.`, + ) + process.exit(0) +} + +console.error('verify-website-yaml: invalid yaml examples found:') +for (const v of violations) { + console.error(` ${v.file}:${v.line} ${v.message}`) +} +process.exit(1) diff --git a/website/zh-CN/develop/practice/index.md b/website/zh-CN/develop/practice/index.md index 9781138c50..2a077aa22e 100644 --- a/website/zh-CN/develop/practice/index.md +++ b/website/zh-CN/develop/practice/index.md @@ -140,7 +140,7 @@ export function apply(ctx: Context) { ### 在 cordis.yml 中组合 -```yaml +```yaml ignore-check - name: '@deepseek-ai/dsh-my-cap-local' - name: '@deepseek-ai/dsh-tool-my-cap' ``` From efba9fab0a43e25f0073365a7aa60144aef162af Mon Sep 17 00:00:00 2001 From: lintianle Date: Thu, 16 Jul 2026 18:13:34 +0800 Subject: [PATCH 221/359] website: generate the API reference from source (cordis + all 15 harness services) scripts/gen-website-api.ts renders website/zh-CN/api/{cordis,harness}/* and the api-sidebar.json fragment the VitePress config imports, so pages and navigation can never drift from the code: signatures, @param/@returns prose, dispatch modes, and GitHub source links are extracted, never transcribed, and the generator hard-errors on any rendered member missing docs. verify-website-api (doc-sync + run-gates) is the freshness gate. Replaces the hand-written zh api pages (7 pages covering 7 of 15 services, with phantom APIs: Context.current/Context.events, agent/post-step, tool/call, compact/*, llm/pre-request none of which exist) with generated English references: 5 cordis pages, 15 per-service pages, and a 35-event catalog grouped by scope. The hand-written hub api/index.md stays and now indexes the full surface; zh for these pages arrives with the unified translation flow. --- AGENTS.md | 2 +- package.json | 4 +- scripts/gen-website-api.ts | 675 ++++++++++++++++++ scripts/run-gates.ts | 1 + website/.vitepress/config/api-sidebar.json | 90 +++ website/.vitepress/config/zh-CN.ts | 20 +- website/zh-CN/api/cordis/context.md | 219 ++++-- website/zh-CN/api/cordis/events.md | 192 ++--- website/zh-CN/api/cordis/fiber.md | 303 ++++++-- website/zh-CN/api/cordis/registry.md | 160 +++-- website/zh-CN/api/cordis/service.md | 163 ++--- website/zh-CN/api/harness/agent-loop.md | 56 ++ website/zh-CN/api/harness/agent.md | 85 --- website/zh-CN/api/harness/agents.md | 91 +++ website/zh-CN/api/harness/bash.md | 173 +++-- website/zh-CN/api/harness/code-runtime.md | 28 + website/zh-CN/api/harness/compact.md | 55 ++ website/zh-CN/api/harness/events.md | 546 ++++++++++++++ website/zh-CN/api/harness/fs.md | 172 +++-- website/zh-CN/api/harness/llm.md | 128 +--- .../zh-CN/api/harness/session-persistence.md | 66 ++ website/zh-CN/api/harness/session.md | 56 -- website/zh-CN/api/harness/sessions.md | 110 +++ website/zh-CN/api/harness/subagent.md | 85 --- website/zh-CN/api/harness/subagents.md | 64 ++ website/zh-CN/api/harness/system-prompt.md | 66 ++ website/zh-CN/api/harness/tools.md | 131 +--- website/zh-CN/api/harness/user-interaction.md | 37 + website/zh-CN/api/harness/web.md | 74 ++ website/zh-CN/api/harness/workflows.md | 28 + website/zh-CN/api/index.md | 34 +- 31 files changed, 2983 insertions(+), 931 deletions(-) create mode 100644 scripts/gen-website-api.ts create mode 100644 website/.vitepress/config/api-sidebar.json create mode 100644 website/zh-CN/api/harness/agent-loop.md delete mode 100644 website/zh-CN/api/harness/agent.md create mode 100644 website/zh-CN/api/harness/agents.md create mode 100644 website/zh-CN/api/harness/code-runtime.md create mode 100644 website/zh-CN/api/harness/compact.md create mode 100644 website/zh-CN/api/harness/events.md create mode 100644 website/zh-CN/api/harness/session-persistence.md delete mode 100644 website/zh-CN/api/harness/session.md create mode 100644 website/zh-CN/api/harness/sessions.md delete mode 100644 website/zh-CN/api/harness/subagent.md create mode 100644 website/zh-CN/api/harness/subagents.md create mode 100644 website/zh-CN/api/harness/system-prompt.md create mode 100644 website/zh-CN/api/harness/user-interaction.md create mode 100644 website/zh-CN/api/harness/web.md create mode 100644 website/zh-CN/api/harness/workflows.md diff --git a/AGENTS.md b/AGENTS.md index 70bd5b3ddf..593b4d39b6 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -30,7 +30,7 @@ packages/ Harness packages at packages///, all named @deepseek-ai examples/ Runnable demos: thin cordis.yml leaves over the app packages (see examples/AGENTS.md) docs/ architecture, generated catalogs, RFCs, postmortems, cookbook (see docs/AGENTS.md) scripts/ repo gates and generators -website/ VitePress docs site (zh-CN) +website/ VitePress docs site (zh-CN); api/ pages generated from source ``` Per-package map: the group READMEs, indexed from [packages/README.md](packages/README.md). diff --git a/package.json b/package.json index acfe588c50..8e524eae18 100644 --- a/package.json +++ b/package.json @@ -61,11 +61,13 @@ "verify-persistence-catalog": "tsx scripts/gen-persistence-catalog.ts --check", "gen-module-graph": "tsx scripts/gen-module-graph.ts", "verify-module-graph": "tsx scripts/gen-module-graph.ts --check", + "gen-website-api": "tsx scripts/gen-website-api.ts", + "verify-website-api": "tsx scripts/gen-website-api.ts --check", "verify-website-yaml": "tsx scripts/verify-website-yaml.ts", "website:dev": "pnpm --filter @deepseek-ai/website run dev", "website:build": "pnpm --filter @deepseek-ai/website run build", "constraints": "tsx scripts/check-workspace-constraints.ts", - "doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-mermaid && pnpm run verify-rfc-classification && pnpm run verify-rfc-format && pnpm run verify-type-equiv && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets && pnpm run verify-website-yaml", + "doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-website-api && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-mermaid && pnpm run verify-rfc-classification && pnpm run verify-rfc-format && pnpm run verify-type-equiv && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets && pnpm run verify-website-yaml", "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-node-next-types", "demo:echo": "node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples/echo-agent/cordis.yml", "demo:repl": "node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples/coding-agent/cordis.yml", diff --git a/scripts/gen-website-api.ts b/scripts/gen-website-api.ts new file mode 100644 index 0000000000..2d74f075e6 --- /dev/null +++ b/scripts/gen-website-api.ts @@ -0,0 +1,675 @@ +/** + * Generate (and verify) the website API reference under `website/zh-CN/api/`. + * + * The website's API section is FULLY GENERATED from source — never hand-edit + * it. The hand-written hub `api/index.md` sits OUTSIDE the generated subdirs + * (`api/cordis/`, `api/harness/`), so the orphan sweep never touches it. Two tiers: + * + * - `api/cordis/*` — the vendored cordis framework surface (Context, Events, + * Fiber, Registry, Service), driven by the CORDIS_PAGES manifest below. + * Members come from the real class declarations and the `declare module + * './context.ts'` interface merges (the typed `ctx.*` surface a plugin + * author actually sees). + * - `api/harness/*` — one page per `ctx.` harness service (walked from + * every `declare module 'cordis'` Context merge under `packages///src`), + * plus `events.md` listing every harness event grouped by scope. + * + * Prose comes from the JSDoc; the generator HARD-ERRORS (aggregated) when a + * rendered member lacks a summary, a parameter lacks `@param`, or a non-void + * annotated return lacks `@returns` — so a vendor sync or a new service method + * cannot land undocumented without CI going red. Pages are English (the + * planned zh translation flow arrives separately; see docs/i18n/README.md). + * + * Signature fences use the ` ```ts website-api ` info string: doc-typecheck + * only processes its known info strings, so these bare (non-compilable) + * signature fragments are skipped there, while VitePress still highlights the + * `ts` token. The sidebar fragment `website/.vitepress/config/api-sidebar.json` + * is generated alongside so navigation can never drift from the page set. + * + * `tsx scripts/gen-website-api.ts` → write pages + sidebar + * `tsx scripts/gen-website-api.ts --check` → exit 1 if committed copies are + * stale (doc-sync / CI gate) + */ + +import { globSync, mkdirSync, readFileSync, writeFileSync } from 'node:fs' +import { dirname, resolve } from 'node:path' +import ts from 'typescript' +import { checkParams, checkReturns, parseJsDoc, parseTags, pointer, rawJsDoc, reportViolations, type Mode } from './jsdoc.ts' + +const root = resolve(import.meta.dirname, '..') + +/** Output roots: generated pages and the generated sidebar fragment. */ +const PAGES_DIR = 'website/zh-CN/api' +const SIDEBAR_OUT = 'website/.vitepress/config/api-sidebar.json' + +/** GitHub blob base for source links on the public site (repo-relative paths + * do not resolve on the built site, unlike the in-repo catalogs). */ +const GITHUB = 'https://github.com/deepseek-harness/deepseek-harness/blob/master' + +/** Signature-fence info string (skipped by doc-typecheck, highlighted as ts). */ +const FENCE = 'ts website-api' + +/** One rendered member: a method/property plus its parsed JSDoc. */ +interface MemberDoc { + /** Display name, e.g. `on` or `agent/pre-step`. */ + name: string + /** Heading suffix with parameter names, e.g. `(name, listener, options?)`; + * empty for properties. */ + heading: string + /** All overload signature lines (bodies stripped). */ + signatures: string[] + /** Description prose, one paragraph per line. */ + doc: string + /** Parameter name → `@param` text, in declaration order. */ + params: { name: string; text: string }[] + /** `@returns` text, or null for void/undocumented. */ + returns: string | null + /** Repo-relative `file:line` of the (first) declaration. */ + source: string +} + +/** A cordis-page section: which declarations it renders. */ +type Section = + | { kind: 'class'; file: string; symbol: string; prefix?: string } + | { kind: 'context-merge'; file: string } + | { kind: 'decl'; file: string; symbol: string } + +/** One generated cordis page. */ +interface CordisPage { + out: string + title: string + intro: string + sections: Section[] +} + +/** + * The cordis tier manifest. Deliberately explicit (not a blind walk): the + * vendor `Context` mixes true plugin-author surface with internals, and page + * grouping is an editorial choice — but every member listed here is still + * EXTRACTED, never transcribed, so signatures and docs cannot drift. + */ +const CORDIS_PAGES: CordisPage[] = [ + { + out: 'cordis/context.md', + title: 'Context', + intro: 'The context is the core cordis object: every service, event, and lifecycle API is reached through `ctx`. Event methods (`ctx.on`, `ctx.emit`, …) are documented on [Events](./events.md); `ctx.effect` and `ctx.fiber` on [Fiber](./fiber.md); `ctx.plugin` and `ctx.inject` on [Registry](./registry.md).', + sections: [ + { kind: 'class', file: 'vendor/cordis/src/context.ts', symbol: 'Context', prefix: 'ctx.' }, + { kind: 'context-merge', file: 'vendor/cordis/src/reflect.ts' }, + ], + }, + { + out: 'cordis/events.md', + title: 'Events', + intro: 'The event system mixed into every context. Harness-defined events are cataloged on [Harness events](../harness/events.md).', + sections: [ + { kind: 'context-merge', file: 'vendor/cordis/src/events.ts' }, + { kind: 'decl', file: 'vendor/cordis/src/events.ts', symbol: 'EventOptions' }, + { kind: 'decl', file: 'vendor/cordis/src/events.ts', symbol: 'DispatchMode' }, + ], + }, + { + out: 'cordis/fiber.md', + title: 'Fiber', + intro: 'A fiber is one loaded plugin instance: its lifecycle state, validated config, and registered effects. `ctx.fiber` is the current fiber; `ctx.effect()` delegates to it.', + sections: [ + { kind: 'context-merge', file: 'vendor/cordis/src/fiber.ts' }, + { kind: 'class', file: 'vendor/cordis/src/fiber.ts', symbol: 'Fiber' }, + { kind: 'decl', file: 'vendor/cordis/src/fiber.ts', symbol: 'Effect' }, + { kind: 'decl', file: 'vendor/cordis/src/fiber.ts', symbol: 'Disposable' }, + { kind: 'decl', file: 'vendor/cordis/src/fiber.ts', symbol: 'EffectMeta' }, + { kind: 'decl', file: 'vendor/cordis/src/fiber.ts', symbol: 'CordisError' }, + { kind: 'decl', file: 'vendor/cordis/src/fiber.ts', symbol: 'ValidationError' }, + ], + }, + { + out: 'cordis/registry.md', + title: 'Registry', + intro: 'Plugin loading and dependency injection.', + sections: [ + { kind: 'context-merge', file: 'vendor/cordis/src/registry.ts' }, + { kind: 'decl', file: 'vendor/cordis/src/registry.ts', symbol: 'Plugin' }, + { kind: 'decl', file: 'vendor/cordis/src/registry.ts', symbol: 'Inject' }, + ], + }, + { + out: 'cordis/service.md', + title: 'Service', + intro: 'Base class for context services: subclass it and load the subclass as a plugin to register `ctx.`.', + sections: [ + { kind: 'class', file: 'vendor/cordis/src/service.ts', symbol: 'Service' }, + ], + }, +] +// --------------------------------------------------------------------------- +// Extraction +// --------------------------------------------------------------------------- + +const sfCache = new Map() + +/** Parse (and cache) one repo-relative source file. */ +function load(rel: string): { sf: ts.SourceFile; text: string } { + const cached = sfCache.get(rel) + if (cached) return cached + const text = readFileSync(resolve(root, rel), 'utf8') + const sf = ts.createSourceFile(rel, text, ts.ScriptTarget.Latest, true) + const entry = { sf, text } + sfCache.set(rel, entry) + return entry +} + +/** The body of a `declare module './context.ts'` / `declare module 'cordis'` + * block, or null. */ +function moduleBody(sf: ts.SourceFile): ts.ModuleBlock | null { + for (const stmt of sf.statements) { + if (!ts.isModuleDeclaration(stmt) || !ts.isStringLiteral(stmt.name)) continue + if (stmt.name.text !== './context.ts' && stmt.name.text !== 'cordis') continue + if (stmt.body && ts.isModuleBlock(stmt.body)) return stmt.body + } + return null +} + +/** Signature text of a member: full text minus body/initializer, whitespace + * collapsed, trailing semicolon stripped. */ +function signatureOf(member: ts.Node, sf: ts.SourceFile): string { + const full = member.getText(sf) + const tail = (member as { body?: ts.Node; initializer?: ts.Node }).body + ?? (member as { initializer?: ts.Node }).initializer + const sig = tail ? full.slice(0, full.length - tail.getText(sf).length).replace(/[=\s]+$/, '') : full + return sig.replace(/\s*;?\s*$/, '').replace(/\s+/g, ' ').trim() +} + +/** `(a, b?, ...rest)` heading suffix from a parameter list, `this` dropped. */ +function headingParams(parameters: readonly ts.ParameterDeclaration[], sf: ts.SourceFile): string { + const names = parameters + .filter(p => !(ts.isIdentifier(p.name) && p.name.text === 'this')) + .map((p) => { + const dots = p.dotDotDotToken ? '...' : '' + const opt = p.questionToken || p.initializer ? '?' : '' + return `${dots}${p.name.getText(sf)}${opt}` + }) + return `(${names.join(', ')})` +} + +/** Whether a class member is renderable public API (non-static half). */ +function isPublicInstance(member: ts.ClassElement): boolean { + const mods = ts.getCombinedModifierFlags(member) + if (mods & (ts.ModifierFlags.Private | ts.ModifierFlags.Protected | ts.ModifierFlags.Static)) return false + if (!member.name) return false + if (ts.isComputedPropertyName(member.name) || ts.isPrivateIdentifier(member.name)) return false + return !member.name.getText().startsWith('_') +} + +/** Whether a class member is renderable public STATIC API. */ +function isPublicStatic(member: ts.ClassElement): boolean { + const mods = ts.getCombinedModifierFlags(member) + if (mods & (ts.ModifierFlags.Private | ts.ModifierFlags.Protected)) return false + if (!(mods & ts.ModifierFlags.Static)) return false + if (!member.name || ts.isComputedPropertyName(member.name) || ts.isPrivateIdentifier(member.name)) return false + return !member.name.getText().startsWith('_') +} + +/** Build a MemberDoc from a declaration group (overloads share one entry), + * collecting completeness violations for everything rendered. */ +function memberDoc( + where: string, + name: string, + group: (ts.MethodDeclaration | ts.MethodSignature | ts.PropertyDeclaration | ts.PropertySignature | ts.GetAccessorDeclaration)[], + rel: string, + violations: string[], +): MemberDoc { + const { sf, text } = load(rel) + const first = group[0] + if (!first) throw new Error(`gen-website-api: empty member group for ${name}`) + // Doc from the first overload that carries JSDoc prose. + const rawDocs = group.map(m => rawJsDoc(text, m)) + const docIndex = rawDocs.findIndex(r => parseJsDoc(r).doc !== '') + const raw = docIndex === -1 ? '' : (rawDocs[docIndex] ?? '') + const doc = parseJsDoc(raw).doc + if (!doc) violations.push(`${where} has no JSDoc prose.`) + const { params: tags, returns } = parseTags(raw) + const params: { name: string; text: string }[] = [] + let returnsText: string | null = null + const funcLike = group.filter((m): m is ts.MethodDeclaration | ts.MethodSignature => ts.isMethodDeclaration(m) || ts.isMethodSignature(m)) + const docCarrier = funcLike[docIndex === -1 ? 0 : docIndex] + if (docCarrier) { + checkParams(where, 'website-api', docCarrier.parameters, tags, sf, + p => ts.isIdentifier(p.name) && p.name.text === 'this', violations) + if (docCarrier.type) { + checkReturns(where, docCarrier.type, returns, sf, violations) + } else if (!returns && ts.isMethodDeclaration(docCarrier)) { + // Comment-only vendor policy: we cannot add a return type annotation to + // pinned upstream source, so an unannotated rendered method must carry + // an explicit @returns describing the result instead. + violations.push(`${where} has no return type annotation; document the result with @returns.`) + } + for (const p of docCarrier.parameters) { + if (ts.isIdentifier(p.name) && p.name.text === 'this') continue + const pname = p.name.getText(sf) + const tag = tags.get(pname) + if (tag) params.push({ name: pname, text: tag }) + } + returnsText = returns + } + const headingSource = docCarrier ?? funcLike[0] + return { + name, + heading: headingSource ? headingParams(headingSource.parameters, sf) : '', + signatures: (ts.isMethodDeclaration(first) && funcLike.length > 1 + ? funcLike.filter(m => ts.isMethodDeclaration(m) && !m.body) + : group).map(m => signatureOf(m, sf)), + doc, + params, + returns: returnsText, + source: pointer(rel, sf, first), + } +} + +/** Members of the `interface Context` merge in `rel`, overloads grouped. */ +function contextMergeMembers(rel: string, violations: string[]): MemberDoc[] { + const { sf } = load(rel) + const body = moduleBody(sf) + if (!body) throw new Error(`gen-website-api: ${rel} has no context module merge`) + const groups = new Map() + for (const stmt of body.statements) { + if (!ts.isInterfaceDeclaration(stmt) || stmt.name.text !== 'Context') continue + for (const member of stmt.members) { + if (!ts.isMethodSignature(member) && !ts.isPropertySignature(member)) continue + if (ts.isComputedPropertyName(member.name)) continue + const name = member.name.getText(sf) + const group = groups.get(name) ?? [] + group.push(member) + groups.set(name, group) + } + } + return [...groups.entries()].map(([name, group]) => + memberDoc(`ctx.${name} (${rel})`, name, group, rel, violations)) +} + +/** Instance + static members of one class, as two rendered lists. */ +function classMembers(rel: string, className: string, violations: string[]): { + doc: string + instance: MemberDoc[] + statics: MemberDoc[] + source: string +} { + const { sf, text } = load(rel) + const cls = sf.statements.find( + (s): s is ts.ClassDeclaration => ts.isClassDeclaration(s) && s.name?.text === className, + ) + if (!cls) throw new Error(`gen-website-api: class ${className} not found in ${rel}`) + const clsDoc = parseJsDoc(rawJsDoc(text, cls)).doc + if (!clsDoc) violations.push(`class ${className} (${pointer(rel, sf, cls)}) has no JSDoc.`) + const instance = new Map() + const statics = new Map() + for (const member of cls.members) { + const renderable = ts.isMethodDeclaration(member) || ts.isPropertyDeclaration(member) || ts.isGetAccessorDeclaration(member) + if (!renderable) continue + const name = member.name.getText(sf) + if (isPublicInstance(member)) { + const group = instance.get(name) ?? [] + group.push(member) + instance.set(name, group) + } else if (isPublicStatic(member) && !ts.isGetAccessorDeclaration(member)) { + const group = statics.get(name) ?? [] + group.push(member) + statics.set(name, group) + } + } + type Renderable = ts.MethodDeclaration | ts.PropertyDeclaration | ts.GetAccessorDeclaration + const toDocs = (groups: Map, prefix: string): MemberDoc[] => + [...groups.entries()].map(([name, group]) => + memberDoc(`${prefix}${name} (${rel})`, name, group, rel, violations)) + return { + doc: clsDoc, + instance: toDocs(instance, `${className}#`), + statics: toDocs(statics, `${className}.`), + source: pointer(rel, sf, cls), + } +} + +/** Splice every function-like BODY out of a declaration's text, leaving the + * signature (`) {` → `)`). A reference paste shows shapes, not implementation; + * property initializers (e.g. an `as const` code table) are data and stay. */ +function stripBodies(node: ts.Node, sf: ts.SourceFile): string { + const cuts: { start: number; end: number }[] = [] + const visit = (n: ts.Node): void => { + const funcLike = ts.isMethodDeclaration(n) || ts.isConstructorDeclaration(n) + || ts.isFunctionDeclaration(n) || ts.isGetAccessorDeclaration(n) || ts.isSetAccessorDeclaration(n) + if (funcLike && n.body) { + // Cut from just after the parameter close (or return-type end) through + // the body, so `foo(a: string) { … }` renders as `foo(a: string)`. + const sigEnd = (n.type ?? n.parameters[n.parameters.length - 1] ?? n).getEnd() + // Find the `)` (and optional `: Type`) boundary: body start is exact. + cuts.push({ start: sigEnd, end: n.body.getEnd() }) + return // nothing renderable inside the body + } + n.forEachChild(visit) + } + visit(node) + const base = node.getStart(sf) + let out = node.getText(sf) + for (const cut of cuts.sort((a, b) => b.start - a.start)) { + const head = out.slice(0, cut.start - base) + // Keep everything of the signature up to the closing paren / return type, + // drop ` { … }`. The head may end mid-signature (last param), so retain + // the source between sigEnd and the body's `{` MINUS trailing space. + const between = out.slice(cut.start - base, cut.end - base) + const bodyBrace = between.indexOf('{') + out = head + between.slice(0, bodyBrace).trimEnd() + out.slice(cut.end - base) + } + return out +} + +/** Verbatim declaration paste: every top-level statement named `symbol` + * (class + merged namespace both), with leading JSDoc prose extracted and + * function bodies stripped (a reference shows shapes, not implementation). */ +function declPaste(rel: string, symbol: string): { doc: string; code: string; source: string } { + const { sf, text } = load(rel) + const matches = sf.statements.filter((s) => { + const named = ts.isInterfaceDeclaration(s) || ts.isTypeAliasDeclaration(s) + || ts.isClassDeclaration(s) || ts.isEnumDeclaration(s) || ts.isModuleDeclaration(s) + return named && s.name?.getText(sf) === symbol + }) + if (matches.length === 0) throw new Error(`gen-website-api: declaration ${symbol} not found in ${rel}`) + const first = matches[0] + if (!first) throw new Error(`gen-website-api: declaration ${symbol} not found in ${rel}`) + const doc = parseJsDoc(rawJsDoc(text, first)).doc + const code = matches.map(s => stripBodies(s, sf).replace(/^export\s+(default\s+)?/, '')).join('\n\n') + return { doc, code, source: pointer(rel, sf, first) } +} + +/** One harness service with member-level detail. */ +interface HarnessService { + key: string + type: string + abstract: boolean + doc: string + members: MemberDoc[] + source: string + /** Owning npm package name (from the package.json beside the entry). */ + pkg: string +} + +/** Walk every harness `declare module 'cordis'` Context merge → services. */ +function collectHarnessServices(violations: string[]): HarnessService[] { + const services: HarnessService[] = [] + for (const rel of globSync('packages/*/*/src/index.ts', { cwd: root }).sort()) { + const { sf, text } = load(rel) + if (!text.includes('interface Context')) continue + const body = moduleBody(sf) + if (!body) continue + const keyToType = new Map() + for (const stmt of body.statements) { + if (!ts.isInterfaceDeclaration(stmt) || stmt.name.text !== 'Context') continue + for (const member of stmt.members) { + if (!ts.isPropertySignature(member) || !member.type) continue + keyToType.set(member.name.getText(sf), member.type.getText(sf)) + } + } + const pkgJson = rel.replace(/src\/index\.ts$/, 'package.json') + const pkg = (JSON.parse(readFileSync(resolve(root, pkgJson), 'utf8')) as { name: string }).name + for (const [key, type] of keyToType) { + const cls = sf.statements.find( + (s): s is ts.ClassDeclaration => ts.isClassDeclaration(s) && s.name?.text === type, + ) + if (!cls) continue // a Pick-mixin member, not a class here + const abstract = cls.modifiers?.some(m => m.kind === ts.SyntaxKind.AbstractKeyword) ?? false + const clsDoc = parseJsDoc(rawJsDoc(text, cls)).doc + if (!clsDoc) violations.push(`service ctx.${key} (${pointer(rel, sf, cls)}): class ${type} has no JSDoc.`) + const groups = new Map() + for (const member of cls.members) { + if (!ts.isMethodDeclaration(member)) continue + if (!isPublicInstance(member)) continue + const name = member.name.getText(sf) + const group = groups.get(name) ?? [] + group.push(member) + groups.set(name, group) + } + const members = [...groups.entries()].map(([name, group]) => + memberDoc(`ctx.${key}.${name} (${rel})`, name, group, rel, violations)) + services.push({ key, type, abstract, doc: clsDoc, members, source: pointer(rel, sf, cls), pkg }) + } + } + return services.sort((a, b) => a.key.localeCompare(b.key)) +} + +/** One harness event with member-level detail. */ +interface HarnessEvent { + name: string + scope: string + mode: Mode | null + signature: string + doc: string + params: { name: string; text: string }[] + source: string +} + +/** Walk every harness `interface Events` merge → events. */ +function collectHarnessEvents(violations: string[]): HarnessEvent[] { + const events: HarnessEvent[] = [] + for (const rel of globSync('packages/*/*/src/*.ts', { cwd: root }).sort()) { + const { sf, text } = load(rel) + if (!text.includes('interface Events')) continue + const body = moduleBody(sf) + if (!body) continue + for (const stmt of body.statements) { + if (!ts.isInterfaceDeclaration(stmt) || stmt.name.text !== 'Events') continue + for (const member of stmt.members) { + if (!ts.isMethodSignature(member)) continue + const name = ts.isStringLiteral(member.name) ? member.name.text : member.name.getText(sf) + const raw = rawJsDoc(text, member) + const { doc, mode } = parseJsDoc(raw) + if (!mode) violations.push(`event '${name}' (${pointer(rel, sf, member)}) is missing @mode.`) + if (!doc) violations.push(`event '${name}' (${pointer(rel, sf, member)}) has no JSDoc prose.`) + const { params: tags } = parseTags(raw) + const last = member.parameters.at(-1) + const hasNext = !!last && last.name.getText(sf) === 'next' + checkParams(`event '${name}' (${pointer(rel, sf, member)})`, 'website-api', member.parameters, tags, sf, + p => (ts.isIdentifier(p.name) && p.name.text === 'this') || (hasNext && p === last), violations) + const params: { name: string; text: string }[] = [] + for (const p of member.parameters) { + const pname = p.name.getText(sf) + const tag = tags.get(pname) + if (tag) params.push({ name: pname, text: tag }) + } + events.push({ name, scope: name.split('/')[0] ?? name, mode, signature: signatureOf(member, sf), doc, params, source: pointer(rel, sf, member) }) + } + } + } + return events.sort((a, b) => a.name.localeCompare(b.name)) +} + +// --------------------------------------------------------------------------- +// Rendering +// --------------------------------------------------------------------------- + +const BANNER = '' + +/** GitHub source link for a `file:line` pointer. */ +function sourceLink(source: string): string { + const [file, line] = source.split(':') + return `[Source](${GITHUB}/${file}#L${line})` +} + +/** Render prose paragraphs (one per line of `doc`). */ +function prose(doc: string): string[] { + return doc.split('\n').filter(l => l.trim() !== '') +} + +/** Render one member section at heading depth 3. */ +function renderMember(prefix: string, m: MemberDoc): string[] { + const lines: string[] = [] + const call = m.heading === '' ? '' : m.heading + lines.push(`### ${prefix}${m.name}${call}`, '') + lines.push('```' + FENCE) + for (const sig of m.signatures) lines.push(sig) + lines.push('```', '') + lines.push(...prose(m.doc), '') + if (m.params.length > 0) { + for (const p of m.params) lines.push(`- \`${p.name}\` — ${p.text}`) + lines.push('') + } + if (m.returns) lines.push(`**Returns** ${m.returns}`, '') + lines.push(sourceLink(m.source), '') + return lines +} + +/** Render one cordis-tier page from its manifest entry. */ +function renderCordisPage(page: CordisPage, violations: string[]): string { + const lines: string[] = [BANNER, '', `# ${page.title}`, '', page.intro, ''] + for (const section of page.sections) { + if (section.kind === 'context-merge') { + for (const m of contextMergeMembers(section.file, violations)) { + lines.push(...renderMember('ctx.', m)) + } + } else if (section.kind === 'class') { + const cls = classMembers(section.file, section.symbol, violations) + lines.push(...prose(cls.doc), '', sourceLink(cls.source), '') + const instancePrefix = section.prefix ?? `${section.symbol.toLowerCase()}.` + for (const m of cls.instance) lines.push(...renderMember(instancePrefix, m)) + if (cls.statics.length > 0) { + lines.push('## Static members', '') + for (const m of cls.statics) lines.push(...renderMember(`${section.symbol}.`, m)) + } + } else { + const decl = declPaste(section.file, section.symbol) + lines.push(`## ${section.symbol}`, '') + if (decl.doc) lines.push(...prose(decl.doc), '') + lines.push('```' + FENCE, decl.code, '```', '', sourceLink(decl.source), '') + } + } + return `${lines.join('\n').replace(/\n{3,}/g, '\n\n').trimEnd()}\n` +} + +/** kebab-case a ctx key: `agentLoop` → `agent-loop`. */ +function kebab(key: string): string { + return key.replace(/[A-Z]/g, c => `-${c.toLowerCase()}`) +} + +/** Render one harness service page. */ +function renderServicePage(svc: HarnessService): string { + const seam = svc.abstract ? ' (abstract seam)' : '' + const lines: string[] = [ + BANNER, '', + `# ctx.${svc.key}`, '', + `\`${svc.type}\`${seam} — provided by \`${svc.pkg}\`.`, '', + ...prose(svc.doc), '', + sourceLink(svc.source), '', + ] + for (const m of svc.members) lines.push(...renderMember(`ctx.${svc.key}.`, m)) + return `${lines.join('\n').replace(/\n{3,}/g, '\n\n').trimEnd()}\n` +} + +/** Render the harness events page, grouped by scope. */ +function renderEventsPage(events: HarnessEvent[]): string { + const lines: string[] = [ + BANNER, '', + '# Harness events', '', + `Every event the harness packages declare on the cordis event bus (${events.length} total), grouped by scope. The **mode** is the dispatch semantics (\`emit\` fire-and-forget, \`parallel\` awaited, \`serial\` first-bail, \`waterfall\` veto-chain — a waterfall listener MUST call \`next()\` to delegate).`, '', + ] + const scopes = [...new Set(events.map(e => e.scope))].sort() + for (const scope of scopes) { + lines.push(`## ${scope}/*`, '') + for (const e of events.filter(ev => ev.scope === scope)) { + lines.push(`### ${e.name}`, '') + lines.push(`**Mode:** \`${e.mode ?? 'unknown'}\``, '') + lines.push('```' + FENCE, e.signature, '```', '') + lines.push(...prose(e.doc), '') + if (e.params.length > 0) { + for (const p of e.params) lines.push(`- \`${p.name}\` — ${p.text}`) + lines.push('') + } + lines.push(sourceLink(e.source), '') + } + } + return `${lines.join('\n').replace(/\n{3,}/g, '\n\n').trimEnd()}\n` +} + +// --------------------------------------------------------------------------- +// Assembly + CLI +// --------------------------------------------------------------------------- + +/** Build every generated file as `relPath → content`. */ +export function generate(): Map { + const violations: string[] = [] + const files = new Map() + + for (const page of CORDIS_PAGES) { + files.set(`${PAGES_DIR}/${page.out}`, renderCordisPage(page, violations)) + } + + const services = collectHarnessServices(violations) + for (const svc of services) { + files.set(`${PAGES_DIR}/harness/${kebab(svc.key)}.md`, renderServicePage(svc)) + } + + const events = collectHarnessEvents(violations) + files.set(`${PAGES_DIR}/harness/events.md`, renderEventsPage(events)) + + reportViolations('gen-website-api', violations) + + const sidebar = { + cordis: CORDIS_PAGES.map(p => ({ + text: p.title, + link: `/zh-CN/api/${p.out.replace(/\.md$/, '')}`, + })), + harness: [ + ...services.map(s => ({ text: `ctx.${s.key}`, link: `/zh-CN/api/harness/${kebab(s.key)}` })), + { text: 'Events', link: '/zh-CN/api/harness/events' }, + ], + } + files.set(SIDEBAR_OUT, `${JSON.stringify(sidebar, null, 2)}\n`) + return files +} + +/** CLI entry: default writes, `--check` fails on stale/orphan files. Guarded + * behind an entry-point check so tests can import `generate()`. */ +function main(): void { + const check = process.argv.includes('--check') + const files = generate() + + // Orphan detection: a generated-dir page that generate() no longer emits + // (e.g. a service was renamed) must be deleted, not left to rot. + const expected = new Set([...files.keys()]) + // Orphans live in the generated subdirs only; the hand-written api/index.md + // is one level up and never matches this glob. + const onDisk = globSync(`${PAGES_DIR}/{cordis,harness}/*.md`, { cwd: root }).sort() + const orphans = onDisk.filter(rel => !expected.has(rel)) + + if (check) { + const stale: string[] = [] + for (const [rel, content] of files) { + let current: string | null = null + try { + current = readFileSync(resolve(root, rel), 'utf8') + } catch { + // Missing file: reported as stale below; readFileSync is the probe. + } + if (current !== content) stale.push(rel) + } + if (stale.length > 0 || orphans.length > 0) { + console.error('gen-website-api: website API reference is stale. Run `pnpm run gen-website-api` and commit the result.') + for (const rel of stale) console.error(` stale: ${rel}`) + for (const rel of orphans) console.error(` orphan (delete): ${rel}`) + process.exit(1) + } + console.log(`gen-website-api: ${files.size} generated file(s) fresh.`) + return + } + + for (const [rel, content] of files) { + const abs = resolve(root, rel) + mkdirSync(dirname(abs), { recursive: true }) + writeFileSync(abs, content) + } + for (const rel of orphans) { + console.log(`gen-website-api: orphan page ${rel} — delete it (no longer generated).`) + } + console.log(`gen-website-api: wrote ${files.size} file(s).`) +} + +// Run only when invoked as a script, not when imported by a test. +if (process.argv[1] && import.meta.filename === resolve(process.argv[1])) { + main() +} diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index 6384697650..6891cf1066 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -264,6 +264,7 @@ function docSyncLeafGates(): Gate[] { pnpmScript('config-catalog', 'verify-config-catalog', { label: 'config catalog' }), pnpmScript('persistence-catalog', 'verify-persistence-catalog', { label: 'persistence catalog' }), pnpmScript('doc-graphs', 'verify-doc-graphs', { label: 'doc graphs' }), + pnpmScript('website-api', 'verify-website-api', { label: 'website api' }), pnpmScript('markdown-wrap', 'verify-md-wrap', { label: 'markdown wrap' }), pnpmScript('markdown-links', 'verify-md-links', { label: 'markdown links' }), pnpmScript('doc-refs', 'verify-doc-refs', { label: 'doc refs' }), diff --git a/website/.vitepress/config/api-sidebar.json b/website/.vitepress/config/api-sidebar.json new file mode 100644 index 0000000000..3b1f94d56f --- /dev/null +++ b/website/.vitepress/config/api-sidebar.json @@ -0,0 +1,90 @@ +{ + "cordis": [ + { + "text": "Context", + "link": "/zh-CN/api/cordis/context" + }, + { + "text": "Events", + "link": "/zh-CN/api/cordis/events" + }, + { + "text": "Fiber", + "link": "/zh-CN/api/cordis/fiber" + }, + { + "text": "Registry", + "link": "/zh-CN/api/cordis/registry" + }, + { + "text": "Service", + "link": "/zh-CN/api/cordis/service" + } + ], + "harness": [ + { + "text": "ctx.agentLoop", + "link": "/zh-CN/api/harness/agent-loop" + }, + { + "text": "ctx.agents", + "link": "/zh-CN/api/harness/agents" + }, + { + "text": "ctx.bash", + "link": "/zh-CN/api/harness/bash" + }, + { + "text": "ctx.codeRuntime", + "link": "/zh-CN/api/harness/code-runtime" + }, + { + "text": "ctx.compact", + "link": "/zh-CN/api/harness/compact" + }, + { + "text": "ctx.fs", + "link": "/zh-CN/api/harness/fs" + }, + { + "text": "ctx.llm", + "link": "/zh-CN/api/harness/llm" + }, + { + "text": "ctx.sessionPersistence", + "link": "/zh-CN/api/harness/session-persistence" + }, + { + "text": "ctx.sessions", + "link": "/zh-CN/api/harness/sessions" + }, + { + "text": "ctx.subagents", + "link": "/zh-CN/api/harness/subagents" + }, + { + "text": "ctx.systemPrompt", + "link": "/zh-CN/api/harness/system-prompt" + }, + { + "text": "ctx.tools", + "link": "/zh-CN/api/harness/tools" + }, + { + "text": "ctx.userInteraction", + "link": "/zh-CN/api/harness/user-interaction" + }, + { + "text": "ctx.web", + "link": "/zh-CN/api/harness/web" + }, + { + "text": "ctx.workflows", + "link": "/zh-CN/api/harness/workflows" + }, + { + "text": "Events", + "link": "/zh-CN/api/harness/events" + } + ] +} diff --git a/website/.vitepress/config/zh-CN.ts b/website/.vitepress/config/zh-CN.ts index 83767b6cbc..ba83cf52c5 100644 --- a/website/.vitepress/config/zh-CN.ts +++ b/website/.vitepress/config/zh-CN.ts @@ -1,4 +1,5 @@ import type { DefaultTheme, LocaleSpecificConfig } from 'vitepress' +import apiSidebarData from './api-sidebar.json' const guideSidebar: DefaultTheme.SidebarItem[] = [ { @@ -37,29 +38,20 @@ const developSidebar: DefaultTheme.SidebarItem[] = [ }, ] +// The API section sidebar is GENERATED (scripts/gen-website-api.ts writes +// api-sidebar.json alongside the pages), so navigation can never drift from +// the generated page set. Only the hand-written hub link lives here. const apiSidebar: DefaultTheme.SidebarItem[] = [ { text: '框架 API', items: [ { text: '总览', link: '/zh-CN/api/' }, - { text: 'Context', link: '/zh-CN/api/cordis/context' }, - { text: 'Events', link: '/zh-CN/api/cordis/events' }, - { text: 'Fiber', link: '/zh-CN/api/cordis/fiber' }, - { text: 'Registry', link: '/zh-CN/api/cordis/registry' }, - { text: 'Service', link: '/zh-CN/api/cordis/service' }, + ...apiSidebarData.cordis, ], }, { text: 'Harness API', - items: [ - { text: 'Tools (dsh-tools)', link: '/zh-CN/api/harness/tools' }, - { text: 'LLM (dsh-llm)', link: '/zh-CN/api/harness/llm' }, - { text: 'Session (dsh-session)', link: '/zh-CN/api/harness/session' }, - { text: 'Agent (dsh-agent)', link: '/zh-CN/api/harness/agent' }, - { text: 'Bash (dsh-bash)', link: '/zh-CN/api/harness/bash' }, - { text: 'Filesystem (dsh-fs)', link: '/zh-CN/api/harness/fs' }, - { text: 'Subagent (dsh-subagent)', link: '/zh-CN/api/harness/subagent' }, - ], + items: apiSidebarData.harness, }, ] diff --git a/website/zh-CN/api/cordis/context.md b/website/zh-CN/api/cordis/context.md index a18f275dad..f8ef268f03 100644 --- a/website/zh-CN/api/cordis/context.md +++ b/website/zh-CN/api/cordis/context.md @@ -1,85 +1,192 @@ + + # Context -上下文对象是 Cordis 的核心。所有服务、方法、属性都通过 `ctx` 访问。 +The context is the core cordis object: every service, event, and lifecycle API is reached through `ctx`. Event methods (`ctx.on`, `ctx.emit`, …) are documented on [Events](./events.md); `ctx.effect` and `ctx.fiber` on [Fiber](./fiber.md); `ctx.plugin` and `ctx.inject` on [Registry](./registry.md). -## 服务与混入 +Root and child dependency containers for Cordis plugins. +A context is a proxy: normal property reads go through the service resolver, while `extend()`, `isolate()`, and `intercept()` create scoped child contexts without mutating their parent. -Context 基于组合式 API 设计，大部分属性和方法挂载在服务上。以下是核心 API： +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/context.ts#L42) -- [`ctx.on`](./events#ctx-on) — 注册事件监听器 -- [`ctx.emit`](./events#ctx-emit) — 触发事件 -- [`ctx.bail`](./events#ctx-bail) — 短路事件 -- [`ctx.serial`](./events#ctx-serial) — 顺序异步事件 -- [`ctx.waterfall`](./events#ctx-waterfall) — 管道事件 -- [`ctx.effect`](./fiber#fiber-effect) — 注册可逆效果 -- [`ctx.plugin`](./registry#ctx-plugin) — 加载子插件 -- [`ctx.inject`](./registry#ctx-inject) — 获取依赖的插件 -- [`ctx.get`](#ctx-get) — 获取服务 -- [`ctx.set`](#ctx-set) — 设置服务 -- [`ctx.provide`](#ctx-provide) — 声明服务 +### ctx.extend(meta?) -## 实例属性 +```ts website-api +extend(meta = {}): this +``` -### ctx.fiber +Create a child context with extra metadata on top of the current scope. +The child prototypally inherits every property of this context; own properties of `meta` shadow the inherited ones. The parent is not mutated. -- **类型:** [`Fiber`](./fiber) +- `meta` — own properties (including symbol keys) to define on the child. -当前上下文的作用域对象。 +**Returns** a child context inheriting from this one. -## 实例方法 - -### ctx.extend(meta) - -- **meta:** `object` -- **返回值:** `Context` - -构造一个以当前上下文为原型的新上下文实例。 - -### ctx.intercept(name, config) - -- **name:** `string` 服务名称 -- **config:** `object` 配置拦截 -- **返回值:** `Context` - -为指定服务添加一层配置拦截，返回新的上下文实例。 +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/context.ts#L99) ### ctx.isolate(name, label?) -- **name:** `string` 服务名称 -- **label:** `symbol` 隔离域符号（可选） -- **返回值:** `Context` +```ts website-api +isolate(name: string, label?: symbol) +``` -创建一个针对指定服务的隔离域，返回新的上下文实例。隔离域中的同名服务互不影响。 +Create a child context with an independent service scope for `name`. +Below the returned context, reads and writes of the service `name` resolve against the new label instead of the parent's, so a different implementation can be provided without affecting the parent scope. Passing the same `label` to two `isolate()` calls joins their scopes. -### ctx.get(name) +- `name` — the service name to isolate. +- `label` — scope label to join; defaults to a fresh unique symbol. -- **name:** `string` 服务名称 -- **返回值:** `Service | undefined` +**Returns** a child context whose `name` service resolves in the new scope. -获取指定名称的服务实例。 +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/context.ts#L121) + +### ctx.intercept(name, config) + +```ts website-api +intercept(name: K, config: Context[K] extends { [symbols.config]: infer T } ? T : never): this +intercept(name: string, config: any): this +``` + +Add service-specific intercept config for plugins started below this context. +Plugins loaded under the returned context see `config` merged into the service's resolved config (ancestor entries first; see `Service[symbols.resolveConfig]`). The parent context is not affected. + +- `name` — the service name whose config to intercept. +- `config` — the intercept config to merge for that service. + +**Returns** a child context carrying the additional intercept entry. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/context.ts#L139) + +## Static members + +### Context.effect + +```ts website-api +static readonly effect: unique symbol +``` + +Symbol key under which a disposer exposes its EffectMeta diagnostics tree. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/context.ts#L44) + +### Context.filter + +```ts website-api +static readonly filter: unique symbol +``` + +Symbol key for a context's listener filter, consulted on every event dispatch. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/context.ts#L46) + +### Context.isolate + +```ts website-api +static readonly isolate: unique symbol +``` + +Symbol key of the isolation map (see the `Context[symbols.isolate]` property). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/context.ts#L48) + +### Context.intercept + +```ts website-api +static readonly intercept: unique symbol +``` + +Symbol key of the intercept map (see the `Context[symbols.intercept]` property). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/context.ts#L50) + +### Context.is(value) + +```ts website-api +static is(value: any): value is Context +``` + +Returns true for Cordis context proxies and context prototypes. +Works across realms and across multiple copies of cordis, because the brand is keyed by a global symbol rather than by `instanceof`. + +- `value` — the value to test. + +**Returns** `true` if `value` is a Cordis context, narrowing its type. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/context.ts#L61) + +### ctx.get(name, strict?) + +```ts website-api +get(name: K, strict?: boolean): undefined | this[K] +get(name: string, strict?: boolean): any +``` + +Read a service from the store without the inject requirement. + +- `name` — the service name. +- `strict` — when `true` (default), only return implementations whose providing fiber is currently active. + +**Returns** the service value, or `undefined` when not (yet) provided. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/reflect.ts#L16) ### ctx.set(name, value) -- **name:** `string` 服务名称 -- **value:** `any` 服务值 +```ts website-api +set(name: K, value: undefined | this[K]): void +set(name: string, value: any): void +``` -设置指定名称的服务。 +Overwrite a provided service's value. +Only the fiber that provided the service may set it; setting an unprovided name throws. -### ctx.provide(name, value?, options?) +- `name` — the service name. +- `value` — the new service value. -- **name:** `string` 服务名称 -- **value:** `any` 初始值（可选） -- **options:** `object` -- **返回值:** `void` +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/reflect.ts#L28) -声明一个服务。声明后其他插件可以通过 `inject` 依赖它。 +### ctx.provide(name, value) -## 静态属性 +```ts website-api +provide(name: K, value: undefined | this[K]): () => void +provide(name: string, value?: any): () => void +``` -### Context.events +Register a service implementation owned by the current fiber. +The service becomes visible to dependents in the same isolation scope once the fiber is active; it is unregistered (waking dependents) when the returned disposer runs or the fiber unloads. Throws if the name is already provided in this scope or declared as an accessor. -内置事件服务的 symbol key。 +- `name` — the service name. +- `value` — the service value. -### Context.current +**Returns** a disposer that unregisters the service. -当前活跃的 Context 实例（在异步链中通过 AsyncLocalStorage 追踪）。 +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/reflect.ts#L43) + +### ctx.accessor(name, options) + +```ts website-api +accessor(name: string, options: Omit): void +``` + +Define a computed context property backed by get/set hooks. +The accessor is removed when the current fiber unloads. Throws if the name is already declared. + +- `name` — the context property name. +- `options` — the `get` hook and optional `set` hook. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/reflect.ts#L55) + +### ctx.mixin(name, mixins) + +```ts website-api +mixin(name: K, mixins: (keyof this & keyof this[K])[] | Dict): void +mixin(source: T, mixins: (keyof this & keyof T)[] | Dict): void +``` + +Expose selected members of a service directly on `ctx`. +Each mixed-in key becomes an accessor that forwards to the service (binding methods to it), so e.g. `ctx.on` forwards to `ctx.events.on`. Mixins are removed when the current fiber unloads. + +- `name` — the context property holding the source service. +- `mixins` — keys to forward, or a source-key → ctx-key map. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/reflect.ts#L66) diff --git a/website/zh-CN/api/cordis/events.md b/website/zh-CN/api/cordis/events.md index dbc03a87bc..b56f8096fe 100644 --- a/website/zh-CN/api/cordis/events.md +++ b/website/zh-CN/api/cordis/events.md @@ -1,120 +1,142 @@ + + # Events -`ctx.events` 是内置服务，提供事件系统相关的全部 API。 +The event system mixed into every context. Harness-defined events are cataloged on [Harness events](../harness/events.md). -## 实例方法 +### ctx.parallel(name, ...args) -### ctx.on(event, listener, options?) {#ctx-on} - -- **event:** `string` 事件名称 -- **listener:** `Function` 事件监听器 -- **options:** `object` - - **prepend:** `boolean` 是否注册为前置（默认 `false`） - - **global:** `boolean` 是否注册为全局（默认 `false`） -- **返回值:** `() => void` 取消注册函数 - -注册一个事件监听器。返回的函数可用于手动取消注册，但通常不需要——插件卸载时会自动清理。 - -```typescript -ctx.on('agent/turn-end', (data) => { - console.log('turn ended:', data) -}) +```ts website-api +parallel(name: K, ...args: Parameters): Promise +parallel(thisArg: NoInfer>, name: K, ...args: Parameters): Promise ``` -### ctx.emit(thisArg?, event, ...args) {#ctx-emit} +Dispatch an event, running all listeners concurrently. -- **thisArg:** `any` 监听器的 `this` 参数（可选） -- **event:** `string` 事件名称 -- **args:** `any[]` 事件参数 -- **返回值:** `void` +- `name` — the event name. +- `args` — arguments passed to every listener. -同步触发所有匹配的监听器（并行，不等待异步完成）。 +**Returns** a promise resolving once every listener has settled. -### ctx.parallel(thisArg?, event, ...args) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/events.ts#L43) -- 签名同 `emit` -- **返回值:** `Promise` +### ctx.emit(name, ...args) -异步触发所有匹配的监听器（并行等待）。 - -### ctx.bail(thisArg?, event, ...args) {#ctx-bail} - -- **返回值:** `any` - -同步依次触发监听器。第一个返回非 `undefined`/`null`/`false` 值的监听器停止链并返回该值。 - -### ctx.serial(thisArg?, event, ...args) {#ctx-serial} - -- **返回值:** `Promise` - -异步依次触发监听器。语义同 `bail` 的异步版本。 - -### ctx.waterfall(thisArg?, event, ...args) {#ctx-waterfall} - -- **返回值:** `Promise` - -管道模式：每个监听器接收前一个的输出。监听器内部必须调用 `next()` 才会传递给下一个。 - -```typescript -// 注册 -ctx.on('llm/pre-request', async (messages, next) => { - messages.push(extraMsg) - return next(messages) // 必须调用 -}) - -// 触发 -const result = await ctx.waterfall('llm/pre-request', initialMessages) +```ts website-api +emit(name: K, ...args: Parameters): void +emit(thisArg: NoInfer>, name: K, ...args: Parameters): void ``` -::: warning -不调用 `next()` 即为否决 (veto)——管道终止。这是设计行为，用于拦截/网关。 -::: +Dispatch an event synchronously, ignoring listener return values. -## Harness 内置事件 +- `name` — the event name. +- `args` — arguments passed to every listener. -### agent/pre-step +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/events.ts#L52) -- **触发模式:** serial -- **参数:** `{ agentId, turnIndex }` +### ctx.serial(name, ...args) -Agent 执行一步之前触发。 +```ts website-api +serial(name: K, ...args: Parameters): Promisify> +serial(thisArg: NoInfer>, name: K, ...args: Parameters): Promisify> +``` -### agent/post-step +Dispatch an event, awaiting listeners in order until one bails. -- **触发模式:** emit -- **参数:** `{ agentId, turnIndex, blocks }` +- `name` — the event name. +- `args` — arguments passed to each listener. -Agent 执行一步之后触发。 +**Returns** the first bail value (non-null, non-false, non-undefined), if any. -### tool/call +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/events.ts#L62) -- **触发模式:** emit -- **参数:** `{ name, args, callId }` +### ctx.bail(name, ...args) -Tool 被模型调用时触发。 +```ts website-api +bail(name: K, ...args: Parameters): ReturnType +bail(thisArg: NoInfer>, name: K, ...args: Parameters): ReturnType +``` -### tool/result +Dispatch an event, calling listeners in order until one bails. -- **触发模式:** emit -- **参数:** `{ name, result, callId }` +- `name` — the event name. +- `args` — arguments passed to each listener. -Tool 返回结果时触发。 +**Returns** the first bail value (non-null, non-false, non-undefined), if any. -### session/event +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/events.ts#L72) -- **触发模式:** emit -- **参数:** `SessionEvent` +### ctx.waterfall(name, ...args) -会话事件被记录时触发。 +```ts website-api +waterfall(name: K, ...args: Parameters): ReturnType +waterfall(thisArg: NoInfer>, name: K, ...args: Parameters): ReturnType +``` -### compact/start +Dispatch an event whose last argument is a `next` continuation. +Each listener wraps the rest of the chain: calling `next()` invokes the next listener (finally the built-in behavior); not calling it vetoes. -- **触发模式:** emit +- `name` — the event name. +- `args` — listener arguments; the final one is the innermost `next`. -上下文压缩开始。 +**Returns** the outermost listener's return value. -### compact/end +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/events.ts#L85) -- **触发模式:** emit +### ctx.on(name, listener, options?) -上下文压缩结束。 +```ts website-api +on(name: K, listener: Events[K], options?: boolean | EventOptions): () => boolean +``` + +Register an event listener owned by the current fiber. + +- `name` — the event name to listen for. +- `listener` — called with the dispatch arguments. +- `options` — listener options; a boolean is shorthand for `prepend`. + +**Returns** a disposer removing the listener; `true` if it was still registered. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/events.ts#L96) + +### ctx.once(name, listener, options?) + +```ts website-api +once(name: K, listener: Events[K], options?: boolean | EventOptions): () => boolean +``` + +Same as `on()`, but the listener disposes itself after its first call. + +- `name` — the event name to listen for. +- `listener` — called at most once with the dispatch arguments. +- `options` — listener options; a boolean is shorthand for `prepend`. + +**Returns** a disposer removing the listener; `true` if it was still registered. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/events.ts#L105) + +## EventOptions + +Options accepted by `ctx.on()` and `ctx.once()`. + +```ts website-api +interface EventOptions { + /** Add the listener before existing listeners for the same event. */ + prepend?: boolean + /** Receive the event regardless of context filter checks. */ + global?: boolean +} +``` + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/events.ts#L111) + +## DispatchMode + +Event dispatch strategy used by the event service. +`emit` runs synchronous listeners without awaiting them, `parallel` awaits all listeners together, `serial` awaits them in order until one bails, `bail` stops on the first synchronous bail value, and `waterfall` composes listeners around a final `next` callback. + +```ts website-api +type DispatchMode = 'emit' | 'parallel' | 'serial' | 'bail' | 'waterfall' +``` + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/events.ts#L31) diff --git a/website/zh-CN/api/cordis/fiber.md b/website/zh-CN/api/cordis/fiber.md index ffb8f23bb5..360986350b 100644 --- a/website/zh-CN/api/cordis/fiber.md +++ b/website/zh-CN/api/cordis/fiber.md @@ -1,108 +1,263 @@ + + # Fiber -Fiber（作用域）是插件实例的运行时容器，管理其生命周期和效果。 +A fiber is one loaded plugin instance: its lifecycle state, validated config, and registered effects. `ctx.fiber` is the current fiber; `ctx.effect()` delegates to it. -## 状态机 +### ctx.fiber -``` -PENDING → LOADING → ACTIVE → UNLOADING → DISPOSED - ↘ FAILED +```ts website-api +fiber: Fiber ``` -| 状态 | 数值 | 含义 | -|------|------|------| -| PENDING | 0 | 依赖未就绪，等待中 | -| LOADING | 1 | 正在执行 `apply` | -| ACTIVE | 2 | 运行中 | -| FAILED | 3 | `apply` 抛出异常 | -| UNLOADING | 4 | 正在撤销效果 | -| DISPOSED | 5 | 已完全卸载 | +The fiber (plugin runtime instance) that owns this context. -## 实例属性 +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L11) + +Runtime instance of one plugin application. +A fiber tracks dependency state, validated config, lifecycle effects, and cleanup for the plugin context returned by `ctx.plugin()`. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L154) ### fiber.uid -- **类型:** `number` +```ts website-api +public uid: number | null +``` -Fiber 的唯一标识符。 +Unique id within the registry; 0 for the root fiber, `null` once disposed. -### fiber.status +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L156) -- **类型:** `number` +### fiber.ctx -当前状态（见状态机）。 +```ts website-api +public readonly ctx: Context +``` + +The context this fiber's plugin runs in (extends the parent context). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L158) ### fiber.config -- **类型:** `object` - -传递给插件的配置对象。 - -### fiber.error - -- **类型:** `Error | undefined` - -如果状态是 FAILED，包含导致失败的异常。 - -## 实例方法 - -### fiber.effect(callback) {#fiber-effect} - -- **callback:** `() => (() => void) | void` -- **返回值:** `() => void` - -注册一个效果。`callback` 在 Fiber 激活时执行；如果返回函数，该函数在 Fiber dispose 时执行。 - -```typescript -ctx.effect(() => { - const timer = setInterval(tick, 1000) - return () => clearInterval(timer) -}) +```ts website-api +public config: any ``` -等价地可以通过 `ctx.effect()` 调用（ctx 代理到当前 fiber）。 +The validated plugin config (updated by `update()`). -### fiber.dispose() +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L160) -- **返回值:** `Promise` +### fiber.state -手动 dispose 该 Fiber。按注册逆序撤销所有效果，递归 dispose 所有子 Fiber。 - -```typescript -const child = ctx.plugin(somePlugin) -// 之后: -await child.dispose() +```ts website-api +public state ``` -### fiber.update(config) +Current lifecycle state; transitions emit `internal/status`. -- **config:** `object` 新配置 -- **返回值:** `void` +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L162) -热更新配置。如果新旧配置不同，触发 dispose + 重新 apply。 +### fiber.dispose + +```ts website-api +public readonly dispose: () => Promise +``` + +Dispose this fiber: unload the plugin, then settle once cleanup finished. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L164) + +### fiber.store + +```ts website-api +public store: Dict | undefined +``` + +Snapshot of required service implementations while loaded; `undefined` otherwise. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L166) + +### fiber.inertia + +```ts website-api +public inertia: Promise | undefined +``` + +The in-flight load/unload transition, if one is currently running. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L168) + +### fiber.name + +```ts website-api +get name() +``` + +The plugin's display name, inherited from the nearest named ancestor, else `'root'`. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L284) + +### fiber.assertActive() + +```ts website-api +assertActive() +``` + +Throw if the fiber has already been disposed. + +**Returns** nothing when the fiber is still active. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L299) + +### fiber.effect(execute, label?) + +```ts website-api +effect(execute: () => SyncEffect, label?: string): Disposable> +effect(execute: () => Effect, label?: string): AsyncDisposable> +``` + +Register a cleanup-aware effect on this fiber. +`execute` runs immediately; the disposers it produces are collected and run (in reverse order) either when the returned disposer is called or when the fiber unloads, whichever comes first. Calling the disposer twice is a no-op. Throws `CordisError('INACTIVE_EFFECT')` if the fiber is already disposed, and `TypeError` if `execute` returns an invalid shape. + +- `execute` — the effect body; see {@link Effect} for accepted shapes. +- `label` — effect label shown in `getEffects()` diagnostics. + +**Returns** a disposer that tears the effect down and settles once done. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L363) + +### fiber.getEffects() + +```ts website-api +getEffects() +``` + +Return metadata for currently registered effects. + +**Returns** one {@link EffectMeta} tree per labeled live effect. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L436) + +### fiber.await() + +```ts website-api +async await() +``` + +Wait for current lifecycle work and rethrow startup errors. + +**Returns** this fiber, once it has settled into a stable state. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L560) ### fiber.restart() -- **返回值:** `void` - -强制重启：dispose 后重新加载。 - -### fiber.then(resolve, reject?) - -- **返回值:** `Promise` - -使 Fiber 可以被 `await`：等到状态进入 ACTIVE 或 FAILED。 - -```typescript -const fiber = ctx.plugin(myPlugin) -await fiber // 等待插件加载完成 +```ts website-api +async restart() ``` -## 访问当前 Fiber +Dispose and immediately reload this plugin with its current config. -```typescript -export function apply(ctx: Context) { - const fiber = ctx.fiber // 当前插件的 Fiber - console.log(fiber.status) // 1 (LOADING, 因为正在 apply 中) +**Returns** a promise resolving once the reload settled. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L574) + +### fiber.update(config, noSave?) + +```ts website-api +update(config: any, noSave = false) +``` + +Validate and apply new config, then restart the plugin. +Runs the `internal/update` waterfall first, so update hooks (and HMR) can veto or replace the restart. + +- `config` — the new raw config; validated before anything restarts. +- `noSave` — hint for persistence hooks not to write the change back. + +**Returns** nothing; the restart runs behind the `internal/update` waterfall. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L592) + +## Effect + +Effect body result accepted by `ctx.effect()` and plugin startup. +Either a single disposer, a promise of one, or a (possibly async) iterable yielding several — generator effects register each yielded disposer as it is produced. + +```ts website-api +type Effect = + | SyncEffect + | AsyncEffect +``` + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L82) + +## Disposable + +Function returned by an effect to release resources during disposal. +Disposers run in reverse registration order when the owning fiber unloads; they may be async, in which case unloading awaits them. + +```ts website-api +type Disposable = () => T +``` + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L73) + +## EffectMeta + +Tree node used to expose nested effect labels for diagnostics. + +```ts website-api +interface EffectMeta { + /** Human-readable effect label, e.g. `ctx.on("event")` or `ctx.provide("name")`. */ + label: string + /** Metadata of nested effects registered while this effect ran. */ + children: EffectMeta[] } ``` + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L95) + +## CordisError + +Framework error with a stable machine-readable code. + +```ts website-api +class CordisError extends Error { + /** + * @param code — the stable error code; also the default message. + * @param message — optional human-readable override. + */ + constructor(public code: CordisError.Code, message?: string) +} + +namespace CordisError { + export type Code = keyof typeof Code + + export const Code = { + INACTIVE_EFFECT: 'cannot create effect on inactive context', + } as const +} +``` + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L127) + +## ValidationError + +Error raised when plugin configuration fails standard-schema validation. + +```ts website-api +class ValidationError extends TypeError { + name = 'ValidationError' + + /** + * Build the aggregated message from schema issues. + * + * @param issues — the standard-schema issues, one message line each. + */ + constructor(issues: readonly StandardSchemaV1.Issue[]) +} +``` + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/fiber.ts#L18) diff --git a/website/zh-CN/api/cordis/registry.md b/website/zh-CN/api/cordis/registry.md index e0f66d8ed7..55f6d666e5 100644 --- a/website/zh-CN/api/cordis/registry.md +++ b/website/zh-CN/api/cordis/registry.md @@ -1,87 +1,121 @@ + + # Registry -插件注册表，管理插件的加载和依赖解析。 +Plugin loading and dependency injection. -## 实例方法 +### ctx.inject(deps, callback) -### ctx.plugin(plugin, config?) {#ctx-plugin} - -- **plugin:** `Plugin` 插件（函数、对象或类） -- **config:** `object` 传递给插件的配置（可选） -- **返回值:** `Fiber` - -加载一个子插件，返回其 Fiber。子 Fiber 的生命周期绑定到父上下文。 - -```typescript -// 函数插件 -ctx.plugin(myPlugin, { key: 'value' }) - -// 类插件 -ctx.plugin(MyService) - -// 返回的 Fiber 可以 await 或 dispose -const fiber = ctx.plugin(myPlugin) -await fiber +```ts website-api +inject(deps: Inject, callback: Plugin.Function): Fiber & PromiseLike ``` -### ctx.inject(names, callback) {#ctx-inject} +Run a callback once the requested services are available. +Shorthand for `ctx.plugin({ inject, apply: callback })`: the callback is unloaded and re-run whenever a required service changes. -- **names:** `string[]` 服务名列表 -- **callback:** `(ctx: Context) => void` -- **返回值:** `() => void` +- `deps` — required services, as an array or a name → config map. +- `callback` — plugin body called with `(ctx, config)`. -等待指定服务全部就绪后执行 callback。如果服务消失，callback 的效果会自动撤销；服务恢复后重新执行。 +**Returns** the fiber; awaiting it settles once loading finished. -```typescript -ctx.inject(['tools', 'llm'], (ctx) => { - // tools 和 llm 都就绪了 - ctx.tools.register(/* ... */) -}) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/registry.ts#L175) + +### ctx.plugin(plugin, ...args) + +```ts website-api +plugin

(plugin: P, ...args: Spread>): Fiber & PromiseLike ``` -这是 `export const inject = [...]` 声明的底层 API。大多数情况下直接使用声明式写法即可。 +Load a plugin in the current context. -## 插件形态 +- `plugin` — a function, class, or `{ apply }` object plugin. +- `args` — the plugin config, validated against its `Config` schema. -`ctx.plugin()` 接受三种插件形态： +**Returns** the fiber; awaiting it settles once loading finished (rejecting on config or startup errors). -### 函数插件 +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/registry.ts#L184) -```typescript -function myPlugin(ctx: Context, config?: Config) { - // ... -} -myPlugin.name = 'my-plugin' -myPlugin.inject = ['tools'] -``` +## Plugin -### 对象插件 +Supported plugin entrypoint shapes. -```typescript -const myPlugin = { - name: 'my-plugin', - inject: ['tools'], - apply(ctx: Context, config?: Config) { - // ... - }, -} -``` +```ts website-api +type Plugin = + | Plugin.Function + | Plugin.Constructor + | Plugin.Object -### 类插件（Service） +namespace Plugin { + /** Shared metadata understood by the plugin registry and related tooling. */ + export interface Base { + /** Display name used for fiber diagnostics and logger names. */ + name?: string + /** Standard-schema validator applied to config before the plugin starts. */ + Config?: StandardSchemaV1 + /** Services the plugin requires; it only loads while all are available. */ + inject?: Inject + /** Service name(s) the plugin provides (read by `Service` and by loaders). */ + provide?: string | string[] + /** Service names whose intercept config the plugin declares it consumes. */ + intercept?: Dict + } -```typescript -class MyService extends Service { - static inject = ['tools'] - constructor(ctx: Context) { - super(ctx, 'myService') + export interface Transform { + /** Marks the transform object as a schema/config transform. */ + schema?: true + /** Convert user-facing config to runtime config. */ + Config: (config: S) => T + } + + /** Function plugin called with `(ctx, config)`. */ + export interface Function extends Base { + (ctx: Context, config: T): any + } + + /** Class plugin constructed with `(ctx, config)`. */ + export interface Constructor extends Base { + new (ctx: Context, config: T): any + } + + /** Object plugin with an `apply(ctx, config)` method. */ + export interface Object extends Base { + apply(ctx: Context, config: T): any + } + + /** Mutable registry record shared by all fibers of one plugin callback. */ + export interface Runtime { + /** Display name copied from the first registered plugin shape. */ + name?: string + /** Every live fiber of this plugin (one per `ctx.plugin()` call). */ + fibers: DisposableList + /** The executable entrypoint all fibers share (registry identity key). */ + callback: globalThis.Function + /** Standard-schema validator applied to each fiber's config. */ + Config?: StandardSchemaV1 } } ``` -## 插件元信息 +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/registry.ts#L91) -| 属性 | 类型 | 说明 | -|------|------|------| -| `name` | `string` | 插件名称（日志用） | -| `inject` | `string[] \| { required?: string[], optional?: string[] }` | 依赖声明 | -| `Config` | `Schema \| object` | 配置 schema 或默认值 | +## Inject + +Service dependency declaration accepted by plugins and the `@Inject` decorator. +Array form requests services without intercept config. Object form maps each service name to optional intercept config for the plugin context. + +```ts website-api +type Inject = (keyof M)[] | { [K in keyof M]?: M[K] } + +namespace Inject { + /** + * Convert array/object/class-inherited inject metadata into a plain map. + * + * @param inject — the declaration to normalize; `null`/`undefined` add nothing. + * @param result — the map to fill (service name → intercept config or `null`). + * @returns `result`. + */ + export function resolve(inject: Inject | null | undefined, result: Dict = Object.create(null)) +} +``` + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/registry.ts#L18) diff --git a/website/zh-CN/api/cordis/service.md b/website/zh-CN/api/cordis/service.md index a57a00c461..acd43163d6 100644 --- a/website/zh-CN/api/cordis/service.md +++ b/website/zh-CN/api/cordis/service.md @@ -1,97 +1,92 @@ + + # Service -Service 基类，用于创建对外暴露能力的插件。 +Base class for context services: subclass it and load the subclass as a plugin to register `ctx.`. -## 基本用法 +Base class for services that expose a named API on `ctx`. +Subclasses call `super(ctx, name)` from their constructor. The service is registered immediately and is automatically removed with the owning fiber. -```typescript -import { Service, type Context } from 'cordis' +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/service.ts#L11) -declare module 'cordis' { - interface Context { - myService: MyService - } -} +### service.name -export default class MyService extends Service { - constructor(ctx: Context) { - super(ctx, 'myService') - } - - // 公开方法 - doSomething() { - // ... - } -} +```ts website-api +public name!: string ``` -加载后，其他插件可通过 `ctx.myService` 访问。 +The service name this instance is registered under. -## 构造函数 +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/service.ts#L30) -### new Service(ctx, name) +## Static members -- **ctx:** `Context` 上下文 -- **name:** `string` 服务名（注册到 `ctx[name]`） +### Service.init -## 实例属性 - -### service.ctx - -- **类型:** `Context` - -该服务绑定的上下文。 - -### service\[Service.tracker\] - -- **类型:** `object` - -服务追踪信息（名称、绑定状态等）。 - -## 生命周期 - -Service 子类可以覆写以下方法： - -### start() - -服务激活时调用。在这里初始化资源。 - -### stop() - -服务停用时调用。在这里释放资源。 - -## 静态属性 - -### Service.inject - -- **类型:** `string[] | { required?: string[], optional?: string[] }` - -声明本服务依赖的其他服务。 - -## 与 inject 的关系 - -当一个 Service 被加载： -1. 框架为该服务名创建声明 (`ctx.provide`) -2. 实例赋值到 `ctx[name]` -3. 依赖该服务的所有 Fiber 从 PENDING 转为 LOADING - -当 Service 被卸载： -1. `ctx[name]` 被置为 `undefined` -2. 依赖它的 Fiber 被 dispose -3. 当新的 provider 出现时，dependant Fiber 重新加载 - -## 示例：Harness 中的 Service - -```typescript -// dsh-tools 的 ToolRegistry 就是一个 Service -export class ToolRegistry extends Service { - constructor(ctx: Context) { - super(ctx, 'tools') - } - - register(tool: ToolDefinition): () => void { - // ...注册逻辑 - return dispose - } -} +```ts website-api +static readonly init: unique symbol ``` + +Symbol key of an instance method run after construction (class plugins). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/service.ts#L13) + +### Service.check + +```ts website-api +static readonly check: unique symbol +``` + +Symbol key of the availability predicate passed to `ctx.provide()`. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/service.ts#L15) + +### Service.config + +```ts website-api +static readonly config: unique symbol +``` + +Symbol key of the phantom intercept-config type parameter. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/service.ts#L17) + +### Service.invoke + +```ts website-api +static readonly invoke: unique symbol +``` + +Symbol key of the call body making a service callable (e.g. `ctx.logger()`). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/service.ts#L19) + +### Service.extend + +```ts website-api +static readonly extend: unique symbol +``` + +Symbol key of the helper deriving an extended service instance. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/service.ts#L21) + +### Service.tracker + +```ts website-api +static readonly tracker: unique symbol +``` + +Symbol key of the tracker metadata used for context tracing. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/service.ts#L23) + +### Service.resolveConfig + +```ts website-api +static readonly resolveConfig: unique symbol +``` + +Symbol key of the intercept-config resolution helper below. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/vendor/cordis/src/service.ts#L25) diff --git a/website/zh-CN/api/harness/agent-loop.md b/website/zh-CN/api/harness/agent-loop.md new file mode 100644 index 0000000000..d664651cd7 --- /dev/null +++ b/website/zh-CN/api/harness/agent-loop.md @@ -0,0 +1,56 @@ + + +# ctx.agentLoop + +`AgentLoop` — provided by `@deepseek-ai/dsh-agent-loop`. + +The agent-loop plugin (`ctx.agentLoop`): creates ReactLoopAgents, runs their loops, and registers them in `ctx.agents`. Also implements the AgentFactory seam, so plugins create/resume agents through `ctx.agents` (the interface) without depending on this concrete package. +The loop itself is deliberately thin — every behavior beyond "call the model, run the tools, repeat" belongs to plugins listening on the event taxonomy declared in @deepseek-ai/dsh-agent. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L68) + +### ctx.agentLoop.create(id, options?) + +```ts website-api +create(id: AgentId, options: AgentOptions = {}): ReactLoopAgent +``` + +Config-driven create: an agent on a FRESH, non-colliding session id per run (`${id}-session-`, no cwd). Used for `cordis.yml`-configured agents and as the shared core for the programmatic factory createAgent. +Why a per-run id, not a fixed `${id}-session`: once a durable persistence backend is loaded, a fixed id collides on the second run — the backend refuses to re-create an id whose log already exists on disk (the SessionId is the identity). A fresh id means each run is a new session. +TODO(demo): each run starting a brand-new session is fine for demos but is NOT real conversation continuity. A production config-driven agent needs a deliberate resume-or-create policy (resume the prior session if one exists, else start fresh) or an explicit caller-chosen session id — revisit when the UI/ACP path owns session selection. + +- `id` — the agent id; also seeds the generated session id. +- `options` — loop options (model, limits, …); defaults applied per option. + +**Returns** the running agent, owned by the calling fiber (no handle). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L142) + +### ctx.agentLoop.createAgent(options) + +```ts website-api +createAgent(options: CreateAgentOptions): AgentHandle +``` + +Programmatic factory create (AgentFactory): an agent on a caller-supplied `sessionId` (NOT `${id}-session`), with optional session metadata (validated `cwd`, lineage) and an optional `seed` event prefix. The ACP bridge uses this so the client-generated session id becomes the live/persisted session id; the in-process FORK subagent backend passes a `seed` (a balanced completed-turn prefix of the parent's log) so the child starts with the parent's context. Returns an AgentHandle the owner disposes to tear down exactly this agent. + +- `options` — agent id, caller-supplied session id, optional seed/meta, and agent options. + +**Returns** the handle whose dispose tears down exactly this agent. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L166) + +### ctx.agentLoop.resume(options) + +```ts website-api +async resume(options: ResumeAgentOptions): Promise +``` + +Resume an agent on a persisted session (AgentFactory). Loads the session log + metadata via `ctx.sessionPersistence`, reconstructs the live session with the loaded events (so `lastTurnNumber`/`deriveMessages` continue), and starts a fresh agent on it. The live session id is the resumed id, NOT `${agentId}-session`. +Requires `ctx.sessionPersistence`; rejects with a clear error if it is not configured. NOT hard-injected (that would make non-persistent demos pend forever) — callers that need resume (ACP) inject `sessionPersistence`, so by the time this runs the service exists. + +- `options` — the persisted session id to reload, plus agent id/options. + +**Returns** the handle for the agent resumed on the reconstructed session. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L194) diff --git a/website/zh-CN/api/harness/agent.md b/website/zh-CN/api/harness/agent.md deleted file mode 100644 index bf46c7e4e1..0000000000 --- a/website/zh-CN/api/harness/agent.md +++ /dev/null @@ -1,85 +0,0 @@ -# Agent (dsh-agent) - -Agent 实例管理和生命周期。 - -**包名:** `@deepseek-ai/dsh-agent` -**服务名:** `ctx.agents` - -## Agent Service - -### ctx.agents.create(options) - -- **options:** `AgentOptions` -- **返回值:** `Agent` - -创建一个新的 Agent 实例。 - -### ctx.agents.get(id) - -- **id:** `AgentId` -- **返回值:** `Agent | undefined` - -获取指定 ID 的 Agent 实例。 - -## AgentOptions - -```typescript -interface AgentOptions { - /** Agent ID（branded） */ - id?: AgentId - /** 使用的模型名 */ - model: string - /** 系统提示词（支持 {{model}} 变量） */ - persona?: string - /** 关联的 session */ - session?: Session -} -``` - -## Agent 实例 - -### agent.id - -- **类型:** `AgentId` - -Agent 的唯一标识符（branded string）。 - -### agent.model - -- **类型:** `string` - -Agent 使用的模型名。 - -### agent.step(input) - -- **input:** `ContentBlock[]` -- **返回值:** `Promise` - -执行一步：将输入发送给模型，获取响应，执行 tool calls。这是 agent-loop 内部使用的核心方法。 - -## Agent Loop - -Agent 的执行循环由 `dsh-agent-loop` 管理。它： - -1. 组装 system prompt + 历史消息 + 当前输入 -2. 调用 LLM（通过 `ctx.llm`） -3. 解析响应中的 tool calls -4. 执行 tools -5. 将 tool results 追加到 session -6. 如果 finish reason 是 `tool-calls`，回到步骤 2 - -### 扩展点 - -- `agent/pre-step` 事件 — 在每一步 LLM 调用前触发 -- `agent/post-step` 事件 — 在每一步完成后触发 -- `llm/pre-request` waterfall — 可修改发送给模型的消息 - -## AgentId - -Opaque branded string： - -```typescript -import { AgentId } from '@deepseek-ai/dsh-agent' - -const id = AgentId('main') -``` diff --git a/website/zh-CN/api/harness/agents.md b/website/zh-CN/api/harness/agents.md new file mode 100644 index 0000000000..9ce78bcf14 --- /dev/null +++ b/website/zh-CN/api/harness/agents.md @@ -0,0 +1,91 @@ + + +# ctx.agents + +`AgentRegistry` — provided by `@deepseek-ai/dsh-agent`. + +Agent registry (`ctx.agents`): tracks live agents so UI, hook, and orchestrator plugins can find them without depending on the concrete loop package. Agent *creation* is provided by whichever plugin implements the AgentFactory (phase 1: `@deepseek-ai/dsh-agent-loop`), registered via setFactory. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L117) + +### ctx.agents.setFactory(factory) + +```ts website-api +setFactory(factory: AgentFactory): () => void +``` + +Register the agent-creation factory (the loop calls this on construction, effect-scoped). Throws if a factory is already registered. Returns the disposer; on dispose the factory slot is cleared. + +- `factory` — the loop-owned factory {@link create}/{@link resume} delegate to. + +**Returns** the disposer that clears the factory slot. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L132) + +### ctx.agents.create(options) + +```ts website-api +create(options: CreateAgentOptions): AgentHandle +``` + +Create, start, and register a new agent through the registered factory. Distinct from register (which records an already-constructed agent): this constructs the agent and its session. Throws if no factory is registered. Returns an AgentHandle — the owner disposes it to tear down exactly this agent. + +- `options` — agent id, session id/seed/metadata, and agent options. + +**Returns** the handle whose dispose tears down exactly this agent. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L150) + +### ctx.agents.resume(options) + +```ts website-api +async resume(options: ResumeAgentOptions): Promise +``` + +Load a persisted session and resume an agent on it through the registered factory. Rejects if no factory is registered; the factory rejects if session persistence is not configured. Returns an AgentHandle. + +- `options` — the persisted session id plus agent id and options. + +**Returns** the handle for the resumed agent. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L162) + +### ctx.agents.register(agent) + +```ts website-api +register(agent: Agent): () => void +``` + +Register a live agent. Throws if an agent with the same id is already registered. Emits `agent/created` on registration and `agent/disposed` when the calling fiber is disposed. Returns the disposer. + +- `agent` — the already-constructed agent to record in the store. + +**Returns** the disposer that removes the agent and emits `agent/disposed`. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L174) + +### ctx.agents.get(id) + +```ts website-api +get(id: AgentId): Agent | undefined +``` + +Look up a live agent. + +- `id` — the agent id to look up. + +**Returns** the agent, or undefined when no live agent has that id. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L216) + +### ctx.agents.list() + +```ts website-api +list(): Agent[] +``` + +All live agents, in registration order. + +**Returns** a fresh array; mutating it does not affect the registry. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L224) diff --git a/website/zh-CN/api/harness/bash.md b/website/zh-CN/api/harness/bash.md index 8e8d8d3068..a18d5e5a0d 100644 --- a/website/zh-CN/api/harness/bash.md +++ b/website/zh-CN/api/harness/bash.md @@ -1,81 +1,138 @@ -# Bash (dsh-bash) + -Bash 命令执行接口。 +# ctx.bash -**接口包:** `@deepseek-ai/dsh-bash` -**实现:** `@deepseek-ai/dsh-bash-local` -**消费者:** `@deepseek-ai/dsh-tool-bash`（内置于 agent-core） +`BashExecutor` (abstract seam) — provided by `@deepseek-ai/dsh-bash`. -## Bash Service +Abstract bash execution service. Subclass, implement the abstract methods, and load the subclass as a plugin — it registers as `ctx.bash` (one implementation per context; loading a second throws, which is cordis' standard duplicate-service behavior). +Semantics every implementation must honor: +- run REJECTS only for infrastructure failures (unusable workdir, missing shell, pre-aborted signal). Nonzero exits, timeout kills, and abort kills RESOLVE with a descriptive BashRunResult — reporting a failed command is the tool layer's job, not an exception. +- start returns immediately; no timeout applies to background tasks (callers stop them via kill or the spec's AbortSignal). Completion must fire the onTaskDone listeners exactly once per task, and must NOT fire after the service is disposed. +- readOutput is incremental: consecutive reads never re-deliver output. Implementations bound their buffers; reads that lost data flag `lossy` and point at full-stream spill files when available. +- Disposal kills every running task and awaits their exit (no orphan processes survive `fiber.dispose()`). -### ctx.bash.execute(request) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/bash/bash/src/index.ts#L59) -- **request:** `BashRequest` -- **返回值:** `Promise` +### ctx.bash.resolve(request) -执行一个 bash 命令。 - -## BashRequest - -```typescript -interface BashRequest { - /** 要执行的命令 */ - command: string - /** 工作目录 */ - workdir?: string - /** 超时时间 (ms) */ - timeoutMs?: number -} +```ts website-api +abstract resolve(request: BashExecRequest): BashExecSpec ``` -## BashResult +Resolve a caller's BashExecRequest into a fully-specified BashExecSpec, applying this implementation's config defaults and caps (working directory, default/max timeout). Consumers (tool layer) call this, then pass the result to run/start — keeping defaulting in the implementation that owns the config while the seam type stays explicit (no hidden `?? default` inside run/start). -```typescript -interface BashResult { - /** 退出码 */ - exitCode: number - /** stdout 输出 */ - stdout: string - /** stderr 输出 */ - stderr: string - /** 是否超时 */ - timedOut: boolean -} +- `request` — the caller's request; omitted fields get this implementation's defaults, capped fields are clamped. + +**Returns** the fully-specified spec to hand to {@link run}/{@link start}. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/bash/bash/src/index.ts#L84) + +### ctx.bash.run(spec) + +```ts website-api +abstract run(spec: BashExecSpec): Promise ``` -## 配置 (dsh-bash-local) +Run a command in the foreground; resolves when it finishes. -```typescript -interface Config { - /** 命令超时时间，默认 120000 (2 分钟) */ - timeoutMs: number -} +- `spec` — a resolved spec from {@link resolve}, never a raw request. + +**Returns** the outcome; nonzero exits, timeout kills, and abort kills resolve with a descriptive result rather than reject. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/bash/bash/src/index.ts#L92) + +### ctx.bash.start(spec) + +```ts website-api +abstract start(spec: BashExecSpec): BashTask ``` -在 `cordis.yml` 中： +Start a background task and return its handle immediately. -```yaml -- name: '@deepseek-ai/dsh-bash-local' - config: - timeoutMs: 60000 +- `spec` — a resolved spec from {@link resolve}, never a raw request. + +**Returns** the live task handle; completion fires {@link onTaskDone}. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/bash/bash/src/index.ts#L99) + +### ctx.bash.get(id) + +```ts website-api +abstract get(id: BashTaskId): BashTask | undefined ``` -## 模型可用的 Tools +Look up a background task by id. -`dsh-tool-bash` 向模型暴露以下 tools（由 `agent-core` 捆绑）： +- `id` — the task id to look up. -| Tool | 说明 | -|------|------| -| `bash` | 执行命令（同步，等待完成） | -| `bash_output` | 获取后台命令的输出 | -| `bash_kill` | 终止后台命令 | +**Returns** the tracked task, or undefined for an id this executor never issued. -## 设计模式 +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/bash/bash/src/index.ts#L106) -Bash 是 Harness 的"能力三件套"典型案例： +### ctx.bash.ownerOf(id) -- `dsh-bash`（接口）：定义 `ctx.bash` 和 `BashRequest`/`BashResult` 类型 -- `dsh-bash-local`（实现）：通过 `child_process.spawn` 在本地执行 -- `dsh-tool-bash`（消费者）：将能力包装为模型可调用的 tool +```ts website-api +abstract ownerOf(id: BashTaskId): OwnerToken | undefined +``` -换一个沙箱执行器只需替换 `dsh-bash-local`，接口和 tool 不变。 +The opaque OWNER token recorded for a background task at start (from the BashExecSpec's `owner`), or `undefined` for an unknown id OR a known-but-ownerless task. The executor stores and returns the token verbatim — it never interprets it; the access POLICY (who may read/kill a task) lives in the consumer (`@deepseek-ai/dsh-tool-bash`), which compares `ownerOf(id)` to the caller's token. Collapsing unknown-id and known-but-unowned into the same `undefined` is fine: the consumer's access gate treats `undefined` as "open", and a genuinely unknown id then fails loudly at the subsequent readOutput/kill ("unknown task"). Storing ownership in the executor (disposed with ITS fiber) — not in the tool plugin — is what makes ownership survive a `tool-bash` HMR reload. + +- `id` — the background task id to look up ownership for. + +**Returns** the token recorded at start, verbatim; undefined for an unknown id or a known-but-ownerless task. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/bash/bash/src/index.ts#L124) + +### ctx.bash.list() + +```ts website-api +abstract list(): BashTask[] +``` + +All tracked background tasks (insertion order). + +**Returns** every task this executor started, running or finished. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/bash/bash/src/index.ts#L130) + +### ctx.bash.readOutput(id) + +```ts website-api +abstract readOutput(id: BashTaskId): BashTaskRead +``` + +Read output produced since the previous read. Throws for unknown ids. + +- `id` — the task to read from. + +**Returns** the incremental read; consecutive reads never re-deliver output. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/bash/bash/src/index.ts#L137) + +### ctx.bash.kill(id) + +```ts website-api +abstract kill(id: BashTaskId): boolean +``` + +Kill a running background task. Returns false when it had already finished (no-op). Throws for unknown ids. + +- `id` — the task to kill. + +**Returns** true when this call killed it, false when it had already finished. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/bash/bash/src/index.ts#L145) + +### ctx.bash.onTaskDone(listener) + +```ts website-api +onTaskDone(listener: BashTaskListener): () => void +``` + +Register a background-task completion listener (disposed with the calling fiber). Listeners never fire after this service is disposed. + +- `listener` — called exactly once per task completion. + +**Returns** the disposer that unregisters the listener. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/bash/bash/src/index.ts#L153) diff --git a/website/zh-CN/api/harness/code-runtime.md b/website/zh-CN/api/harness/code-runtime.md new file mode 100644 index 0000000000..9ce642b1ab --- /dev/null +++ b/website/zh-CN/api/harness/code-runtime.md @@ -0,0 +1,28 @@ + + +# ctx.codeRuntime + +`CodeRuntime` (abstract seam) — provided by `@deepseek-ai/dsh-code-runtime`. + +Abstract code-execution service. Subclass, implement run and the two descriptors, and load the subclass as a plugin — it registers as `ctx.codeRuntime` (one implementation per context; loading a second throws, cordis' standard duplicate-service behavior). +Semantics every implementation must honor: +- run resolves with an error FIELD for every program outcome — parse/transform failures, thrown exceptions, budget expiry, abort, substrate death (CodeRunFailure's taxonomy). It REJECTS only for caller misuse of the seam itself (e.g. a run submitted after disposal). +- Binding calls bridge to the caller's CodeBindingFunctions verbatim; arguments and resolutions must be structured-cloneable, and the runtime treats the program as a hostile peer (arbitrary binding names are own properties, malformed traffic is rejected or ignored, never crashes the host). +- Runs are isolated from each other: no state survives from one run to the next through the runtime. +- Disposal reaches quiescence: in-flight runs are terminated AND awaited before the service's own teardown completes (no orphan substrate survives `fiber.dispose()`). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/code-runtime/code-runtime/src/index.ts#L59) + +### ctx.codeRuntime.run(request) + +```ts website-api +abstract run(request: CodeRunRequest): Promise +``` + +Execute one program against the request's bindings and capture what it emitted. See the class doc for the resolution contract (error is a result field; rejection means seam misuse only). + +- `request` — the program, its bindings, and the abort signal; the request carries everything the runtime acts on, with no hidden defaults. + +**Returns** the run's outcome: completion value (when transferable), the ordered log capture, and the failure (if any). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/code-runtime/code-runtime/src/index.ts#L90) diff --git a/website/zh-CN/api/harness/compact.md b/website/zh-CN/api/harness/compact.md new file mode 100644 index 0000000000..60555f3511 --- /dev/null +++ b/website/zh-CN/api/harness/compact.md @@ -0,0 +1,55 @@ + + +# ctx.compact + +`CompactService` (abstract seam) — provided by `@deepseek-ai/dsh-compact`. + +Abstract compaction service. Subclass implement the two abstract methods, and load the subclass as a plugin — it registers as `ctx.compact` (one implementation per context; loading a second throws, which is cordis' standard duplicate-service behavior). +Both core methods are abstract: the contract states WHAT compaction does, while the entire strategy — token estimation, retention policy, event sequencing, summarization — is a HOW decision owned by the implementation. +Implementations MUST honor: +- **Surface contract**: a successful compaction shadows the compacted surface nodes with a SINGLE replacement node carrying the summary. Because `SurfaceEventType` is a closed union, that node is a `user/message` with `surfaceOp: { op:'replace', start, end }`; the `compact/*` events are log-only (lock + provenance). +- **Blocking**: no compaction begins while another is in progress for the same session. The recommended mechanism is the log-recorded lock — append `compact/start` before the slow work and `compact/end` after (even on failure) — so the lock is visible to replay and crash recovery. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/compact/compact/src/index.ts#L65) + +### ctx.compact.compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal) + +```ts website-api +abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise +``` + +Check token pressure and compact if the conversation is too large. +Estimates the NEXT request's size — the session prefix, the surface-derived history, and the system prompt — and if it exceeds the backend's threshold, compacts an older range via compactRegion, keeping recent context intact. Returns `null` when no compaction is needed. +Scope and guarantees a backend MUST honor: +- **Compaction acts on surface-derived history only**, but the ESTIMATE counts everything the request carries: the loop composes the session prefix before the pre-step seam fires and hands it here, so the gate sees the prefix this instance will actually send (`EpochHeader.messagePrefix` — request-only, never derived history). Non-surface context injected downstream (into the request `messages` by a later listener) is out of this accounting by construction. +- **Head-anchored, best-effort.** Auto-compaction consolidates from the surface HEAD up to a balanced tool-pairing cutoff, so a prior head checkpoint is re-summarized into one fresh checkpoint (the surface holds at most one auto-generated checkpoint, always at the head). It is best-effort over CLOSED steps: when the only compactable content left is an un-splittable open tail step, it declines (`null`) and retries once that step closes. +- **Single-unit overflow is out of scope.** If a single retained unit (one closed step, or a large free node such as a pasted `user/message`) ALONE exceeds the budget, compaction cannot help and the call may go out over-budget. Bounding an individual unit's size is a separate concern — as is a session prefix that alone approaches the window (a configuration error no compactor fixes: compaction cannot shrink the prefix). + +- `agent` — agent context owning the session surface and model options. +- `fullSystemPrompt` — assembled system prompt, counted toward the estimate. +- `sessionPrefix` — the instance's composed session prefix, counted toward the estimate. +- `signal` — cancellation signal. A backend summarizing via `ctx.llm.stream()` MUST forward this into the call's `GenerateOptions.signal` so an abort/dispose tears down the in-flight summarization rather than leaving an orphaned model call running past the cancellation. + +**Returns** the compaction result, or `null` if no compaction was needed. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/compact/compact/src/index.ts#L111) + +### ctx.compact.compactRegion(session, start, end, agent, signal?) + +```ts website-api +abstract compactRegion( session: Session, start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise +``` + +Forcibly compact a range of surface nodes into a single summary node. +`start` and `end` are inclusive seqs of surface nodes to shadow; the backend summarizes their content and appends a replacement surface node. Used by the (future) `/compact` tool and internally by compactIfNeeded. +The region MUST NOT split a step's `assistant/message` tool-calls from their `tool/result`s, leaving the rehydrated transcript with a dangling tool-call or an orphaned tool-result that every provider rejects. A region is safe iff both its edges are balanced cuts on the surface: the cut before `start` and the cut after `end` each have no unanswered tool-call before them. A node that belongs to no step (a pre-step user message, inter-step steering, or an injection context message) is a balanced (free) boundary; an `end` inside an open (unclosed) tail step is invalid — its tool-calls have no results yet. `dsh-session` exports `isToolPairingBalanced` for this check. + +- `session` — the session whose surface is mutated. +- `start` — inclusive seq of the first surface node to compact. +- `end` — inclusive seq of the last surface node to compact. +- `agent` — agent context used by router-aware summarizers. +- `signal` — optional cancellation signal. A backend that summarizes via `ctx.llm.stream()` MUST forward this into the call's `GenerateOptions.signal` so an abort/dispose tears down the in-flight summarization rather than leaving an orphaned model call running past the cancellation. + +**Returns** what the compaction did (the replaced range and its summary node). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/compact/compact/src/index.ts#L151) diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md new file mode 100644 index 0000000000..9aa3d3b791 --- /dev/null +++ b/website/zh-CN/api/harness/events.md @@ -0,0 +1,546 @@ + + +# Harness events + +Every event the harness packages declare on the cordis event bus (35 total), grouped by scope. The **mode** is the dispatch semantics (`emit` fire-and-forget, `parallel` awaited, `serial` first-bail, `waterfall` veto-chain — a waterfall listener MUST call `next()` to delegate). + +## agent/* + +### agent/created + +**Mode:** `emit` + +```ts website-api +'agent/created'(agent: Agent): void +``` + +An agent was registered in the AgentRegistry and is ready to receive messages. + +- `agent` — the newly registered agent, already resolvable in the registry. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L265) + +### agent/disposed + +**Mode:** `emit` + +```ts website-api +'agent/disposed'(agent: Agent): void +``` + +An agent was disposed and removed from the registry; its fiber and any in-flight turn have been torn down. + +- `agent` — the agent that was torn down; its handle is now inert. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L272) + +### agent/error + +**Mode:** `emit` + +```ts website-api +'agent/error'(agent: Agent, turn: number, step: number, error: Error): void +``` + +A step or turn errored. The loop reports a failure here (plus the logger) even when the error has no in-turn position for a session `error` event. + +- `agent` — the agent whose turn errored. +- `turn` — the turn in which the failure surfaced. +- `step` — the step at which the failure surfaced. +- `error` — the failure, verbatim. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L476) + +### agent/pre-step + +**Mode:** `serial` + +```ts website-api +'agent/pre-step'(agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void +``` + +Awaited pre-step surface-mutation checkpoint, fired once per step AFTER `turn/start` (and after the prior step closed) but BEFORE this step's `step/start` — so anything a listener appends lands OUTSIDE the step, between `turn/start`/`step/end` and the upcoming `step/start`. `step` is the number of the step about to start. The loop awaits `ctx.serial('agent/pre-step', …)` after assembling the system prompt, then opens the step and derives the request history ONCE from whatever the surface now holds. This is where compaction belongs: it mutates the session surface in place (shadowing an older range with a summary node) with its log-only `compact/*` records cleanly outside any step, and the single subsequent derive reflects the mutation — so there is no double-derive and no listener can see (or be expected to act on) an assembled `messages` array that does not exist yet. +Serial (awaited in registration order), not a waterfall: a listener mutates the surface as a side effect; there is nothing to transform, but the loop must wait for the mutation to complete before opening the step and deriving. Cordis `serial` bails early if a listener returns a bail value; this event is typed and documented as `void`, so listeners must not return a semantic veto value. `fullSystemPrompt` is the assembled prompt a listener needs to measure pressure (the system prompt counts toward the budget), and `sessionPrefix` is the instance's composed agent/session-prefix product for the same reason — every request carries it in front of the derived history, and it is composed BEFORE this seam fires precisely so a pressure gate counts the prefix the request will actually send (never a stale logged one). `signal` cancels any in-flight work a listener starts (e.g. a summarization model call). + +- `agent` — the agent about to open the step. +- `turn` — the already-open turn this step belongs to. +- `step` — the number of the step about to start. +- `fullSystemPrompt` — the assembled prompt, for measuring token pressure. +- `sessionPrefix` — the instance's frozen session prefix, for the same measurement. +- `signal` — aborts in-flight listener work when the turn is torn down. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L357) + +### agent/prompt-submit + +**Mode:** `waterfall` + +```ts website-api +'agent/prompt-submit'(agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise): Promise +``` + +Waterfall: decide what happens to ONE drained queued message before it becomes a `user/message` — allow (optionally rewriting the prompt bytes or attaching `additionalContext`) or block it. Fires inside the already-open turn, per drained message. Maps onto Claude Code's `UserPromptSubmit` hook. Call `next()` to delegate to the default (allow unchanged), or return a PromptDecision without calling `next()` to short-circuit. + +- `agent` — the agent draining its inbox. +- `content` — the drained message's blocks, as queued. +- `source` — the message's resolved source. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L370) + +### agent/queued + +**Mode:** `emit` + +```ts website-api +'agent/queued'(agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void +``` + +A message entered the agent's inbox (queued or steering). `source` is the resolved source (defaults applied), not the caller's raw options. + +- `agent` — the agent whose inbox received the message. +- `content` — the enqueued content blocks, verbatim. +- `info` — the resolved source plus whether it entered as steering. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L290) + +### agent/request + +**Mode:** `waterfall` + +```ts website-api +'agent/request'(agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise): Promise +``` + +Waterfall: shape the step's call configuration — model switching, sampling overrides — by returning a replacement LlmCallConfig (the frozen seed is the config the loop would otherwise use). Config is ALL a listener shapes here: every request is a pure function of the session log (the reconstructability RFC), so model-visible content flows through the log channels — `inject()`, steering, prompt-submit `additionalContext`, prompt sections via `system-prompt/assemble`, or the header-logged session prefix via agent/session-prefix — never through request mutation, and the loop records whatever config the request actually uses as a `request/header*` event before dispatch. The step's messages are already snapshotted when this fires (the `step/start` boundary): an `inject()` from a listener here lands in the log but joins the NEXT request. For surface mutation that must precede the snapshot (compaction), use agent/pre-step. Call `next()` to delegate, or return an LlmCallConfig without it to short-circuit. + +- `agent` — the agent making the model call. +- `turn` — the open turn number. +- `step` — the step whose request this is. +- `config` — the config the loop would use (frozen); return a replacement to switch. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L394) + +### agent/session-prefix + +**Mode:** `waterfall` + +```ts website-api +'agent/session-prefix'(agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise): Promise +``` + +Waterfall: compose the SESSION PREFIX — request-only messages placed in front of the ENTIRE derived history (directly after the provider's system slot) on every request this loop instance sends. Fired ONCE per loop instance, lazily before its first step's agent/pre-step seam — BEFORE the pre-step so a token-pressure gate (compaction) counts the prefix this instance will actually send, never a previous instance's logged one. The composed result is deep-frozen, recorded as `EpochHeader.messagePrefix` on the instance's anchoring `'initial'`/`'resume'` header snapshot, and reused verbatim for every subsequent request — never recomputed mid-session, so the provider prefix cache holds by construction (a process restart or `ctx.agents.resume()` is a new instance: it recomposes, and any drift lands attributably on the `'resume'` snapshot). Composition runs outside the step, before the boundary snapshot: a composing listener's session append joins the CURRENT request's derived history. A composition interrupted by a cancel/dispose landing inside the waterfall is discarded — never cached, logged, or sent — and the next turn recomposes under a live signal, so an abort-aware listener's degraded fallback cannot leak into later requests. +This is the home for session-stable openers the model must always see but that must NOT become durable history — a skills catalog, an AGENTS.md digest, a workspace baseline: `Session.deriveMessages()` never returns the prefix, and the header events are its only durable record, so the request stays reconstructable from the log. Content that CHANGES mid-session belongs in the append-only history channels instead — `agent.inject()`, a `tools/post-execute` decision's `additionalContext`, prompt-submit `additionalContext` — each a durable `context/message` paid once and prefix-cached thereafter. +The seed is a frozen empty list; a contributing listener returns a NEW array — never an in-place push. The canonical contribution is a PREPEND, `[mine, ...await next()]`: the waterfall unwinds innermost-first (the LAST-registered listener's `next()` resolves first), so prepending yields registration order on the wire, and every plugin using it composes deterministically. The append form `[...await next(), mine]` is legal but places a contribution AFTER every later-registered plugin's — reverse registration order when all contributors append. Call `next()` to delegate, or return a list without it to short-circuit. + +- `agent` — the agent whose session prefix is being composed. +- `prefix` — the frozen empty seed; return an extended replacement to contribute. +- `signal` — aborts in-flight listener work (e.g. a discovery scan) when the step is torn down. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L441) + +### agent/session-start + +**Mode:** `emit` + +```ts website-api +'agent/session-start'(agent: Agent, source: SessionStartSource): void +``` + +The agent's session lifecycle began, fired once before its first turn. `source` says why (SessionStartSource: fresh startup, a resumed persisted session, …). A pure NOTIFICATION (emit, not waterfall): it carries no veto — a session-start listener that wants to seed context does so via `agent.inject()` (a `context/message` the first request sees), not by returning a decision. Cannot block the session from starting; that gap is deliberate (a bridge logs/injects, it does not gate startup). + +- `agent` — the agent whose session lifecycle began. +- `source` — why the session started (fresh startup, resume, …). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L305) + +### agent/status + +**Mode:** `emit` + +```ts website-api +'agent/status'(agent: Agent, status: AgentStatus): void +``` + +Agent status changed (`idle` ⇄ `running`, or → `disposed`). Drive lifecycle off this transition, never off a status you just requested — `send()` does not flip status to `running` before it returns. + +- `agent` — the agent whose status flipped. +- `status` — the status just entered (the transition's destination). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L281) + +### agent/step-result + +**Mode:** `waterfall` + +```ts website-api +'agent/step-result'(agent: Agent, turn: number, step: number, message: Message, next: () => Promise): Promise +``` + +Waterfall: post-process the assembled assistant Message before tool dispatch (validation, content rewriting, …). + +- `agent` — the agent that received the step's response. +- `turn` — the open turn number. +- `step` — the step that produced the message. +- `message` — the assistant message as assembled from the stream. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L451) + +### agent/turn-continuation + +**Mode:** `waterfall` + +```ts website-api +'agent/turn-continuation'(agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise): Promise +``` + +Waterfall: override the turn-continuation decision via a typed ContinuationDecision. The loop's `defaultDecision` is `continue` when the step had tool calls or steering was injected, else `stop`. Listeners force-continue (`/goal`, `/loop` — optionally attaching a `reason` recorded as next-step steering) or force-stop (budget guards). Call `next()` to delegate to the default, or return a decision to override. + +- `agent` — the agent deciding whether to run another step. +- `turn` — the turn being continued or stopped. +- `defaultDecision` — what the loop would do absent an override. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L464) + +## fs/* + +### fs/edit-intent + +**Mode:** `waterfall` + +```ts website-api +'fs/edit-intent'(target: FsTarget, actor: object | undefined, next: () => { version: FsVersion } | undefined | Promise<{ version: FsVersion } | undefined>): Promise<{ version: FsVersion } | undefined> +``` + +Single-slot decision: produce the optional version guard for the next FileSystem.editText. The tool dispatches this as an unbound waterfall and supplies a default thunk returning `undefined` (unconditional edit of the current content — the bare provider; no `stat`). The `@deepseek-ai/dsh-fs-policy` policy listener returns `{ version: vObserved }`, or throws `FS_NOT_OBSERVED` if the actor is unset or has not observed the target. Does NOT call `next()`: one decision, first-wins (see Events.'fs/write-intent'). + +- `target` — the resolved target about to be edited. +- `actor` — the opaque tool-execution context the decider keys off. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/fs/fs/src/index.ts#L123) + +### fs/observed + +**Mode:** `emit` + +```ts website-api +'fs/observed'(target: FsTarget, version: FsVersion, actor: object | undefined): void +``` + +Record that an actor observed a target at a version, after a successful read/write/edit. Fire-and-forget (plain `emit`). A listener MUST be a synchronous, side-effect-only recorder (`@deepseek-ai/dsh-fs-policy`'s is a `WeakMap.set`): the tool does not guard the emit, so a listener that throws surfaces as the tool's `isError` result, and cordis `emit` does not await listener promises — async or fallible audit/telemetry does not belong here. No listener ⇒ nothing recorded. `actor` is the opaque tool-execution context. + +- `target` — the target that was read/written/edited. +- `version` — the version the actor now holds as its observation. +- `actor` — the observing tool-execution context; undefined records nothing useful. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/fs/fs/src/index.ts#L138) + +### fs/write-intent + +**Mode:** `waterfall` + +```ts website-api +'fs/write-intent'(target: FsTarget, actor: object | undefined, next: () => FsWriteIntent | undefined | Promise): Promise +``` + +Single-slot decision: produce the write intent for the next FileSystem.writeText. The tool dispatches this as an unbound waterfall (no `this`) and supplies a default thunk returning `undefined` (unconditional create-or-overwrite — the bare provider). The `@deepseek-ai/dsh-fs-policy` policy listener returns `createIfAbsent` (unobserved actor) or `{ kind: 'replaceIfVersion', version: vObserved }` (observed) and does NOT call `next()` — one decision, not a composable chain. The slot is first-wins: the first non-`next()` decider (registration order, or `prepend`) occupies it; a second decider is a misconfiguration, not layering. `actor` is the opaque tool-execution context, never read here. + +- `target` — the resolved target about to be written. +- `actor` — the opaque tool-execution context the decider keys off. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/fs/fs/src/index.ts#L109) + +## llm/* + +### llm/stream + +**Mode:** `waterfall` + +```ts website-api +'llm/stream'(this: LlmService, options: GenerateOptions, next: () => AsyncIterable): AsyncIterable +``` + +Waterfall around every streaming model call (retry, replay, routing). Bound to the LlmService; call `next()` to reach the resolved adapter's stream, or yield your own chunks to short-circuit. + +- `options` — the full request. A LOOP-built request arrives deep-frozen (mutation throws): its content is a pure function of the session log (the reconstructability RFC), so listeners read it, never rewrite it. A hand-built one-shot (compaction summarize) is the caller's own object and stays mutable here. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L39) + +## session/* + +### session/created + +**Mode:** `emit` + +```ts website-api +'session/created'(session: Session): void +``` + +A session was created in the store. + +- `session` — the session just entered and announced. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L39) + +### session/event + +**Mode:** `emit` + +```ts website-api +'session/event'(session: Session, event: SessionEvent): void +``` + +An event was appended to a session log (sync, fire-and-forget). This is the per-append feed a UI or invariant plugin tails. + +- `session` — the session whose log grew. +- `event` — the appended event, exactly as recorded. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L47) + +### session/flush + +**Mode:** `parallel` + +```ts website-api +'session/flush'(session: Session): Promise | void +``` + +Awaited durability checkpoint. The agent loop awaits `ctx.parallel('session/flush', session)` at every turn end; persistence plugins (JSONL, SQLite) drain their write-behind buffers here and on fiber dispose. Awaited (parallel), not a waterfall: every listener runs and the loop waits for all of them, but none can veto. + +- `session` — the session whose buffered events must reach durable storage. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L57) + +## subagent/* + +### subagent/end + +**Mode:** `emit` + +```ts website-api +'subagent/end'(info: SubagentRunEndInfo): void +``` + +A subagent run settled — emitted when SubagentRun.result resolves (any stop reason). Paired with Events['subagent/start']. + +- `info` — the run identity plus stop reason and final output. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L98) + +### subagent/provider-added + +**Mode:** `emit` + +```ts website-api +'subagent/provider-added'(provider: SubagentProvider): void +``` + +A provider became resolvable in the SubagentService registry. Consumers that derive state from a named provider (e.g. the model-facing tool wording in `dsh-tool-subagent`) react HERE instead of assuming load order — the cordis Loader starts sibling plugins concurrently, so "listed earlier in cordis.yml" does not mean "registered earlier". + +- `provider` — the provider that just registered, live in the registry. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L72) + +### subagent/provider-removed + +**Mode:** `emit` + +```ts website-api +'subagent/provider-removed'(name: string): void +``` + +A provider left the registry (its plugin's fiber was disposed — an unload or an HMR reload). Consumers holding provider-derived state drop it here; a reload re-fires `subagent/provider-added` with the fresh provider. Delivered with per-listener containment: a throwing subscriber is logged, never starves later subscribers, and never disrupts the provider's teardown. + +- `name` — the registry name that no longer resolves. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L83) + +### subagent/start + +**Mode:** `emit` + +```ts website-api +'subagent/start'(info: SubagentRunInfo): void +``` + +A subagent run started — emitted after the provider is resolved and its capabilities validated, as the child run begins. Paired with Events['subagent/end']. + +- `info` — which provider started which child agent. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L91) + +## system-prompt/* + +### system-prompt/assemble + +**Mode:** `waterfall` + +```ts website-api +'system-prompt/assemble'(this: SystemPrompt, assembly: PromptAssembly, context: AssembleContext, next: () => Promise): Promise +``` + +Waterfall around prompt assembly — mutate or extend the PromptAssembly (sections + tools + variables) before it is rendered. Bound to the SystemPrompt service; call `next()` to delegate. + +- `assembly` — the assembly built from the registered sections, tool providers, and variable providers; listeners may mutate it or return a replacement. +- `context` — the per-assembly {@link AssembleContext} the caller passed to {@link SystemPrompt.assemble} (e.g. which agent the prompt is for), so a listener can filter or extend per agent. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/system-prompt/src/index.ts#L38) + +### system-prompt/change + +**Mode:** `emit` + +```ts website-api +'system-prompt/change'(): void +``` + +A section, tool provider, or variable provider was registered or unregistered (the assembly inputs changed). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/system-prompt/src/index.ts#L44) + +## tools/* + +### tools/change + +**Mode:** `emit` + +```ts website-api +'tools/change'(): void +``` + +A tool was registered or unregistered (the available tool set changed). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/tools/src/index.ts#L132) + +### tools/execute + +**Mode:** `waterfall` + +```ts website-api +'tools/execute'(this: ToolRegistry, exec: ToolExecution, next: () => Promise): Promise +``` + +Around-dispatch waterfall wrapping the registry's core tool dispatch, between the `tools/pre-execute` gate and the `tools/post-execute` seam. A listener receives `(exec, next)`: call `next()` to delegate to dispatch (returning its ToolExecutionResult, optionally wrapped), or return a replacement result without calling `next()` to short-circuit dispatch. The base `next()` IS the dispatch-with-normalization thunk — a thrown tool (or unknown tool) is already normalized to an `isError` result by the time a listener's `await next()` returns, so a wrapper never sees a raw throw from the tool body. This is the seam a timeout/retry/metrics plugin wraps: it can mutate `exec` (e.g. replace `exec.signal` with a per-call deadline) BEFORE `next()` and inspect the result AFTER. (Cordis `next()` ignores any passed arguments and re-invokes downstream with the shared payload, so a wrapper mutates `exec` in place rather than passing a new object to `next()`.) Multiple listeners compose by registration order — an outer one wraps the inner ones plus dispatch. + +- `exec` — the allowed call about to dispatch (name, parsed arguments, caller agent, signal). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/tools/src/index.ts#L111) + +### tools/post-execute + +**Mode:** `waterfall` + +```ts website-api +'tools/post-execute'(this: ToolRegistry, exec: ToolExecution, result: ToolExecutionResult, next: () => Promise): Promise +``` + +Waterfall AFTER a tool runs — where hook plugins inspect the result and accept it (optionally REPLACING the model-facing content, and/or attaching `additionalContext` for the next request) or block it with corrective `feedback` (Claude Code's `PostToolUse`). Listeners receive `(exec, result, next)`: call `next()` to delegate to the default (accept unchanged), or return a PostToolDecision to override. Core tool dispatch runs earlier as the base `next()` of the `tools/execute` waterfall, all inside `execute`'s outer try/catch (and the tool body keeps its own inner try/catch, so a thrown tool still reaches `post-execute` as an `isError` result). + +- `exec` — the call that just ran (name, parsed arguments, caller agent). +- `result` — the dispatch outcome a listener may accept, replace, or block. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/tools/src/index.ts#L127) + +### tools/pre-execute + +**Mode:** `waterfall` + +```ts website-api +'tools/pre-execute'(this: ToolRegistry, exec: ToolExecution, next: () => Promise): Promise +``` + +Waterfall BEFORE a tool runs — the gate where sandbox, permission, and hook plugins allow or deny a call (Claude Code's `PreToolUse`). Listeners receive `(exec, next)`: call `next()` to delegate to the default (allow), or return a PreToolDecision without calling `next()` to short-circuit. A `deny` skips dispatch and yields an `isError` result; the tool body never runs. Input rewrite is deliberately NOT offered here (see PreToolDecision); `ask` degrades to deny until the permission system lands (`FIXME(permissions)`). + +- `exec` — the pending call (name, parsed arguments, caller agent). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/tools/src/index.ts#L91) + +## workflow/* + +### workflow/agent-end + +**Mode:** `emit` + +```ts website-api +'workflow/agent-end'(info: WorkflowRunInfo, agent: WorkflowAgentEndInfo): void +``` + +One `agent()` call settled (clean result, child failure, or run cancellation). Paired with Events['workflow/agent-start'] by `agent.seq`, exactly once per started call on every stop path — on an engine termination path (a worker killed past its grace) the end is engine-synthesized with outcome `'cancelled'`. + +- `info` — the run's identity snapshot. +- `agent` — the call identity plus its outcome. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/workflow/workflow/src/index.ts#L96) + +### workflow/agent-start + +**Mode:** `emit` + +```ts website-api +'workflow/agent-start'(info: WorkflowRunInfo, agent: WorkflowAgentInfo): void +``` + +One `agent()` call started a child run. Paired with Events['workflow/agent-end'] by `agent.seq`. + +- `info` — the run's identity snapshot. +- `agent` — the call's sequence number, label, phase, and child id. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/workflow/workflow/src/index.ts#L85) + +### workflow/end + +**Mode:** `emit` + +```ts website-api +'workflow/end'(info: WorkflowRunInfo, result: WorkflowResultInfo): void +``` + +A workflow run settled (any stop reason). Fired when WorkflowRun.result resolves. Paired with Events['workflow/start']. + +- `info` — the run's identity snapshot. +- `result` — the outcome data (stop reason, error, agent count) — deliberately WITHOUT the result value (see {@link WorkflowResultInfo}). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/workflow/workflow/src/index.ts#L106) + +### workflow/log + +**Mode:** `emit` + +```ts website-api +'workflow/log'(info: WorkflowRunInfo, message: string): void +``` + +The script emitted a narration line (a `log(message)` call). + +- `info` — the run's identity snapshot. +- `message` — the logged message, verbatim. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/workflow/workflow/src/index.ts#L77) + +### workflow/phase + +**Mode:** `emit` + +```ts website-api +'workflow/phase'(info: WorkflowRunInfo, title: string): void +``` + +The script entered a phase (a `phase(title)` call) — progress grouping for observers; no execution semantics. + +- `info` — the run's identity snapshot. +- `title` — the phase title, verbatim. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/workflow/workflow/src/index.ts#L70) + +### workflow/start + +**Mode:** `emit` + +```ts website-api +'workflow/start'(info: WorkflowRunInfo): void +``` + +A workflow run started — the script's meta block validated, the body about to execute. Paired with Events['workflow/end']. + +- `info` — the run's identity snapshot (id + meta). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/workflow/workflow/src/index.ts#L62) diff --git a/website/zh-CN/api/harness/fs.md b/website/zh-CN/api/harness/fs.md index 4e336ff962..911bda4db2 100644 --- a/website/zh-CN/api/harness/fs.md +++ b/website/zh-CN/api/harness/fs.md @@ -1,78 +1,126 @@ -# Filesystem (dsh-fs) + -文件系统操作接口。 +# ctx.fs -**接口包:** `@deepseek-ai/dsh-fs` -**实现:** `@deepseek-ai/dsh-fs-local` + `@deepseek-ai/dsh-fs-policy` -**消费者:** `@deepseek-ai/dsh-tool-fs` +`FileSystem` (abstract seam) — provided by `@deepseek-ai/dsh-fs`. -## FS Service +Abstract filesystem provider service. Subclass, implement the seven storage primitives, and load the subclass as a plugin — it registers as `ctx.fs` (one implementation per context; loading a second throws, cordis' standard duplicate-service behavior). +Semantics every backend must honor: +- resolve returns a stable FsTarget; the same underlying file reached by different input paths must yield the same `targetKey` so stale guards and target lookup agree across paths (e.g. through symlinks). +- stat returns FsInfo metadata (never content) or `undefined` when the target is absent. +- readText/streamText read the whole regular text file (the stream for large files); both own regular-file checks, UTF-8 decoding, binary/NUL rejection, and `FS_NOT_TEXT`. +- listDir returns direct children of a directory in stable name order with resolved child targets and cheap metadata only. It never reads file contents. Missing targets throw `FS_NOT_FOUND`, non-directories throw `FS_NOT_DIRECTORY`, permission failures throw `FS_PERMISSION_DENIED`, and other backend I/O failures throw `FS_IO_ERROR`. +- writeText is atomic temp-file + rename. `expected` is OPTIONAL: omit it for an unconditional create-or-overwrite (the bare-provider default), or supply a FsWriteIntent to guard the write. +- editText verifies `expected.version` BEFORE literal matching (so a stale edit reports `FS_STALE_VERSION`, not `FS_EDIT_NOT_FOUND`/ `FS_AMBIGUOUS_EDIT` against newer content), then applies literal replacement and writes atomically — all inside one mutation critical section. `expected` is OPTIONAL: omit it for an unconditional edit of the current content (a missing target still reports `FS_STALE_VERSION`). -### ctx.fs.read(path, options?) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/fs/fs/src/index.ts#L172) -- **path:** `string` -- **options:** `{ offset?: number; limit?: number }` -- **返回值:** `Promise` +### ctx.fs.resolve(path, opts?) -读取文件内容。 - -### ctx.fs.write(path, content) - -- **path:** `string` -- **content:** `string` -- **返回值:** `Promise` - -写入文件（覆盖）。 - -### ctx.fs.edit(path, edits) - -- **path:** `string` -- **edits:** `Edit[]` -- **返回值:** `Promise` - -对文件执行精确的字符串替换编辑。 - -### ctx.fs.stat(path) - -- **path:** `string` -- **返回值:** `Promise` - -获取文件/目录信息。 - -## 配置 (dsh-fs-local) - -```typescript -interface Config { - /** 工作目录（相对路径的基准） */ - cwd: string -} +```ts website-api +abstract resolve(path: string, opts?: { cwd?: string }): Promise ``` -## 策略门 (dsh-fs-policy) +Resolve a model/plugin-supplied path into a stable FsTarget. May perform I/O (a remote/sandboxed backend may need a round-trip to map a path to a stable identity), hence async even though the local backend only normalizes + realpaths. +`opts.cwd` is the base directory a RELATIVE `path` resolves against; an absolute `path` ignores it. Omitted ⇒ the backend's own default base (the local backend uses its configured `cwd`). The CALLER supplies this — the seam does not read a session or agent — so a tool can resolve against the caller's per-session workspace (`exec.agent.session.header.cwd`) without the provider depending on `dsh-agent`/`dsh-session`. Mirrors how `dsh-tool-bash` defaults a bash `workdir` to the session cwd. -`dsh-fs-policy` 是一个可选的中间层插件，实现 read-before-write/edit 策略——模型必须先读取文件才能写入或编辑。这防止模型盲目覆盖文件。 +- `path` — the path to resolve; relative paths resolve against `opts.cwd`. +- `opts` — `cwd` overrides the backend's default base for relative paths. -在 `cordis.yml` 中，它位于 `fs-local` 和 `tool-fs` 之间： +**Returns** the stable target; the same file yields the same `targetKey`. -```yaml -- name: '@deepseek-ai/dsh-fs-local' - config: - cwd: !!js process.cwd() -- name: '@deepseek-ai/dsh-fs-policy' -- name: '@deepseek-ai/dsh-tool-fs' +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/fs/fs/src/index.ts#L194) + +### ctx.fs.stat(target, signal?) + +```ts website-api +abstract stat(target: FsTarget, signal?: AbortSignal): Promise ``` -## 模型可用的 Tools +Return target metadata, or `undefined` when the target does not exist. -| Tool | 说明 | -|------|------| -| `read` | 读取文件内容（支持 offset/limit） | -| `write` | 写入文件（需要先 read） | -| `edit` | 精确字符串替换（需要先 read） | +- `target` — the resolved target to stat. +- `signal` — aborts the metadata round-trip. -## 三件套结构 +**Returns** metadata only, never content; undefined for an absent target. -- `dsh-fs`：接口定义 -- `dsh-fs-local`：本地文件系统实现 -- `dsh-fs-policy`：策略门（read-before-write 检查） -- `dsh-tool-fs`：模型 tool 层 +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/fs/fs/src/index.ts#L202) + +### ctx.fs.readText(target, signal?) + +```ts website-api +abstract readText(target: FsTarget, signal?: AbortSignal): Promise +``` + +Read the whole regular text file as a single decoded string. + +- `target` — the resolved target to read. +- `signal` — aborts the read. + +**Returns** the full decoded UTF-8 content. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/fs/fs/src/index.ts#L210) + +### ctx.fs.streamText(target, signal?) + +```ts website-api +abstract streamText(target: FsTarget, signal?: AbortSignal): Promise> +``` + +Stream the whole regular text file as decoded text chunks (same text semantics as readText, for large files). The backend owns cross-chunk UTF-8 decoding and binary rejection so the policy layer never touches raw bytes. + +- `target` — the resolved target to read. +- `signal` — aborts the stream, including between chunks. + +**Returns** the chunk iterable, decoded and validated like {@link readText}. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/fs/fs/src/index.ts#L221) + +### ctx.fs.listDir(target, signal?) + +```ts website-api +abstract listDir(target: FsTarget, signal?: AbortSignal): Promise +``` + +List direct children of a directory in stable name order. Returns resolved child targets plus cheap metadata only; never reads file contents. + +- `target` — the resolved directory target. +- `signal` — aborts the listing. + +**Returns** one entry per direct child, in stable name order. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/fs/fs/src/index.ts#L230) + +### ctx.fs.writeText(target, content, expected?, signal?) + +```ts website-api +abstract writeText(target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal): Promise +``` + +Create or fully replace a UTF-8 text file atomically. `expected` is the create-vs-replace decision and stale guard when supplied; OMITTING it is an unconditional create-or-overwrite (the bare provider — no version guard, no read-first requirement). Atomic either way. + +- `target` — the resolved target to write. +- `content` — the full new file content. +- `expected` — the write intent guarding the write; omit for unconditional. +- `signal` — aborts before the atomic rename takes effect. + +**Returns** the outcome, including the version the write produced. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/fs/fs/src/index.ts#L243) + +### ctx.fs.editText(target, edit, expected?, signal?) + +```ts website-api +abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal): Promise +``` + +Apply a literal edit to an existing UTF-8 text file. When `expected` is supplied, verifies `expected.version` as the stale guard BEFORE literal matching; OMITTING it edits the current content unconditionally (no version guard). Either way applies the replacement and writes atomically — one mutation critical section — and a missing target reports `FS_STALE_VERSION`. + +- `target` — the resolved target to edit. +- `edit` — the literal search/replace request. +- `expected` — the version guard; omit for an unconditional edit. +- `signal` — aborts before the atomic rename takes effect. + +**Returns** the outcome, including the version the edit produced. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/fs/fs/src/index.ts#L257) diff --git a/website/zh-CN/api/harness/llm.md b/website/zh-CN/api/harness/llm.md index 82a4d8e225..73b5a2484f 100644 --- a/website/zh-CN/api/harness/llm.md +++ b/website/zh-CN/api/harness/llm.md @@ -1,124 +1,50 @@ -# LLM (dsh-llm) + -LLM 服务接口和适配器注册。 +# ctx.llm -**包名:** `@deepseek-ai/dsh-llm` -**服务名:** `ctx.llm` +`LlmService` — provided by `@deepseek-ai/dsh-llm`. -## LLM Service +The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L88) ### ctx.llm.registerAdapter(models, adapter) -- **models:** `string[]` 该适配器支持的模型名列表 -- **adapter:** `LlmAdapter` 适配器实例 -- **返回值:** `() => void` disposer - -注册一个 LLM 适配器。当请求中指定的模型名在 `models` 列表中时，路由到该适配器。 - -```typescript -ctx.llm.registerAdapter(['deepseek-v4-flash', 'deepseek-v4-pro'], adapter) +```ts website-api +registerAdapter(models: string[], adapter: LlmAdapter): () => void ``` -## LlmAdapter +Register an adapter for the given model names. Throws `LlmError` with code `DUPLICATE_ADAPTER` if any model already has an adapter (all-or-nothing). Disposed with the fiber. -适配器基类。子类必须实现 `stream()` 方法。 +- `models` — every model name this adapter should serve. +- `adapter` — the adapter that streams calls for those models. -### stream(options) +**Returns** the disposer that unregisters all of them. -- **options:** `GenerateOptions` -- **返回值:** `AsyncIterable` +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L103) -将统一请求格式转换为具体 API 的流式调用。 +### ctx.llm.models() -## GenerateOptions - -```typescript -interface GenerateOptions { - model: string - messages: Message[] - tools?: ToolSpec[] - system?: string - maxTokens?: number - temperature?: number -} +```ts website-api +models(): string[] ``` -| 字段 | 说明 | -|------|------| -| `model` | 请求的模型名 | -| `messages` | 对话历史 | -| `tools` | 当前可用的 tool 列表（JSON Schema 格式） | -| `system` | 系统提示词 | -| `maxTokens` | 最大输出 token | -| `temperature` | 采样温度 | +Model names with a registered adapter. -## StreamChunk +**Returns** the registered names, in registration order. -流式响应的增量 chunk 类型： +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L124) -```typescript -type StreamChunk = - | { type: 'block-start'; index: number; blockType: 'text' | 'tool-call' } - | { type: 'text-delta'; index: number; text: string } - | { type: 'tool-call-delta'; index: number; id: CallId; name: string; argumentsDelta: string } - | { type: 'block-end'; index: number; block: ContentBlock } - | { type: 'usage'; usage: TokenUsage } - | { type: 'finish'; reason: FinishReason } +### ctx.llm.stream(options) + +```ts website-api +stream(options: GenerateOptions): AsyncIterable ``` -### 协议规则 +Stream one model call as raw chunks (token-level deltas). Throws `LlmError` with code `NO_ADAPTER` if no adapter is registered for `options.model`. Dispatches through the `llm/stream` waterfall. -1. 每个内容块以 `block-start` 开始，以 `block-end` 结束 -2. `index` 从 0 递增 -3. `text-delta` 只在 `blockType: 'text'` 的块中 -4. `tool-call-delta` 只在 `blockType: 'tool-call'` 的块中 -5. `usage` 在 `finish` 之前 -6. `finish` 必须是最后一个 chunk +- `options` — the full request; `options.model` selects the adapter. -## CallId +**Returns** the chunk stream, possibly wrapped by `llm/stream` listeners. -Tool call 的 opaque branded ID： - -```typescript -import { CallId } from '@deepseek-ai/dsh-llm' - -const id = CallId('call-abc123') -``` - -## TokenUsage - -```typescript -interface TokenUsage { - inputTokens: number - outputTokens: number -} -``` - -## FinishReason - -```typescript -type FinishReason = - | { kind: 'stop' } - | { kind: 'tool-calls' } - | { kind: 'max-tokens' } -``` - -## Message - -对话消息类型： - -```typescript -interface Message { - role: 'user' | 'assistant' - content: ContentBlock[] -} -``` - -## ContentBlock - -```typescript -type ContentBlock = - | { type: 'text'; text: string } - | { type: 'tool-call'; id: CallId; name: string; arguments: string } - | { type: 'tool-result'; callId: CallId; content: ContentBlock[]; isError?: boolean } -``` +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L141) diff --git a/website/zh-CN/api/harness/session-persistence.md b/website/zh-CN/api/harness/session-persistence.md new file mode 100644 index 0000000000..6a111cc59f --- /dev/null +++ b/website/zh-CN/api/harness/session-persistence.md @@ -0,0 +1,66 @@ + + +# ctx.sessionPersistence + +`SessionPersistence` (abstract seam) — provided by `@deepseek-ai/dsh-session-persistence`. + +Abstract durable session-persistence service. Subclass, implement the abstract methods, and load the subclass as a plugin — it registers as `ctx.sessionPersistence` (one implementation per context; loading a second throws, cordis' standard duplicate-service behavior). +Contracts every implementation MUST honor (a DB backend asserts them inside a transaction; a file backend appends at EOF): +- **Append-only; a crashed turn is closed, not truncated.** Committed events — those at or below a flushed `turn/end` — are never rewritten. A crash can leave an unclosed final turn whose events are real (and possibly large); load preserves them and closes the orphaned turn with synthetic boundary events (see load). Only a never-fully-written torn tail fragment is discarded. +- **Contiguous seq.** A persisted log is contiguous: `events[i].seq === i`. load rejects a parse error or a `seq` gap in the COMMITTED region (unloadable); append's first event `seq` MUST equal the backend's stored next-seq (after `load` has balanced any interrupted turn). +- **JSON-serializable data.** `SessionEventMap` is merge-extensible and `event.data` is typed only as `SessionEventMap[K]`, so append REJECTS non-JSON-serializable data with an error naming the offending event type. A backend snapshots (serializes/clones) each event when it buffers, since `session.events` hands out the live mutable object. +- **Durability.** append returns only once the batch is durable (the file backend fsyncs; a DB commits). create MAY defer the physical write until the first append (lazy materialization). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/session-persistence/session-persistence/src/index.ts#L102) + +### ctx.sessionPersistence.create(meta) + +```ts website-api +abstract create(meta: SessionHeader): Promise +``` + +Register a new session's metadata. A backend MAY defer the physical write until the first append (lazy materialization), in which case a created-but-never-appended session is absent from list — abandoned sessions leave nothing behind. + +- `meta` — the immutable header (id, version, cwd, lineage) to record. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/session-persistence/session-persistence/src/index.ts#L114) + +### ctx.sessionPersistence.append(id, events) + +```ts website-api +abstract append(id: SessionId, events: readonly SessionEvent[]): Promise +``` + +Durably persist a batch of events (called from the write-behind drain at the `session/flush` checkpoint). Honors the append-only and contiguous-seq contracts: the first event's `seq` MUST equal the stored next-seq (after `load` has durably closed any interrupted turn). Rejects non-JSON- serializable `event.data` with an error naming the offending event type. + +- `id` — the session the batch belongs to. +- `events` — the contiguous batch to persist, in seq order. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/session-persistence/session-persistence/src/index.ts#L125) + +### ctx.sessionPersistence.load(id) + +```ts website-api +abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }> +``` + +Reload a session: its SessionHeader plus the event log up to the last durable checkpoint. Returns `meta` AND `events` so the live session is reconstructed with its `cwd`/lineage, not just its log. +The loop only flushes at `turn/end`, so a crash can leave a durable log whose final turn never closed: real, fully-written events sit after the last `turn/end`. Those events are PRESERVED — a single turn can be huge in a long-horizon task, so truncating it would destroy real work — and `load` CLOSES the orphaned turn by durably appending the minimal synthetic boundary events: an error `tool/result` for every `tool-call` the crash left unanswered (so the rehydrated history is a valid provider transcript — a dangling assistant tool-call is otherwise rejected), then a `step/end` if a step was open, then a `turn/end` carrying the `{ kind: 'interrupted' }` reason. The returned `events` therefore end on a balanced `turn/end` and are immediately usable as a session seed. Only a never-fully-written TORN tail fragment (a half-written final record) is discarded. Returned events are contiguous (`events[i].seq === i`); a parse error or a `seq` gap in the COMMITTED region (at or before the last real `turn/end`) makes the session unloadable (reject). Rejects an unknown format `version`. See the session-persistence RFC for the crash-recovery contract. + +- `id` — the persisted session to reload. + +**Returns** the header plus the event log, ending on a balanced `turn/end` — immediately usable as a session seed. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/session-persistence/session-persistence/src/index.ts#L152) + +### ctx.sessionPersistence.list() + +```ts website-api +abstract list(): Promise +``` + +Lightweight listing from metadata, without a full-log parse. + +**Returns** one header per materialized session. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/session-persistence/session-persistence/src/index.ts#L158) diff --git a/website/zh-CN/api/harness/session.md b/website/zh-CN/api/harness/session.md deleted file mode 100644 index 5ff5b0d97b..0000000000 --- a/website/zh-CN/api/harness/session.md +++ /dev/null @@ -1,56 +0,0 @@ -# Session (dsh-session) - -会话事件流管理。 - -**包名:** `@deepseek-ai/dsh-session` -**服务名:** `ctx.session` - -## 概述 - -Session 是 Agent 的对话状态容器。所有模型可见的内容都必须经过 session 事件流记录——这是"model-visible = logged"原则的实现。 - -## SessionSurface - -会话的外部接口，用于查询当前状态。 - -### surface.messages - -- **类型:** `Message[]` - -当前会话的完整消息列表（经过 compaction 处理后的视图）。 - -### surface.events - -- **类型:** `SessionEvent[]` - -原始事件流。 - -## SessionEvent - -会话中所有变更以事件形式记录： - -```typescript -type SessionEvent = - | { type: 'user/message'; content: ContentBlock[] } - | { type: 'assistant/message'; content: ContentBlock[] } - | { type: 'tool/call'; name: string; args: unknown; callId: CallId } - | { type: 'tool/result'; callId: CallId; content: ContentBlock[]; isError?: boolean } - | { type: 'compact/start'; range: [number, number] } - | { type: 'compact/end'; summary: string } - | { type: 'todo/write'; items: TodoItem[] } - // ... 更多事件类型 -``` - -## 设计原则 - -### Model-visible = Logged - -任何到达模型请求的内容都必须能从 session log 重建。如果你要引入新的模型可见输入，必须先定义对应的 session event。 - -### 事件是 append-only - -Session 事件流是只追加的。修改历史（如 compaction）通过新事件（compact/start + compact/end）表达，而不是修改旧事件。 - -### 持久化 - -Session 事件流可以通过 `dsh-session-persistence` 持久化到磁盘（JSONL 或 SQLite），实现跨进程恢复。 diff --git a/website/zh-CN/api/harness/sessions.md b/website/zh-CN/api/harness/sessions.md new file mode 100644 index 0000000000..d0df73e846 --- /dev/null +++ b/website/zh-CN/api/harness/sessions.md @@ -0,0 +1,110 @@ + + +# ctx.sessions + +`SessionStore` — provided by `@deepseek-ai/dsh-session`. + +In-memory session store (`ctx.sessions`). +Persistence is intentionally not implemented here — persistence plugins subscribe to `session/event` and flush on `session/flush` / dispose. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L405) + +### ctx.sessions.create(id?, options?) + +```ts website-api +create(id?: SessionId, options?: CreateSessionOptions): Session +``` + +Create a session owned by the calling fiber: disposing that fiber stops event notification and removes the session from the store. `options.seed` populates the session with a copy of those events (replay/fork); `options.meta` attaches creation metadata (validated absolute `cwd`, `parentSession` lineage) as the immutable SessionHeader (the store fills `version`/`id`/`createdAt`). +For an agent whose session must be torn down IN ORDER with its loop (so the loop's final flush is captured before `onAppend` detaches), do NOT use this — fold the session lifecycle into the agent's own effect via prepare + enter + announce (see `dsh-agent-loop`'s `startOwned`). + +- `id` — the session id; omitted, the store mints `session-`. +- `options` — seed events and/or creation metadata for the header. + +**Returns** the live session, already entered and announced. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L433) + +### ctx.sessions.prepare(id?, options?) + +```ts website-api +prepare(id?: SessionId, options?: CreateSessionOptions): Session +``` + +Build a session WITHOUT entering it into the store — validate the id/cwd and construct the Session (with its immutable SessionHeader). Pairs with enter + announce: a caller that owns a composite `ctx.effect` (the agent factory) folds the session lifecycle into that ONE effect so a fiber unload tears the session + agent down as a single ORDERED chain rather than as racing sibling effects — which would detach `onAppend` before the loop's closing `session/flush`, dropping the closing events. + +- `id` — the session id; omitted, the store mints `session-`. +- `options` — seed events and/or creation metadata for the header. + +**Returns** the constructed session, NOT yet in the store. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L461) + +### ctx.sessions.enter(session) + +```ts website-api +enter(session: Session): () => void +``` + +Enter a prepared session into the store: wire `onAppend` → `session/event` and add it to the store. Returns the DETACH disposer (`onAppend = undefined` + store removal). Does NOT emit `session/created` — the caller yields this disposer inside its effect and THEN calls announce, so a throwing `session/created` listener rolls the attach back instead of leaking it. +Re-checks the id for a duplicate: `prepare` and `enter` are public cross-package primitives and a caller may interleave arbitrary work (or another create) between them, so a stale prepared session must NOT overwrite a live store entry of the same id — its detach disposer would later delete the REAL session. The create convenience and the agent factory call the two back-to-back so they never trip this, but the public seam cannot assume that. + +- `session` — a {@link prepare}d session not yet in the store. + +**Returns** the detach disposer (`onAppend = undefined` + store removal). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L499) + +### ctx.sessions.announce(session) + +```ts website-api +announce(session: Session): void +``` + +Emit `session/created` for an entered session. Separate from enter so the caller can yield the detach disposer first (rollback safety — see enter). + +- `session` — the entered session to announce to listeners. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L513) + +### ctx.sessions.get(id) + +```ts website-api +get(id: SessionId): Session | undefined +``` + +Look up a live session. + +- `id` — the session id to look up. + +**Returns** the session, or undefined when no live session has that id. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L522) + +### ctx.sessions.list() + +```ts website-api +list(): Session[] +``` + +All live sessions, in creation order. + +**Returns** a fresh array; mutating it does not affect the store. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L530) + +### ctx.sessions.fork(source, boundary?, childSessionId?) + +```ts website-api +fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session +``` + +Create a live child session from a turn-enclosed prefix of a live source. `boundary` is an inclusive source event seq; omitted means the source's current last event. A non-empty selected slice must end at `turn/end`. + +- `source` — Live source session object or id. +- `boundary` — Inclusive source event seq to fork through; omitted means the source's current last event, and omitted on an empty source forks an empty child. +- `childSessionId` — Optional child session id; omitted delegates to `SessionStore`'s id policy. + +**Returns** The created live child session. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L547) diff --git a/website/zh-CN/api/harness/subagent.md b/website/zh-CN/api/harness/subagent.md deleted file mode 100644 index 97ad7b5c87..0000000000 --- a/website/zh-CN/api/harness/subagent.md +++ /dev/null @@ -1,85 +0,0 @@ -# Subagent (dsh-subagent) - -子代理委派接口。 - -**接口包:** `@deepseek-ai/dsh-subagent` -**实现:** `@deepseek-ai/dsh-subagent-spawn` / `@deepseek-ai/dsh-subagent-fork` -**消费者:** `@deepseek-ai/dsh-tool-subagent` - -## Subagent Service - -### ctx.subagent.run(request) - -- **request:** `SubagentRequest` -- **返回值:** `Promise` - -委派一个任务给子代理执行。 - -## SubagentRequest - -```typescript -interface SubagentRequest { - /** 使用的 provider 名称 */ - provider: string - /** 委派给子代理的提示 */ - prompt: string - /** 子代理使用的模型（可选，默认继承父） */ - model?: string -} -``` - -## SubagentResult - -```typescript -interface SubagentResult { - /** 子代理的最终回复 */ - response: string -} -``` - -## Provider 模式 - -Subagent 支持多种"后端"（provider），通过配置选择： - -### spawn - -创建一个全新的子代理实例，没有父级的对话历史： - -```yaml -- name: '@deepseek-ai/dsh-subagent-spawn' - config: - providerName: spawn -``` - -### fork - -创建一个携带父级已完成 turn 前缀的子代理，子代理"知道"父级的对话上下文： - -```yaml -- name: '@deepseek-ai/dsh-subagent-fork' - config: - providerName: fork -``` - -## 模型可用的 Tools - -通过 `dsh-tool-subagent` 暴露。可以加载多次，每次绑定不同 provider： - -```yaml -# 暴露为 "subagent" tool，使用 spawn 后端 -- name: '@deepseek-ai/dsh-tool-subagent' - config: - provider: spawn - toolName: subagent - -# 暴露为 "subagent_fork" tool，使用 fork 后端 -- name: '@deepseek-ai/dsh-tool-subagent' - config: - provider: fork - toolName: subagent_fork -``` - -## 使用场景 - -- **spawn** — 独立子任务（如"搜索这个问题"），子代理不需要知道父级上下文 -- **fork** — 需要上下文的子任务（如"基于我们刚才讨论的，去实现这个"），子代理继承父级的对话前缀 diff --git a/website/zh-CN/api/harness/subagents.md b/website/zh-CN/api/harness/subagents.md new file mode 100644 index 0000000000..258d80e082 --- /dev/null +++ b/website/zh-CN/api/harness/subagents.md @@ -0,0 +1,64 @@ + + +# ctx.subagents + +`SubagentService` — provided by `@deepseek-ai/dsh-subagent`. + +The `subagents` service: a registry of named SubagentProviders and a capability-checked start surface. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L144) + +### ctx.subagents.registerProvider(provider) + +```ts website-api +registerProvider(provider: SubagentProvider): () => void +``` + +Register a provider under its `provider.name`. Throws SubagentError (`DUPLICATE_PROVIDER`) if the name is already taken. Effect-scoped: disposed with the calling fiber (HMR-safe). Emits `subagent/provider-added` after the registration and `subagent/provider-removed` on unregistration, so consumers can mirror provider lifecycle instead of assuming load order. + +- `provider` — the provider; its `name` is the registry key. + +**Returns** the disposer that unregisters the provider. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L160) + +### ctx.subagents.getProvider(name) + +```ts website-api +getProvider(name: string): SubagentProvider | undefined +``` + +Look up a registered provider by name (`undefined` if absent). + +- `name` — the provider name as registered. + +**Returns** the provider, or undefined when the name is unknown. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L188) + +### ctx.subagents.list() + +```ts website-api +list(): string[] +``` + +The names of all registered providers (insertion order). + +**Returns** the registered provider names. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L196) + +### ctx.subagents.start(name, request) + +```ts website-api +start(name: string, request: SubagentStartRequest): SubagentRun +``` + +Start a subagent run on the named provider. Resolves the provider (throws `NO_PROVIDER` if absent), validates every requested START-TIME capability against SubagentProvider.capabilities (throws `UNSUPPORTED_CAPABILITY` for the first unmet one — fail loud, before any child is created), then delegates to SubagentProvider.start and emits `subagent/start` / `subagent/end` around the run. + +- `name` — the provider to run on. +- `request` — the child's prompt, capabilities, and options. + +**Returns** the live run (its `result` resolves when the child settles). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L211) diff --git a/website/zh-CN/api/harness/system-prompt.md b/website/zh-CN/api/harness/system-prompt.md new file mode 100644 index 0000000000..2016285739 --- /dev/null +++ b/website/zh-CN/api/harness/system-prompt.md @@ -0,0 +1,66 @@ + + +# ctx.systemPrompt + +`SystemPrompt` — provided by `@deepseek-ai/dsh-system-prompt`. + +Registry service (`ctx.systemPrompt`): plugins contribute ordered text sections, tool-schema providers, and named prompt variables; the agent loop calls `assemble(context)` once per step. Registers the harness-owned `harness:identity` and `deployment:persona` sections itself (see Config.persona). + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/system-prompt/src/index.ts#L291) + +### ctx.systemPrompt.section(section) + +```ts website-api +section(section: PromptSection): () => void +``` + +Contribute a text section to the system prompt. Order is determined by `section.order` (ascending). Throws if a section with the same name is already registered (a duplicate would silently double prompt text — e.g. a double-loaded tool plugin). The section is removed when the calling fiber is disposed. Emits `system-prompt/change` on register/unregister. + +- `section` — the section to contribute (name, order, text or provider). + +**Returns** the disposer that removes the section. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/system-prompt/src/index.ts#L340) + +### ctx.systemPrompt.tools(provider) + +```ts website-api +tools(provider: () => ToolSchema[]): () => void +``` + +Contribute a tool-schema provider that is evaluated at each assembly call (so it can reflect the live registry state). The provider is removed when the calling fiber is disposed. A provider must not return a schema named TOOL_ORDER_REST; that name is reserved for Config.toolOrder's rest entry and rejects the assembly. Emits `system-prompt/change`. + +- `provider` — evaluated at every {@link assemble} for fresh schemas. + +**Returns** the disposer that removes the provider. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/system-prompt/src/index.ts#L373) + +### ctx.systemPrompt.variable(name, provider) + +```ts website-api +variable(name: string, provider: (context: AssembleContext) => string | undefined): () => void +``` + +Contribute a named prompt variable, referenced from section text as `{{name}}`. The provider is evaluated at each assembly with that assembly's AssembleContext; returning `undefined` means "no value for this assembly" (a section referencing it then fails to render — a deployment must not claim facts it does not have). Throws on a name that does not match `[a-z][a-z0-9_]*` (it could never be referenced) or is already registered. Removed when the calling fiber is disposed; emits `system-prompt/change` on register/unregister. + +- `name` — the reference name (matches `[a-z][a-z0-9_]*`). +- `provider` — evaluated at every {@link assemble} for the value. + +**Returns** the disposer that removes the variable. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/system-prompt/src/index.ts#L403) + +### ctx.systemPrompt.assemble(context?) + +```ts website-api +async assemble(context: AssembleContext = {}): Promise +``` + +Assemble the current prompt for one caller: section texts are resolved against `context` and sorted by order, tools collected from all providers and put in the canonical model-facing order (Config.toolOrder, or lexicographic name order when unconfigured — provider registration order is a plugin-load artifact and never reaches the assembly; a configured order naming a tool no provider contributed rejects the assembly), and every registered variable resolved against `context` into `assembly.variables`. Tool schemas are deep-cloned because adapters and request waterfalls may mutate schema objects. Runs through the `system-prompt/assemble` waterfall, giving listeners the opportunity to mutate or replace the assembly before it reaches the model — like the sections' `order` sort, tool canonicalization happens on the initial assembly, and a listener owns the determinism of whatever it emits. Await the result before reading the assembly values — waterfall listeners may be async. Interpolation happens later, in renderPrompt. + +- `context` — what this assembly is for (defaults to an empty context; see {@link AssembleContext}). + +**Returns** the assembly after the waterfall has run. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/system-prompt/src/index.ts#L447) diff --git a/website/zh-CN/api/harness/tools.md b/website/zh-CN/api/harness/tools.md index d2011ad85e..187f1d5dfc 100644 --- a/website/zh-CN/api/harness/tools.md +++ b/website/zh-CN/api/harness/tools.md @@ -1,122 +1,63 @@ -# Tools (dsh-tools) + -Tool 注册表和 `defineTool` DSL。 +# ctx.tools -**包名:** `@deepseek-ai/dsh-tools` -**服务名:** `ctx.tools` +`ToolRegistry` — provided by `@deepseek-ai/dsh-tools`. -## ToolRegistry +Tool registry (`ctx.tools`): tool plugins register definitions; the agent loop executes calls through the `tools/pre-execute` → `tools/execute` → `tools/post-execute` pipeline. The registry contributes its schemas into the system-prompt assembly — WHICH schemas is governed by its `mode` config (see Config.mode); under a non-native mode it also registers the `run_code` tool and the `tools:sdk` prompt section itself. -### ctx.tools.register(tool) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/tools/src/index.ts#L345) -- **tool:** `ToolDefinition` -- **返回值:** `() => void` disposer +### ctx.tools.register(definition) -注册一个 tool。返回的 disposer 可手动撤销注册（通常不需要，插件卸载时自动撤销）。 - -## defineTool\(options) - -类型安全的 tool 定义辅助函数。 - -```typescript -import { defineTool } from '@deepseek-ai/dsh-tools' - -const tool = defineTool({ - name: 'read_file', - description: 'Read a file from disk.', - parameters: { - path: { type: 'string', required: true, description: 'Absolute file path' }, - offset: { type: 'number' }, - limit: { type: 'number', description: 'Max lines to read' }, - }, - async execute(args) { - // args: { path: string; offset?: number; limit?: number } - }, -}) +```ts website-api +register(definition: ToolDefinition): () => void ``` -### DefineToolOptions\ +Register a tool. Throws if a tool with the same name is already registered. The tool's schema (minus the `execute` function) is automatically contributed to the system-prompt assembly. Disposed with the calling fiber. Emits `tools/change` on register/unregister. -| 字段 | 类型 | 说明 | -|------|------|------| -| `name` | `string` | Tool 名称（全局唯一） | -| `description` | `string` | 发送给模型的描述 | -| `parameters` | `SchemaSpec` | 参数 schema（见下文） | -| `execute` | `(args: InferArgs, exec: ToolExecution) => Promise` | 执行函数 | -| `presentCall?` | `(args: InferArgs) => ToolCallView \| undefined` | UI 展示（纯函数） | -| `presentResult?` | `(args: InferArgs, result: ToolResult) => ToolResultView \| undefined` | 结果 UI 展示（纯函数） | +- `definition` — the tool's schema plus its execute (and optional presentation) functions. -## SchemaSpec +**Returns** the disposer that unregisters the tool. -参数 schema DSL。每个属性是一个 `SchemaProp`： +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/tools/src/index.ts#L420) -```typescript -interface SchemaProp { - type: 'string' | 'number' | 'boolean' | 'object' | 'array' - required?: true - description?: string - enum?: string[] - properties?: SchemaSpec // type: 'object' 时 - items?: SchemaProp // type: 'array' 时 -} +### ctx.tools.get(name) + +```ts website-api +get(name: string): ToolDefinition | undefined ``` -### 类型推导 (InferArgs) +Look up a registered tool. -`InferArgs` 自动从 `SchemaSpec` 推导 TypeScript 类型： +- `name` — the tool name as registered. -- `required: true` → 必填字段 -- 无 `required` → 可选字段（`?`） -- `type: 'object'` + `properties` → 递归推导嵌套对象 -- `type: 'array'` + `items` → 推导为数组 +**Returns** the definition, or undefined when no tool has that name. -## ToolDefinition +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/tools/src/index.ts#L447) -运行时 tool 定义（`defineTool` 的返回值）： +### ctx.tools.schemas() -```typescript -interface ToolDefinition { - name: string - description: string - parameters: Record // JSON Schema - execute(args: unknown, exec: ToolExecution): Promise - presentCall?(args: unknown): ToolCallView | undefined - presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined -} +```ts website-api +schemas(): ToolSchema[] ``` -## ToolExecuteReturn +Return all registered tool schemas — exactly the model-facing fields (`name`, `description`, `parameters`), as sent to the model via the system-prompt assembly. Constructed EXPLICITLY rather than by stripping known non-schema members: a `ToolDefinition` also carries `execute` and the optional `presentCall`/`presentResult` UI callbacks, and those (especially the functions) must never leak into a model request. An allowlist can't drift when a new non-schema member is added to the definition; a denylist (rest-destructure) would silently leak it. -```typescript -type ToolExecuteReturn = - | ContentBlock[] // 仅内容 - | { content: ContentBlock[]; meta?: unknown } // 内容 + 元信息 +**Returns** one deep-cloned schema per registered tool, in registration order. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/tools/src/index.ts#L462) + +### ctx.tools.execute(exec) + +```ts website-api +async execute(exec: ToolExecution): Promise ``` -## ToolArgsError +Execute one tool call through the `tools/pre-execute` → `tools/execute` (around dispatch) → `tools/post-execute` pipeline. `pre-execute` is the gate (allow/deny), `tools/execute` wraps core dispatch (a timeout/retry/metrics seam), and `post-execute` is the inspect/transform seam; core dispatch sits as the base `next()` of the `tools/execute` waterfall. The whole thing is wrapped in one outer try/catch so a throwing listener (in any waterfall) becomes an `isError` result instead of failing the turn; the tool body ALSO keeps its own inner try/catch, so a thrown tool becomes an `isError` result that `tools/execute` and `post-execute` listeners can still inspect. If the tool is not registered, the result is an `isError` carrying a `UNKNOWN_TOOL` structured error. A thrown HarnessError surfaces its `{ name, code }` on the result. -当模型生成的参数不匹配 schema 时抛出： +- `exec` — the call to run (name, parsed arguments, caller agent, signal). -```typescript -class ToolArgsError extends HarnessError { - code: 'INVALID_ARGS' - violations: string[] -} -``` +**Returns** the final result after every waterfall; failures resolve as `isError` results, never rejections. -框架自动捕获并转换为 `isError` 结果返回给模型。 - -## validateArgs(spec, args) - -- **spec:** `SchemaSpec` -- **args:** `unknown` -- **返回值:** `string[]` 违规信息列表（空 = 合法） - -手动校验参数。`defineTool` 内部使用，通常不需要直接调用。 - -## schemaSpecToJsonSchema(spec) - -- **spec:** `SchemaSpec` -- **返回值:** `JsonSchemaObject` - -将 SchemaSpec 转换为标准 JSON Schema。用于发送给模型的 wire format。 +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/tools/src/index.ts#L487) diff --git a/website/zh-CN/api/harness/user-interaction.md b/website/zh-CN/api/harness/user-interaction.md new file mode 100644 index 0000000000..09db0f6107 --- /dev/null +++ b/website/zh-CN/api/harness/user-interaction.md @@ -0,0 +1,37 @@ + + +# ctx.userInteraction + +`UserInteractionService` — provided by `@deepseek-ai/dsh-user-interaction`. + +`ctx.userInteraction`: one active UI provider plus an `ask()` surface. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/user-interaction/src/index.ts#L82) + +### ctx.userInteraction.registerProvider(provider) + +```ts website-api +registerProvider(provider: UserInteractionProvider): () => void +``` + +Register the UI provider. Only one provider may be active in a context. + +- `provider` — UI-side implementation that collects answers. + +**Returns** Disposer that unregisters this provider. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/user-interaction/src/index.ts#L95) + +### ctx.userInteraction.ask(request) + +```ts website-api +async ask(request: AskUserQuestionRequest): Promise +``` + +Ask the active UI provider and wait for the user's answer. + +- `request` — Questions, owner agent, and abort signal. + +**Returns** The answer chosen or typed by the human. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/ui/user-interaction/src/index.ts#L114) diff --git a/website/zh-CN/api/harness/web.md b/website/zh-CN/api/harness/web.md new file mode 100644 index 0000000000..3f25a06839 --- /dev/null +++ b/website/zh-CN/api/harness/web.md @@ -0,0 +1,74 @@ + + +# ctx.web + +`WebService` — provided by `@deepseek-ai/dsh-web`. + +The web access service. Registered as `ctx.web` (one instance per context). +Selection semantics (resolved at execution time, never order-dependent): +- A configured id that is registered and `status().available` → that provider. +- A configured id not registered → `WEB_PROVIDER_CONFIGURED_MISSING`. +- A configured id registered but unavailable → `WEB_PROVIDER_CONFIGURED_UNAVAILABLE`. +- No id configured, exactly one registered usable provider → that provider. +- No id configured, multiple usable providers → `WEB_PROVIDER_AMBIGUOUS`. +- No id configured, no usable provider → `WEB_PROVIDER_UNAVAILABLE`. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/web/web/src/index.ts#L87) + +### ctx.web.registerSearchProvider(provider) + +```ts website-api +registerSearchProvider(provider: WebSearchProvider): () => void +``` + +Register a search provider. Throws WebError `WEB_DUPLICATE_PROVIDER` if its id is already registered for search. Returns a disposer; disposed with the calling fiber. + +- `provider` — the provider; its `id` is the registry key. + +**Returns** the disposer that unregisters the provider. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/web/web/src/index.ts#L116) + +### ctx.web.registerFetchProvider(provider) + +```ts website-api +registerFetchProvider(provider: WebFetchProvider): () => void +``` + +Register a fetch provider. Throws WebError `WEB_DUPLICATE_PROVIDER` if its id is already registered for fetch. Returns a disposer; disposed with the calling fiber. + +- `provider` — the provider; its `id` is the registry key. + +**Returns** the disposer that unregisters the provider. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/web/web/src/index.ts#L127) + +### ctx.web.search(request, exec?) + +```ts website-api +async search(request: WebSearchRequest, exec?: WebExecContext): Promise +``` + +Run one search through the selected provider. Resolves the provider at call time with the selection rules above; throws WebError when the capability cannot run. The seam enforces `request.maxResults` on the result: if the provider over-returns, `sources[]` is truncated and `truncated` set. + +- `request` — the query plus result-shaping options. +- `exec` — the tool-execution context, forwarded to the provider. + +**Returns** the provider's results, capped to `request.maxResults`. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/web/web/src/index.ts#L153) + +### ctx.web.fetch(request, exec?) + +```ts website-api +async fetch(request: WebFetchRequest, exec?: WebExecContext): Promise +``` + +Retrieve one URL through the selected provider. Resolves the provider at call time with the selection rules above; throws WebError when the capability cannot run. A non-2xx response is a result, not a throw. + +- `request` — the URL plus retrieval options. +- `exec` — the tool-execution context, forwarded to the provider. + +**Returns** the retrieval outcome; non-2xx responses resolve descriptively. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/web/web/src/index.ts#L170) diff --git a/website/zh-CN/api/harness/workflows.md b/website/zh-CN/api/harness/workflows.md new file mode 100644 index 0000000000..80e9b84795 --- /dev/null +++ b/website/zh-CN/api/harness/workflows.md @@ -0,0 +1,28 @@ + + +# ctx.workflows + +`WorkflowService` (abstract seam) — provided by `@deepseek-ai/dsh-workflow`. + +Abstract workflow execution service. Subclass, implement start, and load the subclass as a plugin — it registers as `ctx.workflows` (one implementation per context; loading a second throws, cordis' standard duplicate-service behavior). +Semantics every implementation must honor: +- start throws synchronously for a request that cannot begin (an unparseable script, an invalid meta block). Once it returns a WorkflowRun, `result` NEVER rejects — every failure resolves with `stopReason: 'error'` (or `'cancelled'`) — and once the run is cancelled, `result` SETTLES within the implementation's bounded grace even if the script itself never settles (a consumer awaiting `result` must never be wedged past a cancellation). +- The `workflow/*` events fire through emitWorkflowEvent (data snapshots, per-listener containment); `workflow/end` fires exactly once per started run, after `result` is settled or as it settles. +- `dispose()` reaches quiescence within a bounded grace: it cancels, waits for the script to settle AND its started children to finish disposing, and abandons whatever is left rather than hanging its caller (the engine documents what abandonment leaves behind). +- Runs are HOLDER-OWNED: the engine hands control (`cancel`/`dispose`) to the `start()` caller and does not track its live runs — disposing the engine's own fiber mid-run deliberately leaves those runs to their holders' teardown, so an engine reload cannot yank a run out from under the consumer awaiting it. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/workflow/workflow/src/index.ts#L210) + +### ctx.workflows.start(request) + +```ts website-api +abstract start(request: WorkflowStartRequest): WorkflowRun +``` + +Parse and execute a workflow script. + +- `request` — the script, its `args`, the parent agent, and an optional cancel signal. + +**Returns** the live run; its `result` resolves when the script settles. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/workflow/workflow/src/index.ts#L221) diff --git a/website/zh-CN/api/index.md b/website/zh-CN/api/index.md index 371cd1e622..ea43808971 100644 --- a/website/zh-CN/api/index.md +++ b/website/zh-CN/api/index.md @@ -1,25 +1,37 @@ # API 参考 -本节提供 DeepSeek Harness 的完整 API 参考文档，分为两部分： +本节是 DeepSeek Harness 的 API 参考。除本页外，`cordis/` 与 `harness/` 下的所有页面**由脚本从源码生成**（`pnpm run gen-website-api`，CI 校验新鲜度），签名与说明永远与代码一致；生成页目前为英文，中文版将随统一翻译流程提供。 ## 框架 API Cordis 微内核提供的基础能力，所有插件开发都建立在这些 API 之上： - [Context](./cordis/context) — 上下文对象，所有服务和方法的入口 -- [Events](./cordis/events) — 事件系统 API（emit / on / bail / serial / waterfall） -- [Fiber](./cordis/fiber) — 作用域生命周期（状态机、effect、dispose） +- [Events](./cordis/events) — 事件系统 API（on / emit / bail / serial / waterfall） +- [Fiber](./cordis/fiber) — 插件生命周期（状态机、effect、dispose） - [Registry](./cordis/registry) — 插件注册（plugin / inject） - [Service](./cordis/service) — 服务基类 ## Harness API -DeepSeek Harness SDK 提供的扩展 API，用于构建 Agent 能力： +每个 `ctx.*` 服务一页，按服务名索引： -- [Tools (dsh-tools)](./harness/tools) — Tool 注册、defineTool DSL、Schema 类型系统 -- [LLM (dsh-llm)](./harness/llm) — LLM 服务、适配器注册、StreamChunk 协议 -- [Session (dsh-session)](./harness/session) — 会话事件流、消息类型 -- [Agent (dsh-agent)](./harness/agent) — Agent 实例管理、生命周期 -- [Bash (dsh-bash)](./harness/bash) — Bash 执行接口 -- [Filesystem (dsh-fs)](./harness/fs) — 文件系统接口 -- [Subagent (dsh-subagent)](./harness/subagent) — 子代理委派接口 +- [ctx.agentLoop](./harness/agent-loop) — ReAct 循环的创建与恢复 +- [ctx.agents](./harness/agents) — Agent 注册表与工厂 +- [ctx.bash](./harness/bash) — Bash 执行接口（抽象缝） +- [ctx.codeRuntime](./harness/code-runtime) — 代码执行接口（抽象缝） +- [ctx.compact](./harness/compact) — 上下文压缩接口（抽象缝） +- [ctx.fs](./harness/fs) — 文件系统接口（抽象缝） +- [ctx.llm](./harness/llm) — LLM 服务与适配器注册 +- [ctx.sessionPersistence](./harness/session-persistence) — 会话持久化接口（抽象缝） +- [ctx.sessions](./harness/sessions) — 会话存储 +- [ctx.subagents](./harness/subagents) — 子代理委派 +- [ctx.systemPrompt](./harness/system-prompt) — 系统提示词组装 +- [ctx.tools](./harness/tools) — Tool 注册表 +- [ctx.userInteraction](./harness/user-interaction) — 用户交互接口 +- [ctx.web](./harness/web) — Web 搜索与抓取 +- [ctx.workflows](./harness/workflows) — 动态工作流引擎（抽象缝） + +事件总表：[Harness events](./harness/events) — 全部事件按作用域分组，含触发模式与载荷签名。 + +想学"怎么写一个 tool / 插件"？教程在[开发指南](../develop/basic/)；本节只做精确的接口参考。 From 20bcd66dbf147eecff5540ee1da9792e3748db79 Mon Sep 17 00:00:00 2001 From: lintianle Date: Thu, 16 Jul 2026 18:43:12 +0800 Subject: [PATCH 222/359] website: include h3 member headings in the page outline The generated API pages put each member at h3 under an h2 group; default outline depth (h2 only) hid them, leaving e.g. the Context page outline with a single 'Static members' entry. --- website/.vitepress/config/zh-CN.ts | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/website/.vitepress/config/zh-CN.ts b/website/.vitepress/config/zh-CN.ts index ba83cf52c5..0cea119777 100644 --- a/website/.vitepress/config/zh-CN.ts +++ b/website/.vitepress/config/zh-CN.ts @@ -85,7 +85,9 @@ export const zhCN: LocaleSpecificConfig = { '/zh-CN/api/': apiSidebar, '/zh-CN/design/': designSidebar, }, - outline: { label: '本页目录' }, + // level [2,3]: the generated API pages put each member at h3 (### ctx.foo) + // under an h2 scope/statics group — both belong in the page outline. + outline: { label: '本页目录', level: [2, 3] }, docFooter: { prev: '上一篇', next: '下一篇' }, }, } From 4c496774695841f3cb61709086ec060734fd0292 Mon Sep 17 00:00:00 2001 From: lintianle Date: Thu, 16 Jul 2026 18:57:44 +0800 Subject: [PATCH 223/359] website: render the design essays' TeX (math: true, mathjax3 pinned to v4) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit design/revertible-effects and design/context-model carry real TeX that was showing as literal $$ source. markdown: { math: true } enables markdown-it-mathjax3; pinned ^4.3.2 deliberately — v5 injects a